chore: clean up definition of composite class of providers

* fix: fixes of backwords

* fixing hotel information with image placeholders

* chore: clean up product display in hotel and cleaner interfacing

* adding loader with historical data loading

* feature: cleaning up pipeline

* chore: simple surge pricer

* created new pricing pipeline

* adding a checkout page to both sites

* fix: fixing stale pacakge

* test: we wont be using elasticity anymore so its okay

* chore: cleaning elasticity references

* chore: store sting

* feature: e2e intro pipline surge pricing

* fix: CVE vulnerability patching

.gitignore

@@ -6,3 +6,8 @@
 **/session_*.svg
 **/*graph.svg
 paper/src/bib/auto
+
+# Airflow logs - exclude DAG run logs
+experiments/airflow/logs/*
+experiments/airflow/logs/scheduler/
+experiments/airflow/logs/dag_processor_manager/

Makefile

@@ -49,4 +49,8 @@ install: $(VENV)
 test: $(VENV)
 	$(PYTEST) -v
 
+count-lines:
+	@find . \( -path '*/node_modules' -o -path '*/.venv' -o -path '*/venv' \) -prune -o \
+	\( -name "*.ts" -o -name "*.py" \) -type f -print0 | xargs -0 cat | wc -l
+
 .PHONY: all pdf clean watch run.webapp install test

README.md

@@ -1,3 +1,6 @@
+
+<img width="1952" height="2176" alt="nobody_knows" src="https://github.com/user-attachments/assets/d148b00d-e9f9-4280-89cc-0cc866e17251" />
+
 [![Build PDF](https://github.com/velocitatem/PHANTOM/actions/workflows/latex.yml/badge.svg)](https://github.com/velocitatem/PHANTOM/actions/workflows/latex.yml)
 
 - https://phantom-hotel.vercel.app/

backend/provider/app.py

@@ -0,0 +1,113 @@
+from fastapi import FastAPI, HTTPException, Query
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from typing import Literal, Optional
+import uvicorn, os, sys
+from supabase import create_client, Client
+from dotenv import load_dotenv
+import numpy as np
+import pandas as pd
+load_dotenv()
+
+# Local imports of registry and pricing function
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__))+ "/../../experiments/")
+from procesing.providers import SupabaseProvider, BackendAPIProvider
+from procesing.pricers import (
+    StaticPricer,
+    RandomPricer,
+    ElasticityBasedPricer
+)
+from procesing.steps import (
+    PredictPricesStep
+)
+from procesing import PipelineContext
+sys.path.append(os.path.dirname(os.path.abspath(__file__))+ "/../../lib/")
+print(os.path.dirname(os.path.abspath(__file__))+ "/../../lib/")
+from lib.model_registry import ModelRegistry
+
+# Config
+app = FastAPI(title="PHANTOM Pricing Provider")
+app.add_middleware(CORSMiddleware, allow_origins=["*"], allow_credentials=True, allow_methods=["*"], allow_headers=["*"])
+
+supabase: Client = create_client(os.getenv("NEXT_PUBLIC_SUPABASE_URL"), os.getenv("NEXT_PUBLIC_SUPABASE_ANON_KEY"))
+registry = ModelRegistry()
+
+class PriceResponse(BaseModel):
+    productId: str
+    price: float
+    base_price: float
+    markup: float
+    elasticity: Optional[float] = None
+    model_version: str = 'latest'
+
+@app.get("/health")
+def health() -> dict:
+    return {"status": "healthy", "redis": registry.health_check()}
+
+@app.get("/api/{mode}/price/{productId}", response_model=PriceResponse)
+def get_price(mode: Literal['hotel', 'airline'], productId: str, sessionId: Optional[str] = Query(None), experimentId: Optional[str] = Query(None)):
+    product = supabase.table(f'{mode}_products').select("metadata").eq('id', productId).execute().data[0]
+    if not product: raise HTTPException(404, f"Product {productId} not found")
+
+    metadata = product['metadata']
+    base_price = metadata.get('base_price', 100.0)
+
+    # fetch pre-computed prices from registry
+    prices_df = registry.get_prices('latest')
+    elasticity_df = registry.get_elasticity('latest')
+
+    if prices_df is None:
+        # fallback: no pre-computed prices available
+        return PriceResponse(
+            productId=productId,
+            price=base_price,
+            base_price=base_price,
+            markup=1.0,
+            elasticity=None
+        )
+
+    # lookup pre-computed price for this product
+    product_price_row = prices_df[prices_df['productId'] == productId]
+    if product_price_row.empty:
+        # product not in pre-computed prices, fallback to base
+        return PriceResponse(
+            productId=productId,
+            price=base_price,
+            base_price=base_price,
+            markup=1.0,
+            elasticity=None
+        )
+
+    optimal_price = float(product_price_row['optimal_price'].iloc[0]) # TODO: use optimal_price everywhere as  aresult
+
+    # get elasticity if available
+    product_elasticity = None
+    if elasticity_df is not None:
+        product_elasticity_row = elasticity_df[elasticity_df['productId'] == productId]
+        if not product_elasticity_row.empty:
+            product_elasticity = float(product_elasticity_row['elasticity'].iloc[0])
+
+    return PriceResponse(
+        productId=productId,
+        price=optimal_price,
+        base_price=base_price,
+        markup=optimal_price/base_price,
+        elasticity=product_elasticity
+    )
+
+@app.get("/models")
+def list_models(): return registry.list_models()
+
+@app.post("/models/reload")
+def reload_models():
+    elasticity, pricing_model = registry.get_elasticity('latest'), registry.get_pricing_model('latest')
+    return {
+        "elasticity_loaded": bool(elasticity),
+        "n_products": len(elasticity) if elasticity is not None else 0,
+        "pricing_model_loaded": bool(pricing_model),
+        "model_class": pricing_model.__class__.__name__ if pricing_model else None
+    }
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PROVIDER_PORT", "5001")))

backend/provider/requirements.txt

@@ -0,0 +1,16 @@
+fastapi
+uvicorn[standard]
+pydantic
+numpy
+pandas
+scikit-learn
+redis
+supabase
+confluent-kafka>=2.3.0
+kafka-python
+graphviz
+python-dotenv>=1.0.0
+requests>=2.31.0
+typing-extensions>=4.8.0
+pypickle
+pymc

backend/server/app.py

@@ -64,6 +64,14 @@ class EventPayload(BaseModel):
     userAgent: Optional[str] = None
     ts: Optional[str] = None
 
+class PriceLogPayload(BaseModel):
+    productId: str
+    price: float
+    sessionId: str
+    experimentId: Optional[str] = None
+    storeMode: str
+    ts: Optional[str] = None
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -87,7 +95,8 @@ async def startup_event():
         )
 
         topics = [
-            NewTopic(name='user-interactions', num_partitions=3, replication_factor=1)
+            NewTopic(name='user-interactions', num_partitions=3, replication_factor=1),
+            NewTopic(name='price-logs', num_partitions=3, replication_factor=1)
         ]
 
         admin.create_topics(new_topics=topics, validate_only=False)
@@ -139,26 +148,52 @@ async def ingest_logs(event: EventPayload):
         print(traceback.format_exc())
         raise HTTPException(status_code=500, detail=str(e))
 
+@app.post("/api/kafka/price-log")
+async def ingest_price_log(price_log: PriceLogPayload):
+    try:
+        if not price_log.ts:
+            price_log.ts = datetime.utcnow().isoformat() + 'Z'
+
+        producer = get_producer()
+        future = producer.send(
+            'price-logs',
+            key=price_log.productId,
+            value=price_log.model_dump()
+        )
+        future.add_errback(lambda e: print(f"[KAFKA_PRICE_LOG_ERROR] {e}"))
+
+        return {"success": True}
+    except Exception as e:
+        import traceback
+        print(f"[PRICE_LOG_ERROR] {e}")
+        print(traceback.format_exc())
+        raise HTTPException(status_code=500, detail=str(e))
+
 @app.get("/api/kafka/dump")
 def dump_logs(
+    topic: str = 'user-interactions',
     last_n: Optional[int] = None,
     t_start: Optional[str] = None,
     t_end: Optional[str] = None
 ):
-    """dump all messages from user-interactions topic
+    """dump all messages from specified kafka topic
 
     params:
+        topic: kafka topic to dump (default: user-interactions)
         last_n: return only last n messages (default: all)
-        t_start: filter by start timestamp iso format (future use)
-        t_end: filter by end timestamp iso format (future use)
+        t_start: filter by start timestamp iso format
+        t_end: filter by end timestamp iso format
     """
+    if topic not in ['user-interactions', 'price-logs']:
+        raise HTTPException(status_code=400, detail="Invalid topic")
+
     host = os.getenv('KAFKA_HOST', 'localhost')
     port = os.getenv('KAFKA_PORT', '9092')
     broker = f'{host}:{port}'
 
     try:
         consumer = KafkaConsumer(
-            'user-interactions',
+            topic,
             bootstrap_servers=[broker],
             auto_offset_reset='earliest',
             enable_auto_commit=False,
@@ -174,7 +209,6 @@ def dump_logs(
 
         # apply filters
         if t_start or t_end:
-            # filter by timestamp range if provided
             filtered = []
             for e in events:
                 ts = e.get('ts')
@@ -256,6 +290,7 @@ async def get_products(
         query = supabase.table(table).select('*')
 
         # filter by exact date_index if provided
+        # dateIndex from frontend is days from today, convert to days since epoch
         if dateIndex is not None:
             query = query.eq('date_index', dateIndex)
 

docker-compose.yml

@@ -71,6 +71,133 @@ services:
       - "${REDPANDA_CONSOLE_PORT:-8080}:8080"
     restart: unless-stopped
 
+  postgres:
+    container_name: "PHANTOM-postgres"
+    image: postgres:13
+    environment:
+      - POSTGRES_USER=airflow
+      - POSTGRES_PASSWORD=airflow
+      - POSTGRES_DB=airflow
+    ports:
+      - "5433:5432"
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    restart: unless-stopped
+
+  airflow-init:
+    container_name: "PHANTOM-airflow-init"
+    build:
+      context: .
+      dockerfile: docker/Airflow.dockerfile
+    depends_on:
+      - postgres
+    environment:
+      - AIRFLOW__CORE__EXECUTOR=SequentialExecutor
+      - AIRFLOW__DATABASE__SQL_ALCHEMY_CONN=postgresql+psycopg2://airflow:airflow@postgres/airflow
+      - AIRFLOW__CORE__FERNET_KEY=${AIRFLOW_FERNET_KEY}
+      - AIRFLOW__CORE__LOAD_EXAMPLES=false
+      - AIRFLOW__CORE__ENABLE_XCOM_PICKLING=true
+      - _AIRFLOW_DB_MIGRATE=true
+      - _AIRFLOW_WWW_USER_CREATE=true
+      - _AIRFLOW_WWW_USER_USERNAME=admin
+      - _AIRFLOW_WWW_USER_PASSWORD=admin
+      - REDIS_HOST=redis
+      - REDIS_PORT=6379
+    command: version
+    restart: "no"
+
+  airflow-webserver:
+    container_name: "PHANTOM-airflow-webserver"
+    build:
+      context: .
+      dockerfile: docker/Airflow.dockerfile
+    depends_on:
+      - postgres
+      - airflow-init
+      - redis
+    environment:
+      - AIRFLOW__CORE__EXECUTOR=SequentialExecutor
+      - AIRFLOW__DATABASE__SQL_ALCHEMY_CONN=postgresql+psycopg2://airflow:airflow@postgres/airflow
+      - AIRFLOW__CORE__FERNET_KEY=${AIRFLOW_FERNET_KEY}
+      - AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION=true
+      - AIRFLOW__CORE__LOAD_EXAMPLES=false
+      - AIRFLOW__CORE__ENABLE_XCOM_PICKLING=true
+      - AIRFLOW__WEBSERVER__EXPOSE_CONFIG=true
+      - AIRFLOW__WEBSERVER__SECRET_KEY=${AIRFLOW_SECRET_KEY}
+      - KAFKA_HOST=kafka
+      - KAFKA_PORT=29092
+      - BACKEND_URL=http://backend:5000
+      - NEXT_PUBLIC_SUPABASE_URL=${NEXT_PUBLIC_SUPABASE_URL}
+      - NEXT_PUBLIC_SUPABASE_ANON_KEY=${NEXT_PUBLIC_SUPABASE_ANON_KEY}
+      - REDIS_HOST=redis
+      - REDIS_PORT=6379
+    ports:
+      - "${AIRFLOW_WEBSERVER_PORT:-8085}:8080"
+    command: webserver
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
+  airflow-scheduler:
+    container_name: "PHANTOM-airflow-scheduler"
+    build:
+      context: .
+      dockerfile: docker/Airflow.dockerfile
+    depends_on:
+      airflow-webserver:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    environment:
+      - AIRFLOW__CORE__EXECUTOR=SequentialExecutor
+      - AIRFLOW__DATABASE__SQL_ALCHEMY_CONN=postgresql+psycopg2://airflow:airflow@postgres/airflow
+      - AIRFLOW__CORE__FERNET_KEY=${AIRFLOW_FERNET_KEY}
+      - AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION=true
+      - AIRFLOW__CORE__LOAD_EXAMPLES=false
+      - AIRFLOW__CORE__ENABLE_XCOM_PICKLING=true
+      - AIRFLOW__WEBSERVER__SECRET_KEY=${AIRFLOW_SECRET_KEY}
+      - KAFKA_HOST=kafka
+      - KAFKA_PORT=29092
+      - BACKEND_URL=http://backend:5000
+      - NEXT_PUBLIC_SUPABASE_URL=${NEXT_PUBLIC_SUPABASE_URL}
+      - NEXT_PUBLIC_SUPABASE_ANON_KEY=${NEXT_PUBLIC_SUPABASE_ANON_KEY}
+      - REDIS_HOST=redis
+      - REDIS_PORT=6379
+    command: scheduler
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD-SHELL", 'airflow jobs check --job-type SchedulerJob --hostname "$${HOSTNAME}"']
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
+  pricing-provider:
+    container_name: "PHANTOM-pricing-provider"
+    build:
+      context: .
+      dockerfile: docker/Provider.dockerfile
+    depends_on:
+      - redis
+      - kafka
+    environment:
+      - PROVIDER_PORT=5001
+      - REDIS_HOST=redis
+      - REDIS_PORT=6379
+      - KAFKA_HOST=kafka
+      - KAFKA_PORT=29092
+      - NEXT_PUBLIC_SUPABASE_URL=${NEXT_PUBLIC_SUPABASE_URL}
+      - NEXT_PUBLIC_SUPABASE_ANON_KEY=${NEXT_PUBLIC_SUPABASE_ANON_KEY}
+      - BACKEND_URL=http://localhost:5000
+    ports:
+      - "${PROVIDER_PORT:-5001}:5001"
+    restart: unless-stopped
+
 volumes:
   phantom_kafka_data:
   phantom_redis_data:
+  postgres_data:

docker/Airflow.dockerfile

@@ -0,0 +1,30 @@
+FROM apache/airflow:2.7.3-python3.11
+
+USER root
+
+# install system deps if needed
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+USER airflow
+
+# copy requirements for pipeline dependencies
+COPY requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir -r /tmp/requirements.txt
+
+# install postgres driver and providers
+RUN pip install --no-cache-dir \
+    psycopg2-binary \
+    apache-airflow-providers-postgres
+
+# set airflow home
+ENV AIRFLOW_HOME=/opt/airflow
+
+COPY --chown=airflow:root experiments/airflow/dags ${AIRFLOW_HOME}/dags
+COPY --chown=airflow:root experiments/procesing ${AIRFLOW_HOME}/procesing
+COPY --chown=airflow:root lib ${AIRFLOW_HOME}/lib
+
+# create logs and plugins dirs (airflow expects them)
+RUN mkdir -p ${AIRFLOW_HOME}/logs ${AIRFLOW_HOME}/plugins

docker/Airflow.railway.dockerfile

@@ -0,0 +1,41 @@
+FROM apache/airflow:2.7.3-python3.11
+
+USER root
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    supervisor \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+USER airflow
+
+COPY requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir -r /tmp/requirements.txt
+
+RUN pip install --no-cache-dir \
+    psycopg2-binary \
+    apache-airflow-providers-postgres
+
+ENV AIRFLOW_HOME=/opt/airflow
+ENV AIRFLOW__CORE__EXECUTOR=SequentialExecutor
+ENV AIRFLOW__CORE__LOAD_EXAMPLES=false
+ENV AIRFLOW__CORE__ENABLE_XCOM_PICKLING=true
+ENV AIRFLOW__WEBSERVER__EXPOSE_CONFIG=true
+
+# copy all code into image (standalone - no volume mounts needed)
+COPY --chown=airflow:root experiments/airflow/dags ${AIRFLOW_HOME}/dags
+COPY --chown=airflow:root experiments/procesing ${AIRFLOW_HOME}/procesing
+COPY --chown=airflow:root lib ${AIRFLOW_HOME}/lib
+
+RUN mkdir -p ${AIRFLOW_HOME}/logs ${AIRFLOW_HOME}/plugins
+
+# copy entrypoint script
+COPY --chown=airflow:root docker/airflow-railway-entrypoint.sh /entrypoint.sh
+USER root
+RUN chmod +x /entrypoint.sh
+USER airflow
+
+EXPOSE 8080
+
+ENTRYPOINT ["/entrypoint.sh"]

docker/Provider.dockerfile

@@ -0,0 +1,26 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies including graphviz
+RUN apt-get update && apt-get install -y \
+    gcc \
+    g++ \
+    graphviz \
+    libgraphviz-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy and install Python dependencies
+COPY backend/provider/requirements.txt /app/
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code into image
+COPY lib/ /app/lib/
+COPY experiments/procesing/ /app/procesing/
+COPY backend/provider/ /app/provider/
+
+ENV PYTHONPATH=/app:/app/lib:/app/procesing
+
+WORKDIR /app/provider
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "5001"]

docker/airflow-railway-entrypoint.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+set -e
+
+# init db and create admin user on first run
+airflow db migrate
+
+# create admin user if not exists
+airflow users create \
+    --username "${AIRFLOW_ADMIN_USER:-admin}" \
+    --password "${AIRFLOW_ADMIN_PASSWORD:-admin}" \
+    --firstname Admin \
+    --lastname User \
+    --role Admin \
+    --email admin@example.com || true
+
+# start scheduler in background
+airflow scheduler &
+
+# start webserver in foreground (Railway needs one foreground process)
+exec airflow webserver --port ${PORT:-8080}

experiments/README.md

@@ -0,0 +1,8 @@
+
+# Products
+# Agents
+# Pipeline
+
+Our pipeline technically should follow principles in a style like this:
+- Each step should be defined as an inheriting child of an scikit pipeline step, the granularity of the steps is dictated by the following: a step should be a transformation, augmentation or computation independently, no single stage should run multiple in-itself. This way we can modularize properly all the components and track properly in airflow. A stage can be defined as an sklearn step but then must be transalted to a function that takes the context in our DAG of airflow. All parametrization must be done via contexts.
+

experiments/agents/agent.py

@@ -38,7 +38,10 @@ def get_agent(agent_type: AgentTypes,  **kwargs) -> Agent:
 
 if __name__ == "__main__":
     import asyncio
-    JTBD= "Name all the products on this site and try to find out more about each product by clicking into them (they might not open)"
-    agent = get_agent(AgentTypes.GENERIC_BROWSER_USE_AGENT, goal=JTBD, url="http://localhost:3000/products", timeout=300)
+    JTBD= "Find me the cheapest room in Madrid for 2 people in the next two days, review each hotel room in detail and then add it to cart."
+    agent = get_agent(AgentTypes.GENERIC_BROWSER_USE_AGENT,
+                      goal=JTBD,
+                      url="http://localhost:3000/start-task?uuid=d10f5ab3-a7b7-4e97-8d94-ab06f1537c0a",
+                      timeout=300)
     R=asyncio.run(agent.act())
     print(R)

