Create predictive_analytics.py

predictive_analytics.py

@@ -0,0 +1,62 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier
+from sklearn.metrics import mean_squared_error, r2_score, accuracy_score, classification_report
+
+class PredictiveAnalytics:
+    def __init__(self):
+        self.model = None
+        self.scaler = StandardScaler()
+        self.target_column = None
+
+    def predict(self, data):
+        # Identify the target column (assuming it's the last column)
+        self.target_column = data.columns[-1]
+        
+        # Prepare the data
+        X = data.drop(columns=[self.target_column])
+        y = data[self.target_column]
+
+        # Split the data
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+        # Scale the features
+        X_train_scaled = self.scaler.fit_transform(X_train)
+        X_test_scaled = self.scaler.transform(X_test)
+
+        # Determine if it's a regression or classification problem
+        if y.dtype == 'object' or len(np.unique(y)) < 10:
+            self.model = RandomForestClassifier(n_estimators=100, random_state=42)
+            is_classification = True
+        else:
+            self.model = RandomForestRegressor(n_estimators=100, random_state=42)
+            is_classification = False
+
+        # Train the model
+        self.model.fit(X_train_scaled, y_train)
+
+        # Make predictions
+        y_pred = self.model.predict(X_test_scaled)
+
+        # Evaluate the model
+        if is_classification:
+            accuracy = accuracy_score(y_test, y_pred)
+            report = classification_report(y_test, y_pred)
+            return f"Classification Results:\nAccuracy: {accuracy:.2f}\n\nClassification Report:\n{report}"
+        else:
+            mse = mean_squared_error(y_test, y_pred)
+            r2 = r2_score(y_test, y_pred)
+            return f"Regression Results:\nMean Squared Error: {mse:.2f}\nR-squared Score: {r2:.2f}"
+
+    def get_feature_importance(self):
+        if self.model is None:
+            return "Model has not been trained yet."
+        
+        feature_importance = pd.DataFrame({
+            'feature': self.model.feature_names_in_,
+            'importance': self.model.feature_importances_
+        }).sort_values('importance', ascending=False)
+        
+        return feature_importance