Update app.py

app.py

@@ -17,78 +17,86 @@ st.set_page_config(page_title="Electronics Sales Prediction", layout="wide")
 
 st.title("📊 Consumer Electronics Sales Prediction App")
 
-st.markdown("## 📂 Upload Your Dataset")
+# Load default dataset
+@st.cache_data
+def load_default_data():
+    return pd.read_csv('/mnt/data/consumer_electronics_sales_data.csv')
+
+st.markdown("## 📂 Upload Your Dataset or Use Default")
 uploaded_file = st.file_uploader("Upload CSV file", type=["csv"])
 
 if uploaded_file is not None:
     with st.spinner('Loading Data...'):
         time.sleep(1)
-    
     data = pd.read_csv(uploaded_file)
     st.success("Data Uploaded Successfully ✅")
+else:
+    st.info("📊 Using Default Dataset")
+    data = load_default_data()
+
+st.subheader("👀 Data Preview")
+st.write(data.head())
+
     
-    st.subheader("👀 Data Preview")
-    st.write(data.head())
-
-    df = data.copy()
-
-    # Rename columns (Check if 'Sales' exists)
-    if 'Sales' in df.columns:
-        df = df.rename(columns={'Order Date': 'order_date', 'Category': 'category', 'Sub-Category': 'sub_category', 'Sales': 'sales'})
-    else:
-        st.error("🚨 'Sales' column not found in the uploaded file. Please ensure the correct dataset is uploaded.")
-        st.stop()
-
-    st.subheader("📊 Data Summary")
-    st.write(df.describe())
-
-    # Data Visualization
-    st.subheader("📈 Sales Distribution")
-    fig, ax = plt.subplots()
-    sns.histplot(df['sales'], kde=True, color='skyblue', ax=ax)
-    st.pyplot(fig)
-
-    st.markdown("### 🔄 Encoding Categorical Variables")
-    le = LabelEncoder()
-    df['category'] = le.fit_transform(df['category'])
-    df['sub_category'] = le.fit_transform(df['sub_category'])
-    st.write("Categorical Encoding Done 🎯")
-
-    # Train-test split
-    X = df[['category', 'sub_category']]
-    y = df['sales']
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-    st.markdown("### 🚀 Model Training")
-    model = LogisticRegression()
-    model.fit(X_train, y_train)
-    
-    # Predictions
-    y_pred = model.predict(X_test)
-
-    # Evaluation
-    st.markdown("### 📈 Model Evaluation")
-    accuracy = accuracy_score(y_test, y_pred)
-    st.metric(label="Model Accuracy", value=f"{accuracy:.2%}")
-    st.write("🔍 Classification Report:")
-    st.text(classification_report(y_test, y_pred))
-
-    # Confusion Matrix
-    st.subheader("🎯 Confusion Matrix")
-    fig, ax = plt.subplots()
-    sns.heatmap(confusion_matrix(y_test, y_pred), annot=True, fmt='d', cmap='Blues', ax=ax)
-    st.pyplot(fig)
-
-    # Additional Feature: Interactive Plot
-    st.subheader("📊 Interactive Sales Analysis")
-    fig = px.scatter(df, x='category', y='sales', color='sub_category', title="Sales by Category and Sub-Category")
-    st.plotly_chart(fig)
-
-    # Sidebar Information
-    st.sidebar.title("📋 App Navigation")
-    st.sidebar.markdown("- Upload Dataset")
-    st.sidebar.markdown("- View Data Summary")
-    st.sidebar.markdown("- Train Model")
-    st.sidebar.markdown("- View Results")
-
-    st.sidebar.info("🔧 **Ensure to preprocess your data properly for accurate results.**")
+df = data.copy()
+
+# Rename columns (Check if 'Sales' exists)
+if 'Sales' in df.columns:
+    df = df.rename(columns={'Order Date': 'order_date', 'Category': 'category', 'Sub-Category': 'sub_category', 'Sales': 'sales'})
+else:
+    st.error("🚨 'Sales' column not found in the dataset. Please check the file format.")
+    st.stop()
+
+st.subheader("📊 Data Summary")
+st.write(df.describe())
+
+# Data Visualization
+st.subheader("📈 Sales Distribution")
+fig, ax = plt.subplots()
+sns.histplot(df['sales'], kde=True, color='skyblue', ax=ax)
+st.pyplot(fig)
+
+st.markdown("### 🔄 Encoding Categorical Variables")
+le = LabelEncoder()
+df['category'] = le.fit_transform(df['category'])
+df['sub_category'] = le.fit_transform(df['sub_category'])
+st.write("Categorical Encoding Done 🎯")
+
+# Train-test split
+X = df[['category', 'sub_category']]
+y = df['sales']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+st.markdown("### 🚀 Model Training")
+model = LogisticRegression()
+model.fit(X_train, y_train)
+
+# Predictions
+y_pred = model.predict(X_test)
+
+# Evaluation
+st.markdown("### 📈 Model Evaluation")
+accuracy = accuracy_score(y_test, y_pred)
+st.metric(label="Model Accuracy", value=f"{accuracy:.2%}")
+st.write("🔍 Classification Report:")
+st.text(classification_report(y_test, y_pred))
+
+# Confusion Matrix
+st.subheader("🎯 Confusion Matrix")
+fig, ax = plt.subplots()
+sns.heatmap(confusion_matrix(y_test, y_pred), annot=True, fmt='d', cmap='Blues', ax=ax)
+st.pyplot(fig)
+
+# Additional Feature: Interactive Plot
+st.subheader("📊 Interactive Sales Analysis")
+fig = px.scatter(df, x='category', y='sales', color='sub_category', title="Sales by Category and Sub-Category")
+st.plotly_chart(fig)
+
+# Sidebar Information
+st.sidebar.title("📋 App Navigation")
+st.sidebar.markdown("- Upload Dataset")
+st.sidebar.markdown("- View Data Summary")
+st.sidebar.markdown("- Train Model")
+st.sidebar.markdown("- View Results")
+
+st.sidebar.info("🔧 **Ensure to preprocess your data properly for accurate results.**")