experiments/airflow/dags/surge_pricing_factory.py

@@ -0,0 +1,210 @@
+from airflow import DAG
+from airflow.operators.python import PythonOperator
+from airflow.utils.dates import days_ago
+from datetime import timedelta
+import pandas as pd
+import logging
+import sys
+import pickle
+
+sys.path.insert(0, '/opt/airflow')
+
+from procesing.context import PipelineContext
+from procesing.providers import SupabaseProvider, BackendAPIProvider
+from procesing.steps import (
+    FetchInteractionsStep,
+    FetchPriceLogsStep,
+    ComputeDemandStep,
+    AggregatePriceLogsStep,
+    JoinProductFeaturesStep,
+)
+from procesing.pricers.simple import SimpleSurgePricer
+
+DEFAULT_ARGS = {
+    'owner': 'phantom-research',
+    'depends_on_past': False,
+    'email_on_failure': False,
+    'email_on_retry': False,
+    'retries': 2,
+    'retry_delay': timedelta(minutes=5),
+}
+
+class CompositeProvider(SupabaseProvider, BackendAPIProvider):
+    def __init__(self):
+        SupabaseProvider.__init__(self)
+        BackendAPIProvider.__init__(self)
+
+def _get_provider():
+    return CompositeProvider()
+
+def _make_task_callables(store_mode: str):
+    """Generate task callables bound to a specific store_mode."""
+
+    def get_context(**kwargs):
+        return PipelineContext(provider=_get_provider(), store_mode=store_mode)
+
+    def fetch_interactions(**kwargs):
+        ctx = get_context(**kwargs)
+        df = FetchInteractionsStep(ctx).transform(None)
+        kwargs['ti'].xcom_push(key='interactions_raw', value=pickle.dumps(df))
+        logging.info(f"[{store_mode}] Fetched {len(df)} interaction records")
+        return len(df)
+
+    def fetch_price_logs(**kwargs):
+        ctx = get_context(**kwargs)
+        df = FetchPriceLogsStep(ctx).transform(None)
+        kwargs['ti'].xcom_push(key='price_logs_raw', value=pickle.dumps(df))
+        logging.info(f"[{store_mode}] Fetched {len(df)} price records")
+        return len(df)
+
+    def compute_demand(**kwargs):
+        ti = kwargs['ti']
+        df = pickle.loads(ti.xcom_pull(key='interactions_raw'))
+        ctx = get_context(**kwargs)
+        demand_df = ComputeDemandStep(ctx).transform(df)
+        ti.xcom_push(key='demand_data', value=pickle.dumps(demand_df))
+        logging.info(f"[{store_mode}] Computed demand for {len(demand_df)} products")
+        return len(demand_df)
+
+    def aggregate_price_logs(**kwargs):
+        ti = kwargs['ti']
+        df = pickle.loads(ti.xcom_pull(key='price_logs_raw'))
+        ctx = get_context(**kwargs)
+        price_df = AggregatePriceLogsStep(ctx).transform(df)
+        ti.xcom_push(key='price_data', value=pickle.dumps(price_df))
+        logging.info(f"[{store_mode}] Aggregated price logs for {len(price_df)} products")
+        return len(price_df)
+
+    def join_product_features(**kwargs):
+        ti = kwargs['ti']
+        demand_df = pickle.loads(ti.xcom_pull(key='demand_data'))
+        price_df = pickle.loads(ti.xcom_pull(key='price_data'))
+        ctx = get_context(**kwargs)
+        joined_df = JoinProductFeaturesStep(ctx).transform((demand_df, price_df))
+        ti.xcom_push(key='product_features', value=pickle.dumps(joined_df))
+        logging.info(f"[{store_mode}] Joined features for {len(joined_df)} products")
+        return len(joined_df)
+
+    def apply_surge_pricing(**kwargs):
+        ti = kwargs['ti']
+        product_features = pickle.loads(ti.xcom_pull(key='product_features'))
+        dag_conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
+
+        data = product_features.rename(columns={'demand_score': 'demand'})
+        surge_pricer = SimpleSurgePricer(
+            high_threshold=dag_conf.get('high_threshold', 10),
+            low_threshold=dag_conf.get('low_threshold', 2),
+            surge_multiplier=dag_conf.get('surge_multiplier', 1.2),
+            discount_multiplier=dag_conf.get('discount_multiplier', 0.9)
+        )
+        surge_pricer.fit(data)
+        data['optimal_price'] = surge_pricer.predict()
+
+        prices_df = data[['productId', 'price', 'base_price', 'optimal_price', 'demand']].rename(columns={
+            'price': 'current_price', 'demand': 'demand_score'
+        })
+        ti.xcom_push(key='predicted_prices', value=pickle.dumps(prices_df))
+        logging.info(f"[{store_mode}] Applied surge pricing for {len(prices_df)} products")
+        return len(prices_df)
+
+    def publish_results(**kwargs):
+        ti = kwargs['ti']
+        prices_df = pickle.loads(ti.xcom_pull(key='predicted_prices'))
+        from lib.model_registry import ModelRegistry
+
+        registry = ModelRegistry()
+        dag_conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
+
+        metadata = {
+            'timestamp': pd.Timestamp.now().isoformat(),
+            'store_mode': store_mode,
+            'dag_run_id': kwargs['dag_run'].run_id if kwargs.get('dag_run') else 'manual',
+            'pricing_method': 'surge',
+            'high_threshold': dag_conf.get('high_threshold', 10),
+            'low_threshold': dag_conf.get('low_threshold', 2),
+            'surge_multiplier': dag_conf.get('surge_multiplier', 1.2),
+            'discount_multiplier': dag_conf.get('discount_multiplier', 0.9)
+        }
+        registry.publish_prices(prices_df, model_name=f'{store_mode}_latest', metadata=metadata)
+        logging.info(f"[{store_mode}] Published surge pricing for {len(prices_df)} products")
+
+        return {
+            'n_products': len(prices_df),
+            'registry_status': 'success',
+            'store_mode': store_mode,
+            'mean_demand': float(prices_df['demand_score'].mean()) if 'demand_score' in prices_df.columns else None
+        }
+
+    return {
+        'fetch_interactions': fetch_interactions,
+        'fetch_price_logs': fetch_price_logs,
+        'compute_demand': compute_demand,
+        'aggregate_price_logs': aggregate_price_logs,
+        'join_product_features': join_product_features,
+        'apply_surge_pricing': apply_surge_pricing,
+        'publish_results': publish_results,
+    }
+
+
+def create_surge_pricing_dag(store_mode: str) -> DAG:
+    """Factory: generates a surge pricing DAG for a given store_mode."""
+    callables = _make_task_callables(store_mode)
+
+    dag = DAG(
+        f'surge_pricing_{store_mode}',
+        default_args=DEFAULT_ARGS,
+        description=f'Surge pricing pipeline for {store_mode} store mode',
+        schedule_interval='*/15 * * * *',
+        start_date=days_ago(1),
+        catchup=False,
+        max_active_runs=1,
+        tags=['pricing', 'surge', 'research', store_mode],
+    )
+
+    with dag:
+        t_fetch_interactions = PythonOperator(
+            task_id='fetch_interactions',
+            python_callable=callables['fetch_interactions'],
+            provide_context=True,
+        )
+        t_fetch_price_logs = PythonOperator(
+            task_id='fetch_price_logs',
+            python_callable=callables['fetch_price_logs'],
+            provide_context=True,
+        )
+        t_compute_demand = PythonOperator(
+            task_id='compute_demand',
+            python_callable=callables['compute_demand'],
+            provide_context=True,
+        )
+        t_aggregate_prices = PythonOperator(
+            task_id='aggregate_price_logs',
+            python_callable=callables['aggregate_price_logs'],
+            provide_context=True,
+        )
+        t_join_features = PythonOperator(
+            task_id='join_product_features',
+            python_callable=callables['join_product_features'],
+            provide_context=True,
+        )
+        t_surge_pricing = PythonOperator(
+            task_id='apply_surge_pricing',
+            python_callable=callables['apply_surge_pricing'],
+            provide_context=True,
+        )
+        t_publish = PythonOperator(
+            task_id='publish_results',
+            python_callable=callables['publish_results'],
+            provide_context=True,
+        )
+
+        t_fetch_interactions >> t_compute_demand
+        t_fetch_price_logs >> t_aggregate_prices
+        [t_compute_demand, t_aggregate_prices] >> t_join_features >> t_surge_pricing >> t_publish
+
+    return dag
+
+
+# instantiate DAGs for Airflow to discover
+dag_airline = create_surge_pricing_dag('airline')
+dag_hotel = create_surge_pricing_dag('hotel')

experiments/airflow/dags/surge_pricing_pipeline.py

@@ -0,0 +1,237 @@
+from airflow import DAG
+from airflow.operators.python import PythonOperator
+from airflow.utils.dates import days_ago
+from datetime import timedelta
+import pandas as pd
+import logging
+import sys
+import pickle
+import io
+
+# add parent dir to path so procesing package can be imported
+sys.path.insert(0, '/opt/airflow')
+
+from procesing.context import PipelineContext
+from procesing.providers import SupabaseProvider, BackendAPIProvider
+from procesing.steps import (
+    FetchInteractionsStep,
+    FetchPriceLogsStep,
+    ComputeDemandStep,
+    AggregatePriceLogsStep,
+    JoinProductFeaturesStep,
+)
+from procesing.pricers.simple import SimpleSurgePricer
+
+default_args = {
+    'owner': 'phantom-research',
+    'depends_on_past': False,
+    'email_on_failure': False,
+    'email_on_retry': False,
+    'retries': 2,
+    'retry_delay': timedelta(minutes=5),
+}
+
+def get_provider():
+    """Factory to create composite provider"""
+    class CompositeProvider(SupabaseProvider, BackendAPIProvider): # TODO: Fix this into one global provider singelton instead of multiple inheritance declarations acoss the codebase
+        def __init__(self):
+            SupabaseProvider.__init__(self)
+            BackendAPIProvider.__init__(self)
+    return CompositeProvider()
+
+def get_context(**kwargs):
+    """Build pipeline context from Airflow config"""
+    dag_conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
+    return PipelineContext(
+        provider=get_provider(),
+        store_mode=dag_conf.get('store_mode', 'hotel'),
+    )
+
+# atomic task functions (each wraps one sklearn step)
+def fetch_interactions(**kwargs):
+    """Task: Fetch interaction data from Kafka"""
+    context = get_context(**kwargs)
+    step = FetchInteractionsStep(context)
+    df = step.transform(None)
+
+    kwargs['ti'].xcom_push(key='interactions_raw', value=pickle.dumps(df))
+    logging.info(f"Fetched {len(df)} interaction records")
+    return len(df)
+
+def fetch_price_logs(**kwargs):
+    """Task: Fetch price logs from Kafka"""
+    context = get_context(**kwargs)
+    step = FetchPriceLogsStep(context)
+    df = step.transform(None)
+
+    kwargs['ti'].xcom_push(key='price_logs_raw', value=pickle.dumps(df))
+    logging.info(f"Fetched {len(df)} price records")
+    return len(df)
+
+def compute_demand(**kwargs):
+    """Task: Compute demand scores from interactions"""
+    ti = kwargs['ti']
+    df = pickle.loads(ti.xcom_pull(key='interactions_raw'))
+
+    context = get_context(**kwargs)
+    step = ComputeDemandStep(context)
+    demand_df = step.transform(df)
+    # TODO: clear the xcom
+
+
+    ti.xcom_push(key='demand_data', value=pickle.dumps(demand_df))
+    logging.info(f"Computed demand for {len(demand_df)} products")
+    return len(demand_df)
+
+def aggregate_price_logs(**kwargs):
+    """Task: Aggregate price logs"""
+    ti = kwargs['ti']
+    df = pickle.loads(ti.xcom_pull(key='price_logs_raw'))
+
+    context = get_context(**kwargs)
+    step = AggregatePriceLogsStep(context)
+    price_df = step.transform(df)
+
+    ti.xcom_push(key='price_data', value=pickle.dumps(price_df))
+    logging.info(f"Aggregated price logs for {len(price_df)} products")
+    return len(price_df)
+
+def join_product_features(**kwargs):
+    """Task: Join demand and price data"""
+    ti = kwargs['ti']
+    demand_df = pickle.loads(ti.xcom_pull(key='demand_data'))
+    price_df = pickle.loads(ti.xcom_pull(key='price_data'))
+
+    context = get_context(**kwargs)
+    step = JoinProductFeaturesStep(context)
+    joined_df = step.transform((demand_df, price_df))
+
+    ti.xcom_push(key='product_features', value=pickle.dumps(joined_df))
+    logging.info(f"Joined features for {len(joined_df)} products")
+    return len(joined_df)
+
+def apply_surge_pricing(**kwargs):
+    """Task: Apply surge pricing rules to generate optimal prices"""
+    ti = kwargs['ti']
+    product_features = pickle.loads(ti.xcom_pull(key='product_features'))
+
+    dag_conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
+
+    # rename demand_score to demand for pricer compatibility
+    data = product_features.rename(columns={'demand_score': 'demand'})
+
+    surge_pricer = SimpleSurgePricer(
+        high_threshold=dag_conf.get('high_threshold', 10),
+        low_threshold=dag_conf.get('low_threshold', 2),
+        surge_multiplier=dag_conf.get('surge_multiplier', 1.2),
+        discount_multiplier=dag_conf.get('discount_multiplier', 0.9)
+    )
+    surge_pricer.fit(data)
+    data['optimal_price'] = surge_pricer.predict()
+
+    prices_df = data[['productId', 'price', 'base_price', 'optimal_price', 'demand']].rename(columns={
+        'price': 'current_price',
+        'demand': 'demand_score'
+    })
+
+    ti.xcom_push(key='predicted_prices', value=pickle.dumps(prices_df))
+    logging.info(f"Applied surge pricing for {len(prices_df)} products")
+    return len(prices_df)
+
+def publish_results(**kwargs):
+    """Task: Publish surge pricing results to registry"""
+    ti = kwargs['ti']
+    prices_df = pickle.loads(ti.xcom_pull(key='predicted_prices'))
+
+    sys.path.insert(0, '/opt/airflow')
+    from lib.model_registry import ModelRegistry
+
+    registry = ModelRegistry()
+    dag_conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
+
+    metadata = {
+        'timestamp': pd.Timestamp.now().isoformat(),
+        'store_mode': dag_conf.get('store_mode', 'hotel'),
+        'dag_run_id': kwargs['dag_run'].run_id if kwargs.get('dag_run') else 'manual',
+        'pricing_method': 'surge',
+        'high_threshold': dag_conf.get('high_threshold', 10),
+        'low_threshold': dag_conf.get('low_threshold', 2),
+        'surge_multiplier': dag_conf.get('surge_multiplier', 1.2),
+        'discount_multiplier': dag_conf.get('discount_multiplier', 0.9)
+    }
+
+    registry.publish_prices(prices_df, model_name='latest', metadata=metadata)
+
+    logging.info(f"Published surge pricing for {len(prices_df)} products")
+
+    return {
+        'n_products': len(prices_df),
+        'registry_status': 'success',
+        'mean_demand': float(prices_df['demand_score'].mean()) if 'demand_score' in prices_df.columns else None
+    }
+
+
+# DAG definition
+with DAG(
+    'surge_pricing_pipeline',
+    default_args=default_args,
+    description='Simple surge pricing pipeline: demand aggregation + rule-based pricing',
+    schedule_interval='*/15 * * * *',
+    start_date=days_ago(1),
+    catchup=False,
+    max_active_runs=1,
+    tags=['pricing', 'surge', 'research', 'simplified'],
+) as dag:
+
+    # parallel data fetching
+    t_fetch_interactions = PythonOperator(
+        task_id='fetch_interactions',
+        python_callable=fetch_interactions,
+        provide_context=True,
+    )
+
+    t_fetch_price_logs = PythonOperator(
+        task_id='fetch_price_logs',
+        python_callable=fetch_price_logs,
+        provide_context=True,
+    )
+
+    # compute demand from interactions
+    t_compute_demand = PythonOperator(
+        task_id='compute_demand',
+        python_callable=compute_demand,
+        provide_context=True,
+    )
+
+    # aggregate price logs
+    t_aggregate_prices = PythonOperator(
+        task_id='aggregate_price_logs',
+        python_callable=aggregate_price_logs,
+        provide_context=True,
+    )
+
+    # join demand and prices
+    t_join_features = PythonOperator(
+        task_id='join_product_features',
+        python_callable=join_product_features,
+        provide_context=True,
+    )
+
+    # apply surge pricing
+    t_surge_pricing = PythonOperator(
+        task_id='apply_surge_pricing',
+        python_callable=apply_surge_pricing,
+        provide_context=True,
+    )
+
+    # publish to registry
+    t_publish = PythonOperator(
+        task_id='publish_results',
+        python_callable=publish_results,
+        provide_context=True,
+    )
+
+    # dependency graph: parallel fetch -> process -> join -> surge -> publish
+    t_fetch_interactions >> t_compute_demand
+    t_fetch_price_logs >> t_aggregate_prices
+    [t_compute_demand, t_aggregate_prices] >> t_join_features >> t_surge_pricing >> t_publish

experiments/procesing/__init__.py

@@ -1,19 +1,51 @@
-from .extract import (
-    KafkaDataFetcher,
-    ExperimentJoiner,
-    EventTitleAugmenter,
+from procesing.context import PipelineContext
+from procesing.providers import DataProvider, SupabaseProvider, BackendAPIProvider
+from procesing.steps import (
+    BaseContextStep,
+    FetchInteractionsStep,
+    FetchPriceLogsStep,
+    FetchExperimentsStep,
+    JoinExperimentsStep,
+    CreatePriceBucketsStep,
+    AugmentEventNamesStep,
+    ChunkByTimeWindowStep,
+    ComputeDemandStep,
+    ComputeDemandForChunksStep,
+    AggregatePriceLogsStep,
+    # StateSpace,
+    # BuildStateSpaceStep,
+    FitPricingFunctionStep,
+    PredictPricesStep,
+)
+from procesing.pipelines import (
+    interaction_extraction_pipeline,
+    price_extraction_pipeline,
+    pricing_pipeline,
+    full_pipeline,
 )
-from .demand import DemandEstimator
-from .mapping import SessionTransitionProbMatrixTransformer, render_graph
-from .pipeline import etl_pipeline, pricing_pipeline
 
 __all__ = [
-    'KafkaDataFetcher',
-    'ExperimentJoiner',
-    'EventTitleAugmenter',
-    'DemandEstimator',
-    'SessionTransitionProbMatrixTransformer',
-    'render_graph',
-    'etl_pipeline',
+    'PipelineContext',
+    'DataProvider',
+    'SupabaseProvider',
+    'BackendAPIProvider',
+    'BaseContextStep',
+    'FetchInteractionsStep',
+    'FetchPriceLogsStep',
+    'FetchExperimentsStep',
+    'JoinExperimentsStep',
+    'CreatePriceBucketsStep',
+    'AugmentEventNamesStep',
+    'ChunkByTimeWindowStep',
+    'ComputeDemandStep',
+    'ComputeDemandForChunksStep',
+    'AggregatePriceLogsStep',
+    # 'StateSpace',
+    # 'BuildStateSpaceStep',
+    'FitPricingFunctionStep',
+    'PredictPricesStep',
+    'interaction_extraction_pipeline',
+    'price_extraction_pipeline',
     'pricing_pipeline',
+    'full_pipeline',
 ]

experiments/procesing/context.py

@@ -0,0 +1,34 @@
+from typing import Any, Dict
+import pandas as pd
+from procesing.providers.base import DataProvider
+
+class PipelineContext:
+    """
+    Context for pipeline execution holding config, provider, and cached data.
+    Enables dependency injection and eliminates global state.
+    """
+
+    def __init__(self,
+                 provider: DataProvider,
+                 store_mode: str,
+                 window_size: str = '30s',
+                 **config):
+        self.provider = provider
+        self.store_mode = store_mode
+        self.window_size = window_size
+        self.config = config
+        self._cache: Dict[str, Any] = {}
+
+    def get_cached(self, key: str, default=None):
+        return self._cache.get(key, default)
+
+    def cache(self, key: str, value):
+        self._cache[key] = value
+        return value
+
+    @property
+    def products(self) -> pd.DataFrame:
+        """Lazy-load and cache product catalog, single fetch per pipeline run"""
+        if 'products' not in self._cache:
+            self._cache['products'] = self.provider.fetch_products(self.store_mode)
+        return self._cache['products']

experiments/procesing/demand.py

@@ -1,39 +0,0 @@
-from sklearn.base import BaseEstimator, TransformerMixin
-import numpy as np
-import pandas as pd
-from supabase import create_client, Client
-import pandas as pd
-import os
-
-SUPABASE_URL = os.getenv("NEXT_PUBLIC_SUPABASE_URL")
-SUPABASE_KEY = os.getenv("NEXT_PUBLIC_SUPABASE_ANON_KEY")
-
-supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
-
-class DemandEstimator(BaseEstimator, TransformerMixin):
-    def __init__(self,
-                 store_mode:str='hotel',
-                 session_filter:str="",
-                 experiment_filter:str=""):
-        self.store=store_mode
-        self.session_filter=session_filter if len(session_filter)>0 else None
-        self.experiment_filter=experiment_filter if len(experiment_filter)>0 else None
-    def fit(self, X):
-        return self
-
-    def transform(self, interactions : pd.DataFrame):
-        if interactions.empty:
-            return pd.DataFrame(columns=["productId", "demand_score"])
-        if self.session_filter:
-            interactions = interactions[interactions['sessionId'] == self.session_filter]
-        if self.experiment_filter:
-            interactions = interactions[interactions['experimentId'] == self.experiment_filter]
-        products=supabase.table(f'{self.store}_products').select("id, room_type, date_index, metadata, availability").execute()
-        products = pd.DataFrame(products.data)
-        unique_products = products['id'].unique()
-        # TODO: improve demand score calculation rather than just counting interactions (use weights..)
-        # while maintaining simplicity of a simple cross tab approach
-        product_demand = pd.crosstab(interactions['productId'], "no_of_interactions")
-        product_demand = product_demand.reindex(unique_products, fill_value=0).reset_index()
-        product_demand.columns = ['productId', 'demand_score']
-        return product_demand

experiments/procesing/elasticity.py

@@ -0,0 +1,332 @@
+import numpy as np
+import pandas as pd
+from typing import List, Dict, Optional
+from sklearn.base import BaseEstimator, TransformerMixin
+from supabase import create_client, Client
+import os
+
+SUPABASE_URL = os.getenv("NEXT_PUBLIC_SUPABASE_URL", "")
+SUPABASE_KEY = os.getenv("NEXT_PUBLIC_SUPABASE_ANON_KEY", "")
+
+supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
+
+class TemporalElasticityEstimator(BaseEstimator, TransformerMixin):
+    """
+    Compute price elasticity from time-series demand and price data.
+
+    Elasticity = (% change in quantity) / (% change in price)
+
+    Works with chunked time-window data from ChunkInteractionsIntoSteps.
+    """
+
+    def __init__(self,
+                 method:str='point',
+                 min_observations:int=2,
+                 smooth_window:Optional[int]=None):
+        """
+        Args:
+            method: 'point' (point elasticity) or 'arc' (arc elasticity)
+            min_observations: min data points needed per product
+            smooth_window: if set, apply rolling avg smoothing to time series
+        """
+        self.method = method
+        self.min_observations = min_observations
+        self.smooth_window = smooth_window
+
+    def fit(self, X):
+        return self
+
+    def transform(self,
+                  demand_chunks: List[Dict],
+                  price_chunks: List[Dict],
+                  store_mode: str = 'hotel') -> pd.DataFrame:
+        """
+        Args:
+            demand_chunks: list from ChunkInteractionsIntoSteps + DemandEstimator
+                           each item: {'window_start', 'window_end', 'demand_vector'}
+            price_chunks: list of dicts with {'window_start', 'window_end', 'price_vector'}
+            store_mode: 'hotel' or 'airline' to fetch all products
+
+        Returns:
+            df with [productId, elasticity, std_error, n_observations]
+        """
+        # fetch all products from database
+        all_products = supabase.table(f'{store_mode}_products').select("id").execute()
+        all_product_ids = [p['id'] for p in all_products.data]
+
+        aligned = self._align_chunks(demand_chunks, price_chunks)
+        if not aligned:
+            # return all products with zero elasticity
+            return pd.DataFrame({
+                'productId': all_product_ids,
+                'elasticity': 0.0,
+                'std_error': 0.0,
+                'n_obs': 0
+            })
+
+        # build time series per product
+        product_series = self._build_product_timeseries(aligned)
+
+        # compute elasticity per product
+        elasticities = []
+        for pid, series in product_series.items():
+            if len(series) < self.min_observations:
+                # assign 0 elasticity for products with insufficient data
+                elasticities.append({
+                    'productId': pid,
+                    'elasticity': 0.0,
+                    'std_error': 0.0,
+                    'n_obs': len(series)
+                })
+                continue
+
+            # apply smoothing if requested
+            if self.smooth_window and len(series) >= self.smooth_window:
+                series = self._smooth_series(series, self.smooth_window)
+
+            elast = self._compute_elasticity(series)
+            elasticities.append({
+                'productId': pid,
+                'elasticity': elast['value'],
+                'std_error': elast.get('std_error', 0.0),
+                'n_obs': len(series)
+            })
+
+        result_df = pd.DataFrame(elasticities)
+
+        # fill in missing products with zero elasticity
+        observed_pids = set(result_df['productId'].unique())
+        missing_pids = [pid for pid in all_product_ids if pid not in observed_pids]
+
+        if missing_pids:
+            missing_df = pd.DataFrame({
+                'productId': missing_pids,
+                'elasticity': 0.0,
+                'std_error': 0.0,
+                'n_obs': 0
+            })
+            result_df = pd.concat([result_df, missing_df], ignore_index=True)
+
+        return result_df
+
+    def _align_chunks(self, demand_chunks, price_chunks):
+        """Align demand and price data by matching time windows."""
+        aligned = []
+
+        # create lookup for price chunks by window_start
+        price_lookup = {chunk['window_start']: chunk for chunk in price_chunks}
+
+        for demand_chunk in demand_chunks:
+            window_start = demand_chunk['window_start']
+            if window_start in price_lookup:
+                aligned.append({
+                    'window_start': window_start,
+                    'window_end': demand_chunk['window_end'],
+                    'demand': demand_chunk['demand_vector'],
+                    'prices': price_lookup[window_start]['price_vector']
+                })
+
+        return aligned
+
+    def _build_product_timeseries(self, aligned_chunks):
+        """Build time series [price, quantity] per product."""
+        # vectorize chunk merging instead of iterating rows
+        all_merged = []
+        for chunk in aligned_chunks:
+            merged = chunk['demand'].merge(chunk['prices'], on='productId', how='inner')
+            merged['timestamp'] = chunk['window_start']
+            all_merged.append(merged[['productId', 'timestamp', 'price', 'demand_score']])
+
+        if not all_merged:
+            return {}
+
+        # concat all chunks and group by productId in one pass
+        combined = pd.concat(all_merged, ignore_index=True)
+        series_by_product = {
+            pid: group[['timestamp', 'price', 'demand_score']].rename(
+                columns={'demand_score': 'quantity'}
+            ).to_dict('records')
+            for pid, group in combined.groupby('productId')
+        }
+
+        return series_by_product
+
+    def _smooth_series(self, series, window):
+        """Apply rolling average smoothing."""
+        df = pd.DataFrame(series)
+        df['price_smooth'] = df['price'].rolling(window=window, center=True).mean()
+        df['quantity_smooth'] = df['quantity'].rolling(window=window, center=True).mean()
+        df = df.dropna()
+
+        return [{'timestamp': row['timestamp'],
+                 'price': row['price_smooth'],
+                 'quantity': row['quantity_smooth']}
+                for _, row in df.iterrows()]
+
+    def _compute_elasticity(self, series):
+        """Compute elasticity from time series."""
+        if len(series) < 2:
+            return {'value': 0.0, 'std_error': 0.0}
+
+        prices = np.array([s['price'] for s in series])
+        quantities = np.array([s['quantity'] for s in series])
+
+        # filter out zero/negative values
+        valid = (prices > 0) & (quantities > 0)
+        if valid.sum() < 2:
+            return {'value': 0.0, 'std_error': 0.0}
+
+        prices = prices[valid]
+        quantities = quantities[valid]
+
+        if self.method == 'point':
+            return self._point_elasticity(prices, quantities)
+        elif self.method == 'arc':
+            return self._arc_elasticity(prices, quantities)
+        else:
+            raise ValueError(f"Unknown method: {self.method}")
+
+    def _point_elasticity(self, prices, quantities):
+        """
+        Point elasticity using log-log regression.
+        log(Q) = a + b*log(P), elasticity = b
+        """
+        if len(prices) < 2:
+            return {'value': 0.0, 'std_error': 0.0}
+
+        log_p = np.log(prices)
+        log_q = np.log(quantities)
+
+        # simple linear regression
+        if log_p.std() == 0:
+            return {'value': 0.0, 'std_error': 0.0}
+
+        cov = np.cov(log_p, log_q)[0, 1]
+        var = np.var(log_p)
+        b = cov / var
+
+        # std error estimate (avoid div by zero)
+        if len(prices) <= 2:
+            se_b = 0.0
+        else:
+            residuals = log_q - (log_q.mean() + b * (log_p - log_p.mean()))
+            mse = (residuals ** 2).sum() / (len(prices) - 2)
+            se_b = np.sqrt(mse / (len(prices) * var))
+
+        return {'value': b, 'std_error': se_b}
+
+    def _arc_elasticity(self, prices, quantities):
+        """
+        Arc elasticity: average of period-over-period elasticities.
+        E_t = (ΔQ/Q_avg) / (ΔP/P_avg)
+        """
+        elasticities = []
+
+        for i in range(1, len(prices)):
+            p1, p2 = prices[i-1], prices[i]
+            q1, q2 = quantities[i-1], quantities[i]
+
+            p_avg = (p1 + p2) / 2
+            q_avg = (q1 + q2) / 2
+
+            if p_avg == 0 or q_avg == 0:
+                continue
+
+            delta_p = p2 - p1
+            delta_q = q2 - q1
+
+            if delta_p == 0:
+                continue
+
+            e = (delta_q / q_avg) / (delta_p / p_avg)
+            elasticities.append(e)
+
+        if not elasticities:
+            return None
+
+        return {
+            'value': np.mean(elasticities),
+            'std_error': np.std(elasticities) / np.sqrt(len(elasticities))
+        }
+
+
+def aggregate_price_logs(price_logs: pd.DataFrame,
+                         window_size: str = '1H',
+                         ts_col: str = 'ts',
+                         store_mode : str = 'hotel') -> List[Dict]:
+    """
+    Recover price vectors treating prices as persistent state changes.
+
+    Prices are set-operations that persist until next change. For each window:
+    - If price logs exist: average all changes within window
+    - If no logs: carry forward last price before window end
+
+    Args:
+        price_logs: df with [productId, price, ts, ...]
+        window_size: time window size matching ChunkInteractionsIntoSteps
+        ts_col: timestamp column name
+
+    Returns:
+        list of dicts with {'window_start', 'window_end', 'price_vector'}
+        where price_vector is df with [productId, price]
+    """
+    if price_logs.empty:
+        return []
+
+    df = price_logs.copy()
+
+    if not pd.api.types.is_datetime64_any_dtype(df[ts_col]):
+        df[ts_col] = pd.to_datetime(df[ts_col])
+
+    df = df.sort_values([ts_col, 'productId'])
+    all_products=supabase.table(f'{store_mode}_products').select("id, room_type, date_index, metadata, availability").execute()
+    all_products = pd.DataFrame(all_products.data)
+    unique_products = all_products['id'].unique()
+
+    # generate windows across data range
+    min_time, max_time = df[ts_col].min(), df[ts_col].max()
+    windows = pd.date_range(
+        start=min_time.floor(window_size),
+        end=max_time,
+        freq=window_size
+    )
+
+    chunks = []
+
+    for window_start in windows:
+        window_end = window_start + pd.Timedelta(window_size)
+        price_vector = []
+
+        # all products with price history by window_end
+        #historical_products = df[df[ts_col] < window_end]['productId'].unique()
+        historical_products = unique_products.tolist()
+
+        for pid in historical_products:
+            product_data = df[df['productId'] == pid]
+
+            # logs within window
+            in_window = product_data[
+                (product_data[ts_col] >= window_start) &
+                (product_data[ts_col] < window_end)
+            ]
+
+            if not in_window.empty:
+                # average changes within window
+                price = in_window['price'].mean()
+            else:
+                # carry forward: last price before window end
+                before_window = product_data[product_data[ts_col] < window_end]
+                if before_window.empty:
+                    continue
+                price = before_window['price'].iloc[-1]
+
+            price_vector.append({'productId': pid, 'price': price})
+
+        if price_vector:
+            chunks.append({
+                'window_start': window_start,
+                'window_end': window_end,
+                'price_vector': pd.DataFrame(price_vector)
+            })
+
+    return chunks

