Update app.py

app.py

@@ -544,319 +544,325 @@ import streamlit as st
 
 st.markdown('[Click to register a suggestion or comment](https://docs.google.com/forms/d/e/1FAIpQLScLyP7bBbqMfGdspjL7Ij64UZ6v2KjqjKNbm8gwEsgWsFs_Qg/viewform?usp=header)')
 
-st.subheader("Displaying the first few rows of the DataFrame")
-st.dataframe(df.head())
+df = upload_and_select_dataframe()
 
-cols = edit_strings(df.columns)
-cols = sorted(list(set(cols)))
-
-main_option = st.selectbox("Please select an option:", ["Tabulation", "Funnel Analysis", "Segmentation Analysis", "Hypothesis test", "Machine Learning", "Coding"])
-
-if main_option == "Tabulation":
-    st.header("Tabulation Analysis")
-
-    tabulation_option = st.selectbox("Please select the type of analysis:", ["Univariate", "Multivariate", "All"])
-
-    if tabulation_option == "All":
-        
-        st.sidebar.header("Settings")
-
-        main_dict = {"single": [], "multi": [], "score": []}
-        
-        st.sidebar.subheader("Main")
-        main_dict["single"] = st.sidebar.multiselect(
-            'Main: Single answer questions', 
-            cols,
-            default=[]
-        )
-        
-        main_dict["multi"] = st.sidebar.multiselect(
-            'Main: Multi answer questions',
-            cols,
-            default=[]
-        )
-
-        main_dict["score"] = st.sidebar.multiselect(
-            'Main: Score answer questions',
-            cols,
-            default=[]
-        )
-
-        follow_dict = {"single": [], "multi": [], "score": []}
-        
-        st.sidebar.subheader("Follow")
-        follow_dict["single"] = st.sidebar.multiselect(
-            'Follow: Single answer questions', 
-            cols,
-            default=[]
-        )
-        
-        follow_dict["multi"] = st.sidebar.multiselect(
-            'Follow: Multi answer questions',
-            cols,
-            default=[]
-        )
-
-        follow_dict["score"] = st.sidebar.multiselect(
-            'Follow: Score answer questions',
-            cols,
-            default=[]
-        )
-
-        all_tabulation(df, main_dict, follow_dict)
-        
-    elif tabulation_option == "Univariate":
-        uni_option = st.selectbox("Select the type of univariate analysis:", ["Multiple answer", "Single answer", "Score answer"])
-
-        if uni_option == "Single answer":
-            var = st.text_input("Please enter the name of the desired column:")
-            if var:
-                if var in df.columns:
-                    result_df = single_answer(df[var])
-                    st.subheader("Univariate Analysis Results")
-                    st.dataframe(result_df)
-
-                    fig = figo('Bar', result_df["Percentage"][:-1, ], title='Percentage Histogram', xlabel=var, ylabel='Percentage', colorscale='Plotly3')
-                    st.plotly_chart(fig, use_container_width=True)
-                else:
-                    st.error("The entered column was not found.")
-        elif uni_option == "Multiple answer":
-            var = st.text_input("Please enter the name of the desired column:")
-            if var:
-                matching_cols = [col for col in df.columns if is_matching_pattern(col, var)]
-                if matching_cols:
-                    subset_df = df[matching_cols]
-                    result_df = multi_answer(subset_df)
+try:
+    st.subheader("Displaying the first few rows of the DataFrame")
+    st.dataframe(df.head())
+    
+    cols = edit_strings(df.columns)
+    cols = sorted(list(set(cols)))
+    
+    main_option = st.selectbox("Please select an option:", ["Tabulation", "Funnel Analysis", "Segmentation Analysis", "Hypothesis test", "Machine Learning", "Coding"])
+    
+    if main_option == "Tabulation":
+        st.header("Tabulation Analysis")
+    
+        tabulation_option = st.selectbox("Please select the type of analysis:", ["Univariate", "Multivariate", "All"])
+    
+        if tabulation_option == "All":
+            
+            st.sidebar.header("Settings")
+    
+            main_dict = {"single": [], "multi": [], "score": []}
+            
+            st.sidebar.subheader("Main")
+            main_dict["single"] = st.sidebar.multiselect(
+                'Main: Single answer questions', 
+                cols,
+                default=[]
+            )
+            
+            main_dict["multi"] = st.sidebar.multiselect(
+                'Main: Multi answer questions',
+                cols,
+                default=[]
+            )
+    
+            main_dict["score"] = st.sidebar.multiselect(
+                'Main: Score answer questions',
+                cols,
+                default=[]
+            )
+    
+            follow_dict = {"single": [], "multi": [], "score": []}
+            
+            st.sidebar.subheader("Follow")
+            follow_dict["single"] = st.sidebar.multiselect(
+                'Follow: Single answer questions', 
+                cols,
+                default=[]
+            )
+            
+            follow_dict["multi"] = st.sidebar.multiselect(
+                'Follow: Multi answer questions',
+                cols,
+                default=[]
+            )
+    
+            follow_dict["score"] = st.sidebar.multiselect(
+                'Follow: Score answer questions',
+                cols,
+                default=[]
+            )
+    
+            all_tabulation(df, main_dict, follow_dict)
+            
+        elif tabulation_option == "Univariate":
+            uni_option = st.selectbox("Select the type of univariate analysis:", ["Multiple answer", "Single answer", "Score answer"])
+    
+            if uni_option == "Single answer":
+                var = st.text_input("Please enter the name of the desired column:")
+                if var:
+                    if var in df.columns:
+                        result_df = single_answer(df[var])
+                        st.subheader("Univariate Analysis Results")
+                        st.dataframe(result_df)
+    
+                        fig = figo('Bar', result_df["Percentage"][:-1, ], title='Percentage Histogram', xlabel=var, ylabel='Percentage', colorscale='Plotly3')
+                        st.plotly_chart(fig, use_container_width=True)
+                    else:
+                        st.error("The entered column was not found.")
+            elif uni_option == "Multiple answer":
+                var = st.text_input("Please enter the name of the desired column:")
+                if var:
+                    matching_cols = [col for col in df.columns if is_matching_pattern(col, var)]
+                    if matching_cols:
+                        subset_df = df[matching_cols]
+                        result_df = multi_answer(subset_df)
+                            
+                        st.subheader("Multiple Answer Analysis Results")
+                        st.dataframe(result_df)
                         
