Update app.py

app.py

@@ -1,80 +1,44 @@
 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)
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
 
-st.title("Lightweight Electric Vehicle ML App")
+st.set_page_config(page_title="EV Predictor", layout="centered")
+st.title("🔋 EV Range Classifier (Ultra-Light)")
 
 @st.cache_data
 def load_data():
     url = "https://drive.google.com/uc?export=download&id=1QBTnXxORRbJzE5Z2aqKHsVqgB7mqowiN"
     return pd.read_csv(url)
 
+# Load and clean data
 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] = LabelEncoder().fit_transform(df[col])
+for col in df.select_dtypes(include='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.")
+# Prepare features
+target_col = 'Electric Range'
+if target_col not in df.columns:
+    st.error("Required column not found: 'Electric Range'")
     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)
+df['Target'] = (df[target_col] > df[target_col].median()).astype(int)
+feature_cols = [col for col in df.select_dtypes(include='number').columns if col != target_col and col != 'Target'][:2]
 
-st.subheader("2. Model Evaluation")
-st.text("Classification Report:")
-st.text(classification_report(y_test, y_pred))
+X = df[feature_cols]
+y = df['Target']
 
-st.text("Confusion Matrix:")
-st.write(confusion_matrix(y_test, y_pred))
+# Train model on split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+model = RandomForestClassifier(n_estimators=10, random_state=42)
+model.fit(X_train, y_train)
 
-# 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()
+# Output
+acc = model.score(X_test, y_test)
+st.success(f"✅ Accuracy: {acc:.2f}")
+if st.checkbox("Show features used"):
+    st.write(feature_cols)