experiments/procesing/extract.py

@@ -1,112 +0,0 @@
-import pandas as pd
-import json
-import numpy as np
-import os
-import requests
-from dotenv import load_dotenv
-from sklearn.base import BaseEstimator, TransformerMixin
-from supabase import create_client, Client
-load_dotenv()
-
-BACKEND_URL = os.getenv("BACKEND_URL", "http://localhost:5000")
-SUPABASE_URL = os.getenv("NEXT_PUBLIC_SUPABASE_URL")
-SUPABASE_KEY = os.getenv("NEXT_PUBLIC_SUPABASE_ANON_KEY")
-N_PRICE_BUCKETS = 5
-
-supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
-
-
-class KafkaDataFetcher(BaseEstimator, TransformerMixin):
-    def fit(self, X=None, y=None):
-        return self
-
-    def transform(self, X=None):
-        resp = requests.get(f"{BACKEND_URL}/api/kafka/dump")
-        resp.raise_for_status()
-        data = resp.json()
-
-        if not data.get('success') or not data.get('data'):
-            return pd.DataFrame()
-
-        df = pd.DataFrame(data['data'])
-        # explode metadata col json
-        if 'metadata' in df.columns:
-            df = df.join(pd.json_normalize(df.pop("metadata"), sep=".").add_prefix("metadata_"))
-        df = df.dropna(subset=['eventName'])
-        # remape dateIndex
-        df['dateIndex'] = df['metadata_dateIndex'].astype('Int64')
-        return df
-
-
-class ExperimentJoiner(BaseEstimator, TransformerMixin):
-    def fit(self, X=None, y=None):
-        return self
-
-    def transform(self, df):
-        if df.empty or 'experimentId' not in df.columns:
-            return df
-
-        unique_exp_ids = df['experimentId'].dropna().unique()
-        if len(unique_exp_ids) == 0:
-            return df
-
-        resp = supabase.table('experiments').select(
-            'id, subject_name, xp_human_only, xp_market_mode, xp_task_id, task:tasks(task_name, task_description, task_def_of_done)'
-        ).in_('id', unique_exp_ids.tolist()).execute()
-
-        if not resp.data:
-            return df
-
-        exp_df = pd.DataFrame(resp.data)
-
-        # flatten task nested object if present
-        if 'task' in exp_df.columns and exp_df['task'].notnull().any():
-            task_normalized = pd.json_normalize(exp_df['task'].dropna())
-            task_normalized.index = exp_df[exp_df['task'].notnull()].index
-            exp_df = exp_df.drop(columns=['task']).join(task_normalized, rsuffix='_task')
-
-        # rename experiment columns for clarity
-        exp_df = exp_df.rename(columns={
-            'id': 'experimentId',
-            'subject_name': 'exp_subject',
-            'xp_human_only': 'exp_human_only',
-            'xp_market_mode': 'exp_market_mode',
-            'xp_task_id': 'exp_task_id'
-        })
-
-        df = df.merge(exp_df, on='experimentId', how='left')
-        return df
-
-
-class EventTitleAugmenter(BaseEstimator, TransformerMixin):
-    def fit(self, X=None, y=None):
-        return self
-
-    def transform(self, df):
-        # from taking standard view_item_page in eventName to view_item_page_{metadata_schema}
-        # we want metadata schema to create product specific event names
-
-        # only create price buckets if we have enough unique prices
-        if df["metadata_price"].notnull().sum() > 0:
-            try:
-                price_buckets = pd.qcut(
-                    df["metadata_price"],
-                    q=N_PRICE_BUCKETS,
-                    labels=[f"PB_{i+1}" for i in range(N_PRICE_BUCKETS)],
-                    duplicates='drop'  # handle duplicate bin edges
-                )
-            except ValueError:
-                # fallback: if still not enough unique values, use cut with fixed ranges or just use raw price
-                price_buckets = df["metadata_price"].apply(lambda x: f"P_{int(x)}" if pd.notnull(x) else "")
-        else:
-            price_buckets = pd.Series([""] * len(df), index=df.index)
-
-        # metadata_schema: _product_id@price_bucket_{i} only if we have product metadata otherswise keep original event name
-        # TODO: make this adaptive, if we have hover_over_title we append the title, if its view_page we say which page
-        df["metadata_schema"] = np.where(
-            df["productId"].notnull() & df["metadata_price"].notnull(),
-            "_" + df["productId"].astype(str) + "@" + price_buckets.astype(str),
-            ""
-        )
-        df["eventName"] = df["eventName"] + df["metadata_schema"].astype(str)
-        return df

experiments/procesing/mapping.py

@@ -1,158 +0,0 @@
-import numpy as np
-import pandas as pd
-from sklearn.base import BaseEstimator, TransformerMixin
-
-def build_transition_prob_matrix(df: pd.DataFrame):
-    df = df.dropna(subset=['eventName'])
-    events = df['eventName'].tolist()
-    labels = pd.Index(events).unique().tolist()
-    idx = {e:i for i,e in enumerate(labels)}
-    M = np.zeros((len(labels), len(labels)), dtype=float)
-    for a, b in zip(events, events[1:]):
-        M[idx[a], idx[b]] += 1
-    row_sums = M.sum(axis=1, keepdims=True)
-    with np.errstate(divide='ignore', invalid='ignore'):
-        P = np.divide(M, row_sums, where=row_sums>0)  # row-normalized
-    return P, labels
-
-# https://medium.com/data-science/time-series-data-markov-transition-matrices-7060771e362b
-from graphviz import Digraph
-import numpy as np
-import pandas as pd
-
-def _as_prob_df(matrix, labels=None):
-    """Return a square DataFrame with index=columns=labels."""
-    if isinstance(matrix, pd.DataFrame):
-        # Ensure square and aligned
-        assert (matrix.index == matrix.columns).all(), "Index/columns must match."
-        return matrix
-    matrix = np.asarray(matrix, dtype=float)
-    assert matrix.shape[0] == matrix.shape[1], "Matrix must be square."
-    if labels is None:
-        raise ValueError("labels are required when matrix is not a DataFrame")
-    assert len(labels) == matrix.shape[0], "labels length must match matrix size."
-    return pd.DataFrame(matrix, index=list(labels), columns=list(labels))
-
-def _df_to_edgelist(P: pd.DataFrame, threshold=0.0, round_digits=2):
-    """Build weighted edges > threshold."""
-    edges = []
-    for src in P.index:
-        for dst in P.columns:
-            w = float(P.loc[src, dst])
-            if w > threshold:
-                edges.append((str(src), str(dst), f"{w:.{round_digits}f}"))
-    return edges
-
-def render_graph(fname, matrix, ls_index=None, threshold=0.0, fmt="svg", view=False):
-    """
-    fname: output file stem (no extension)
-    matrix: NumPy array or pandas DataFrame of transition PROBABILITIES
-    ls_index: ordered labels (required if matrix is not a DataFrame)
-    threshold: hide edges with weight <= threshold
-    fmt: 'svg'|'png'|'pdf' etc.
-    view: open after rendering
-    """
-    P = _as_prob_df(matrix, labels=ls_index)
-    edges = _df_to_edgelist(P, threshold=threshold)
-
-    g = Digraph(format=fmt)
-    g.attr(rankdir="LR", size="30")
-    g.attr("node", shape="circle")
-
-    # ensure isolated nodes appear
-    for node in P.index:
-        g.node(str(node), width="1", height="1")
-
-    for src, dst, label in edges:
-        g.edge(src, dst, label=label)
-
-    g.render(fname, view=view, cleanup=True)
-    return g
-
-
-class TransitionProbMatrixTransformer(BaseEstimator, TransformerMixin):
-    def __init__(self, threshold=0.0):
-        self.threshold = threshold
-        self.P_ = None
-        self.labels_ = None
-
-    def fit(self, X: pd.DataFrame, y=None):
-        P, labels = build_transition_prob_matrix(X)
-        self.P_ = P
-        self.labels_ = labels
-        return self
-
-    def transform(self, X: pd.DataFrame = None):
-        return self.P_, self.labels_
-
-    def render(self, fname: str, fmt="svg", view=False):
-        if self.P_ is None or self.labels_ is None:
-            raise ValueError("Transformer has not been fitted yet.")
-        return render_graph(
-            fname,
-            self.P_,
-            ls_index=self.labels_,
-            threshold=self.threshold,
-            fmt=fmt,
-            view=view
-        )
-
-
-class SessionTransitionProbMatrixTransformer(BaseEstimator, TransformerMixin):
-    def __init__(self, threshold=0.0, session_col='sessionId'):
-        self.threshold = threshold
-        self.session_col = session_col
-        self.session_matrices_ = None
-
-    def fit(self, X: pd.DataFrame, y=None):
-        if self.session_col not in X.columns:
-            raise ValueError(f"Column '{self.session_col}' not found in DataFrame")
-
-        session_matrices = {}
-        for session_id, grp in X.groupby(self.session_col):
-            if len(grp) > 1:  # need at least 2 events for transitions
-                P, labels = build_transition_prob_matrix(grp)
-                session_matrices[session_id] = {'matrix': P, 'labels': labels}
-
-        self.session_matrices_ = session_matrices
-        return self
-
-    def transform(self, X: pd.DataFrame = None):
-        if self.session_matrices_ is None:
-            raise ValueError("Transformer has not been fitted yet.")
-        return pd.Series(self.session_matrices_)
-
-    def render_session(self, session_id: str, fname: str, fmt="svg", view=False):
-        if self.session_matrices_ is None:
-            raise ValueError("Transformer has not been fitted yet.")
-        if session_id not in self.session_matrices_:
-            raise ValueError(f"Session '{session_id}' not found in fitted data.")
-
-        sess_data = self.session_matrices_[session_id]
-        return render_graph(
-            fname,
-            sess_data['matrix'],
-            ls_index=sess_data['labels'],
-            threshold=self.threshold,
-            fmt=fmt,
-            view=view
-        )
-if __name__ == "__main__":
-    # Example usage
-    data = {
-        'eventName': [
-            'A', 'B', 'A', 'C', 'B', 'A', 'A', 'C', 'B', 'C',
-            'A', 'B', 'C', 'A', 'B', 'C', 'A', 'B', 'C', 'A'
-        ]
-    }
-    df = pd.DataFrame(data)
-
-    transformer = TransitionProbMatrixTransformer(threshold=0.1)
-    transformer.fit(df)
-    P, labels = transformer.transform(None)
-
-    print("Transition Probability Matrix:")
-    print(pd.DataFrame(P, index=labels, columns=labels))
-
-    # Render the graph
-    transformer.render("transition_graph", fmt="svg", view=False)

experiments/procesing/metrics.py

@@ -0,0 +1,245 @@
+"""
+Revenue and KPI benchmark framework for pricing strategies.
+
+Computes session-level and aggregate metrics to compare pricing functions:
+    - Revenue: R_T = Σ P_t^T · Q_t
+    - Conversion rate
+    - Average order value (AOV)
+    - Agent exploitation loss: L_agent = R_oracle - R_observed
+"""
+from typing import Dict, List, Any, Optional
+from dataclasses import dataclass, field, asdict
+import pandas as pd
+import numpy as np
+
+
+@dataclass
+class SessionMetrics:
+    """KPIs for single session."""
+    session_id: str
+    experiment_id: Optional[str] = None
+
+    # interaction metrics
+    total_interactions: int = 0
+    page_views: int = 0
+    item_views: int = 0
+    searches: int = 0
+    cart_adds: int = 0
+
+    # revenue metrics
+    items_purchased: int = 0
+    total_revenue: float = 0.0
+    avg_item_price: float = 0.0
+    conversion_rate: float = 0.0
+
+    # pricing signals
+    total_price_shown: float = 0.0  # sum of all prices displayed
+    avg_markup: float = 0.0  # avg (price / base_price)
+
+    # behavioral features (for agent detection)
+    interaction_velocity: float = 0.0  # interactions per minute
+    session_duration_sec: float = 0.0
+    unique_products_viewed: int = 0
+
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> Dict[str, Any]:
+        return asdict(self)
+
+
+@dataclass
+class AggregateMetrics:
+    """Aggregate KPIs across sessions/experiments."""
+    experiment_id: Optional[str] = None
+    n_sessions: int = 0
+
+    # revenue aggregates
+    total_revenue: float = 0.0
+    avg_revenue_per_session: float = 0.0
+    median_revenue_per_session: float = 0.0
+
+    # conversion aggregates
+    total_conversions: int = 0
+    conversion_rate: float = 0.0  # purchases / sessions
+
+    # pricing aggregates
+    avg_markup: float = 0.0
+    median_markup: float = 0.0
+
+    # agent exploitation metrics
+    estimated_agent_sessions: int = 0  # sessions flagged as agent-driven
+    agent_revenue: float = 0.0
+    human_revenue: float = 0.0
+    agent_loss: float = 0.0  # L_agent = R_oracle - R_observed (if available)
+
+    def to_dict(self) -> Dict[str, Any]:
+        return asdict(self)
+
+
+class MetricsComputer:
+    """Compute session and aggregate metrics from interaction/price logs."""
+
+    @staticmethod
+    def compute_session_metrics(
+        session_id: str,
+        interactions: pd.DataFrame,
+        price_logs: pd.DataFrame,
+        purchases: Optional[pd.DataFrame] = None,
+        experiment_id: Optional[str] = None
+    ) -> SessionMetrics:
+        """
+        Compute metrics for single session.
+
+        Args:
+            session_id: session identifier
+            interactions: user-interactions events for this session
+            price_logs: price-logs for this session
+            purchases: purchase events (if available)
+            experiment_id: experiment identifier
+        """
+        metrics = SessionMetrics(session_id=session_id, experiment_id=experiment_id)
+
+        if interactions.empty:
+            return metrics
+
+        # interaction counts
+        event_counts = interactions['eventName'].value_counts().to_dict()
+        metrics.total_interactions = len(interactions)
+        metrics.page_views = event_counts.get('page_view', 0) + event_counts.get('view_item_page', 0)
+        metrics.item_views = event_counts.get('view_item_page', 0)
+        metrics.searches = event_counts.get('search', 0)
+        metrics.cart_adds = event_counts.get('add_item_to_cart', 0)
+
+        # unique products viewed
+        metrics.unique_products_viewed = interactions['productId'].dropna().nunique()
+
+        # session duration
+        if 'ts' in interactions.columns:
+            timestamps = pd.to_datetime(interactions['ts'])
+            metrics.session_duration_sec = (timestamps.max() - timestamps.min()).total_seconds()
+            if metrics.session_duration_sec > 0:
+                metrics.interaction_velocity = (metrics.total_interactions / metrics.session_duration_sec) * 60
+
+        # revenue from purchases
+        if purchases is not None and not purchases.empty:
+            metrics.items_purchased = len(purchases)
+            metrics.total_revenue = purchases['price'].sum() if 'price' in purchases.columns else 0.0
+            metrics.avg_item_price = metrics.total_revenue / metrics.items_purchased if metrics.items_purchased > 0 else 0.0
+            metrics.conversion_rate = 1.0 if metrics.items_purchased > 0 else 0.0
+
+        # pricing metrics
+        if not price_logs.empty:
+            metrics.total_price_shown = price_logs['price'].sum()
+            # compute markup if base_price available in price logs or join with product catalog
+            if 'base_price' in price_logs.columns:
+                valid_markup = price_logs[price_logs['base_price'] > 0]
+                if not valid_markup.empty:
+                    metrics.avg_markup = (valid_markup['price'] / valid_markup['base_price']).mean()
+
+        return metrics
+
+    @staticmethod
+    def compute_aggregate_metrics(
+        session_metrics_list: List[SessionMetrics],
+        experiment_id: Optional[str] = None,
+        agent_detector_fn: Optional[callable] = None
+    ) -> AggregateMetrics:
+        """
+        Aggregate metrics across sessions.
+
+        Args:
+            session_metrics_list: list of SessionMetrics
+            experiment_id: experiment identifier
+            agent_detector_fn: optional function to classify session as agent (returns bool)
+        """
+        agg = AggregateMetrics(experiment_id=experiment_id)
+        agg.n_sessions = len(session_metrics_list)
+
+        if agg.n_sessions == 0:
+            return agg
+
+        df = pd.DataFrame([m.to_dict() for m in session_metrics_list])
+
+        # revenue aggregates
+        agg.total_revenue = df['total_revenue'].sum()
+        agg.avg_revenue_per_session = df['total_revenue'].mean()
+        agg.median_revenue_per_session = df['total_revenue'].median()
+
+        # conversion aggregates
+        agg.total_conversions = (df['items_purchased'] > 0).sum()
+        agg.conversion_rate = agg.total_conversions / agg.n_sessions
+
+        # pricing aggregates
+        valid_markups = df[df['avg_markup'] > 0]
+        if not valid_markups.empty:
+            agg.avg_markup = valid_markups['avg_markup'].mean()
+            agg.median_markup = valid_markups['avg_markup'].median()
+
+        # agent detection (if detector provided)
+        if agent_detector_fn is not None:
+            agent_flags = [agent_detector_fn(m) for m in session_metrics_list]
+            agg.estimated_agent_sessions = sum(agent_flags)
+
+            agent_revenue = sum(m.total_revenue for m, is_agent in zip(session_metrics_list, agent_flags) if is_agent)
+            human_revenue = sum(m.total_revenue for m, is_agent in zip(session_metrics_list, agent_flags) if not is_agent)
+
+            agg.agent_revenue = agent_revenue
+            agg.human_revenue = human_revenue
+
+        return agg
+
+    @staticmethod
+    def compare_pricing_strategies(
+        experiments: Dict[str, List[SessionMetrics]],
+        baseline_experiment_id: Optional[str] = None
+    ) -> pd.DataFrame:
+        """
+        Compare multiple pricing strategies/experiments.
+
+        Args:
+            experiments: dict mapping experiment_id -> list of SessionMetrics
+            baseline_experiment_id: experiment to use as baseline for comparison
+
+        Returns:
+            DataFrame with comparative metrics
+        """
+        results = []
+        baseline_agg = None
+
+        for exp_id, session_metrics in experiments.items():
+            agg = MetricsComputer.compute_aggregate_metrics(session_metrics, experiment_id=exp_id)
+            result = agg.to_dict()
+
+            if exp_id == baseline_experiment_id:
+                baseline_agg = agg
+
+            results.append(result)
+
+        df = pd.DataFrame(results)
+
+        # add relative metrics if baseline exists
+        if baseline_agg is not None:
+            df['revenue_lift_pct'] = ((df['total_revenue'] - baseline_agg.total_revenue) / baseline_agg.total_revenue * 100)
+            df['conversion_lift_pct'] = ((df['conversion_rate'] - baseline_agg.conversion_rate) / baseline_agg.conversion_rate * 100)
+
+        return df
+
+
+def simple_agent_detector(session_metrics: SessionMetrics, velocity_threshold: float = 5.0) -> bool:
+    """
+    Simple heuristic agent detector based on interaction velocity.
+
+    Args:
+        session_metrics: SessionMetrics instance
+        velocity_threshold: interactions per minute threshold (default: 5.0)
+
+    Returns:
+        True if session likely agent-driven
+    """
+    # agents tend to have higher interaction velocity and lower session duration
+    if session_metrics.interaction_velocity > velocity_threshold:
+        return True
+    # agents often view many products quickly without converting
+    if session_metrics.unique_products_viewed > 10 and session_metrics.conversion_rate == 0:
+        return True
+    return False

