Feature extraction and model training

app.py

@@ -8,7 +8,7 @@ from sklearn.preprocessing import StandardScaler, LabelEncoder
 from sklearn.feature_selection import SelectKBest, f_classif
 from sklearn.impute import SimpleImputer
 from imblearn.over_sampling import SMOTE
-from sklearn.metrics import accuracy_score, classification_report
+from sklearn.metrics import accuracy_score, classification_report, mean_squared_error, mean_absolute_error, r2_score
 
 # Import ML Models
 from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
@@ -49,14 +49,20 @@ problems = {
 
 problem = st.sidebar.selectbox("Choose a Problem:", problems[task][model])
 
-# Dataset Selection (User selects a pre-existing fake dataset)
-dataset_mapping = {
-    "Spam Detection": "datasets/spam_detection.csv",
-    "Disease Prediction": "datasets/disease_prediction.csv",
-    "Fraud Detection": "datasets/fraud_detection.csv",
-    "House Price Prediction": "datasets/house_price.csv",
-    "Sales Forecasting": "datasets/sales_forecasting.csv",
-}
+dataset_mapping = {name: f"datasets/{name.lower().replace(' ', '_')}.csv" for sublist in problems.values() for model in sublist for name in sublist[model]}
+
+# # Dataset Selection (User selects a pre-existing fake dataset)
+# dataset_mapping = {
+#     "Spam Detection": "datasets/spam_detection.csv",
+#     "Disease Prediction": "datasets/disease_prediction.csv",
+#     "Image Recognition": "datasets/image_recognition.csv",
+#     "Text Classification": "datasets/text_classification.csv",
+#     "Fraud Detection": "datasets/fraud_detection.csv",
+#     "Customer Segmentation": "datasets/customer_segmentation.csv",
+#     "Loan Approval": "datasets/loan_approval.csv",
+#     "House Price Prediction": "datasets/house_price_prediction.csv",
+#     "Sales Forecasting": "datasets/sales_forecasting.csv",
+# }
 
 dataset_path = dataset_mapping.get(problem, "datasets/spam_detection.csv")
 df = pd.read_csv(dataset_path)
@@ -96,7 +102,7 @@ X_train = scaler.fit_transform(X_train)
 X_test = scaler.transform(X_test)
 
 # Feature Selection
-selector = SelectKBest(score_func=f_classif, k=5)
+selector = SelectKBest(score_func=f_classif, k=min(5, X.shape[1]))  # Ensure k does not exceed available features
 X_train = selector.fit_transform(X_train, y_train)
 X_test = selector.transform(X_test)
 
@@ -106,13 +112,24 @@ if task == "Classification":
     X_train, y_train = smote.fit_resample(X_train, y_train)
 
 # Model Initialization
-model_mapping = {
- "KNN": KNeighborsClassifier(n_neighbors=min(5, len(X_train))) if task == "Classification" 
-           else KNeighborsRegressor(n_neighbors=min(5, len(X_train))),    "SVM": SVC() if task == "Classification" else SVR(),
-    "Random Forest": RandomForestClassifier() if task == "Classification" else RandomForestRegressor(),
-    "Decision Tree": DecisionTreeClassifier() if task == "Classification" else DecisionTreeRegressor(),
-    "Perceptron": Perceptron() if task == "Classification" else Perceptron()
-}
+if task == "Classification":
+    n_neighbors = min(5, len(y_train))  # Ensure k is valid
+    model_mapping = {
+        "KNN": KNeighborsClassifier(n_neighbors=n_neighbors),
+        "SVM": SVC(),
+        "Random Forest": RandomForestClassifier(),
+        "Decision Tree": DecisionTreeClassifier(),
+        "Perceptron": Perceptron()
+    }
+else:
+    n_neighbors = min(5, len(y_train))  # Ensure k is valid
+    model_mapping = {
+        "KNN": KNeighborsRegressor(n_neighbors=n_neighbors),
+        "SVM": SVR(),
+        "Random Forest": RandomForestRegressor(),
+        "Decision Tree": DecisionTreeRegressor(),
+        "Perceptron": Perceptron()
+    }
 
 model_instance = model_mapping[model]
 
@@ -120,22 +137,51 @@ model_instance = model_mapping[model]
 model_instance.fit(X_train, y_train)
 y_pred = model_instance.predict(X_test)
 
-# Evaluation Metrics
+# Model Evaluation
 st.subheader("📊 Model Evaluation")
+
 if task == "Classification":
     accuracy = accuracy_score(y_test, y_pred)
-    report = classification_report(y_test, y_pred)
-    st.write(f"**Accuracy:** {accuracy:.2f}")
-    st.text(report)
-else:
-    st.write("Regression evaluation metrics will be added soon!")
+    report = classification_report(y_test, y_pred, output_dict=True)
 
-# Visualization
+    st.write(f"**Accuracy:** {accuracy:.2f}")
+    st.json(report)  # Shows detailed structured metrics
+    
+elif task == "Regression":
+    mse = mean_squared_error(y_test, y_pred)
+    mae = mean_absolute_error(y_test, y_pred)
+    r2 = r2_score(y_test, y_pred)
+    
+    st.write(f"**Mean Squared Error (MSE):** {mse:.4f}")
+    st.write(f"**Mean Absolute Error (MAE):** {mae:.4f}")
+    st.write(f"**R² Score:** {r2:.4f}")
+
+# Data Visualization
 st.subheader("📈 Data Visualization")
+
+# Heatmap
+st.write("### 🔥 Feature Correlation")
 plt.figure(figsize=(8, 5))
 sns.heatmap(df.corr(), annot=True, cmap="coolwarm")
 st.pyplot(plt)
 
+# Pair Plot
+st.write("### 📊 Pair Plot of Features")
+sns.pairplot(df, diag_kind='kde')
+st.pyplot()
+
+# Feature Importance (for tree-based models)
+if model in ["Random Forest", "Decision Tree"]:
+    feature_importances = model_instance.feature_importances_
+    feature_names = X.columns
+    importance_df = pd.DataFrame({"Feature": feature_names, "Importance": feature_importances})
+    importance_df = importance_df.sort_values(by="Importance", ascending=False)
+    
+    st.write("### 🌟 Feature Importance")
+    fig, ax = plt.subplots()
+    sns.barplot(x=importance_df["Importance"], y=importance_df["Feature"], ax=ax)
+    st.pyplot(fig)
+
 # Download Code
 st.download_button("🐍 Download Python Code (.py)", "ai_model.py")
 st.download_button("📓 Download Notebook (.ipynb)", "ai_model.ipynb")