Create app3.py

app3.py

@@ -0,0 +1,80 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import classification_report, confusion_matrix
+
+st.set_option('deprecation.showPyplotGlobalUse', False)
+
+st.title("Lightweight Electric Vehicle ML App")
+
+@st.cache_data
+def load_data():
+    url = "https://drive.google.com/uc?export=download&id=1QBTnXxORRbJzE5Z2aqKHsVqgB7mqowiN"
+    return pd.read_csv(url)
+
+df = load_data()
+
+st.subheader("1. Dataset Preview")
+st.write(df.head())
+
+# Fill missing values
+for col in df.select_dtypes(include='object').columns:
+    df[col] = df[col].fillna(df[col].mode()[0])
+for col in df.select_dtypes(include=np.number).columns:
+    df[col] = df[col].fillna(df[col].median())
+
+# Encode categorical columns
+cat_cols = df.select_dtypes(include='object').columns
+for col in cat_cols:
+    le = LabelEncoder()
+    df[col] = le.fit_transform(df[col])
+
+# Create target and features
+if 'Electric Range' in df.columns:
+    df['Target'] = (df['Electric Range'] > df['Electric Range'].median()).astype(int)
+    y = df['Target']
+    X = df.drop(columns=['Electric Range', 'Target'])
+else:
+    st.error("Dataset missing 'Electric Range' column.")
+    st.stop()
+
+# Use only top 5 numeric features
+num_features = X.select_dtypes(include=np.number).columns[:5]
+X = X[num_features]
+
+# Train/Test Split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+# Standardize features
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+# Model Training
+model = RandomForestClassifier(n_estimators=50, random_state=42)
+model.fit(X_train_scaled, y_train)
+y_pred = model.predict(X_test_scaled)
+
+st.subheader("2. Model Evaluation")
+st.text("Classification Report:")
+st.text(classification_report(y_test, y_pred))
+
+st.text("Confusion Matrix:")
+st.write(confusion_matrix(y_test, y_pred))
+
+# Optional: simple plot
+if st.checkbox("Show Feature Importance"):
+    importances = model.feature_importances_
+    indices = np.argsort(importances)[::-1]
+    plt.figure(figsize=(8, 4))
+    plt.title("Feature Importances")
+    plt.bar(range(len(indices)), importances[indices], align="center")
+    plt.xticks(range(len(indices)), [num_features[i] for i in indices], rotation=45)
+    plt.tight_layout()
+    st.pyplot()