chore: redefined and connected pricers

experiments/procesing/pricers/__init__.py

@@ -1,10 +1,13 @@
 from procesing.pricers.base import PricingFunction
 from procesing.pricers.elasticity import ElasticityBasedPricer
 from procesing.pricers.simple import StaticPricer, RandomPricer
+from procesing.pricers.session_aware import SessionAwarePricer, ProductSpecificSessionPricer
 
 __all__ = [
     'PricingFunction',
     'ElasticityBasedPricer',
     'StaticPricer',
-    'RandomPricer'
+    'RandomPricer',
+    'SessionAwarePricer',
+    'ProductSpecificSessionPricer'
 ]

experiments/procesing/pricers/base.py

@@ -1,4 +1,5 @@
 from abc import ABC, abstractmethod
+from typing import Optional, Dict, Any, List
 import numpy as np
 import pandas as pd
 
@@ -6,23 +7,64 @@ import pandas as pd
 class PricingFunction(ABC):
     """
     Abstract base for pricing functions.
-    Defines the mapping f: StateSpace -> prices
+
+    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, historical_data: pd.DataFrame):
-        """Train/calibrate the pricing function on historical data"""
+    def fit(self, historical_data: pd.DataFrame, **kwargs):
+        """
+        Offline training on historical data.
+
+        Args:
+            historical_data: DataFrame with elasticity, prices, demand signals
+            **kwargs: additional training parameters
+        """
         pass
 
     @abstractmethod
     def predict(self, state_space) -> np.ndarray:
         """
-        Generate prices given current state space.
+        Generate optimal prices given current state.
 
         Args:
-            state_space: StateSpace object containing demand, prices, session features
+            state_space: StateSpace object containing Q_t, P_t, S_t, H_t
 
         Returns:
-            prices: price vector P_{t+1} in R^n
+            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/steps/pricing.py

@@ -1,30 +1,77 @@
 import numpy as np
 import pandas as pd
+from typing import Optional, List, Dict, Any
+from dataclasses import dataclass, field
 from procesing.steps.base import BaseContextStep
 from procesing.pricers import ElasticityBasedPricer
 
+@dataclass
 class StateSpace:
-    """State representation for pricing functions"""
-    def __init__(self,
-                 demand: np.ndarray,
-                 prices: np.ndarray,
-                 session_features: pd.DataFrame = None):
-        self.demand = demand
-        self.prices = prices
-        self.session_features = session_features if session_features is not None else pd.DataFrame()
+    """
+    State representation for pricing functions.
+
+    Components:
+        Q_t: demand ∈ R^n (current demand signal per product)
+        P_t: prices ∈ R^n (current/base prices)
+        S_t: session_features (behavioral signals, interaction data)
+        H_t: history = {Q_{t-k}, P_{t-k}, S_{t-k}} for k in [1, history_length]
+
+    Additionally stores:
+        - product_ids: product identifiers (n,)
+        - elasticity: price elasticity per product (n,)
+        - metadata: arbitrary context (experiment_id, timestamp, etc.)
+    """
+    demand: np.ndarray  # Q_t ∈ R^n
+    prices: np.ndarray  # P_t ∈ R^n
+    session_features: pd.DataFrame = field(default_factory=pd.DataFrame)  # S_t
+
+    # augmented state components
+    product_ids: Optional[np.ndarray] = None
+    elasticity: Optional[np.ndarray] = None
+
+    # historical trajectory H_t = {(Q_{t-k}, P_{t-k}, S_{t-k})}
+    history: List[Dict[str, Any]] = field(default_factory=list)
+
+    # metadata for context
+    metadata: Dict[str, Any] = field(default_factory=dict)
+
+    def __post_init__(self):
+        """Validate dimensions."""
+        n = len(self.demand)
+        assert len(self.prices) == n, "demand and prices must have same dimension"
+        if self.elasticity is not None:
+            assert len(self.elasticity) == n, "elasticity must match dimension"
+        if self.product_ids is not None:
+            assert len(self.product_ids) == n, "product_ids must match dimension"
+
+    @property
+    def n_products(self) -> int:
+        """Number of products in state space."""
+        return len(self.demand)
+
+    def add_history(self, q: np.ndarray, p: np.ndarray, s: pd.DataFrame, max_length: int = 10):
+        """Append historical state to trajectory H_t."""
+        self.history.append({'demand': q, 'prices': p, 'session_features': s})
+        if len(self.history) > max_length:
+            self.history.pop(0)
+
+    def get_history_window(self, k: int = 5) -> List[Dict[str, Any]]:
+        """Retrieve last k historical states."""
+        return self.history[-k:] if len(self.history) >= k else self.history
 
 
 class BuildStateSpaceStep(BaseContextStep):
     """
-    Build state space from elasticity and price data.
-    Input: elasticity_df
-    Output: StateSpace instance
+    Build state space from elasticity, demand, and price data.
+
+    Input: elasticity_df [productId, elasticity, ...], optional demand_df
+    Output: StateSpace instance with Q_t, P_t, elasticity, product_ids
     """
 
-    def transform(self, elasticity_df: pd.DataFrame):
+    def transform(self, elasticity_df: pd.DataFrame, demand_df: Optional[pd.DataFrame] = None):
         products = self.context.products
 
-        # fetch current/base prices from product metadata
+        # extract base prices from product metadata
         products_with_prices = products.copy()
         if 'metadata' in products_with_prices.columns:
             products_with_prices['base_price'] = products_with_prices['metadata'].apply(
@@ -42,10 +89,25 @@ class BuildStateSpaceStep(BaseContextStep):
             how='left'
         ).fillna({'elasticity': 0.0, 'base_price': 0.0})
 
+        # merge with demand if provided, else use default
+        if demand_df is not None and 'demand' in demand_df.columns:
+            merged = merged.merge(
+                demand_df[['productId', 'demand']],
+                on='productId',
+                how='left'
+            ).fillna({'demand': 0.0})
+            demand_vector = merged['demand'].values
+        else:
+            # default: uniform demand or use elasticity as proxy
+            demand_vector = np.ones(len(merged)) * 10.0
+
         return StateSpace(
-            demand=merged['elasticity'].values,
+            demand=demand_vector,
             prices=merged['base_price'].values,
-            session_features=pd.DataFrame()
+            session_features=pd.DataFrame(),
+            product_ids=merged['productId'].values,
+            elasticity=merged['elasticity'].values,
+            metadata={'timestamp': pd.Timestamp.now().isoformat()}
         )