experiments/procesing/pipeline.py

@@ -1,22 +0,0 @@
-from sklearn.pipeline import Pipeline
-from sklearn.preprocessing import StandardScaler
-
-from extract import KafkaDataFetcher, ExperimentJoiner, EventTitleAugmenter
-from mapping import SessionTransitionProbMatrixTransformer, render_graph
-from demand import DemandEstimator
-
-
-# exposable pipelines
-etl_pipeline = Pipeline([
-    ('kafka_fetch', KafkaDataFetcher()),
-    ('experiment_join', ExperimentJoiner()),
-    ('event_augment', EventTitleAugmenter()),
-])
-pricing_pipeline = Pipeline([
-    ('demand_estimation', DemandEstimator()),
-])
-
-if __name__ == "__main__":
-    processed_data = etl_pipeline.fit_transform(None)
-    pricing = pricing_pipeline.fit_transform(processed_data)
-    print(pricing)

experiments/procesing/pipelines.py

@@ -0,0 +1,138 @@
+from sklearn.pipeline import Pipeline
+import pandas as pd
+from procesing.context import PipelineContext
+from procesing.providers import SupabaseProvider, BackendAPIProvider
+from procesing.steps import (
+    FetchInteractionsStep,
+    FetchPriceLogsStep,
+    FetchExperimentsStep,
+    JoinExperimentsStep,
+    CreatePriceBucketsStep,
+    AugmentEventNamesStep,
+    ChunkByTimeWindowStep,
+    ComputeDemandForChunksStep,
+    AggregatePriceLogsStep,
+    # BuildStateSpaceStep,
+    FitPricingFunctionStep,
+    PredictPricesStep,
+    ComputeDemandStep,
+    JoinProductFeaturesStep
+)
+from procesing.pricers import SimpleSurgePricer
+
+def interaction_extraction_pipeline(context: PipelineContext):
+    """Pipeline for extracting and augmenting interaction data"""
+    return Pipeline([
+        ('fetch', FetchInteractionsStep(context)),
+        ('create_buckets', CreatePriceBucketsStep(context)),
+        ('augment_events', AugmentEventNamesStep(context)),
+    ])
+
+
+def price_extraction_pipeline(context: PipelineContext):
+    """Pipeline for extracting price logs"""
+    return Pipeline([
+        ('fetch', FetchPriceLogsStep(context)),
+    ])
+
+
+def product_features_pipeline(context: PipelineContext,
+                                    interactions_df: pd.DataFrame,
+                                    price_logs_df: pd.DataFrame):
+    demand_step = ComputeDemandStep(context)
+    price_step = AggregatePriceLogsStep(context)
+    join_step = JoinProductFeaturesStep(context)
+
+
+    demand_data = demand_step.transform(interactions_df)
+    price_data= price_step.transform(price_logs_df)
+    joined_data = join_step.transform((demand_data, price_data))
+
+    return joined_data
+
+
+
+def pricing_pipeline(context: "PipelineContext",
+                     data: pd.DataFrame,
+                     high_threshold: int = 10,
+                     low_threshold: int = 2,
+                     surge_multiplier: float = 1.2,
+                     discount_multiplier: float = 0.9) -> pd.DataFrame:
+
+    if data.empty or 'productId' not in data.columns:
+        return pd.DataFrame()
+
+    surge_pricer = SimpleSurgePricer()
+    surge_pricer.fit(data)
+    data['optimal_price'] = surge_pricer.predict()
+    return data
+
+
+def full_pipeline(context: PipelineContext,
+                  high_threshold: int = 10,
+                  low_threshold: int = 2,
+                  surge_multiplier: float = 1.2,
+                  discount_multiplier: float = 0.9):
+    """
+    Complete end-to-end pipeline: data extraction -> demand/price aggregation -> surge pricing
+
+    Args:
+        context: Pipeline context
+        high_threshold: Demand threshold for surge pricing
+        low_threshold: Demand threshold for discounts
+        surge_multiplier: Price multiplier for high demand
+        discount_multiplier: Price multiplier for low demand
+
+    Returns:
+        tuple: (product_features_df, optimal_prices_df)
+            - product_features_df: [productId, demand_score, price]
+            - optimal_prices_df: [productId, current_price, optimal_price, demand_score]
+    """
+    interaction_pipe = interaction_extraction_pipeline(context)
+    price_pipe = price_extraction_pipeline(context)
+
+    interactions_df = interaction_pipe.fit_transform(None)
+    price_logs_df = price_pipe.fit_transform(None)
+    product_features_df = product_features_pipeline(context, interactions_df, price_logs_df)
+    print(product_features_df.to_string())
+
+    # generate optimal prices using surge rules
+    optimal_prices_df = pricing_pipeline(context, product_features_df,
+                                          high_threshold=high_threshold,
+                                          low_threshold=low_threshold,
+                                          surge_multiplier=surge_multiplier,
+                                          discount_multiplier=discount_multiplier)
+
+    return product_features_df, optimal_prices_df
+
+
+
+
+if __name__ == '__main__':
+
+    class Provider(SupabaseProvider, BackendAPIProvider):
+        def __init__(self, backend_url: str):
+            SupabaseProvider.__init__(self)
+            BackendAPIProvider.__init__(self, backend_url=backend_url)
+
+
+    class HistoricalProvider(SupabaseProvider, BackendAPIProvider):
+        def fetch_kafka_topic(self, topic: str) -> pd.DataFrame:
+            path = "/home/velocitatem/Documents/Projects/PHANTOM/experiments/collected_data/858c61ab-0a7f-4595-ae49-33f4365517b9/"
+            interactions_file = "messages(2).json"
+            prices_file = "messages(3).json"
+
+            data = pd.read_json(path + (interactions_file if topic == "user-interactions" else prices_file))
+            data = [r['payload'] for r in data['value'].to_list()]
+            data = pd.DataFrame(data)
+            return data
+
+
+    # example run
+    context = PipelineContext(
+        provider=HistoricalProvider(),
+        store_mode='airline',
+    )
+
+    product_features, prices = full_pipeline(context)
+    print(prices.to_string())

experiments/procesing/pricers/__init__.py

@@ -0,0 +1,14 @@
+from procesing.pricers.base import PricingFunction
+from procesing.pricers.elasticity import ElasticityBasedPricer
+from procesing.pricers.simple import StaticPricer, RandomPricer, SimpleSurgePricer
+from procesing.pricers.session_aware import SessionAwarePricer, ProductSpecificSessionPricer
+
+__all__ = [
+    'PricingFunction',
+    'ElasticityBasedPricer',
+    'StaticPricer',
+    'RandomPricer',
+    'SimpleSurgePricer',
+    'SessionAwarePricer',
+    'ProductSpecificSessionPricer'
+]

experiments/procesing/pricers/base.py

@@ -0,0 +1,70 @@
+from abc import ABC, abstractmethod
+from typing import Optional, Dict, Any, List
+import numpy as np
+import pandas as pd
+
+
+class PricingFunction(ABC):
+    """
+    Abstract base for pricing functions.
+
+    Defines mapping: f(Q_t, P_t, S_t, H_t) -> P_{t+1}
+
+    Where:
+        Q_t ∈ R^n: demand vector at time t
+        P_t ∈ R^n: price vector at time t
+        S_t: session features (behavioral signals, interactions)
+        H_t = {Q_{t-k}, P_{t-k}, S_{t-k}}: historical state trajectory
+
+    Objective:
+        maximize E[R_T] = E[Σ P_t^T · Q_t]
+        subject to:
+            Q_t = g(P_t, S_t)  (demand response via elasticity)
+            P_t ≥ C  (cost floor)
+            minimize L_agent = R_oracle - R_observed
+    """
+
+    @abstractmethod
+    def fit(self, *kwargs):
+        """
+        Offline training on historical data.
+
+        Args:
+            historical_data: DataFrame with elasticity, prices, demand signals
+            **kwargs: additional training parameters
+        """
+        pass
+
+    @abstractmethod
+    def predict(self, *kwargs) -> np.ndarray:
+        """
+        Generate optimal prices given current state.
+
+        Args:
+            state_space: StateSpace object containing Q_t, P_t, S_t, H_t
+
+        Returns:
+            P_{t+1}: price vector in R^n
+        """
+        pass
+
+    def update(self, observation: Dict[str, Any]):
+        """
+        Online learning update (optional).
+
+        Args:
+            observation: dict with {state, action, reward, next_state}
+                - state: StateSpace before pricing decision
+                - action: prices shown (P_t)
+                - reward: revenue/conversion signal
+                - next_state: StateSpace after user interaction
+        """
+        pass  # default: no online learning
+
+    def get_params(self) -> Dict[str, Any]:
+        """Return pricing function parameters for serialization."""
+        return {}
+
+    def set_params(self, params: Dict[str, Any]):
+        """Load pricing function parameters from dict."""
+        pass

experiments/procesing/pricers/elasticity.py

@@ -0,0 +1,59 @@
+import numpy as np
+import pandas as pd
+from procesing.pricers.base import PricingFunction
+
+
+class ElasticityBasedPricer(PricingFunction):
+    """
+    Pricing based on demand elasticity estimates.
+    f(Q, S) = base_price * (1 + alpha * elasticity * demand_deviation)
+    """
+
+    def __init__(self, alpha: float = 0.1, price_floor: float = 0.0, price_ceil: float = np.inf):
+        self.alpha = alpha
+        self.price_floor = price_floor
+        self.price_ceil = price_ceil
+        self.elasticity = None
+        self.base_prices = None
+        self.mean_demand = None
+
+    def fit(self, historical_data: pd.DataFrame):
+        """
+        Calibrate from historical elasticity estimates.
+        Expects: [productId, elasticity, base_price, mean_demand]
+        """
+        if 'elasticity' not in historical_data.columns:
+            raise ValueError("historical_data must contain 'elasticity' column")
+
+        self.elasticity = historical_data['elasticity'].values
+        self.base_prices = (historical_data['base_price'].values
+                           if 'base_price' in historical_data.columns
+                           else np.ones(len(historical_data)) * 100)
+        self.mean_demand = (historical_data['mean_demand'].values
+                           if 'mean_demand' in historical_data.columns
+                           else np.ones(len(historical_data)) * 10)
+        return self
+
+    def predict(self, state_space) -> np.ndarray:
+        """
+        Adjust prices based on demand deviation and elasticity.
+        Higher demand -> increase price (but less for elastic goods)
+        """
+        if self.elasticity is None:
+            raise ValueError("Must call fit() before predict()")
+
+        demand = np.asarray(state_space.demand)
+        if len(demand) != len(self.elasticity):
+            raise ValueError(f"Demand vector size {len(demand)} != elasticity size {len(self.elasticity)}")
+
+        # compute demand deviation from mean
+        demand_dev = (demand - self.mean_demand) / (self.mean_demand + 1e-6)
+
+        # adjust price: if demand high and elastic, don't increase much
+        # if demand high and inelastic, increase more
+        price_multiplier = 1 + self.alpha * np.abs(self.elasticity) * demand_dev
+        prices = self.base_prices * price_multiplier
+
+        # enforce bounds
+        prices = np.clip(prices, self.price_floor, self.price_ceil)
+        return prices

experiments/procesing/pricers/session_aware.py

@@ -0,0 +1,172 @@
+"""
+Session-aware pricing functions that leverage behavioral features S_t.
+These pricers aim to minimize L_agent = R_oracle - R_observed.
+"""
+import numpy as np
+import pandas as pd
+from procesing.pricers.base import PricingFunction
+from procesing.pricers.elasticity import ElasticityBasedPricer
+
+
+class SessionAwarePricer(PricingFunction):
+    """
+    Extends elasticity-based pricing with session behavioral signals.
+
+    f(Q, P, S) = base_price * elasticity_factor * session_factor
+
+    Where session_factor adjusts for:
+        - interaction_velocity (agent detection proxy)
+        - product_view_depth (interest signal)
+        - cart_to_view_ratio (conversion intent)
+
+    Strategy: charge higher prices to suspected agents (high velocity)
+    to recover oracle revenue from reconnaissance sessions.
+    """
+
+    def __init__(self,
+                 alpha: float = 0.1,
+                 beta_velocity: float = 0.05,
+                 beta_attention: float = 0.03,
+                 agent_velocity_threshold: float = 5.0,
+                 agent_markup: float = 1.2,
+                 price_floor: float = 0.0,
+                 price_ceil: float = np.inf):
+        """
+        Args:
+            alpha: elasticity sensitivity
+            beta_velocity: interaction velocity weight
+            beta_attention: product attention weight
+            agent_velocity_threshold: velocity above which to apply agent markup
+            agent_markup: price multiplier for suspected agent sessions
+            price_floor, price_ceil: price bounds
+        """
+        self.alpha = alpha
+        self.beta_velocity = beta_velocity
+        self.beta_attention = beta_attention
+        self.agent_velocity_threshold = agent_velocity_threshold
+        self.agent_markup = agent_markup
+        self.price_floor = price_floor
+        self.price_ceil = price_ceil
+
+        # fitted parameters
+        self.elasticity = None
+        self.base_prices = None
+        self.mean_demand = None
+
+    def fit(self, historical_data: pd.DataFrame, **kwargs):
+        """Calibrate from historical elasticity data."""
+        if 'elasticity' not in historical_data.columns:
+            raise ValueError("historical_data must contain 'elasticity'")
+
+        self.elasticity = historical_data['elasticity'].values
+        self.base_prices = (historical_data['base_price'].values
+                           if 'base_price' in historical_data.columns
+                           else np.ones(len(historical_data)) * 100)
+        self.mean_demand = (historical_data['mean_demand'].values
+                           if 'mean_demand' in historical_data.columns
+                           else np.ones(len(historical_data)) * 10)
+        return self
+
+    def predict(self, state_space) -> np.ndarray:
+        """Generate prices with session awareness."""
+        if self.elasticity is None:
+            raise ValueError("Must call fit() before predict()")
+
+        demand = np.asarray(state_space.demand)
+        n_products = len(demand)
+
+        # base elasticity-driven pricing
+        demand_dev = (demand - self.mean_demand) / (self.mean_demand + 1e-6)
+        elasticity_factor = 1 + self.alpha * np.abs(self.elasticity) * demand_dev
+
+        # session-aware adjustments
+        session_factor = np.ones(n_products)
+
+        if not state_space.session_features.empty:
+            sf = state_space.session_features.iloc[0]  # single session features
+
+            # agent detection via velocity
+            velocity = sf.get('interaction_velocity', 0.0)
+            if velocity > self.agent_velocity_threshold:
+                # suspected agent: apply markup to recover oracle revenue
+                session_factor *= self.agent_markup
+
+            # attention signal: higher view depth -> user interested -> can charge more
+            view_depth = sf.get('product_view_depth', 0)
+            if view_depth > 0:
+                attention_boost = 1 + self.beta_attention * np.log1p(view_depth)
+                session_factor *= attention_boost
+
+            # cart presence: if user has items in cart, slightly increase prices
+            cart_to_view = sf.get('cart_to_view_ratio', 0.0)
+            if cart_to_view > 0.1:
+                session_factor *= (1 + 0.02)  # small boost for conversion intent
+
+        prices = self.base_prices * elasticity_factor * session_factor
+        prices = np.clip(prices, self.price_floor, self.price_ceil)
+
+        return prices
+
+
+class ProductSpecificSessionPricer(PricingFunction):
+    """
+    Session-aware pricer with product-specific demand signals.
+
+    Uses S_t to extract per-product interaction counts and adjusts pricing
+    for products the user has already viewed/hovered.
+
+    Strategy: products viewed multiple times = high interest -> price up
+    """
+
+    def __init__(self,
+                 alpha: float = 0.1,
+                 view_boost: float = 0.02,
+                 max_view_boost: float = 0.15,
+                 price_floor: float = 0.0,
+                 price_ceil: float = np.inf):
+        self.alpha = alpha
+        self.view_boost = view_boost
+        self.max_view_boost = max_view_boost
+        self.price_floor = price_floor
+        self.price_ceil = price_ceil
+
+        self.elasticity = None
+        self.base_prices = None
+        self.mean_demand = None
+        self.product_ids = None
+
+    def fit(self, historical_data: pd.DataFrame, **kwargs):
+        if 'elasticity' not in historical_data.columns or 'productId' not in historical_data.columns:
+            raise ValueError("historical_data must contain 'elasticity' and 'productId'")
+
+        self.elasticity = historical_data['elasticity'].values
+        self.base_prices = (historical_data['base_price'].values
+                           if 'base_price' in historical_data.columns
+                           else np.ones(len(historical_data)) * 100)
+        self.mean_demand = (historical_data['mean_demand'].values
+                           if 'mean_demand' in historical_data.columns
+                           else np.ones(len(historical_data)) * 10)
+        self.product_ids = historical_data['productId'].values
+        return self
+
+    def predict(self, state_space) -> np.ndarray:
+        if self.elasticity is None:
+            raise ValueError("Must call fit() before predict()")
+
+        demand = np.asarray(state_space.demand)
+        n_products = len(demand)
+
+        # base pricing
+        demand_dev = (demand - self.mean_demand) / (self.mean_demand + 1e-6)
+        base_prices = self.base_prices * (1 + self.alpha * np.abs(self.elasticity) * demand_dev)
+
+        # product-specific session adjustments
+        if not state_space.session_features.empty and state_space.product_ids is not None:
+            # extract product interaction counts from session metadata
+            # (this would require session features to include per-product signals)
+            # for now, use uniform boost as placeholder
+            # TODO: extend session feature extraction to include product-specific counts
+            pass
+
+        prices = np.clip(base_prices, self.price_floor, self.price_ceil)
+        return prices

experiments/procesing/pricers/simple.py

@@ -0,0 +1,91 @@
+import numpy as np
+import pandas as pd
+from procesing.pricers.base import PricingFunction
+
+
+class StaticPricer(PricingFunction):
+    """Static pricing: always return fixed base prices"""
+
+    def __init__(self, base_prices: np.ndarray = None):
+        self.base_prices = base_prices
+
+    def fit(self, historical_data: pd.DataFrame):
+        """Extract base prices from historical data"""
+        if 'base_price' in historical_data.columns:
+            self.base_prices = historical_data['base_price'].values
+        elif 'price' in historical_data.columns:
+            self.base_prices = historical_data['price'].values
+        else:
+            raise ValueError("historical_data must contain 'base_price' or 'price' column")
+        return self
+
+    def predict(self, state_space) -> np.ndarray:
+        """Return static base prices regardless of state"""
+        if self.base_prices is None:
+            raise ValueError("Must call fit() or provide base_prices in constructor")
+        return self.base_prices.copy()
+
+
+class RandomPricer(PricingFunction):
+    """Random pricing within bounds (for baseline comparison)"""
+
+    def __init__(self, price_min: float = 50.0, price_max: float = 500.0, seed: int = None):
+        self.price_min = price_min
+        self.price_max = price_max
+        self.seed = seed
+        self.n_products = None
+        self.rng = np.random.default_rng(seed)
+
+    def fit(self, historical_data: pd.DataFrame):
+        """Learn number of products"""
+        self.n_products = len(historical_data)
+        return self
+
+    def predict(self, state_space) -> np.ndarray:
+        """Generate random prices"""
+        if self.n_products is None:
+            self.n_products = len(state_space.demand)
+        return self.rng.uniform(self.price_min, self.price_max, size=self.n_products)
+
+
+class SimpleSurgePricer(PricingFunction):
+    """
+    Rule-based surge pricer adjusting prices via demand thresholds.
+    Logic: if demand > high_threshold -> surge, if demand < low_threshold -> discount.
+    Simpler and more controllable than curve fitting approaches.
+    """
+
+    def __init__(self,
+                 base_prices: np.ndarray = None,
+                 high_threshold: int = 10,
+                 low_threshold: int = 2,
+                 surge_multiplier: float = 1.2,
+                 discount_multiplier: float = 0.9):
+        self.base_prices = base_prices
+        self.high_threshold = high_threshold
+        self.low_threshold = low_threshold
+        self.surge_multiplier = surge_multiplier
+        self.discount_multiplier = discount_multiplier
+
+    def fit(self, market_data : pd.DataFrame):
+        """Extract base prices from product catalog or historical averages"""
+        self.base_prices = market_data['base_price'].to_numpy() if 'base_price' in market_data.columns else market_data['price'].values
+        self.demand_history = market_data['demand'].to_numpy() if 'demand' in market_data.columns else np.zeros_like(self.base_prices)
+
+    def predict(self) -> np.ndarray:
+        """
+        Adjust prices based on current demand using surge rules.
+        state_space.demand: demand counts per product
+        state_space.prices: current prices (fallback if base_prices not set)
+        """
+        current_prices = self.base_prices if self.base_prices is not None else np.ones_like(demand_vector) * 99.99
+        demand = self.demand_history if self.demand_history is not None else np.zeros_like(current_prices)
+        new_prices = current_prices.copy()
+
+        high_mask = demand >= self.high_threshold
+        new_prices[high_mask] *= self.surge_multiplier
+
+        low_mask = demand <= self.low_threshold
+        new_prices[low_mask] *= self.discount_multiplier
+
+        return new_prices