-                    st.subheader("Multiple Answer Analysis Results")
+                        fig = figo('Bar', result_df["Percentage"][:-1], title='Percentage Histogram', xlabel=var, ylabel='Percentage', colorscale='Plotly3')
+                        st.plotly_chart(fig, use_container_width=True)
+                    else:
+                        st.error("No columns matching the entered pattern were found.")
+    
+            elif uni_option == "Score answer":
+                var = st.text_input("Please enter the name of the desired column:")
+                if var:
+                    subset_df = df[var]
+                    result_df = score_answer(subset_df)
+    
+                    st.subheader("Score Answer Analysis Results")
                     st.dataframe(result_df)
                     
-                    fig = figo('Bar', result_df["Percentage"][:-1], title='Percentage Histogram', xlabel=var, ylabel='Percentage', colorscale='Plotly3')
+                    fig = figo('Bar', result_df["Percentage"][:-2], title='Percentage Histogram', xlabel=var, ylabel='Percentage', colorscale='Plotly3')
                     st.plotly_chart(fig, use_container_width=True)
                 else:
                     st.error("No columns matching the entered pattern were found.")
-
-        elif uni_option == "Score answer":
-            var = st.text_input("Please enter the name of the desired column:")
-            if var:
-                subset_df = df[var]
-                result_df = score_answer(subset_df)
-
-                st.subheader("Score Answer Analysis Results")
-                st.dataframe(result_df)
-                
-                fig = figo('Bar', result_df["Percentage"][:-2], title='Percentage Histogram', xlabel=var, ylabel='Percentage', colorscale='Plotly3')
-                st.plotly_chart(fig, use_container_width=True)
-            else:
-                st.error("No columns matching the entered pattern were found.")
-                
-    elif tabulation_option == "Multivariate":
-        st.subheader("Multivariate Analysis")
-        var1 = st.text_input("Please enter the name of the first column:")
-        var2 = st.text_input("Please enter the name of the second column:")
-
-        if var1 and var2:
-            type1 = st.selectbox("Select the type of analysis for the first column:", ["Multiple answer", "Single answer"], key='type1')
-            type2 = st.selectbox("Select the type of analysis for the second column:", ["Multiple answer", "Single answer", "Score answer"], key='type2')
-
-            if type1 == "Single answer" and type2 == "Single answer":
-                percentile_df, frequency_df = two_variable_ss(df[[var1, var2]], var1, var2)
-                st.subheader("Percentage Table")
-                st.write(z_test_data(percentile_df))
-
-                st.subheader("Frequency Table")
-                st.dataframe(frequency_df)
-
-                row, col = df.shape
-                fig = figo('Scatter', percentile_df.iloc[:-1,:], title='Percentage Scatter plot', width=(col*5)+5, height=(row*25) + 10)
-                st.plotly_chart(fig, use_container_width=True)
-
-            elif type1 == "Single answer" and type2 == "Multiple answer":
-                matching_cols = [col for col in df.columns if is_matching_pattern(col, var2)]
-                if matching_cols:
-                    percentile_df, frequency_df = two_variable_sm(df[[var1] + matching_cols], var1, matching_cols)
-                    st.subheader("Percentage Table")
-                    st.write(z_test_data(percentile_df))
-
-                    st.subheader("Frequency Table")
-                    st.dataframe(frequency_df)
-
-                    row, col = df.shape
-                    fig = figo('Scatter', percentile_df.iloc[:-1,:], title='Percentage Scatter plot', width=(col*5)+5, height=(row*25) + 10)
-                    st.plotly_chart(fig, use_container_width=True)
                     
