Update app.py

app.py

@@ -376,16 +376,16 @@ elif app_mode == "Advanced EDA":
         with st.expander("🔎 Data Filtering", expanded=False):
             # Use direct session state assignment for reactivity
             st.session_state.plot_config['filter_col'] = st.selectbox(
-                "Filter Column", 
+                "Filter Column",
                 [None] + list(df.columns),
                 help="Choose a column to filter the data."
             )
-            
+
             if st.session_state.plot_config['filter_col']:
                 unique_values = df[st.session_state.plot_config['filter_col']].unique()
                 st.session_state.plot_config['filter_options'] = st.multiselect(
-                    "Filter Values", 
-                    unique_values, 
+                    "Filter Values",
+                    unique_values,
                     default=unique_values,
                     help=f"Select values from '{st.session_state.plot_config['filter_col']}'"
                 )
@@ -395,13 +395,13 @@ elif app_mode == "Advanced EDA":
 
         # Visualization Configuration
         st.sidebar.header("📊 Plot Configuration")
-        
+
         # Plot type selector
         st.session_state.plot_config['plot_type'] = st.sidebar.selectbox(
-            "Choose Visualization", 
+            "Choose Visualization",
             [
-                "Histogram", "Scatter Plot", "Box Plot", 
-                "Correlation Heatmap", "3D Scatter", 
+                "Histogram", "Scatter Plot", "Box Plot",
+                "Correlation Heatmap", "3D Scatter",
                 "Violin Plot", "Time Series", "Scatter Matrix"
             ],
             index=0  # Reset to first option when plot type changes
@@ -410,17 +410,17 @@ elif app_mode == "Advanced EDA":
         # Dynamic controls based on plot type
         if st.session_state.plot_config['plot_type'] != "Correlation Heatmap":
             st.session_state.plot_config['x_col'] = st.sidebar.selectbox(
-                "X Axis", 
+                "X Axis",
                 df.columns,
-                index=df.columns.get_loc(st.session_state.plot_config['x_col']) 
+                index=df.columns.get_loc(st.session_state.plot_config['x_col'])
                 if st.session_state.plot_config['x_col'] in df.columns else 0
             )
 
-        if st.session_state.plot_config['plot_type'] in ["Scatter Plot", "Box Plot", 
-                                                        "Violin Plot", "Time Series", 
-                                                        "3D Scatter", "Histogram"]:
+        if st.session_state.plot_config['plot_type'] in ["Scatter Plot", "Box Plot",
+                                                            "Violin Plot", "Time Series",
+                                                            "3D Scatter", "Histogram"]:
             st.session_state.plot_config['y_col'] = st.sidebar.selectbox(
-                "Y Axis", 
+                "Y Axis",
                 df.columns,
                 index=df.columns.get_loc(st.session_state.plot_config['y_col'])
                 if st.session_state.plot_config['y_col'] in df.columns else 0
@@ -428,52 +428,52 @@ elif app_mode == "Advanced EDA":
 
         if st.session_state.plot_config['plot_type'] == "3D Scatter":
             st.session_state.plot_config['z_col'] = st.sidebar.selectbox(
-                "Z Axis", 
+                "Z Axis",
                 df.columns,
                 index=df.columns.get_loc(st.session_state.plot_config['z_col'])
                 if st.session_state.plot_config['z_col'] in df.columns else 0
             )
             st.session_state.plot_config['color_col'] = st.sidebar.selectbox(
-                "Color by", 
+                "Color by",
                 [None] + list(df.columns)
             )
 
         # Color configuration
         if st.session_state.plot_config['plot_type'] == "Correlation Heatmap":
             st.session_state.plot_config['color_continuous_scale'] = st.sidebar.selectbox(
-                "Color Scale", 
+                "Color Scale",
                 ['Viridis', 'Plasma', 'Magma', 'Cividis', 'RdBu']
             )
         else:
             st.session_state.plot_config['color_palette'] = st.sidebar.selectbox(
-                "Color Palette", 
+                "Color Palette",
                 ['#00f7ff', '#ff00ff', '#f70000', '#0000f7']
             )
 
         # Additional configurations
         if st.session_state.plot_config['plot_type'] == "Scatter Plot":
             st.session_state.plot_config['size_col'] = st.sidebar.selectbox(
-                "Size by", 
+                "Size by",
                 [None] + list(df.columns)
             )
             st.session_state.plot_config['hover_data_cols'] = st.sidebar.multiselect(
-                "Hover Data", 
+                "Hover Data",
                 df.columns
             )
 
         if st.session_state.plot_config['plot_type'] == "Time Series":
             st.session_state.plot_config['time_col'] = st.sidebar.selectbox(
-                "Time Column", 
+                "Time Column",
                 df.columns
             )
             st.session_state.plot_config['value_col'] = st.sidebar.selectbox(
-                "Value Column", 
+                "Value Column",
                 df.columns
             )
 
