Feature extraction and model training

app.py

@@ -3,13 +3,15 @@ import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 import seaborn as sns
-from collections import Counter
+import json
 from sklearn.model_selection import train_test_split
 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, RandomOverSampler
+from imblearn.over_sampling import SMOTE
 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
 from sklearn.svm import SVC, SVR
 from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
@@ -48,9 +50,18 @@ problems = {
 
 problem = st.sidebar.selectbox("Choose a Problem:", problems[task][model])
 
-# Dataset Mapping (Dynamic)
-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 (Simulated dataset paths)
+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)
@@ -80,8 +91,8 @@ for col in df.select_dtypes(include=['object']).columns:
     df[col] = label_encoders[col].fit_transform(df[col])
 
 # Split Data
-X = df.iloc[:, :-1]
-y = df.iloc[:, -1]
+X = df.iloc[:, :-1]  # Features
+y = df.iloc[:, -1]   # Target
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
 # Feature Scaling
@@ -90,31 +101,25 @@ X_train = scaler.fit_transform(X_train)
 X_test = scaler.transform(X_test)
 
 # Feature Selection
-selector = SelectKBest(score_func=f_classif, k=min(X.shape[1], 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)
 
-# Handle imbalanced data
+# Handle imbalanced data (only for classification)
 if task == "Classification":
-    class_counts = Counter(y_train)
-    min_class_samples = min(class_counts.values())
-
-    if min_class_samples > 5:
+    if len(set(y_train)) > 1 and len(y_train) > 5:  # Avoid SMOTE errors
         smote = SMOTE()
         X_train, y_train = smote.fit_resample(X_train, y_train)
-    else:
-        ros = RandomOverSampler()
-        X_train, y_train = ros.fit_resample(X_train, y_train)
 
 # Model Initialization
-n_neighbors = min(5, len(y_train))
 model_mapping = {
-    "KNN": KNeighborsClassifier(n_neighbors=n_neighbors) if task == "Classification" else KNeighborsRegressor(n_neighbors=n_neighbors),
+    "KNN": KNeighborsClassifier() if task == "Classification" else KNeighborsRegressor(),
     "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()
 }
+
 model_instance = model_mapping[model]
 
 # Train Model
@@ -123,30 +128,76 @@ y_pred = model_instance.predict(X_test)
 
 # Model Evaluation
 st.subheader("📊 Model Evaluation")
+
 if task == "Classification":
     accuracy = accuracy_score(y_test, y_pred)
     report = classification_report(y_test, y_pred, output_dict=True)
     st.write(f"**Accuracy:** {accuracy:.2f}")
     st.json(report)
-else:
+
+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"**MSE:** {mse:.4f}, **MAE:** {mae:.4f}, **R² Score:** {r2:.4f}")
+    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")
 fig, ax = plt.subplots(figsize=(8, 5))
 sns.heatmap(df.corr(), annot=True, cmap="coolwarm", ax=ax)
 st.pyplot(fig)
 
-if model in ["Random Forest", "Decision Tree"] and hasattr(model_instance, "feature_importances_"):
-    importance_df = pd.DataFrame({"Feature": X.columns, "Importance": model_instance.feature_importances_}).sort_values(by="Importance", ascending=False)
+# 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}).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)
 
-st.success("Code generated! 🚀 Download & run!")
+# Show and Download Generated Code
+generated_code = f"""
+# AI Model Code
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from {model_instance.__module__} import {model_instance.__class__.__name__}
+
+# Load Data
+df = pd.read_csv('{dataset_path}')
+X = df.iloc[:, :-1]
+y = df.iloc[:, -1]
+
+# Train/Test Split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Scaling
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
+
+# Train Model
+model = {model_instance.__class__.__name__}()
+model.fit(X_train, y_train)
+
+# Predict
+y_pred = model.predict(X_test)
+print(y_pred)
+"""
+
+st.subheader("📜 Generated Code")
+st.code(generated_code, language="python")
+
+# Download buttons
+st.download_button("📥 Download Python Script (.py)", generated_code, file_name="ai_model.py", mime="text/x-python")
+st.download_button("📥 Download Jupyter Notebook (.ipynb)", json.dumps({"cells": [{"cell_type": "code", "source": generated_code.split("\n"), "metadata": {}}], "metadata": {}, "nbformat": 4, "nbformat_minor": 2}), file_name="ai_model.ipynb", mime="application/json")
+
+st.success("Code generated! Download and start using it! 🚀")