-                else:
-                    st.error("No columns matching the entered pattern were found.")
-
-            elif type1 == "Multiple answer" and type2 == "Multiple answer":
-                matching_cols1 = [col for col in df.columns if is_matching_pattern(col, var1)]
-                matching_cols2 = [col for col in df.columns if is_matching_pattern(col, var2)]
-                if matching_cols1 and matching_cols2:
-                    percentile_df, frequency_df = two_variable_mm(df[matching_cols1 + matching_cols2], matching_cols1, matching_cols2)
+        elif tabulation_option == "Multivariate":
+            st.subheader("Multivariate Analysis")
+            var1 = st.text_input("Please enter the name of the first column:")
+            var2 = st.text_input("Please enter the name of the second column:")
+    
+            if var1 and var2:
+                type1 = st.selectbox("Select the type of analysis for the first column:", ["Multiple answer", "Single answer"], key='type1')
+                type2 = st.selectbox("Select the type of analysis for the second column:", ["Multiple answer", "Single answer", "Score answer"], key='type2')
+    
+                if type1 == "Single answer" and type2 == "Single answer":
+                    percentile_df, frequency_df = two_variable_ss(df[[var1, var2]], var1, var2)
                     st.subheader("Percentage Table")
                     st.write(z_test_data(percentile_df))
-
+    
                     st.subheader("Frequency Table")
                     st.dataframe(frequency_df)
-
+    
                     row, col = df.shape
                     fig = figo('Scatter', percentile_df.iloc[:-1,:], title='Percentage Scatter plot', width=(col*5)+5, height=(row*25) + 10)
                     st.plotly_chart(fig, use_container_width=True)
-
-            elif type1 == "Single answer" and type2 == "Score answer":
-
-                mean_df = two_variable_ssc(df[[var1, var2]], var1, var2)
-                st.subheader("Mean Table")
-                st.write(t_test_data(mean_df))
-
-                row, col = df.shape
-                fig = figo('Bar', mean_df["Mean"][:-1], title='Mean Histogram', xlabel=var1, ylabel='Mean', colorscale='Plotly3')
-                st.plotly_chart(fig, use_container_width=True)                            
-
-
-            elif type1 == "Multiple answer" and type2 == "Score answer":
-                matching_cols1 = [col for col in df.columns if is_matching_pattern(col, var1)]
-                if matching_cols1:
-                    mean_df = two_variable_msc(df[matching_cols1 + [var2]], matching_cols1, var2)
+    
+                elif type1 == "Single answer" and type2 == "Multiple answer":
+                    matching_cols = [col for col in df.columns if is_matching_pattern(col, var2)]
+                    if matching_cols:
+                        percentile_df, frequency_df = two_variable_sm(df[[var1] + matching_cols], var1, matching_cols)
+                        st.subheader("Percentage Table")
+                        st.write(z_test_data(percentile_df))
+    
+                        st.subheader("Frequency Table")
+                        st.dataframe(frequency_df)
+    
+                        row, col = df.shape
+                        fig = figo('Scatter', percentile_df.iloc[:-1,:], title='Percentage Scatter plot', width=(col*5)+5, height=(row*25) + 10)
+                        st.plotly_chart(fig, use_container_width=True)
+                        
+                    else:
+                        st.error("No columns matching the entered pattern were found.")
+    
+                elif type1 == "Multiple answer" and type2 == "Multiple answer":
+                    matching_cols1 = [col for col in df.columns if is_matching_pattern(col, var1)]
+                    matching_cols2 = [col for col in df.columns if is_matching_pattern(col, var2)]
+                    if matching_cols1 and matching_cols2:
+                        percentile_df, frequency_df = two_variable_mm(df[matching_cols1 + matching_cols2], matching_cols1, matching_cols2)
+                        st.subheader("Percentage Table")
+                        st.write(z_test_data(percentile_df))
+    
+                        st.subheader("Frequency Table")
+                        st.dataframe(frequency_df)
+    
+                        row, col = df.shape
+                        fig = figo('Scatter', percentile_df.iloc[:-1,:], title='Percentage Scatter plot', width=(col*5)+5, height=(row*25) + 10)
+                        st.plotly_chart(fig, use_container_width=True)
+    