experiments/procesing/pricing.py

@@ -0,0 +1,272 @@
+r"""
+Our state space comes as:
+$Q_t in R^n$ - our demand at a time t
+$P_t in R^n$ - prices at time t
+$S_t$ some form of interaction session features
+
+This is a single sate which we map under
+
+$f: (Q, S, H) \to P_{t+1}$
+
+With:
+
+$H_t = \{Q_{t-k}, P_{t-k}, S_{t-k}\}$
+
+
+We can have f be literally anything, analytical or learned or rule based or an RL policy.
+
+Our goal is to mazimize the expected revenue:
+
+$E[R_T] = E[\sum_{t=1}^T P_t^T \dot Q_t]$
+
+subject to Q_t = g(P_t, S_t) : demand response to price (estimated via elasticity) and P_t ≥ C : prices above cost floor and additionally minimizing the following:
+
+$L_{agent} = R_{oracle} - R_{observed}
+
+where: R_oracle = revenue if we knew agent intentions (from recon session) and R_observed = revenue under current pricing policy f
+
+I would start be defning a pricing function interface and standardizing how to train that based on historical data and define how to make it behave for online training (if we do that)
+
+We also need to develop a solid benchmark with mapping revenue and full KPIs from session interactions to measure differences between different price learning methods
+"""
+
+from abc import ABC, abstractmethod
+from sklearn.base import BaseEstimator, TransformerMixin
+import numpy as np
+import pandas as pd
+import os
+from dotenv import load_dotenv
+load_dotenv()
+from supabase import create_client, Client
+
+SUPABASE_URL = os.getenv("NEXT_PUBLIC_SUPABASE_URL", "")
+SUPABASE_KEY = os.getenv("NEXT_PUBLIC_SUPABASE_ANON_KEY", "")
+supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
+
+def expected_revenue(prices: np.ndarray, demand: np.ndarray) -> float:
+    """Returns: expected revenue R_t = P_t^T * Q_t"""
+    return float(np.dot(prices, demand))
+
+class StateSpace:
+    def __init__(self,
+                 demand : np.ndarray, # at time t, only values (assuming aligned by productId order)
+                 prices : np.ndarray, # at time t, only values (assuming aligned by productId order)
+                 session_features : pd.DataFrame):
+        self.demand = demand  # Q_t
+        self.prices = prices  # P_t
+        self.session_features = session_features  # S_t
+        self.history = []  # H_t
+
+class PricingFunction(BaseEstimator, TransformerMixin, ABC):
+    def __init__(self):
+        pass
+
+    def fit(self, historical_data):
+        """
+        Train the pricing function based on historical data.
+        historical_data: list of StateSpace instances with known outcomes
+        """
+        raise NotImplementedError("Train method must be implemented by subclass.")
+
+    def transform(self, state_space) -> np.ndarray:
+        """
+        Predict the next prices given the current state space.
+        state_space: StateSpace instance
+        Returns: predicted prices P_{t+1}
+        """
+        raise NotImplementedError("Predict method must be implemented by subclass.")
+
+
+class SimpleLinearPricingFunction(PricingFunction):
+    def __init__(self, price_sensitivity: float = -0.1):
+        super().__init__()
+        self.price_sensitivity = price_sensitivity
+
+    def fit(self, historical_data):
+        return self
+
+    def transform(self, state_space: StateSpace) -> np.ndarray:
+        new_prices = state_space.prices + self.price_sensitivity * state_space.demand
+        return np.maximum(new_prices, 0)
+
+
+class ElasticityBasedPricingFunction(PricingFunction):
+    """
+    Revenue-maximizing pricing using elasticity estimates.
+
+    For each product, optimal price P* maximizes R = P * Q(P)
+    where Q(P) follows power law: Q(P) = Q_0 * (P/P_0)^ε
+
+    Taking derivative dR/dP = 0 gives optimal markup:
+    P* = P_0 * (1 + 1/ε) if ε < -1 (elastic)
+
+    For inelastic demand (|ε| < 1), we apply bounded markup.
+    """
+
+    def __init__(self,
+                 cost_floor: float = 0.5,
+                 max_markup: float = 2.0,
+                 min_markup: float = 1.0,
+                 inelastic_markup: float = 1.3):
+        super().__init__()
+        self.cost_floor = cost_floor  # prices as fraction of base
+        self.max_markup = max_markup  # max price = base * max_markup
+        self.min_markup = min_markup  # min price = base * min_markup
+        self.inelastic_markup = inelastic_markup  # default for |ε| < 1
+        self.elasticity_map = {}  # productId -> elasticity
+
+    def fit(self, elasticity_df: pd.DataFrame):
+        """
+        Args:
+            elasticity_df: df with [productId, elasticity, std_error, n_obs]
+        """
+        if elasticity_df is not None and not elasticity_df.empty:
+            self.elasticity_map = dict(zip(
+                elasticity_df['productId'],
+                elasticity_df['elasticity']
+            ))
+        return self
+
+    def transform(self, state_space: StateSpace, product_ids: np.ndarray = None) -> np.ndarray:
+        """
+        Args:
+            state_space: current state (prices = base prices)
+            product_ids: array of productIds aligned with state_space.prices
+
+        Returns:
+            optimized prices P_{t+1}
+        """
+        base_prices = state_space.prices
+
+        if product_ids is None:
+            # fallback: use positional index as productId (not ideal)
+            product_ids = np.arange(len(base_prices))
+
+        new_prices = np.zeros_like(base_prices)
+
+        for i, (base_p, pid) in enumerate(zip(base_prices, product_ids)):
+            elasticity = self.elasticity_map.get(pid, 0.0)
+
+            if elasticity < -1:  # elastic demand
+                # optimal markup: (1 + 1/ε)
+                markup = 1 + (1 / elasticity)
+                optimal_p = base_p * markup
+            elif elasticity > -1 and elasticity < 0:  # inelastic
+                # conservative markup
+                optimal_p = base_p * self.inelastic_markup
+            else:  # ε ≥ 0 (demand increases with price, or no data)
+                # no elasticity data or anomalous, keep base price
+                optimal_p = base_p
+
+            # apply bounds
+            optimal_p = np.clip(
+                optimal_p,
+                base_p * self.min_markup,
+                base_p * self.max_markup
+            )
+            optimal_p = max(optimal_p, self.cost_floor)
+
+            new_prices[i] = optimal_p
+
+        return new_prices
+
+
+class ContextualElasticityPricing(PricingFunction):
+    """
+    Revenue optimization with contextual adjustments based on session features.
+
+    Combines elasticity-based pricing with surge/demand-based multipliers.
+    """
+
+    def __init__(self,
+                 base_pricer: ElasticityBasedPricingFunction = None,
+                 demand_sensitivity: float = 0.1,
+                 surge_threshold: float = 0.7):
+        super().__init__()
+        self.base_pricer = base_pricer or ElasticityBasedPricingFunction()
+        self.demand_sensitivity = demand_sensitivity
+        self.surge_threshold = surge_threshold
+
+    def fit(self, elasticity_df: pd.DataFrame):
+        self.base_pricer.fit(elasticity_df)
+        return self
+
+    def transform(self, state_space: StateSpace, product_ids: np.ndarray = None) -> np.ndarray:
+        # get base optimal prices from elasticity
+        base_optimal = self.base_pricer.transform(state_space, product_ids)
+
+        # compute surge multiplier from demand
+        if len(state_space.demand) > 0:
+            demand_normalized = state_space.demand / (state_space.demand.max() + 1e-8)
+            surge_multiplier = 1 + self.demand_sensitivity * np.maximum(
+                demand_normalized - self.surge_threshold, 0
+            )
+        else:
+            surge_multiplier = np.ones_like(base_optimal)
+
+        return base_optimal * surge_multiplier
+
+# Example usage:
+if __name__ == "__main__":
+    from pipeline import interaction_pipeline, price_data_pipeline, elasticity_pipeline
+
+    store_mode = 'hotel'
+    interaction_data = interaction_pipeline.fit_transform(None)
+    price_data = price_data_pipeline.fit_transform(None)
+
+    elasticity_df = elasticity_pipeline(interaction_data, price_data, window_size="30s", store_mode=store_mode)
+
+    # fetch all products with base prices from database
+    products_resp = supabase.table(f'{store_mode}_products').select("id, metadata").execute()
+    products_df = pd.DataFrame(products_resp.data)
+
+    # extract base_price from metadata
+    products_df['base_price'] = products_df['metadata'].apply(lambda m: m.get('base_price', 0) if isinstance(m, dict) else 0)
+    products_df = products_df.rename(columns={'id': 'productId'})[['productId', 'base_price']]
+
+    # override with logged prices where available
+    if not price_data.empty:
+        if 'ts' in price_data.columns and not pd.api.types.is_datetime64_any_dtype(price_data['ts']):
+            price_data['ts'] = pd.to_datetime(price_data['ts'])
+
+        # get latest logged price per product
+        price_logs_agg = price_data.sort_values('ts').groupby('productId', as_index=False).last()
+
+        # merge: start with all products (base prices), override with logged prices
+        products_df = products_df.merge(
+            price_logs_agg[['productId', 'price']],
+            on='productId',
+            how='left'
+        )
+        products_df['final_price'] = products_df['price'].fillna(products_df['base_price'])
+    else:
+        products_df['final_price'] = products_df['base_price']
+
+    # merge with elasticity
+    if elasticity_df is not None and not elasticity_df.empty:
+        price_data_merged = products_df[['productId', 'final_price']].merge(
+            elasticity_df[['productId', 'elasticity']],
+            on='productId',
+            how='left'
+        ).fillna({'elasticity': 0.0})
+
+        prices = price_data_merged['final_price'].values
+        elasticities = price_data_merged['elasticity'].values
+    else:
+        prices = np.array([])
+        elasticities = np.array([])
+
+    print(elasticities)
+    print(prices)
+
+    state_space = StateSpace(
+        demand=elasticities,
+        prices=prices,
+        session_features=interaction_data
+    )
+
+    pricing_function = SimpleLinearPricingFunction(price_sensitivity=-0.05)
+    pricing_function.fit([])  # No training data for simple model
+    predicted_prices = pricing_function.transform(state_space)
+
+    print("Predicted Prices:", predicted_prices)

experiments/procesing/providers/__init__.py

@@ -0,0 +1,5 @@
+from procesing.providers.base import DataProvider
+from procesing.providers.supabase import SupabaseProvider
+from procesing.providers.backend import BackendAPIProvider
+
+__all__ = ['DataProvider', 'SupabaseProvider', 'BackendAPIProvider']

experiments/procesing/providers/backend.py

@@ -0,0 +1,19 @@
+import os
+import pandas as pd
+import requests
+from typing import List
+from procesing.providers.base import DataProvider
+
+class BackendAPIProvider(DataProvider):
+    """Concrete backend API implementation"""
+    def __init__(self, backend_url: str = None):
+        self.backend_url = backend_url or os.getenv("BACKEND_URL", "http://localhost:5000")
+    def fetch_kafka_topic(self, topic: str) -> pd.DataFrame:
+        resp = requests.get(f"{self.backend_url}/api/kafka/dump?topic={topic}")
+        resp.raise_for_status()
+        data = resp.json()
+
+        if not data.get('success') or not data.get('data'):
+            return pd.DataFrame()
+
+        return pd.DataFrame(data['data'])

experiments/procesing/providers/base.py

@@ -0,0 +1,21 @@
+from abc import ABC, abstractmethod
+from typing import List
+import pandas as pd
+
+class DataProvider(ABC):
+    """Abstract interface for data access, enables DI and testing"""
+
+    @abstractmethod
+    def fetch_products(self, store_mode: str) -> pd.DataFrame:
+        """Fetch product catalog for given store mode"""
+        pass
+
+    @abstractmethod
+    def fetch_experiments(self, experiment_ids: List[str]) -> pd.DataFrame:
+        """Fetch experiment metadata for given IDs"""
+        pass
+
+    @abstractmethod
+    def fetch_kafka_topic(self, topic: str) -> pd.DataFrame:
+        """Fetch data from Kafka topic via backend API"""
+        pass

experiments/procesing/providers/supabase.py

@@ -0,0 +1,42 @@
+import os
+import pandas as pd
+import requests
+from typing import List
+from supabase import create_client, Client
+from procesing.providers.base import DataProvider
+from dotenv import load_dotenv
+
+class SupabaseProvider(DataProvider):
+    """Concrete Supabase + backend API implementation"""
+
+    def __init__(self,
+                 supabase_url: str = None,
+                 supabase_key: str = None,):
+        load_dotenv()
+        self.supabase_url = supabase_url or os.getenv("NEXT_PUBLIC_SUPABASE_URL")
+        self.supabase_key = supabase_key or os.getenv("NEXT_PUBLIC_SUPABASE_ANON_KEY")
+        self.supabase: Client = create_client(self.supabase_url, self.supabase_key)
+
+    def fetch_products(self, store_mode: str) -> pd.DataFrame:
+        # hotel uses room_type, airline uses flight_type; select all and normalize
+        resp = self.supabase.table(f'{store_mode}_products').select("*").execute()
+        if not resp.data:
+            return pd.DataFrame()
+        df = pd.DataFrame(resp.data)
+        # normalize type column: hotel has room_type, airline has flight_type
+        if 'room_type' in df.columns:
+            df['product_type'] = df['room_type']
+        elif 'flight_type' in df.columns:
+            df['product_type'] = df['flight_type']
+        return df
+
+    def fetch_experiments(self, experiment_ids: List[str]) -> pd.DataFrame:
+        if not experiment_ids:
+            return pd.DataFrame()
+
+        resp = self.supabase.table('experiments').select(
+            'id, subject_name, xp_human_only, xp_market_mode, xp_task_id, '
+            'task:tasks(task_name, task_description, task_def_of_done)'
+        ).in_('id', experiment_ids).execute()
+
+        return pd.DataFrame(resp.data) if resp.data else pd.DataFrame()

experiments/procesing/steps/__init__.py

@@ -0,0 +1,29 @@
+from procesing.steps.base import BaseContextStep
+from procesing.steps.fetch import FetchInteractionsStep, FetchPriceLogsStep, FetchExperimentsStep
+from procesing.steps.join import JoinExperimentsStep, JoinProductFeaturesStep
+from procesing.steps.augment import CreatePriceBucketsStep, AugmentEventNamesStep, AugmentInteractionsStep
+from procesing.steps.chunk import ChunkByTimeWindowStep
+from procesing.steps.demand import ComputeDemandStep, ComputeDemandForChunksStep
+from procesing.steps.elasticity import AggregatePriceLogsStep
+from procesing.steps.pricing import FitPricingFunctionStep, PredictPricesStep
+from procesing.steps.session import ExtractSessionFeaturesStep, _extract_features_for_session
+
+__all__ = [
+    'BaseContextStep',
+    'FetchInteractionsStep',
+    'FetchPriceLogsStep',
+    'FetchExperimentsStep',
+    'JoinExperimentsStep',
+    'JoinProductFeaturesStep',
+    'CreatePriceBucketsStep',
+    'AugmentEventNamesStep',
+    'AugmentInteractionsStep',
+    'ChunkByTimeWindowStep',
+    'ComputeDemandStep',
+    'ComputeDemandForChunksStep',
+    'AggregatePriceLogsStep',
+    'FitPricingFunctionStep',
+    'PredictPricesStep',
+    'ExtractSessionFeaturesStep',
+    '_extract_features_for_session',
+]

experiments/procesing/steps/augment.py

@@ -0,0 +1,140 @@
+import numpy as np
+import pandas as pd
+from procesing.steps.base import BaseContextStep
+
+
+class AugmentInteractionsStep(BaseContextStep):
+    """
+    Consolidated step: create price buckets, augment event names, join experiments.
+    Input: (interactions_df, price_logs_df)
+    Output: enriched interactions_df
+    """
+
+    def transform(self, data: tuple):
+        interactions_df, price_logs_df = data
+
+        if interactions_df.empty:
+            return interactions_df
+
+        # Step 1: Create price buckets
+        interactions_df = self._create_price_buckets(interactions_df)
+
+        # Step 2: Augment event names
+        interactions_df = self._augment_event_names(interactions_df)
+
+        # Step 3: Join experiments (optional)
+        if 'experimentId' in interactions_df.columns:
+            interactions_df = self._join_experiments(interactions_df)
+
+        return interactions_df
+
+    def _create_price_buckets(self, df: pd.DataFrame):
+        """Create price bucket labels from price data"""
+        if 'metadata_price' not in df.columns:
+            df['price_bucket'] = ""
+            return df
+
+        n_buckets = self.context.config.get('n_price_buckets', 5)
+
+        if df['metadata_price'].notnull().sum() > 0:
+            try:
+                price_buckets = pd.qcut(
+                    df['metadata_price'],
+                    q=n_buckets,
+                    labels=[f"PB_{i+1}" for i in range(n_buckets)],
+                    duplicates='drop'
+                )
+            except ValueError:
+                # fallback for insufficient unique values
+                price_buckets = df['metadata_price'].apply(
+                    lambda x: f"P_{int(x)}" if pd.notnull(x) else ""
+                )
+        else:
+            price_buckets = pd.Series([""] * len(df), index=df.index)
+
+        df['price_bucket'] = price_buckets
+        return df
+
+    def _augment_event_names(self, df: pd.DataFrame):
+        """Augment event names with product and price bucket schema"""
+        # Create schema: _productId@price_bucket
+        has_product = df.get('productId', pd.Series()).notnull()
+        has_bucket = df.get('price_bucket', pd.Series()).notnull()
+
+        df['metadata_schema'] = np.where(
+            has_product & has_bucket,
+            "_" + df['productId'].astype(str) + "@" + df['price_bucket'].astype(str),
+            ""
+        )
+
+        df['eventName'] = df['eventName'] + df['metadata_schema']
+        return df
+
+    def _join_experiments(self, df: pd.DataFrame):
+        """Join experiment metadata if experimentId present"""
+        exp_ids = df['experimentId'].dropna().unique().tolist()
+        if not exp_ids:
+            return df
+
+        experiments_df = self.context.provider.fetch_experiments(exp_ids)
+        if experiments_df.empty:
+            return df
+
+        return df.merge(
+            experiments_df,
+            left_on='experimentId',
+            right_on='id',
+            how='left',
+            suffixes=('', '_exp')
+        )
+
+
+class CreatePriceBucketsStep(BaseContextStep):
+    """Create price bucket labels from price data"""
+
+    def transform(self, df: pd.DataFrame):
+        if df.empty or 'metadata_price' not in df.columns:
+            df['price_bucket'] = ""
+            return df
+
+        n_buckets = self.context.config.get('n_price_buckets', 5)
+
+        if df['metadata_price'].notnull().sum() > 0:
+            try:
+                price_buckets = pd.qcut(
+                    df['metadata_price'],
+                    q=n_buckets,
+                    labels=[f"PB_{i+1}" for i in range(n_buckets)],
+                    duplicates='drop'
+                )
+            except ValueError:
+                # fallback for insufficient unique values
+                price_buckets = df['metadata_price'].apply(
+                    lambda x: f"P_{int(x)}" if pd.notnull(x) else ""
+                )
+        else:
+            price_buckets = pd.Series([""] * len(df), index=df.index)
+
+        df['price_bucket'] = price_buckets
+        return df
+
+
+class AugmentEventNamesStep(BaseContextStep):
+    """Augment event names with product and price bucket schema"""
+
+    def transform(self, df: pd.DataFrame):
+        if df.empty:
+            return df
+
+        # Create schema: _productId@price_bucket
+        has_product = df.get('productId', pd.Series()).notnull()
+        has_bucket = df.get('price_bucket', pd.Series()).notnull()
+
+        df['metadata_schema'] = np.where(
+            has_product & has_bucket,
+            "_" + df['productId'].astype(str) + "@" + df['price_bucket'].astype(str),
+            ""
+        )
+
+        df['eventName'] = df['eventName'] + df['metadata_schema']
+        return df

experiments/procesing/steps/base.py

@@ -0,0 +1,31 @@
+from abc import ABC, abstractmethod
+from sklearn.base import BaseEstimator, TransformerMixin
+from procesing.context import PipelineContext
+
+class BaseContextStep(BaseEstimator, TransformerMixin, ABC):
+    """
+    Base for all pipeline steps.
+    Each step is stateless, context-driven, and performs ONE transformation.
+    """
+
+    def __init__(self, context: PipelineContext):
+        self.context = context
+
+    def fit(self, X=None, y=None):
+        """Most steps don't need training"""
+        return self
+
+    @abstractmethod
+    def transform(self, X):
+        """Transform input using context. Must be implemented by subclass."""
+        pass
+
+    def get_params(self, deep=True):
+        """sklearn compatibility"""
+        return {'context': self.context}
+
+    def set_params(self, **params):
+        """sklearn compatibility"""
+        if 'context' in params:
+            self.context = params['context']
+        return self

experiments/procesing/steps/chunk.py

@@ -0,0 +1,34 @@
+import pandas as pd
+from procesing.steps.base import BaseContextStep
+
+class ChunkByTimeWindowStep(BaseContextStep):
+    """
+    Chunk dataframe into time windows.
+    Returns list of dicts with window metadata.
+    """
+
+    def transform(self, df: pd.DataFrame):
+        if df.empty:
+            return []
+
+        df = df.copy()
+        ts_col = self.context.config.get('ts_col', 'ts')
+        window_size = self.context.window_size
+
+        # ensure datetime
+        if not pd.api.types.is_datetime64_any_dtype(df[ts_col]):
+            df[ts_col] = pd.to_datetime(df[ts_col])
+
+        df = df.sort_values(ts_col)
+        df['_window'] = df[ts_col].dt.floor(window_size)
+
+        chunks = []
+        for idx, (window_start, group) in enumerate(df.groupby('_window')):
+            chunks.append({
+                'window_start': window_start,
+                'window_end': window_start + pd.Timedelta(window_size),
+                'window_idx': idx,
+                'data': group.drop(columns=['_window'])
+            })
+
+        return chunks

experiments/procesing/steps/demand.py

@@ -0,0 +1,61 @@
+import pandas as pd
+from procesing.steps.base import BaseContextStep
+
+class ComputeDemandStep(BaseContextStep):
+    """
+    Compute demand vector for a single time window or dataframe.
+    Input: single chunk dict OR raw dataframe
+    Output: demand dataframe with [productId, demand_score]
+    """
+
+    def transform(self, chunk):
+        # handle both chunk dict and raw dataframe
+        if isinstance(chunk, dict):
+            interactions = chunk['data']
+            window_meta = {k: v for k, v in chunk.items() if k != 'data'}
+        else:
+            interactions = chunk
+            window_meta = {}
+
+        products = self.context.products
+        unique_products = products['id'].unique()
+
+        # apply filters if configured
+        session_filter = self.context.config.get('session_filter')
+        experiment_filter = self.context.config.get('experiment_filter')
+
+        if session_filter and 'sessionId' in interactions.columns:
+            interactions = interactions[interactions['sessionId'] == session_filter]
+        if experiment_filter and 'experimentId' in interactions.columns:
+            interactions = interactions[interactions['experimentId'] == experiment_filter]
+
+        interactions_with_products = interactions.dropna(subset=['productId'])
+
+        if interactions_with_products.empty:
+            demand_df = pd.DataFrame({
+                'productId': unique_products,
+                'demand_score': 0
+            })
+        else:
+            # crosstab for simple demand count
+            demand_df = pd.crosstab(
+                interactions_with_products['productId'],
+                'count'
+            ).reindex(unique_products, fill_value=0).reset_index()
+            demand_df.columns = ['productId', 'demand_score']
+
+        # attach window metadata if present
+        if window_meta:
+            return {**window_meta, 'demand_vector': demand_df}
+        return demand_df
+
+
+class ComputeDemandForChunksStep(BaseContextStep):
+    """Apply ComputeDemandStep to list of chunks"""
+
+    def transform(self, chunks: list):
+        if not chunks:
+            return []
+
+        demand_step = ComputeDemandStep(self.context)
+        return [demand_step.transform(chunk) for chunk in chunks]

experiments/procesing/steps/elasticity.py

@@ -0,0 +1,42 @@
+import numpy as np
+import pandas as pd
+from typing import Dict, List
+from procesing.steps.base import BaseContextStep
+
+class AggregatePriceLogsStep(BaseContextStep):
+    """
+    Aggregate price logs into time windows using VECTORIZED operations.
+    Input: price_logs_df
+    Output: list of price chunks with [productId, price]
+    """
+
+    def transform(self, price_logs_df: pd.DataFrame):
+        if price_logs_df.empty:
+            return []
+
+        df = price_logs_df.copy()
+        ts_col = self.context.config.get('ts_col', 'ts')
+        #window_size = self.context.window_size WE ARE NOT USING CHUNKS ANYMORE
+
+        # ensure datetime
+        if not pd.api.types.is_datetime64_any_dtype(df[ts_col]):
+            df[ts_col] = pd.to_datetime(df[ts_col])
+
+        df = df.sort_values([ts_col, 'productId'])
+        products = self.context.products
+        # get base price from metadata if available 1) read the metadata col as json and get the base_price
+        products['base_price'] = products.apply(
+            lambda row: row['metadata'].get('base_price', 0) if isinstance(row['metadata'], dict) else 0,
+            axis=1
+        )
+
+        unique_products = products['id'].unique()
+
+        df_indexed = df.set_index(ts_col)
+        # we return a df of average price per product over the entire period
+        # TODO: maybe consider different opration to handle price aggregation over time
+        avg_prices = df_indexed.groupby('productId')['price'].mean().reindex(unique_products, fill_value=0).reset_index()
+        avg_prices.columns = ['productId', 'price']
+        # fill 0s with base_price from products
+        base_price_map = products.set_index('id')['base_price'].to_dict()
+        return avg_prices

