Update app.py

app.py

@@ -1,7 +1,9 @@
 import streamlit as st
 import pandas as pd
+from utils.data_cleaning import handle_missing_values, remove_outliers_iqr, cap_extreme_values
 from utils.visualizations import plot_correlation_heatmap, save_plot_as_png
-from utils.model_training import train_all_models  # Import from model_training.py
+from utils.model_training import train_all_models
+
 # File uploader
 st.title("Model Training with Metrics and Correlation Heatmap")
 uploaded_file = st.file_uploader("Choose a CSV file", type=["csv"])
@@ -13,12 +15,12 @@ if uploaded_file is not None:
     st.write("Dataset:")
     st.dataframe(df)
 
-    # Clean data: Missing values, outliers, and extreme values (You can add the functions like handle_missing_values, etc.)
-    # df = handle_missing_values(df)  # Un-comment when cleaning functions are added
-    # df = remove_outliers_iqr(df)    # Un-comment when cleaning functions are added
-    # df = cap_extreme_values(df)     # Un-comment when cleaning functions are added
+    # Clean data: Missing values, outliers, and extreme values
+    df = handle_missing_values(df)
+    df = remove_outliers_iqr(df)
+    df = cap_extreme_values(df)
 
-    st.write("Cleaned Dataset (after applying any cleaning steps):")
+    st.write("Cleaned Dataset:")
     st.dataframe(df)
 
     # Add clean data download option
@@ -33,9 +35,9 @@ if uploaded_file is not None:
     # Correlation Heatmap
     st.subheader("Correlation Heatmap")
     corr_plot = plot_correlation_heatmap(df)
-    st.pyplot(corr_plot)  # Display the heatmap in Streamlit
+    st.pyplot(corr_plot)
 
-    # Save heatmap as PNG and allow download
+    # Save heatmap as PNG
     heatmap_buf = save_plot_as_png(corr_plot)
     st.download_button(
         label="Download Correlation Heatmap as PNG",
@@ -50,12 +52,6 @@ if uploaded_file is not None:
     X = df[features]
     y = df[target]
 
-    # Assuming model training and evaluation functions (train_classification_model, etc.) are implemented and imported
-    if y.dtype == 'object' or len(y.unique()) <= 10:  # Classification
-        st.subheader("Classification Model Training")
-        # Example: metrics_df = train_classification_model(X, y)
-        # st.dataframe(metrics_df)
-    else:  # Regression
-        st.subheader("Regression Model Training")
-        # Example: regression_metrics_df = train_regression_model(X, y)
-        # st.dataframe(regression_metrics_df)
+    # Train and evaluate models
+    model_results = train_all_models(X, y)  # Train all models based on data type
+    st.dataframe(model_results)