+                elif type1 == "Single answer" and type2 == "Score answer":
+    
+                    mean_df = two_variable_ssc(df[[var1, var2]], var1, var2)
                     st.subheader("Mean Table")
                     st.write(t_test_data(mean_df))
-
+    
                     row, col = df.shape
                     fig = figo('Bar', mean_df["Mean"][:-1], title='Mean Histogram', xlabel=var1, ylabel='Mean', colorscale='Plotly3')
-                    st.plotly_chart(fig, use_container_width=True)                    
-            else:
-                st.info("This section of the program is under development.")
-
-elif main_option == "Funnel Analysis":
-    st.header("Funnel")
-    
-    st.sidebar.header("Funnel Settings")
-    single_list = st.sidebar.multiselect(
-        'Single answer questions', 
-        cols,
-        default=[]
-    )
-    
-    multi_list = st.sidebar.multiselect(
-        'Multi answer questions',
-        cols,
-        default=[]
-    )
-    selected_dict = {}
-    
-    for option in single_list:
-        selected_dict[option] = "Single"
-    for option in multi_list:
-        selected_dict[option] = "Multi"
-    
-    funnel_frequency, funnel_percentage = funnel(df, selected_dict)
-    st.subheader("Percentage Table")
-    st.dataframe(funnel_percentage)
-    
-    st.subheader("Frequency Table")
-    st.dataframe(funnel_frequency)
-    
-    st.sidebar.header("Chart Settings")
-    bar_columns = st.sidebar.multiselect('Which columns should be displayed as bar charts?', sorted(funnel_percentage.columns))
-    line_columns = st.sidebar.multiselect('Which columns should be displayed as line charts?', sorted(funnel_percentage.columns))
-
-    funnel_percentage_cleaned = funnel_percentage.dropna(axis=0, how='all')
-    
-    fig = go.Figure()
-    
-    # Define modern and diverse color palette
-    modern_colors = [
-        "#FF6F61", "#6B5B95", "#88B04B", "#F7CAC9", "#92A8D1", 
-        "#955251", "#B565A7", "#009B77", "#DD4124", "#45B8AC"
-    ]
-    
-    # Add Bar traces with transparency and custom colors
-    for idx, col in enumerate(bar_columns):
-        funnel_percentage_col = funnel_percentage_cleaned[col]
-        fig.add_trace(
-            go.Bar(
-                x=funnel_percentage_cleaned.index, 
-                y=funnel_percentage_col, 
-                name=col,
-                marker_color=modern_colors[idx % len(modern_colors)],  # Cycle through colors
-                opacity=0.8  # Set transparency
-            )
+                    st.plotly_chart(fig, use_container_width=True)                            
+    
+    
+                elif type1 == "Multiple answer" and type2 == "Score answer":
+                    matching_cols1 = [col for col in df.columns if is_matching_pattern(col, var1)]
+                    if matching_cols1:
+                        mean_df = two_variable_msc(df[matching_cols1 + [var2]], matching_cols1, var2)
+                        st.subheader("Mean Table")
+                        st.write(t_test_data(mean_df))
+    
+                        row, col = df.shape
+                        fig = figo('Bar', mean_df["Mean"][:-1], title='Mean Histogram', xlabel=var1, ylabel='Mean', colorscale='Plotly3')
+                        st.plotly_chart(fig, use_container_width=True)                    
+                else:
+                    st.info("This section of the program is under development.")
+    
+    elif main_option == "Funnel Analysis":
+        st.header("Funnel")
+        
+        st.sidebar.header("Funnel Settings")
+        single_list = st.sidebar.multiselect(
+            'Single answer questions', 
+            cols,
+            default=[]
+        )
+        
+        multi_list = st.sidebar.multiselect(
+            'Multi answer questions',
+            cols,
+            default=[]
         )
+        selected_dict = {}
+        
+        for option in single_list:
+            selected_dict[option] = "Single"
+        for option in multi_list:
+            selected_dict[option] = "Multi"
+        
+        funnel_frequency, funnel_percentage = funnel(df, selected_dict)
+        st.subheader("Percentage Table")
+        st.dataframe(funnel_percentage)
+        
+        st.subheader("Frequency Table")
+        st.dataframe(funnel_frequency)
+        
+        st.sidebar.header("Chart Settings")
+        bar_columns = st.sidebar.multiselect('Which columns should be displayed as bar charts?', sorted(funnel_percentage.columns))
+        line_columns = st.sidebar.multiselect('Which columns should be displayed as line charts?', sorted(funnel_percentage.columns))
     