experiments/procesing/steps/fetch.py

@@ -0,0 +1,81 @@
+import pandas as pd
+from procesing.steps.base import BaseContextStep
+
+class FetchInteractionsStep(BaseContextStep):
+    """Fetch raw interaction data from Kafka topic with optional time and store_mode filtering"""
+
+    def __init__(self, context, lookback: str = None):
+        super().__init__(context)
+        self.lookback = lookback
+
+    def transform(self, X=None):
+        df = self.context.provider.fetch_kafka_topic('user-interactions')
+
+        if df.empty:
+            return df
+
+        # Explode metadata JSON column
+        if 'metadata' in df.columns:
+            df = df.join(
+                pd.json_normalize(df.pop('metadata'), sep='.').add_prefix('metadata_')
+            )
+
+        df = df.dropna(subset=['eventName'])
+        # drop all where page has /admin/
+        df = df[~df['page'].str.contains('/admin/', na=False)]
+
+        # filter by store_mode from context
+        if 'storeMode' in df.columns:
+            df = df[df['storeMode'] == self.context.store_mode]
+
+        # Remap dateIndex if present
+        if 'metadata_dateIndex' in df.columns:
+            df['dateIndex'] = df['metadata_dateIndex'].astype('Int64')
+
+        # Apply time filtering if lookback specified
+        if self.lookback and 'ts' in df.columns:
+            df['ts'] = pd.to_datetime(df['ts'])
+            cutoff = pd.Timestamp.now() - pd.Timedelta(self.lookback)
+            df = df[df['ts'] >= cutoff]
+
+        return df
+
+
+class FetchPriceLogsStep(BaseContextStep):
+    """Fetch price log data from Kafka topic with optional time and store_mode filtering"""
+
+    def __init__(self, context, lookback: str = None):
+        super().__init__(context)
+        self.lookback = lookback
+
+    def transform(self, X=None):
+        df = self.context.provider.fetch_kafka_topic('price-logs')
+
+        if df.empty:
+            return df
+
+        # filter by store_mode from context
+        if 'storeMode' in df.columns:
+            df = df[df['storeMode'] == self.context.store_mode]
+
+        # Apply time filtering if lookback specified
+        if self.lookback and 'ts' in df.columns:
+            df['ts'] = pd.to_datetime(df['ts'])
+            cutoff = pd.Timestamp.now() - pd.Timedelta(self.lookback)
+            df = df[df['ts'] >= cutoff]
+
+        return df
+
+
+class FetchExperimentsStep(BaseContextStep):
+    """Fetch experiment metadata for given interaction data"""
+
+    def transform(self, interactions_df: pd.DataFrame):
+        if interactions_df.empty or 'experimentId' not in interactions_df.columns:
+            return pd.DataFrame()
+
+        exp_ids = interactions_df['experimentId'].dropna().unique().tolist()
+        if not exp_ids:
+            return pd.DataFrame()
+
+        return self.context.provider.fetch_experiments(exp_ids)

experiments/procesing/steps/join.py

@@ -0,0 +1,58 @@
+import pandas as pd
+from procesing.steps.base import BaseContextStep
+
+class JoinExperimentsStep(BaseContextStep):
+    """Join experiment metadata to interactions"""
+
+    def transform(self, data: tuple):
+        """
+        Args:
+            data: (interactions_df, experiments_df)
+        Returns:
+            merged interactions dataframe
+        """
+        interactions_df, experiments_df = data
+
+        if experiments_df.empty:
+            return interactions_df
+
+        # Flatten nested task field if present
+        if 'task' in experiments_df.columns and experiments_df['task'].notnull().any():
+            task_norm = pd.json_normalize(experiments_df['task'].dropna())
+            task_norm.index = experiments_df[experiments_df['task'].notnull()].index
+            experiments_df = experiments_df.drop('task', axis=1).join(task_norm, rsuffix='_task')
+
+        # Rename for clarity
+        experiments_df = experiments_df.rename(columns={
+            'id': 'experimentId',
+            'subject_name': 'exp_subject',
+            'xp_human_only': 'exp_human_only',
+            'xp_market_mode': 'exp_market_mode',
+            'xp_task_id': 'exp_task_id'
+        })
+
+        return interactions_df.merge(experiments_df, on='experimentId', how='left')
+
+class JoinProductFeaturesStep(BaseContextStep):
+    """Join product features to interactions"""
+
+    def transform(self, data: tuple):
+        """
+        Args:
+            data: (interactions_df, products_df)
+        Returns:
+            merged interactions dataframe
+        """
+        demand_df, price_df = data
+
+        # get base prices from products if available
+        products = self.context.products
+        products['base_price'] = products.apply(
+            lambda row: float(row['metadata'].get('base_price', 0.0)) if isinstance(row['metadata'], dict) else 0,
+            axis=1
+        )
+        products = products[['id', 'base_price']].rename(columns={'id': 'productId'})
+
+        if price_df.empty:
+            return demand_df
+        return demand_df.merge(price_df, on='productId', how='left').merge(products, on='productId', how='left')

experiments/procesing/steps/pricing.py

@@ -0,0 +1,55 @@
+import numpy as np
+import pandas as pd
+from typing import Optional, List, Dict, Any
+from dataclasses import dataclass, field
+from procesing.pricers.simple import StaticPricer
+from procesing.steps.base import BaseContextStep
+from procesing.pricers import ElasticityBasedPricer
+
+class State:
+    def __init__(self,
+                 last_action : str,
+                 last_productId : str,
+                 last_price : float,
+                 session_features : np.ndarray
+                 ):
+        pass
+
+
+
+class FitPricingFunctionStep(BaseContextStep):
+    """
+    Fit pricing function using data.
+    Input: pricing_data
+    Output: fitted pricing function instance
+    """
+
+    def transform(self, pricing_data: pd.DataFrame):
+        pricing_class = self.context.config.get('pricing_function_class', StaticPricer)
+        pricing_params = self.context.config.get('pricing_function_params', {})
+
+        pricer = pricing_class(**pricing_params)
+        pricer.fit(pricing_data)
+
+        return pricer
+
+
+class PredictPricesStep(BaseContextStep):
+    """
+    Predict optimal prices using fitted pricing function.
+    Input: (pricer, state_space)
+    Output: prices_df [productId, predicted_price]
+    """
+
+    def transform(self, data: tuple):
+        pricer, state_space = data
+
+        products = self.context.products
+        product_ids = products['id'].values
+
+        predicted_prices = pricer.predict(state_space)
+
+        return pd.DataFrame({
+            'productId': product_ids,
+            'predicted_price': predicted_prices
+        })

experiments/procesing/steps/session.py

@@ -0,0 +1,159 @@
+"""
+Session feature extraction for S_t component of state space.
+Computes behavioral signals from interaction data already in pipeline.
+"""
+import pandas as pd
+import numpy as np
+from typing import Optional, Dict, Any
+from collections import Counter
+from procesing.steps.base import BaseContextStep
+
+def _extract_features_for_session(session_df: pd.DataFrame, session_timeout_sec: float = 900) -> Dict[str, Any]:
+    """Compute features for single session.
+
+    Args:
+        session_df: interaction events for this session
+        session_timeout_sec: max gap between events before resetting duration (default 900s = 15min)
+    """
+    features = {}
+
+    # basic counts
+    features['total_interactions'] = len(session_df)
+
+    event_counts = session_df['eventName'].value_counts().to_dict()
+    features['page_views'] = event_counts.get('page_view', 0) + event_counts.get('view_item_page', 0)
+    features['item_views'] = event_counts.get('view_item_page', 0)
+    features['searches'] = event_counts.get('search', 0)
+    features['cart_adds'] = event_counts.get('add_item_to_cart', 0)
+
+    # hover events
+    hover_events = ['hover_over_title', 'hover_over_paragraph', 'hover_over_link', 'hover_over_button']
+    features['hovers'] = sum(event_counts.get(ev, 0) for ev in hover_events)
+
+    # product-level signals
+    product_ids = session_df['productId'].dropna()
+    features['unique_products_viewed'] = product_ids.nunique()
+
+    if len(product_ids) > 0:
+        product_view_counts = Counter(product_ids)
+        features['product_view_depth'] = max(product_view_counts.values())
+    else:
+        features['product_view_depth'] = 0
+
+    # temporal features with session timeout logic
+    if 'ts' in session_df.columns:
+        timestamps = session_df['ts'].sort_values()
+
+        # compute active duration considering timeout gaps
+        if len(timestamps) > 1:
+            time_diffs = timestamps.diff().dropna().dt.total_seconds()
+            # only count gaps shorter than timeout towards active session duration
+            active_diffs = time_diffs[time_diffs <= session_timeout_sec]
+            features['session_duration_sec'] = active_diffs.sum() if len(active_diffs) > 0 else 0.0
+
+            features['avg_time_between_events'] = time_diffs.mean()
+            features['std_time_between_events'] = time_diffs.std()
+        else:
+            features['session_duration_sec'] = 0.0
+            features['avg_time_between_events'] = 0.0
+            features['std_time_between_events'] = 0.0
+
+        if features['session_duration_sec'] > 0:
+            features['interaction_velocity'] = (features['total_interactions'] / features['session_duration_sec']) * 60
+        else:
+            features['interaction_velocity'] = 0.0
+    else:
+        features['session_duration_sec'] = 0.0
+        features['interaction_velocity'] = 0.0
+        features['avg_time_between_events'] = 0.0
+        features['std_time_between_events'] = 0.0
+
+    # cart/conversion signals
+    features['cart_to_view_ratio'] = features['cart_adds'] / features['item_views'] if features['item_views'] > 0 else 0.0
+
+    return features
+
+
+def _apply_to_slice(df: pd.DataFrame) -> pd.DataFrame:
+    """Apply feature extraction to sliding window of interactions."""
+    # add columns of all features at each step
+    new_cols = ["total_interactions", "page_views", "item_views", "searches",
+                "cart_adds", "hovers", "unique_products_viewed", "product_view_depth",
+                "session_duration_sec", "interaction_velocity",
+                "avg_time_between_events", "std_time_between_events",
+                "cart_to_view_ratio"]
+    for col in new_cols: df[col] = np.nan
+    for idx in range(1, len(df) + 1):
+        features = _extract_features_for_session(df.iloc[:idx])
+        # fillna kinda meh
+        features = { k: (v if not pd.isna(v) else 0.0) for k, v in features.items() }
+        for col in new_cols:
+            df.at[df.index[idx - 1], col] = features[col]
+        #print(f"Processed {idx}/{len(df)} events for session {df['sessionId'].iloc[0]}")
+    return df
+
+class BuildStateSpaceStep(BaseContextStep):
+    """
+    Build state space representation S_t from session features.
+
+    Input: session_features DataFrame
+    Output: state_space_df DataFrame with S_t vectors
+    """
+
+    def transform(self, rich_dataset: pd.DataFrame) -> pd.DataFrame:
+        # check if features are present
+        required_cols = ["total_interactions", "page_views", "item_views", "searches",
+                         "cart_adds", "hovers", "unique_products_viewed", "product_view_depth",
+                         "session_duration_sec", "interaction_velocity",
+                         "avg_time_between_events", "std_time_between_events",
+                         "cart_to_view_ratio"]
+        if not all(col in rich_dataset.columns for col in required_cols):
+            raise ValueError("Missing required columns for feature extraction.")
+        if rich_dataset.empty:
+            return pd.DataFrame()
+
+
+        # For simplicity, we return as is
+        return rich_dataset.copy()
+
+
+
+
+class ExtractSessionFeaturesStep(BaseContextStep):
+    """
+    Extract session-level behavioral features from interaction logs.
+
+    Input: interactions_df (user-interactions from earlier pipeline step)
+    Output: interactions_df with added session feature columns
+    """
+
+    def transform(self, interactions_df: pd.DataFrame) -> pd.DataFrame:
+        if interactions_df.empty:
+            return pd.DataFrame()
+
+        # ensure timestamp column
+        if 'ts' in interactions_df.columns:
+            interactions_df = interactions_df.copy()
+            interactions_df['ts'] = pd.to_datetime(interactions_df['ts'])
+
+        # group by session and compute features
+        session_features = []
+        for session_id, session_df in interactions_df.groupby('sessionId'):
+            new_slice = _apply_to_slice(session_df.sort_values('ts'))
+            session_features.append(new_slice)
+
+        return pd.concat(session_features, ignore_index=True)
+
+
+
+class FilterSessionInteractionsStep(BaseContextStep):
+    """
+    Filter interactions DataFrame to specific session.
+
+    Input: (interactions_df, session_id)
+    Output: interactions_df filtered to session_id
+    """
+
+    def transform(self, data: tuple) -> pd.DataFrame:
+        interactions_df, session_id = data
+        return interactions_df[interactions_df['sessionId'] == session_id].copy()

experiments/procesing/tests/conftest.py

@@ -0,0 +1,271 @@
+import pytest
+import pandas as pd
+from typing import List
+from procesing.providers.base import DataProvider
+from procesing.context import PipelineContext
+
+
+class MockProvider(DataProvider):
+    """Mock provider for testing, holds in-memory fixtures"""
+
+    def __init__(self, products_df=None, experiments_df=None, kafka_data=None):
+        self._products = products_df if products_df is not None else pd.DataFrame()
+        self._experiments = experiments_df if experiments_df is not None else pd.DataFrame()
+        self._kafka_data = kafka_data if kafka_data is not None else {}
+
+    def fetch_products(self, store_mode: str) -> pd.DataFrame:
+        return self._products.copy()
+
+    def fetch_experiments(self, experiment_ids: List[str]) -> pd.DataFrame:
+        if self._experiments.empty:
+            return pd.DataFrame()
+        return self._experiments[
+            self._experiments['id'].isin(experiment_ids)
+        ].copy()
+
+    def fetch_kafka_topic(self, topic: str) -> pd.DataFrame:
+        return self._kafka_data.get(topic, pd.DataFrame()).copy()
+
+
+@pytest.fixture
+def mock_products():
+    """Standard product catalog fixture with realistic IDs from test data"""
+    return pd.DataFrame({
+        'id': [
+            'd018efc1-25e9-4284-b276-80386e048b25',
+            '51266ddb-5b07-47b7-89ee-5b5cae94bb11',
+            '2cd7f756-fc65-4ba0-ab01-74521c1fff43'
+        ],
+        'name': ['Junior Suite', 'Superior Room', 'Deluxe Room'],
+        'base_price': [200.0, 150.0, 180.0]
+    })
+
+
+@pytest.fixture
+def mock_interactions_raw_kafka():
+    """Raw Kafka message structure for interactions, matches production format"""
+    return [
+        {
+            'partitionID': 0, 'offset': 203, 'timestamp': 1764102082676,
+            'value': {
+                'payload': {
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'eventName': 'learn_more_about_item',
+                    'page': '/hotel/products/d018efc1-25e9-4284-b276-80386e048b25',
+                    'productId': 'd018efc1-25e9-4284-b276-80386e048b25',
+                    'metadata': {'type': 'hotel', 'dateIndex': 1, 'roomType': 'Junior Suite'},
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T20:21:22.674Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 204, 'timestamp': 1764102086982,
+            'value': {
+                'payload': {
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'eventName': 'page_view',
+                    'page': '/hotel/products',
+                    'productId': None,
+                    'metadata': {'referrer': ''},
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T20:21:26.947Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 205, 'timestamp': 1764102091825,
+            'value': {
+                'payload': {
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'eventName': 'hover_over_title',
+                    'page': '/hotel/products',
+                    'productId': '51266ddb-5b07-47b7-89ee-5b5cae94bb11',
+                    'metadata': {'elementText': 'Superior Room', 'dateIndex': 1, 'dwellTime': 1200},
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T20:21:31.823Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 206, 'timestamp': 1764102094193,
+            'value': {
+                'payload': {
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': 'bbbbcccc-dddd-eeee-ffff-000011112222',
+                    'eventName': 'hover_over_paragraph',
+                    'page': '/hotel/products',
+                    'productId': '51266ddb-5b07-47b7-89ee-5b5cae94bb11',
+                    'metadata': {'elementText': 'price', 'dateIndex': 1, 'dwellTime': 1307},
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T20:21:34.191Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 207, 'timestamp': 1764102101970,
+            'value': {
+                'payload': {
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': 'bbbbcccc-dddd-eeee-ffff-000011112222',
+                    'eventName': 'hover_over_paragraph',
+                    'page': '/hotel/products',
+                    'productId': 'd018efc1-25e9-4284-b276-80386e048b25',
+                    'metadata': {'elementText': 'price', 'dateIndex': 1, 'dwellTime': 1201},
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T20:21:41.967Z'
+                }
+            }
+        }
+    ]
+
+
+@pytest.fixture
+def mock_interactions(mock_interactions_raw_kafka):
+    """Processed interaction DataFrame (what provider.fetch_kafka_topic returns)"""
+    records = [msg['value']['payload'] for msg in mock_interactions_raw_kafka]
+    df = pd.DataFrame(records)
+    df['timestamp'] = pd.to_datetime(df['ts'])
+    return df
+
+
+@pytest.fixture
+def mock_price_logs_raw_kafka():
+    """Raw Kafka message structure for price logs, matches production format"""
+    return [
+        {
+            'partitionID': 0, 'offset': 32, 'timestamp': 1764104757969,
+            'value': {
+                'payload': {
+                    'productId': '2cd7f756-fc65-4ba0-ab01-74521c1fff43',
+                    'price': 162.47,
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T21:05:57.967Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 33, 'timestamp': 1764104757995,
+            'value': {
+                'payload': {
+                    'productId': '2ddabbfc-4127-48fc-86dc-ebc4c677efa2',
+                    'price': 743.49,
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T21:05:57.993Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 34, 'timestamp': 1764104758011,
+            'value': {
+                'payload': {
+                    'productId': '2cd7f756-fc65-4ba0-ab01-74521c1fff43',
+                    'price': 163.87,
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T21:05:58.009Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 35, 'timestamp': 1764104758050,
+            'value': {
+                'payload': {
+                    'productId': '2ddabbfc-4127-48fc-86dc-ebc4c677efa2',
+                    'price': 397.46,
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T21:05:58.049Z'
+                }
+            }
+        },
+        {
+            'partitionID': 0, 'offset': 36, 'timestamp': 1764104768865,
+            'value': {
+                'payload': {
+                    'productId': '2cd7f756-fc65-4ba0-ab01-74521c1fff43',
+                    'price': 401.66,
+                    'sessionId': 'd423ce8a-77aa-4c9a-94d4-d1adddcc3472',
+                    'experimentId': '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35',
+                    'storeMode': 'hotel',
+                    'ts': '2025-11-25T21:06:08.864Z'
+                }
+            }
+        }
+    ]
+
+
+@pytest.fixture
+def mock_price_logs(mock_price_logs_raw_kafka):
+    """Processed price logs DataFrame (what provider.fetch_kafka_topic returns)"""
+    # extract payloads and flatten
+    records = [msg['value']['payload'] for msg in mock_price_logs_raw_kafka]
+    df = pd.DataFrame(records)
+    df['timestamp'] = pd.to_datetime(df['ts'])
+    return df
+
+
+@pytest.fixture
+def mock_experiments():
+    """Standard experiment metadata fixture matching Supabase schema"""
+    return pd.DataFrame({
+        'id': ['53aefd07-f66a-4d7f-ba8b-7ea1fc562d35', 'bbbbcccc-dddd-eeee-ffff-000011112222'],
+        'created_at': pd.to_datetime(['2025-11-25T20:00:00Z', '2025-11-26T10:00:00Z']),
+        'subject_name': ['Session A', 'Session B'],
+        'xp_human_only': [True, False],
+        'xp_market_mode': ['hotel', 'airline'],
+        'xp_task_id': [None, None]
+    })
+
+
+@pytest.fixture
+def mock_provider(mock_products, mock_experiments, mock_interactions, mock_price_logs):
+    """Fully configured mock provider"""
+    return MockProvider(
+        products_df=mock_products,
+        experiments_df=mock_experiments,
+        kafka_data={
+            'user-interactions': mock_interactions,
+            'price-logs': mock_price_logs
+        }
+    )
+
+
+@pytest.fixture
+def pipeline_context(mock_provider):
+    """Standard pipeline context for testing"""
+    return PipelineContext(
+        provider=mock_provider,
+        store_mode='hotel',
+        window_size='30s',
+        n_price_buckets=3
+    )
+
+
+@pytest.fixture
+def empty_provider():
+    """Provider with no data, for edge case testing"""
+    return MockProvider(
+        products_df=pd.DataFrame(columns=['id', 'name', 'base_price']),
+        experiments_df=pd.DataFrame(columns=['id', 'created_at', 'subject_name', 'xp_human_only', 'xp_market_mode', 'xp_task_id']),
+        kafka_data={'user-interactions': pd.DataFrame(), 'price-logs': pd.DataFrame()}
+    )
+
+
+@pytest.fixture
+def empty_context(empty_provider):
+    """Context with empty provider"""
+    return PipelineContext(
+        provider=empty_provider,
+        store_mode='hotel',
+        window_size='30s'
+    )

experiments/procesing/tests/test_augement.py

@@ -0,0 +1,45 @@
+import pytest
+import random
+import pandas as pd
+from procesing.steps import (
+    CreatePriceBucketsStep,
+    AugmentEventNamesStep
+)
+
+def test_bucketing(pipeline_context):
+    step = CreatePriceBucketsStep(context=pipeline_context)
+
+    # Test with normal price data
+    df = pd.DataFrame({
+        'metadata_price': random.sample(range(10, 1000), 100)
+    })
+    result = step.transform(df)
+    assert 'price_bucket' in result.columns
+    # test if is categorical
+    assert isinstance(result['price_bucket'].dtype, pd.CategoricalDtype)
+    assert result['price_bucket'].nunique() == 3 # as per context config
+    # distribution check
+    counts = result['price_bucket'].value_counts()
+    assert all(counts > 0)
+    assert counts.max() - counts.min() <= 10  # roughly equal distribution for 100 samples
+    # Test with empty DataFrame
+    df = pd.DataFrame()
+    result = step.transform(df)
+    assert 'price_bucket' in result.columns
+    assert result.empty
+
+
+def test_augment_names(pipeline_context):
+    df = pd.DataFrame({
+        'eventName': ['click', 'view', 'purchase'],
+        'productId': ['prod_1', 'prod_2', None],
+        'price_bucket': ['PB_1', None, 'PB_3']
+    })
+    step = AugmentEventNamesStep(context=pipeline_context)
+    result = step.transform(df)
+    expected_event_names = [
+        'click_prod_1@PB_1',
+        'view',
+        'purchase'
+    ]
+    assert result['eventName'].tolist() == expected_event_names

experiments/procesing/tests/test_demand.py

@@ -0,0 +1,49 @@
+import pytest
+import random
+import pandas as pd
+from procesing.steps import (
+    ComputeDemandStep
+)
+
+def test_compute_demand(pipeline_context):
+    step = ComputeDemandStep(context=pipeline_context)
+
+    # Test with normal interaction data
+    df = pd.DataFrame({
+        'ts': pd.date_range(start='2023-01-01', periods=100, freq='h'),
+        'productId': random.choices([
+            'd018efc1-25e9-4284-b276-80386e048b25',
+            '51266ddb-5b07-47b7-89ee-5b5cae94bb11',
+            '2cd7f756-fc65-4ba0-ab01-74521c1fff43'
+        ], k=100),
+        'eventName': random.choices(['view', 'click', 'purchase'], k=100)
+    })
+    result = step.transform(df)
+    assert type(result) == pd.DataFrame
+    assert not result.empty
+    assert set(result['productId']) == set(pipeline_context.products['id'])
+    assert all(result['demand_score'] > 100/3 -10)
+
+
+def test_compute_demand_skewed(pipeline_context):
+    step = ComputeDemandStep(context=pipeline_context)
+
+    # Test with normal interaction data
+    df = pd.DataFrame({
+        'ts': pd.date_range(start='2023-01-01', periods=100, freq='h'),
+        'productId': random.choices([
+            'd018efc1-25e9-4284-b276-80386e048b25',
+            '51266ddb-5b07-47b7-89ee-5b5cae94bb11',
+            '2cd7f756-fc65-4ba0-ab01-74521c1fff43'
+        ], weights=[0.7, 0.2, 0.1], k=100),
+        'eventName': random.choices(['view', 'click', 'purchase'], k=100)
+    })
+    result = step.transform(df)
+    assert type(result) == pd.DataFrame
+    assert not result.empty
+    assert set(result['productId']) == set(pipeline_context.products['id'])
+    # test for skewness
+    scores = result.set_index('productId')['demand_score'].to_dict()
+    assert scores['d018efc1-25e9-4284-b276-80386e048b25'] > \
+           scores['51266ddb-5b07-47b7-89ee-5b5cae94bb11'] > \
+           scores['2cd7f756-fc65-4ba0-ab01-74521c1fff43']