         if st.session_state.plot_config['plot_type'] == "Scatter Matrix":
             st.session_state.plot_config['scatter_matrix_cols'] = st.multiselect(
-                "Columns for Scatter Matrix", 
+                "Columns for Scatter Matrix",
                 df.select_dtypes(include=np.number).columns,
                 default=st.session_state.plot_config['scatter_matrix_cols']
             )
@@ -482,29 +482,29 @@ elif app_mode == "Advanced EDA":
         try:
             fig = None
             config = st.session_state.plot_config
-            
+
             if config['plot_type'] == "Histogram":
                 fig = px.histogram(
-                    df, x=config['x_col'], y=config['y_col'], 
+                    df, x=config['x_col'], y=config['y_col'],
                     nbins=30, template="plotly_dark",
                     color_discrete_sequence=[config['color_palette']]
                 )
-            
+
             elif config['plot_type'] == "Scatter Plot":
                 fig = px.scatter(
                     df, x=config['x_col'], y=config['y_col'],
                     color_discrete_sequence=[config['color_palette']],
-                    size=config['size_col'], 
+                    size=config['size_col'],
                     hover_data=config['hover_data_cols']
                 )
-            
+
             elif config['plot_type'] == "3D Scatter":
                 fig = px.scatter_3d(
                     df, x=config['x_col'], y=config['y_col'], z=config['z_col'],
                     color=config['color_col'],
                     color_discrete_sequence=[config['color_palette']]
                 )
-            
+
             elif config['plot_type'] == "Correlation Heatmap":
                 numeric_df = df.select_dtypes(include=np.number)
                 if not numeric_df.empty:
@@ -515,27 +515,27 @@ elif app_mode == "Advanced EDA":
                     )
                 else:
                     st.warning("No numerical columns found for correlation heatmap.")
-            
+
             elif config['plot_type'] == "Box Plot":
                 fig = px.box(
                     df, x=config['x_col'], y=config['y_col'],
                     color_discrete_sequence=[config['color_palette']]
                 )
-            
+
             elif config['plot_type'] == "Violin Plot":
                 fig = px.violin(
                     df, x=config['x_col'], y=config['y_col'],
                     box=True, points="all",
                     color_discrete_sequence=[config['color_palette']]
                 )
-            
+
             elif config['plot_type'] == "Time Series":
                 df = df.sort_values(by=config['time_col'])
                 fig = px.line(
                     df, x=config['time_col'], y=config['value_col'],
                     color_discrete_sequence=[config['color_palette']]
                 )
-            
+
             elif config['plot_type'] == "Scatter Matrix":
                 fig = px.scatter_matrix(
                     df, dimensions=config['scatter_matrix_cols'],
@@ -546,25 +546,29 @@ elif app_mode == "Advanced EDA":
                 st.plotly_chart(fig, use_container_width=True)
         except Exception as e:
             st.error(f"An error occurred while generating the plot: {e}")
+
         with st.expander("🧪 Hypothesis Testing"):
-        test_type = st.selectbox("Select Test Type", ["T-test", "Chi-Squared Test"])
-
-    if test_type == "T-test":
-        col1 = st.selectbox("Column 1 (Numeric)", df.select_dtypes(include=np.number).columns)
-        col2 = st.selectbox("Column 2 (Categorical)", df.select_dtypes(include='object').columns)
-        if st.button("Run T-test"):
-            # Example: Split data by category and perform t-test
-            groups = df.groupby(col2)[col1].apply(list)
-            if len(groups) == 2:
-                t_stat, p_value = stats.ttest_ind(groups.iloc[0], groups.iloc[1])
-                st.write(f"T-statistic: {t_stat:.4f}")
-                st.write(f"P-value: {p_value:.4f}")
-                if p_value < 0.05:
-                    st.write("Reject the null hypothesis.")
-                else:
-                    st.write("Fail to reject the null hypothesis.")
-            else:
-                st.write("Select a categorical column with exactly two categories.")
+            test_type = st.selectbox("Select Test Type", ["T-test", "Chi-Squared Test"])
+
+            if test_type == "T-test":
+                col1 = st.selectbox("Column 1 (Numeric)", df.select_dtypes(include=np.number).columns)
+                col2 = st.selectbox("Column 2 (Categorical)", df.select_dtypes(include='object').columns)
+                if st.button("Run T-test"):
+                    # Example: Split data by category and perform t-test
+                    try:
+                        groups = df.groupby(col2)[col1].apply(list)
+                        if len(groups) == 2:
+                            t_stat, p_value = stats.ttest_ind(groups.iloc[0], groups.iloc[1])
+                            st.write(f"T-statistic: {t_stat:.4f}")
+                            st.write(f"P-value: {p_value:.4f}")
+                            if p_value < 0.05:
+                                st.write("Reject the null hypothesis.")
+                            else:
+                                st.write("Fail to reject the null hypothesis.")
+                        else:
+                            st.write("Select a categorical column with exactly two categories.")
+                    except Exception as e:
+                        st.error(f"An error occurred during the T-test: {e}")
 
 elif app_mode == "Model Training":
     st.title("🚂 Model Training")