Upload potato_price_model.py

potato_price_model.py

@@ -0,0 +1,73 @@
+from transformers import pipeline
+import joblib
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta
+
+class PotatoPricePredictor:
+    def __init__(self):
+        self.model = joblib.load('best_potato_price_model_Ridge.joblib')
+        self.sentiment_analyzer = pipeline("sentiment-analysis")
+
+    def preprocess(self, data):
+        df = pd.DataFrame([data])
+        df['Date'] = pd.to_datetime(df['Date'])
+        
+        df['DayOfWeek'] = df['Date'].dt.dayofweek
+        df['Month'] = df['Date'].dt.month
+        df['Quarter'] = df['Date'].dt.quarter
+        df['Year'] = df['Date'].dt.year
+        
+        df['Events_Sentiment'] = df['Events'].apply(lambda x: self.sentiment_analyzer(x)[0]['score'] if x else 0)
+        df['Impacts_Sentiment'] = df['Impacts'].apply(lambda x: self.sentiment_analyzer(x)[0]['score'] if x else 0)
+        
+        return df
+
+    def predict(self, data):
+        processed_data = self.preprocess(data)
+        features = ['ArrivalQuantity', 'Temperature', 'Humidity', 'Wind direction',
+                    'Events_Sentiment', 'Impacts_Sentiment', 'DayOfWeek', 'Month', 'Quarter', 'Year',
+                    'PriceLag1', 'PriceLag7', 'PriceRollingMean7', 'PriceRollingStd7', 'PrevWeekAvgPrice']
+        
+        X = processed_data[features]
+        prediction = self.model.predict(X)
+        
+        return {'predicted_price': float(prediction[0])}
+
+    def predict_future(self, days=30):
+        last_date = datetime.now().date()
+        future_dates = [last_date + timedelta(days=i) for i in range(1, days + 1)]
+        
+        future_prices = []
+        last_price = 50  # You may want to adjust this initial value
+
+        for date in future_dates:
+            data = {
+                'Date': date.strftime('%Y-%m-%d'),
+                'ArrivalQuantity': 1000,  # You may want to randomize or adjust these values
+                'Temperature': 25,
+                'Humidity': 60,
+                'Wind direction': 180,
+                'Events': 'Normal day',
+                'Impacts': 'No significant impacts',
+                'PriceLag1': last_price,
+                'PriceLag7': last_price,
+                'PriceRollingMean7': last_price,
+                'PriceRollingStd7': 2,
+                'PrevWeekAvgPrice': last_price
+            }
+            
+            prediction = self.predict(data)
+            future_prices.append(prediction['predicted_price'])
+            last_price = prediction['predicted_price']
+
+        return {'future_prices': [{'date': date.strftime('%Y-%m-%d'), 'price': price} for date, price in zip(future_dates, future_prices)]}
+
+predictor = PotatoPricePredictor()
+
+def query(payload):
+    if payload.get('predict_future'):
+        days = payload.get('days', 30)
+        return predictor.predict_future(days)
+    else:
+        return predictor.predict(payload)