experiments/procesing/tests/test_fetch.py

@@ -0,0 +1,51 @@
+import pytest
+import pandas as pd
+from procesing.steps import (
+    FetchInteractionsStep,
+    FetchPriceLogsStep,
+    FetchExperimentsStep,
+)
+
+
+def test_fetch_interactions_data(pipeline_context):
+    step = FetchInteractionsStep(pipeline_context)
+    data = step.transform(None)
+    assert data is not None
+    assert isinstance(data, pd.DataFrame)
+    expected_cols = [
+        "eventName",
+        "dateIndex",
+        "experimentId",
+        "storeMode",
+        "metadata_elementText"
+    ]
+    for expected in expected_cols:
+        assert expected in data.columns
+
+def test_fetch_price_logs(pipeline_context):
+    step = FetchPriceLogsStep(pipeline_context)
+    data = step.transform(None)
+    assert data is not None
+    assert isinstance(data, pd.DataFrame)
+    expected_cols = [
+        "price",
+        "productId"
+    ]
+    for expected in expected_cols:
+        assert expected in data.columns
+    prices = data['price'].to_list()
+    assert min(prices) >= 0
+    assert max(prices) <= 9999
+
+
+def test_experiments_fetching(pipeline_context):
+    interactions = FetchInteractionsStep(pipeline_context).transform(None)
+    assert interactions is not None
+    experiments = FetchExperimentsStep(pipeline_context)
+    experiment_data = experiments.transform(interactions)
+    assert experiment_data is not None
+    assert isinstance(experiment_data, pd.DataFrame)
+    assert not experiment_data.empty
+    assert 'id' in experiment_data.columns
+    assert len(experiment_data) == 2
+    assert '53aefd07-f66a-4d7f-ba8b-7ea1fc562d35' in experiment_data['id'].values

experiments/procesing/tests/test_pricing.py

@@ -0,0 +1,87 @@
+import pytest
+import pandas as pd
+
+from procesing.pricers import (
+    StaticPricer,
+    RandomPricer,
+    ElasticityBasedPricer
+)
+
+
+def test_static_pricer_fit_and_predict():
+    # Sample historical data
+    historical_data = pd.DataFrame({
+        'product_id': [1, 2, 3],
+        'base_price': [100.0, 150.0, 200.0]
+    })
+
+    # Initialize and fit StaticPricer
+    pricer = StaticPricer()
+    pricer.fit(historical_data)
+
+    # Predict prices
+    predicted_prices = pricer.predict(None)
+
+    # Assert that predicted prices match base prices
+    expected_prices = historical_data['base_price'].values
+    assert all(predicted_prices == expected_prices), "Predicted prices do not match base prices"
+
+
+def test_random_pricer_fit_and_predict():
+    # Sample historical data
+    historical_data = pd.DataFrame({
+        'product_id': [1, 2, 3],
+        'base_price': [100.0, 150.0, 200.0]
+    })
+
+    # Initialize and fit RandomPricer
+    pricer = RandomPricer(price_min=50.0, price_max=250.0, seed=42)
+    pricer.fit(historical_data)
+
+    # Predict prices
+    predicted_prices = pricer.predict(None)
+
+    # Assert that predicted prices are within bounds
+    assert predicted_prices.min() >= 50.0, "Predicted prices are below minimum bound"
+    assert predicted_prices.max() <= 250.0, "Predicted prices are above maximum bound"
+    # distribution check (not so strict)
+    assert len(set(predicted_prices)) > 1, "Predicted prices are not varied enough"
+    assert len(predicted_prices) == len(historical_data), "Number of predicted prices does not match number of products"
+
+def test_elasticity_based_pricer_fit_and_predict():
+    # Sample historical data
+    historical_data = pd.DataFrame({
+        'productId': [1, 2, 3],
+        'elasticity': [-1.5, -0.5, -2.0],
+        'base_price': [100.0, 150.0, 200.0],
+        'mean_demand': [10, 20, 15]
+    })
+
+    # Initialize and fit ElasticityBasedPricer
+    pricer = ElasticityBasedPricer(alpha=0.1, price_floor=50.0, price_ceil=300.0)
+    pricer.fit(historical_data)
+
+    # Create a mock state space with demand deviations
+    class MockStateSpace:
+        def __init__(self, demand):
+            self.demand = demand
+
+    # Simulate demand higher than mean for all products
+    state_space = MockStateSpace(demand=[15, 25, 20])
+
+    # Predict prices
+    predicted_prices = pricer.predict(state_space)
+
+    # Assert that predicted prices are within bounds
+    assert predicted_prices.min() >= 50.0, "Predicted prices are below minimum bound"
+    assert predicted_prices.max() <= 300.0, "Predicted prices are above maximum bound"
+    assert len(predicted_prices) == len(historical_data), "Number of predicted prices does not match number of products"
+
+    # now we gotta check semantic validity
+    # since demand is higher than mean, prices should generally increase
+    for i, row in historical_data.iterrows():
+        base_price = row['base_price']
+        elasticity = row['elasticity']
+        expected_increase = base_price * (1 + 0.1 * abs(elasticity) * ((state_space.demand[i] - row['mean_demand']) / row['mean_demand']))
+        assert predicted_prices[i] >= base_price, f"Predicted price for product {row['productId']} did not increase as expected"
+        assert abs(predicted_prices[i] - expected_increase) < 1e-5, f"Predicted price for product {row['productId']} does not match expected calculation within 1e-5 tolerance"

experiments/pytest.ini

@@ -0,0 +1,8 @@
+[pytest]
+pythonpath = .
+testpaths = procesing/tests agents
+python_files = test*.py
+python_classes = Test*
+python_functions = test_*
+asyncio_mode = auto
+asyncio_default_fixture_loop_scope = function

lib/model_registry.py

@@ -0,0 +1,180 @@
+import redis
+import pickle
+import json
+import pandas as pd
+from typing import Optional, Dict, Any
+import os
+import logging
+log = logging.getLogger(__name__)
+
+class ModelRegistry:
+    """
+    Lightweight model registry using Redis for storing pricing models and elasticity data.
+    Models are serialized using pickle, metadata stored as JSON.
+    """
+
+    def __init__(self, redis_host: str = None, redis_port: int = None):
+        host = redis_host or os.getenv('REDIS_HOST', 'localhost')
+        port = redis_port or int(os.getenv('REDIS_PORT', '6378'))
+
+        self.redis_client = redis.Redis(
+            host=host,
+            port=port,
+            db=0,
+            decode_responses=False
+        )
+        self.metadata_prefix = "model:meta:"
+        self.data_prefix = "model:data:"
+        self.elasticity_prefix = "elasticity:"
+        self.prices_prefix = "prices:"
+
+    def publish_elasticity(self,
+                          elasticity_df: pd.DataFrame,
+                          model_name: str = 'latest',
+                          metadata: Optional[Dict[str, Any]] = None):
+        """
+        Store elasticity estimates in registry.
+
+        Args:
+            elasticity_df: df with [productId, elasticity, std_error, n_obs]
+            model_name: identifier for this elasticity snapshot
+            metadata: additional info (timestamp, window_size, etc)
+        """
+        key = f"{self.elasticity_prefix}{model_name}"
+
+        # serialize dataframe as JSON
+        data_json = elasticity_df.to_json(orient='records')
+
+        # store data
+        self.redis_client.set(key, data_json)
+
+        # store metadata
+        meta = metadata or {}
+        meta.update({
+            'n_products': len(elasticity_df),
+            'mean_elasticity': float(elasticity_df['elasticity'].mean()),
+            'model_type': 'elasticity_snapshot'
+        })
+
+        meta_key = f"{self.metadata_prefix}{model_name}"
+        self.redis_client.set(meta_key, json.dumps(meta))
+
+        log.info(f"Published elasticity model '{model_name}' with {len(elasticity_df)} products")
+
+    def get_elasticity(self, model_name: str = 'latest') -> Optional[pd.DataFrame]:
+        """Retrieve elasticity estimates from registry."""
+        key = f"{self.elasticity_prefix}{model_name}"
+        data_json = self.redis_client.get(key)
+
+        if data_json is None:
+            return None
+
+        # decode bytes to string if needed
+        if isinstance(data_json, bytes):
+            data_json = data_json.decode('utf-8')
+
+        return pd.read_json(data_json, orient='records')
+
+    def publish_pricing_model(self,
+                              pricing_function,
+                              model_name: str = 'latest',
+                              metadata: Optional[Dict[str, Any]] = None):
+        """
+        Store a fitted pricing function object.
+
+        Args:
+            pricing_function: fitted PricingFunction instance
+            model_name: identifier
+            metadata: additional info
+        """
+        key = f"{self.data_prefix}{model_name}"
+
+        # serialize object
+        model_bytes = pickle.dumps(pricing_function)
+        self.redis_client.set(key, model_bytes)
+
+        # store metadata
+        meta = metadata or {}
+        meta.update({
+            'model_class': pricing_function.__class__.__name__,
+            'model_type': 'pricing_function'
+        })
+
+        meta_key = f"{self.metadata_prefix}{model_name}"
+        self.redis_client.set(meta_key, json.dumps(meta))
+
+        log.info(f"Published pricing model '{model_name}' ({meta['model_class']})")
+
+    def get_pricing_model(self, model_name: str = 'latest'):
+        """Retrieve a pricing function from registry."""
+        key = f"{self.data_prefix}{model_name}"
+        model_bytes = self.redis_client.get(key)
+
+        if model_bytes is None:
+            return None
+
+        return pickle.loads(model_bytes)
+
+    def list_models(self) -> Dict[str, Any]:
+        """List all registered models with metadata."""
+        models = {}
+
+        for key in self.redis_client.scan_iter(f"{self.metadata_prefix}*"):
+            key_str = key.decode('utf-8') if isinstance(key, bytes) else key
+            model_name = key_str.replace(self.metadata_prefix, '')
+            meta_json = self.redis_client.get(key)
+
+            if meta_json:
+                if isinstance(meta_json, bytes):
+                    meta_json = meta_json.decode('utf-8')
+                models[model_name] = json.loads(meta_json)
+
+        return models
+
+    def publish_prices(self,
+                      prices_df: pd.DataFrame,
+                      model_name: str = 'latest',
+                      metadata: Optional[Dict[str, Any]] = None):
+        """Store predicted prices in registry.
+
+        Args:
+            prices_df: df with [productId, predicted_price, ...]
+            model_name: identifier for this price snapshot
+            metadata: additional info
+        """
+        key = f"{self.prices_prefix}{model_name}"
+        data_json = prices_df.to_json(orient='records')
+
+        self.redis_client.set(key, data_json)
+
+        meta = metadata or {}
+        meta.update({
+            'n_products': len(prices_df),
+            'model_type': 'predicted_prices'
+        })
+
+        meta_key = f"{self.metadata_prefix}prices_{model_name}"
+        self.redis_client.set(meta_key, json.dumps(meta))
+
+        log.info(f"Published prices '{model_name}' for {len(prices_df)} products")
+
+    def get_prices(self, model_name: str = 'latest') -> Optional[pd.DataFrame]:
+        """Retrieve predicted prices from registry."""
+        key = f"{self.prices_prefix}{model_name}"
+        data_json = self.redis_client.get(key)
+
+        if data_json is None:
+            return None
+
+        if isinstance(data_json, bytes):
+            data_json = data_json.decode('utf-8')
+
+        return pd.read_json(data_json, orient='records')
+
+    def health_check(self) -> bool:
+        """Check if Redis connection is alive."""
+        try:
+            self.redis_client.ping()
+            return True
+        except:
+            return False

pytest.ini

@@ -1,4 +1,5 @@
 [pytest]
+pythonpath = experiments
 testpaths = experiments
 python_files = test*.py
 python_classes = Test*

requirements.txt

@@ -11,3 +11,4 @@ pytest-asyncio
 uv
 scikit-learn
 supabase
+pymc

web/package-lock.json

@@ -10,7 +10,7 @@
       "dependencies": {
         "@supabase/ssr": "^0.7.0",
         "@supabase/supabase-js": "^2.81.1",
-        "next": "16.0.0",
+        "next": "^16.0.0",
         "react": "19.2.0",
         "react-dom": "19.2.0",
         "zod": "^4.1.12"
@@ -526,15 +526,15 @@
       }
     },
     "node_modules/@next/env": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/env/-/env-16.0.0.tgz",
-      "integrity": "sha512-s5j2iFGp38QsG1LWRQaE2iUY3h1jc014/melHFfLdrsMJPqxqDQwWNwyQTcNoUSGZlCVZuM7t7JDMmSyRilsnA==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/env/-/env-16.0.7.tgz",
+      "integrity": "sha512-gpaNgUh5nftFKRkRQGnVi5dpcYSKGcZZkQffZ172OrG/XkrnS7UBTQ648YY+8ME92cC4IojpI2LqTC8sTDhAaw==",
       "license": "MIT"
     },
     "node_modules/@next/swc-darwin-arm64": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-16.0.0.tgz",
-      "integrity": "sha512-/CntqDCnk5w2qIwMiF0a9r6+9qunZzFmU0cBX4T82LOflE72zzH6gnOjCwUXYKOBlQi8OpP/rMj8cBIr18x4TA==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-16.0.7.tgz",
+      "integrity": "sha512-LlDtCYOEj/rfSnEn/Idi+j1QKHxY9BJFmxx7108A6D8K0SB+bNgfYQATPk/4LqOl4C0Wo3LACg2ie6s7xqMpJg==",
       "cpu": [
         "arm64"
       ],
@@ -548,9 +548,9 @@
       }
     },
     "node_modules/@next/swc-darwin-x64": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-16.0.0.tgz",
-      "integrity": "sha512-hB4GZnJGKa8m4efvTGNyii6qs76vTNl+3dKHTCAUaksN6KjYy4iEO3Q5ira405NW2PKb3EcqWiRaL9DrYJfMHg==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-16.0.7.tgz",
+      "integrity": "sha512-rtZ7BhnVvO1ICf3QzfW9H3aPz7GhBrnSIMZyr4Qy6boXF0b5E3QLs+cvJmg3PsTCG2M1PBoC+DANUi4wCOKXpA==",
       "cpu": [
         "x64"
       ],
@@ -564,9 +564,9 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-gnu": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-16.0.0.tgz",
-      "integrity": "sha512-E2IHMdE+C1k+nUgndM13/BY/iJY9KGCphCftMh7SXWcaQqExq/pJU/1Hgn8n/tFwSoLoYC/yUghOv97tAsIxqg==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-16.0.7.tgz",
+      "integrity": "sha512-mloD5WcPIeIeeZqAIP5c2kdaTa6StwP4/2EGy1mUw8HiexSHGK/jcM7lFuS3u3i2zn+xH9+wXJs6njO7VrAqww==",
       "cpu": [
         "arm64"
       ],
@@ -580,9 +580,9 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-musl": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-16.0.0.tgz",
-      "integrity": "sha512-xzgl7c7BVk4+7PDWldU+On2nlwnGgFqJ1siWp3/8S0KBBLCjonB6zwJYPtl4MUY7YZJrzzumdUpUoquu5zk8vg==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-16.0.7.tgz",
+      "integrity": "sha512-+ksWNrZrthisXuo9gd1XnjHRowCbMtl/YgMpbRvFeDEqEBd523YHPWpBuDjomod88U8Xliw5DHhekBC3EOOd9g==",
       "cpu": [
         "arm64"
       ],
@@ -596,9 +596,9 @@
       }
     },
     "node_modules/@next/swc-linux-x64-gnu": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-16.0.0.tgz",
-      "integrity": "sha512-sdyOg4cbiCw7YUr0F/7ya42oiVBXLD21EYkSwN+PhE4csJH4MSXUsYyslliiiBwkM+KsuQH/y9wuxVz6s7Nstg==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-16.0.7.tgz",
+      "integrity": "sha512-4WtJU5cRDxpEE44Ana2Xro1284hnyVpBb62lIpU5k85D8xXxatT+rXxBgPkc7C1XwkZMWpK5rXLXTh9PFipWsA==",
       "cpu": [
         "x64"
       ],
@@ -612,9 +612,9 @@
       }
     },
     "node_modules/@next/swc-linux-x64-musl": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-16.0.0.tgz",
-      "integrity": "sha512-IAXv3OBYqVaNOgyd3kxR4L3msuhmSy1bcchPHxDOjypG33i2yDWvGBwFD94OuuTjjTt/7cuIKtAmoOOml6kfbg==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-16.0.7.tgz",
+      "integrity": "sha512-HYlhqIP6kBPXalW2dbMTSuB4+8fe+j9juyxwfMwCe9kQPPeiyFn7NMjNfoFOfJ2eXkeQsoUGXg+O2SE3m4Qg2w==",
       "cpu": [
         "x64"
       ],
@@ -628,9 +628,9 @@
       }
     },
     "node_modules/@next/swc-win32-arm64-msvc": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-16.0.0.tgz",
-      "integrity": "sha512-bmo3ncIJKUS9PWK1JD9pEVv0yuvp1KPuOsyJTHXTv8KDrEmgV/K+U0C75rl9rhIaODcS7JEb6/7eJhdwXI0XmA==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-16.0.7.tgz",
+      "integrity": "sha512-EviG+43iOoBRZg9deGauXExjRphhuYmIOJ12b9sAPy0eQ6iwcPxfED2asb/s2/yiLYOdm37kPaiZu8uXSYPs0Q==",
       "cpu": [
         "arm64"
       ],
@@ -644,9 +644,9 @@
       }
     },
     "node_modules/@next/swc-win32-x64-msvc": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-16.0.0.tgz",
-      "integrity": "sha512-O1cJbT+lZp+cTjYyZGiDwsOjO3UHHzSqobkPNipdlnnuPb1swfcuY6r3p8dsKU4hAIEO4cO67ZCfVVH/M1ETXA==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-16.0.7.tgz",
+      "integrity": "sha512-gniPjy55zp5Eg0896qSrf3yB1dw4F/3s8VK1ephdsZZ129j2n6e1WqCbE2YgcKhW9hPB9TVZENugquWJD5x0ug==",
       "cpu": [
         "x64"
       ],
@@ -1447,12 +1447,12 @@
       }
     },
     "node_modules/next": {
-      "version": "16.0.0",
-      "resolved": "https://registry.npmjs.org/next/-/next-16.0.0.tgz",
-      "integrity": "sha512-nYohiNdxGu4OmBzggxy9rczmjIGI+TpR5vbKTsE1HqYwNm1B+YSiugSrFguX6omMOKnDHAmBPY4+8TNJk0Idyg==",
+      "version": "16.0.7",
+      "resolved": "https://registry.npmjs.org/next/-/next-16.0.7.tgz",
+      "integrity": "sha512-3mBRJyPxT4LOxAJI6IsXeFtKfiJUbjCLgvXO02fV8Wy/lIhPvP94Fe7dGhUgHXcQy4sSuYwQNcOLhIfOm0rL0A==",
       "license": "MIT",
       "dependencies": {
-        "@next/env": "16.0.0",
+        "@next/env": "16.0.7",
         "@swc/helpers": "0.5.15",
         "caniuse-lite": "^1.0.30001579",
         "postcss": "8.4.31",
@@ -1465,14 +1465,14 @@
         "node": ">=20.9.0"
       },
       "optionalDependencies": {
-        "@next/swc-darwin-arm64": "16.0.0",
-        "@next/swc-darwin-x64": "16.0.0",
-        "@next/swc-linux-arm64-gnu": "16.0.0",
-        "@next/swc-linux-arm64-musl": "16.0.0",
-        "@next/swc-linux-x64-gnu": "16.0.0",
-        "@next/swc-linux-x64-musl": "16.0.0",
-        "@next/swc-win32-arm64-msvc": "16.0.0",
-        "@next/swc-win32-x64-msvc": "16.0.0",
+        "@next/swc-darwin-arm64": "16.0.7",
+        "@next/swc-darwin-x64": "16.0.7",
+        "@next/swc-linux-arm64-gnu": "16.0.7",
+        "@next/swc-linux-arm64-musl": "16.0.7",
+        "@next/swc-linux-x64-gnu": "16.0.7",
+        "@next/swc-linux-x64-musl": "16.0.7",
+        "@next/swc-win32-arm64-msvc": "16.0.7",
+        "@next/swc-win32-x64-msvc": "16.0.7",
         "sharp": "^0.34.4"
       },
       "peerDependencies": {

web/package.json

@@ -10,7 +10,7 @@
   "dependencies": {
     "@supabase/ssr": "^0.7.0",
     "@supabase/supabase-js": "^2.81.1",
-    "next": "16.0.0",
+    "next": "^16.0.0",
     "react": "19.2.0",
     "react-dom": "19.2.0",
     "zod": "^4.1.12"

web/src/app/airline/checkout/page.tsx

@@ -0,0 +1,11 @@
+export default function AirlineCheckout() {
+  return (
+    <div className="min-h-screen flex items-center justify-center bg-gradient-to-br from-sky-50 to-blue-50">
+      <div className="text-center p-8">
+        <h1 className="text-4xl font-light text-gray-800 mb-4">
+          Thank you for flying with us
+        </h1>
+      </div>
+    </div>
+  );
+}

web/src/app/api/ingest/route.ts

@@ -7,7 +7,7 @@ export async function POST(req: NextRequest) {
   try {
     const body = await req.json();
 
-    const storeMode = process.env.STORE_MODE || 'hotel';
+    const storeMode = process.env.NEXT_PUBLIC_STORE_MODE || process.env.STORE_MODE || 'hotel';
     const userAgent = req.headers.get('user-agent') || undefined;
 
     const event: EventBase = {

web/src/app/api/pricing/route.ts

@@ -11,18 +11,7 @@ export async function GET(req: NextRequest) {
     const productId = searchParams.get('productId');
     const sessionId = searchParams.get('sessionId');
     const experimentId = searchParams.get('experimentId');
-    const storeMode = process.env.NEXT_PUBLIC_STORE_MODE || 'shop';
-
-    // log in dev
-    if (process.env.NODE_ENV === 'development') {
-        console.log('[pricing-api]', {
-            productId,
-            sessionId,
-            experimentId,
-            storeMode,
-            timestamp: new Date().toISOString(),
-        });
-    }
+    const storeMode = process.env.NEXT_PUBLIC_STORE_MODE || process.env.STORE_MODE || 'hotel';
 
     if (!productId) {
         return NextResponse.json(
@@ -31,14 +20,73 @@ export async function GET(req: NextRequest) {
         );
     }
 
