mirror of
https://github.com/velocitatem/PHANTOM.git
synced 2026-05-31 16:43:36 +00:00
Improving interface after experiment01 (#30)
* 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
This commit is contained in:
Daniel Alves Rösel
committed by
GitHub
GitHub
parent
59d4fb7891
commit
8751583764
@@ -2,7 +2,6 @@ from sklearn.pipeline import Pipeline
|
||||
import pandas as pd
|
||||
from procesing.context import PipelineContext
|
||||
from procesing.providers import SupabaseProvider, BackendAPIProvider
|
||||
from typing import Union
|
||||
from procesing.steps import (
|
||||
FetchInteractionsStep,
|
||||
FetchPriceLogsStep,
|
||||
@@ -13,11 +12,13 @@ from procesing.steps import (
|
||||
ChunkByTimeWindowStep,
|
||||
ComputeDemandForChunksStep,
|
||||
AggregatePriceLogsStep,
|
||||
ComputeElasticityStep,
|
||||
# BuildStateSpaceStep,
|
||||
FitPricingFunctionStep,
|
||||
PredictPricesStep,
|
||||
ComputeDemandStep,
|
||||
JoinProductFeaturesStep
|
||||
)
|
||||
from procesing.pricers import SimpleSurgePricer
|
||||
|
||||
def interaction_extraction_pipeline(context: PipelineContext):
|
||||
"""Pipeline for extracting and augmenting interaction data"""
|
||||
@@ -35,80 +36,76 @@ def price_extraction_pipeline(context: PipelineContext):
|
||||
])
|
||||
|
||||
|
||||
def elasticity_computation_pipeline(context: PipelineContext,
|
||||
def product_features_pipeline(context: PipelineContext,
|
||||
interactions_df: pd.DataFrame,
|
||||
price_logs_df: pd.DataFrame):
|
||||
"""
|
||||
Compute elasticity from interactions and price logs.
|
||||
Manual orchestration needed for branching logic.
|
||||
"""
|
||||
# branch 1: chunk interactions and compute demand
|
||||
chunk_step = ChunkByTimeWindowStep(context)
|
||||
interaction_chunks = chunk_step.transform(interactions_df)
|
||||
|
||||
demand_step = ComputeDemandForChunksStep(context)
|
||||
demand_chunks = demand_step.transform(interaction_chunks)
|
||||
|
||||
# branch 2: aggregate price logs
|
||||
demand_step = ComputeDemandStep(context)
|
||||
price_step = AggregatePriceLogsStep(context)
|
||||
price_chunks = price_step.transform(price_logs_df)
|
||||
|
||||
# convergence: compute elasticity
|
||||
elasticity_step = ComputeElasticityStep(context)
|
||||
elasticity_df = elasticity_step.transform((demand_chunks, price_chunks))
|
||||
|
||||
return elasticity_df
|
||||
join_step = JoinProductFeaturesStep(context)
|
||||
|
||||
|
||||
def pricing_pipeline(context: PipelineContext, elasticity_df: pd.DataFrame):
|
||||
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):
|
||||
"""
|
||||
Generate optimal prices from elasticity estimates.
|
||||
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]
|
||||
"""
|
||||
# build state space
|
||||
state_step = BuildStateSpaceStep(context)
|
||||
state_space = state_step.transform(elasticity_df)
|
||||
|
||||
# fit pricing function
|
||||
fit_step = FitPricingFunctionStep(context)
|
||||
pricer = fit_step.transform(elasticity_df)
|
||||
|
||||
# predict prices
|
||||
predict_step = PredictPricesStep(context)
|
||||
prices_df = predict_step.transform((pricer, state_space))
|
||||
|
||||
return prices_df
|
||||
|
||||
|
||||
def full_pipeline(context: PipelineContext):
|
||||
"""
|
||||
Complete end-to-end pipeline: data extraction -> elasticity -> pricing
|
||||
Returns: (elasticity_df, prices_df)
|
||||
"""
|
||||
# extract interactions
|
||||
interaction_pipe = interaction_extraction_pipeline(context)
|
||||
interactions_df = interaction_pipe.fit_transform(None)
|
||||
|
||||
# extract price logs
|
||||
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())
|
||||
|
||||
if interactions_df.empty or price_logs_df.empty:
|
||||
return None, None
|
||||
# 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)
|
||||
|
||||
# compute elasticity
|
||||
elasticity_df = elasticity_computation_pipeline(
|
||||
context,
|
||||
interactions_df,
|
||||
price_logs_df
|
||||
)
|
||||
return product_features_df, optimal_prices_df
|
||||
|
||||
if elasticity_df is None or elasticity_df.empty:
|
||||
return elasticity_df, None
|
||||
|
||||
# generate prices
|
||||
prices_df = pricing_pipeline(context, elasticity_df)
|
||||
|
||||
return elasticity_df, prices_df
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
@@ -117,24 +114,25 @@ if __name__ == '__main__':
|
||||
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=Provider(backend_url="http://localhost:5000"),
|
||||
provider=HistoricalProvider(),
|
||||
store_mode='hotel',
|
||||
# 15 min not month
|
||||
window_size='15min',
|
||||
)
|
||||
|
||||
elasticity_df, prices_df = full_pipeline(context)
|
||||
|
||||
if elasticity_df is not None and not elasticity_df.empty:
|
||||
print("Elasticity Estimates:")
|
||||
print(elasticity_df.to_string(index=False))
|
||||
else:
|
||||
print("No elasticity estimates computed.")
|
||||
|
||||
if prices_df is not None and not prices_df.empty:
|
||||
print("\nPredicted Prices:")
|
||||
print(prices_df.to_string(index=False))
|
||||
else:
|
||||
print("No prices predicted.")
|
||||
product_features, prices = full_pipeline(context)
|
||||
print(prices.to_string())
|
||||
|
||||
Reference in New Issue
Block a user