Update app.py

app.py

@@ -105,8 +105,7 @@ if uploaded_file is not None:
     # Highlight highly correlated pairs
     st.subheader("Highly Correlated Features")
     high_corr = corr.abs().unstack().sort_values(ascending=False).drop_duplicates()
-    high_corr = high_corr[high_corr >= 0.8]
-    high_corr_df = high_corr[high_corr.index.get_level_values(0) != high_corr.index.get_level_values(1)]
+    high_corr = high_corr[high_corr.index.get_level_values(0) != high_corr.index.get_level_values(1)]
     st.write(high_corr_df)
 
     target = st.selectbox("Select Target Variable", df.columns)
@@ -145,15 +144,18 @@ if uploaded_file is not None:
         st.dataframe(metrics_df)
 
         # Save metrics as PNG
-        fig, ax = plt.subplots()
-        sns.barplot(data=metrics_df, x="Model", y="Accuracy", ax=ax)
-        ax.set_title("Classification Model Performance")
-        buf = BytesIO()
-        fig.savefig(buf, format="png")
-        buf.seek(0)
+        def generate_classification_report_image():
+            fig, ax = plt.subplots()
+            sns.barplot(data=metrics_df, x="Model", y="Accuracy", ax=ax)
+            ax.set_title("Classification Model Performance")
+            buf = BytesIO()
+            fig.savefig(buf, format="png")
+            buf.seek(0)
+            return buf
+
         st.download_button(
             label="Download Classification Report as PNG",
-            data=buf,
+            data=generate_classification_report_image(),
             file_name="classification_report.png",
             mime="image/png"
         )
@@ -187,58 +189,18 @@ if uploaded_file is not None:
         st.dataframe(regression_metrics_df)
 
         # Save metrics as PNG
-        fig, ax = plt.subplots()
-        sns.barplot(data=regression_metrics_df, x="Model", y="R² Score", ax=ax)
-        ax.set_title("Regression Model Performance")
-        buf = BytesIO()
-        fig.savefig(buf, format="png")
-        buf.seek(0)
-        st.download_button(
-            label="Download Regression Report as PNG",
-            data=buf,
-            file_name="regression_report.png",
-            mime="image/png"
-        ) alse add the button to generate the report as image
-
-
-
-
+        def generate_regression_report_image():
+            fig, ax = plt.subplots()
+            sns.barplot(data=regression_metrics_df, x="Model", y="R² Score", ax=ax)
+            ax.set_title("Regression Model Performance")
+            buf = BytesIO()
+            fig.savefig(buf, format="png")
+            buf.seek(0)
+            return buf
 
-
-# After generating the metrics (classification or regression)
-# Add a button to generate the performance report as an image
-generate_report_button = st.button("Generate Performance Report as Image")
-
-if generate_report_button:
-    if y.dtype == 'object' or len(y.unique()) <= 10:  # Categorical target (classification)
-        fig, ax = plt.subplots(figsize=(10, 6))
-        sns.barplot(data=metrics_df, x="Model", y="Accuracy", ax=ax)
-        ax.set_title("Classification Model Performance")
-        
-        # Save the classification report as PNG
-        buf = BytesIO()
-        fig.savefig(buf, format="png")
-        buf.seek(0)
-        
-        st.download_button(
-            label="Download Classification Report as PNG",
-            data=buf,
-            file_name="classification_report.png",
-            mime="image/png"
-        )
-    else:  # Continuous target (regression)
-        fig, ax = plt.subplots(figsize=(10, 6))
-        sns.barplot(data=regression_metrics_df, x="Model", y="R² Score", ax=ax)
-        ax.set_title("Regression Model Performance")
-        
-        # Save the regression report as PNG
-        buf = BytesIO()
-        fig.savefig(buf, format="png")
-        buf.seek(0)
-        
         st.download_button(
             label="Download Regression Report as PNG",
-            data=buf,
+            data=generate_regression_report_image(),
             file_name="regression_report.png",
             mime="image/png"
         )