-    // stub: call external pricing provider (random for now)
-    const basePrice = 100 + Math.random() * 900; // 100-1000 range
-    const price = Math.round(basePrice * 100) / 100;
+    const timestamp = new Date().toISOString();
+    let price: number;
+    let basePrice: number | undefined;
+    let markup: number | undefined;
+    let elasticity: number | undefined;
+
+    // call real pricing provider
+    const providerUrl = process.env.PRICING_PROVIDER_URL || 'http://localhost:5001';
+    try {
+        const queryParams = new URLSearchParams();
+        if (sessionId) queryParams.append('sessionId', sessionId);
+        if (experimentId) queryParams.append('experimentId', experimentId);
+
+        const providerResponse = await fetch(
+            `${providerUrl}/api/${storeMode}/price/${productId}?${queryParams.toString()}`,
+            { headers: { 'Accept': 'application/json' }, cache: 'no-store' }
+        );
+
+        if (!providerResponse.ok) {
+            throw new Error(`Provider returned ${providerResponse.status}`);
+        }
+
+        const providerData = await providerResponse.json();
+        price = providerData.price;
+        basePrice = providerData.base_price;
+        markup = providerData.markup;
+        elasticity = providerData.elasticity;
+
+    } catch (err) {
+        console.error('[pricing-provider-error]', err);
+        // fallback to random pricing if provider unavailable
+        const randomBase = 100 + Math.random() * 900;
+        price = Math.round(randomBase * 100) / 100;
+    }
+
+    // log price to kafka for elasticity computation
+    if (sessionId) {
+        const backendUrl = process.env.BACKEND_URL || 'http://localhost:5000';
+        try {
+            await fetch(`${backendUrl}/api/kafka/price-log`, {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' },
+                body: JSON.stringify({
+                    productId,
+                    price,
+                    sessionId,
+                    experimentId: experimentId || undefined,
+                    storeMode,
+                    ts: timestamp,
+                }),
+            });
+        } catch (err) {
+            console.error('[price-log-error]', err);
+        }
+    }
+
+    if (process.env.NODE_ENV === 'development') {
+        console.log('[pricing-api]', {
+            productId, sessionId, experimentId, storeMode,
+            price, basePrice, markup, elasticity, timestamp,
+        });
+    }
 
     const response: PricingResponse = {
         price,
         currency: 'EUR',
-        cachedAt: new Date().toISOString(),
+        cachedAt: timestamp,
     };
 
     return NextResponse.json(response);

web/src/app/cart/page.tsx

@@ -96,7 +96,10 @@ export default function CartPage() {
                                 <span className="text-3xl font-bold">${total.toFixed(2)}</span>
                             </div>
                             <button
-                                onClick={() => dispatchInteraction('checkout_start', undefined, { total, itemCount })}
+                                onClick={() => {
+                                    dispatchInteraction('checkout_start', undefined, { total, itemCount });
+                                    window.location.href = '/checkout';
+                                }}
                                 className="w-full py-3 bg-blue-600 hover:bg-blue-700 text-white rounded-lg font-medium transition-colors"
                             >
                                 Proceed to Checkout

web/src/app/hotel/checkout/page.tsx

@@ -0,0 +1,11 @@
+export default function HotelCheckout() {
+  return (
+    <div className="min-h-screen flex items-center justify-center bg-gradient-to-br from-blue-50 to-indigo-50">
+      <div className="text-center p-8">
+        <h1 className="text-4xl font-light text-gray-800 mb-4">
+          Thank you for staying with us
+        </h1>
+      </div>
+    </div>
+  );
+}

web/src/components/feats/airline/AirlineHero.tsx

@@ -2,10 +2,20 @@
 
 import { useState, FormEvent } from 'react';
 import { useRouter } from 'next/navigation';
-import { Button, Label, Input, DateInput, RadioGroup, Dropdown, DropdownCounter } from '@/components/ui';
+import { Button, Label, DateInput, Dropdown, DropdownCounter, SelectDropdown, SelectOption } from '@/components/ui';
 import { dateToDaysFromToday } from '@/lib/airline-utils';
 
-type TripType = 'roundtrip' | 'oneway' | 'multicity';
+const CITIES: SelectOption[] = [
+  { value: 'JFK', label: 'New York (JFK)', sublabel: 'John F. Kennedy International' },
+  { value: 'LAX', label: 'Los Angeles (LAX)', sublabel: 'Los Angeles International' },
+  { value: 'ORD', label: 'Chicago (ORD)', sublabel: "O'Hare International" },
+  { value: 'MIA', label: 'Miami (MIA)', sublabel: 'Miami International' },
+  { value: 'SFO', label: 'San Francisco (SFO)', sublabel: 'San Francisco International' },
+  { value: 'SEA', label: 'Seattle (SEA)', sublabel: 'Seattle-Tacoma International' },
+  { value: 'ATL', label: 'Atlanta (ATL)', sublabel: 'Hartsfield-Jackson International' },
+  { value: 'DFW', label: 'Dallas (DFW)', sublabel: 'Dallas/Fort Worth International' },
+];
+
 
 const PlaneIcon = () => (
   <svg className="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
@@ -22,11 +32,9 @@ const LocationIcon = () => (
 
 export default function AirlineHero() {
   const router = useRouter();
-  const [tripType, setTripType] = useState<TripType>('roundtrip');
   const [origin, setOrigin] = useState('');
   const [destination, setDestination] = useState('');
   const [departDate, setDepartDate] = useState('');
-  const [returnDate, setReturnDate] = useState('');
   const [passengers, setPassengers] = useState({ adults: 1, children: 0, infants: 0 });
 
   const handleSearch = (e: FormEvent) => {
@@ -40,8 +48,6 @@ export default function AirlineHero() {
 
     if (origin) params.set('origin', origin);
     if (destination) params.set('destination', destination);
-    if (tripType !== 'roundtrip') params.set('tripType', tripType);
-    if (returnDate && tripType === 'roundtrip') params.set('returnDate', returnDate);
 
     params.set('adults', passengers.adults.toString());
     params.set('children', passengers.children.toString());
@@ -66,28 +72,15 @@ export default function AirlineHero() {
 
         <div className="search-form">
           <form onSubmit={handleSearch}>
-            <div className="mb-6">
-              <RadioGroup
-                name="tripType"
-                value={tripType}
-                onChange={setTripType}
-                options={[
-                  { value: 'roundtrip', label: 'Round-trip' },
-                  { value: 'oneway', label: 'One-way' },
-                  { value: 'multicity', label: 'Multi-city' },
-                ]}
-              />
-            </div>
-
-            <div className="grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-4 gap-4">
+            <div className="grid grid-cols-1 sm:grid-cols-2 lg:grid-cols-3 gap-4">
               <div>
                 <Label htmlFor="origin">From</Label>
-                <Input
-                  type="text"
+                <SelectDropdown
                   id="origin"
                   value={origin}
-                  onChange={(e) => setOrigin(e.target.value)}
-                  placeholder="Airport or city"
+                  onChange={setOrigin}
+                  options={CITIES}
+                  placeholder="Select origin"
                   icon={<PlaneIcon />}
                   required
                 />
@@ -95,12 +88,12 @@ export default function AirlineHero() {
 
               <div>
                 <Label htmlFor="destination">To</Label>
-                <Input
-                  type="text"
+                <SelectDropdown
                   id="destination"
                   value={destination}
-                  onChange={(e) => setDestination(e.target.value)}
-                  placeholder="Airport or city"
+                  onChange={setDestination}
+                  options={CITIES}
+                  placeholder="Select destination"
                   icon={<LocationIcon />}
                   required
                 />
@@ -115,20 +108,6 @@ export default function AirlineHero() {
                   required
                 />
               </div>
-
-              <div>
-                <Label htmlFor="returnDate">Return</Label>
-                {tripType === 'roundtrip' ? (
-                  <DateInput
-                    id="returnDate"
-                    value={returnDate}
-                    onChange={(e) => setReturnDate(e.target.value)}
-                    required
-                  />
-                ) : (
-                  <DateInput id="returnDate" disabled />
-                )}
-              </div>
             </div>
 
             <div className="grid grid-cols-4 sm:grid-cols-3 lg:grid-cols-4 gap-4 mt-4">

web/src/components/feats/hotel/HotelCard.tsx

@@ -21,7 +21,7 @@ const AmenityIcon = ({ name }: { name: string }) => {
         breakfast: 'Breakfast',
         spa: 'Spa',
     };
-    return <span className="feature-tag">{iconMap[name.toLowerCase()] || name}</span>;
+    return <span className="feature-tag">{iconMap[name.toLowerCase()] || name.replaceAll("_", " ")}</span>;
 };
 
 export default function HotelCard({ hotel }: { hotel: Hotel }) {
@@ -47,18 +47,31 @@ export default function HotelCard({ hotel }: { hotel: Hotel }) {
         window.location.href = `/hotel/products/${hotel.id}`;
     };
 
+    const imageUrl = `https://images.unsplash.com/photo-1551882547-ff40c63fe5fa?w=400&h=300&fit=crop`;
+
     return (
         <div
             className="hotel-card cursor-pointer"
             onClick={handleCardClick}
         >
-            <div className="hotel-image bg-gray-200 flex items-center justify-center">
-                <span className="text-gray-400 text-sm">Image</span>
+            <div className="hotel-image relative overflow-hidden">
+                <img
+                    src={imageUrl}
+                    alt={hotel.name}
+                    className="w-full h-full object-cover"
+                    onError={(e) => {
+                        e.currentTarget.style.display = 'none';
+                        const fallback = e.currentTarget.nextElementSibling as HTMLElement;
+                        if (fallback) fallback.style.display = 'flex';
+                    }}
+                />
+                <div className="absolute inset-0 bg-gray-200 flex items-center justify-center" style={{ display: 'none' }}>
+                    <span className="text-gray-400 text-sm">Image</span>
+                </div>
             </div>
 
             <div className="hotel-info">
                 <h3 ref={titleRef} className="hotel-name">{hotel.name}</h3>
-                <div className="hotel-location text-sm mb-2">{hotel.roomType}</div>
                 <div className="text-sm text-[var(--text-secondary)] mb-2">
                     {hotel.checkIn} - {hotel.checkOut}
                 </div>
@@ -67,9 +80,6 @@ export default function HotelCard({ hotel }: { hotel: Hotel }) {
                         <AmenityIcon key={a} name={a} />
                     ))}
                 </div>
-                {hotel.refundable && (
-                    <div className="free-cancellation mt-2">Free cancellation</div>
-                )}
             </div>
 
             <div className="hotel-pricing">

web/src/components/feats/hotel/HotelDetails.tsx

@@ -1,6 +1,8 @@
 'use client';
 
+import { useState, useEffect } from 'react';
 import type { Hotel } from '@/lib/hotel-utils';
+import PriceDisplay from '@/components/ui/PriceDisplay';
 
 interface HotelDetailsProps {
   product: Hotel;
@@ -8,19 +10,63 @@ interface HotelDetailsProps {
   addedToCart: boolean;
 }
 
+const PriceTotalDisplay = ({ productId, nights }: { productId: string; nights: number }) => {
+  const [price, setPrice] = useState<number | null>(null);
+
+  useEffect(() => {
+    const fetchPrice = async () => {
+      try {
+        const sessionRes = await fetch('/api/session');
+        const sessionData = await sessionRes.json();
+        const params = new URLSearchParams({
+          productId,
+          sessionId: sessionData.sessionId || '',
+          experimentId: sessionData.experimentId || '',
+        });
+        const res = await fetch(`/api/pricing?${params.toString()}`);
+        const data = await res.json();
+        setPrice(data.price);
+      } catch (err) {
+        console.error('failed to fetch price for total:', err);
+      }
+    };
+    fetchPrice();
+  }, [productId]);
+
+  if (!price) return <span className="text-4xl font-bold text-gray-900">Loading...</span>;
+
+  return (
+    <span className="text-4xl font-bold text-gray-900">
+      ${(price * nights).toFixed(2)}
+    </span>
+  );
+};
+
 export default function HotelDetails({ product, onAddToCart, addedToCart }: HotelDetailsProps) {
+  const imageUrl = `https://images.unsplash.com/photo-1566073771259-6a8506099945?w=800&h=600&fit=crop`;
+
   return (
     <div className="w-full flex flex-col lg:flex-row gap-12 py-8">
-      {/* Image Section - Larger and cleaner */}
-      <div className="w-full lg:w-1/2 bg-gray-100 rounded-lg aspect-[4/3] flex items-center justify-center shrink-0">
-        <span className="text-gray-400 text-lg font-medium">Hotel Image</span>
+      <div className="w-full lg:w-1/2 rounded-lg aspect-[4/3] overflow-hidden shrink-0">
+        <img
+          src={imageUrl}
+          alt={product.name}
+          className="w-full h-full object-cover"
+          onError={(e) => {
+            e.currentTarget.style.display = 'none';
+            if (e.currentTarget.nextElementSibling) {
+              (e.currentTarget.nextElementSibling as HTMLElement).style.display = 'flex';
+            }
+          }}
+        />
+        <div className="w-full h-full bg-gray-100 rounded-lg flex items-center justify-center" style={{ display: 'none' }}>
+          <span className="text-gray-400 text-lg font-medium">Hotel Image</span>
+        </div>
       </div>
 
-      {/* Details Section - Full height/width usage */}
       <div className="flex-1 flex flex-col">
         <div className="border-b pb-6 mb-6">
           <h1 className="text-4xl font-bold text-gray-900 mb-2">{product.name}</h1>
-          <p className="text-xl text-gray-500">{product.roomType}</p>
         </div>
 
         <div className="grid grid-cols-2 gap-8 mb-8">
@@ -39,24 +85,17 @@ export default function HotelDetails({ product, onAddToCart, addedToCart }: Hote
           <div className="flex flex-wrap gap-3">
             {product.amenities.map(a => (
               <span key={a} className="px-3 py-1.5 bg-gray-100 text-gray-700 rounded-md text-sm font-medium">
-                {a}
+                  {a.replaceAll('_', ' ')}
               </span>
             ))}
           </div>
         </div>
 
-        {product.refundable && (
-          <div className="mb-8 p-4 bg-green-50 text-green-800 rounded-md inline-block">
-            <span className="font-medium">Free cancellation available</span>
-          </div>
-        )}
-
         <div className="mt-auto pt-6 border-t flex items-center justify-between">
           <div>
-            <p className="text-sm text-gray-500 mb-1">Total for {product.nights} night{product.nights > 1 ? 's' : ''}</p>
-            <div className="flex items-baseline gap-2">
-              <span className="text-4xl font-bold text-gray-900">${product.pricePerNight * product.nights}</span>
-              <span className="text-gray-500">/ {product.nights} nights</span>
+            <p className="text-sm text-gray-500 mb-1">Price per night</p>
+            <div className="mb-3">
+              <PriceDisplay productId={product.id} className="!text-2xl" />
             </div>
           </div>
 

web/src/components/ui/DateInput.tsx

@@ -1,7 +1,29 @@
-import { InputHTMLAttributes } from 'react';
+import { InputHTMLAttributes, useMemo } from 'react';
 
 interface DateInpProps extends Omit<InputHTMLAttributes<HTMLInputElement>, 'type'> {}
 
 export default function DateInput({ className = '', ...props }: DateInpProps) {
-  return <input type="date" className={`input-field ${className}`.trim()} {...props} />;
+  const { minDate, maxDate } = useMemo(() => {
+    const today = new Date();
+    const tomorrow = new Date(today);
+    tomorrow.setDate(today.getDate() + 1);
+
+    const tenDaysOut = new Date(tomorrow);
+    tenDaysOut.setDate(tomorrow.getDate() + 9); // tomorrow + 9 = 10 days total
+
+    return {
+      minDate: tomorrow.toISOString().split('T')[0],
+      maxDate: tenDaysOut.toISOString().split('T')[0]
+    };
+  }, []);
+
+  return (
+    <input
+      type="date"
+      className={`input-field ${className}`.trim()}
+      min={minDate}
+      max={maxDate}
+      {...props}
+    />
+  );
 }

web/src/components/ui/Navigation.tsx

@@ -20,7 +20,7 @@ const NavLink = ({ href, children }: { href: string; children: React.ReactNode }
       href={href}
       className={`px-4 py-2 rounded-md transition-colors ${
         isActive
-          ? 'bg-[var(--accent-primary)] text-white font-semibold'
+          ? 'bg-[var(--accent-primary)] font-semibold'
           : 'hover:bg-[var(--accent-primary-light)] text-[var(--text-primary)]'
       }`}
     >
@@ -37,9 +37,7 @@ export default function Navigation() {
           <div className="flex items-center space-x-1">
             <NavLink href="/">Home</NavLink>
             <NavLink href="/products">Products</NavLink>
-            <NavLink href="/search">Search</NavLink>
             <NavLink href="/cart">Cart</NavLink>
-            <NavLink href="/checkout">Checkout</NavLink>
           </div>
         </div>
       </div>

web/src/components/ui/SelectDropdown.tsx

@@ -0,0 +1,119 @@
+'use client';
+
+import { useState, useRef, useEffect, ReactNode } from 'react';
+
+export interface SelectOption {
+  value: string;
+  label: string;
+  sublabel?: string;
+}
+
+interface SelectDropdownProps {
+  value: string;
+  onChange: (value: string) => void;
+  options: SelectOption[];
+  placeholder?: string;
+  icon?: ReactNode;
+  required?: boolean;
+  id?: string;
+}
+
+export default function SelectDropdown({
+  value,
+  onChange,
+  options,
+  placeholder = 'Select...',
+  icon,
+  required,
+  id,
+}: SelectDropdownProps) {
+  const [open, setOpen] = useState(false);
+  const [filter, setFilter] = useState('');
+  const ref = useRef<HTMLDivElement>(null);
+  const inputRef = useRef<HTMLInputElement>(null);
+
+  useEffect(() => {
+    const handleClick = (e: MouseEvent) => {
+      if (ref.current && !ref.current.contains(e.target as Node)) {
+        setOpen(false);
+        setFilter('');
+      }
+    };
+    document.addEventListener('mousedown', handleClick);
+    return () => document.removeEventListener('mousedown', handleClick);
+  }, []);
+
+  const selectedOption = options.find((o) => o.value === value);
+  const filtered = options.filter(
+    (o) =>
+      o.label.toLowerCase().includes(filter.toLowerCase()) ||
+      o.value.toLowerCase().includes(filter.toLowerCase()) ||
+      o.sublabel?.toLowerCase().includes(filter.toLowerCase())
+  );
+
+  const handleSelect = (opt: SelectOption) => {
+    onChange(opt.value);
+    setOpen(false);
+    setFilter('');
+  };
+
+  return (
+    <div className="relative" ref={ref}>
+      <div
+        className="input-field flex items-center gap-2 cursor-pointer box-border"
+        onClick={() => {
+          setOpen(true);
+          setTimeout(() => inputRef.current?.focus(), 0);
+        }}
+      >
+        {icon && <span className="text-[var(--text-secondary)]">{icon}</span>}
+        {open ? (
+          <input
+            ref={inputRef}
+            type="text"
+            id={id}
+            value={filter}
+            onChange={(e) => setFilter(e.target.value)}
+            placeholder={placeholder}
+            className="flex-1 bg-transparent outline-none text-sm text-[var(--text-primary)]"
+          />
+        ) : (
+          <span className={`flex-1 text-sm ${value ? 'text-[var(--text-primary)]' : 'text-[var(--text-secondary)]'}`}>
+            {selectedOption ? selectedOption.label : placeholder}
+          </span>
+        )}
+        <svg
+          className={`w-4 h-4 text-[var(--text-secondary)] transition-transform ${open ? 'rotate-180' : ''}`}
+          fill="none"
+          stroke="currentColor"
+          viewBox="0 0 24 24"
+        >
+          <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 9l-7 7-7-7" />
+        </svg>
+      </div>
+      {open && (
+        <div className="absolute z-20 mt-1 w-full bg-[var(--bg-primary)] border-2 border-[var(--accent-primary)] rounded-md shadow-lg max-h-60 overflow-y-auto">
+          {filtered.length === 0 ? (
+            <div className="px-4 py-3 text-sm text-[var(--text-secondary)]">No results</div>
+          ) : (
+            filtered.map((opt) => (
+              <div
+                key={opt.value}
+                onClick={() => handleSelect(opt)}
+                className={`px-4 py-2 cursor-pointer transition-colors hover:bg-[var(--accent-primary-light)] ${
+                  opt.value === value ? 'bg-[var(--accent-primary-light)]' : ''
+                }`}
+              >
+                <div className="text-sm font-medium text-[var(--text-primary)]">{opt.label}</div>
+                {opt.sublabel && <div className="text-xs text-[var(--text-secondary)]">{opt.sublabel}</div>}
+              </div>
+            ))
+          )}
+        </div>
+      )}
+      {required && !value && (
+        <input type="text" required className="sr-only" tabIndex={-1} value="" onChange={() => {}} />
+      )}
+    </div>
+  );
+}

web/src/components/ui/index.ts

@@ -5,3 +5,5 @@ export { default as DateInput } from './DateInput';
 export { default as RadioGroup } from './RadioGroup';
 export { default as Dropdown, DropdownCounter } from './Dropdown';
 export { default as Navigation } from './Navigation';
+export { default as SelectDropdown } from './SelectDropdown';
+export type { SelectOption } from './SelectDropdown';

web/src/lib/config.ts

@@ -16,7 +16,7 @@ const envSchema = z.object({
 // parse and validate env at module load, fail fast with descriptive errors
 const parseEnv = (): Env => {
     const result = envSchema.safeParse({
-        STORE_MODE: process.env.STORE_MODE,
+        STORE_MODE: process.env.NEXT_PUBLIC_STORE_MODE || process.env.STORE_MODE,
         NEXT_PUBLIC_API_BASE: process.env.NEXT_PUBLIC_API_BASE,
         NEXT_PUBLIC_APP_ENV: process.env.NEXT_PUBLIC_APP_ENV,
     });

web/src/lib/hotel-utils.ts

@@ -21,7 +21,6 @@ export interface Hotel {
   checkOut: string;
   dateIndex: number;
   amenities: string[];
-  refundable: boolean;
   pricePerNight: number;
   nights: number;
 }
@@ -30,19 +29,37 @@ const EPOCH = new Date(0);
 
 export const transformProduct = (p: HotelProduct): Hotel => {
   const { id, room_type, date_index, metadata } = p;
-  const checkIn = new Date(EPOCH.getTime() + date_index * 86400000);
+
+  // DB stores date_index as days since epoch
+  // but if value is small (<1000), treat as days from today for backward compat
+  let checkIn: Date;
+  if (date_index < 1000) {
+    // legacy: treat as offset from today
+    const today = new Date();
+    today.setHours(0, 0, 0, 0);
+    checkIn = new Date(today.getTime() + date_index * 86400000);
+  } else {
+    // proper: days since epoch
+    checkIn = new Date(EPOCH.getTime() + date_index * 86400000);
+  }
+
   const nights = 1;
   const checkOut = new Date(checkIn.getTime() + nights * 86400000);
 
+  const formatOpts: Intl.DateTimeFormatOptions = {
+    month: 'short',
+    day: 'numeric',
+    year: checkIn.getFullYear() !== new Date().getFullYear() ? 'numeric' : undefined
+  };
+
   return {
     id,
     name: metadata?.name || room_type,
     roomType: room_type,
-    checkIn: checkIn.toLocaleDateString('en-US', { month: 'short', day: 'numeric' }),
-    checkOut: checkOut.toLocaleDateString('en-US', { month: 'short', day: 'numeric' }),
+    checkIn: checkIn.toLocaleDateString('en-US', formatOpts),
+    checkOut: checkOut.toLocaleDateString('en-US', formatOpts),
     dateIndex: date_index,
     amenities: metadata?.amenities || [],
-    refundable: metadata?.refundable || false,
     pricePerNight: metadata?.base_price || 100,
     nights,
   };

web/src/styles/airline.css

@@ -278,6 +278,8 @@
   padding: 12px;
   transition: border-color 0.2s ease;
   width: 100%;
+  min-height: 48px;
+  box-sizing: border-box;
 }
 
 [data-mode="airline"] .input-field:focus {