-    # Add Line traces with transparency and custom colors
-    for idx, col in enumerate(line_columns):
-        funnel_percentage_col = funnel_percentage_cleaned[col]
-        fig.add_trace(
-            go.Scatter(
-                x=funnel_percentage_cleaned.index, 
-                y=funnel_percentage_col, 
-                mode='lines', 
-                name=col,
-                line=dict(color=modern_colors[(idx + len(bar_columns)) % len(modern_colors)]),  # Cycle through colors
-                opacity=0.8  # Set transparency
+        funnel_percentage_cleaned = funnel_percentage.dropna(axis=0, how='all')
+        
+        fig = go.Figure()
+        
+        # Define modern and diverse color palette
+        modern_colors = [
+            "#FF6F61", "#6B5B95", "#88B04B", "#F7CAC9", "#92A8D1", 
+            "#955251", "#B565A7", "#009B77", "#DD4124", "#45B8AC"
+        ]
+        
+        # Add Bar traces with transparency and custom colors
+        for idx, col in enumerate(bar_columns):
+            funnel_percentage_col = funnel_percentage_cleaned[col]
+            fig.add_trace(
+                go.Bar(
+                    x=funnel_percentage_cleaned.index, 
+                    y=funnel_percentage_col, 
+                    name=col,
+                    marker_color=modern_colors[idx % len(modern_colors)],  # Cycle through colors
+                    opacity=0.8  # Set transparency
+                )
+            )
+        
+        # Add Line traces with transparency and custom colors
+        for idx, col in enumerate(line_columns):
+            funnel_percentage_col = funnel_percentage_cleaned[col]
+            fig.add_trace(
+                go.Scatter(
+                    x=funnel_percentage_cleaned.index, 
+                    y=funnel_percentage_col, 
+                    mode='lines', 
+                    name=col,
+                    line=dict(color=modern_colors[(idx + len(bar_columns)) % len(modern_colors)]),  # Cycle through colors
+                    opacity=0.8  # Set transparency
+                )
             )
+                
+        fig.update_layout(
+            title="Combined Bar and Line Chart",
+            xaxis_title="Brands",
+            yaxis_title="Percentage",
+            template="plotly_dark",
+            barmode="group",
+            xaxis=dict(tickmode='linear')
         )
-            
-    fig.update_layout(
-        title="Combined Bar and Line Chart",
-        xaxis_title="Brands",
-        yaxis_title="Percentage",
-        template="plotly_dark",
-        barmode="group",
-        xaxis=dict(tickmode='linear')
-    )
+        
+        st.plotly_chart(fig)
     
-    st.plotly_chart(fig)
-
-elif main_option == "Segmentation Analysis":
-    st.header("Segmentation Analysis")
-    
-    st.sidebar.header("Selection of questions")
-    single_list = st.sidebar.multiselect(
-        'Single answer questions', 
-        cols,
-        default=[]
-    )
-
-    multi_list = st.sidebar.multiselect(
-        'Multi answer questions', 
-        cols,
-        default=[]
-    )
-
-    score_list = st.sidebar.multiselect(
-        'Score answer questions', 
-        cols,
-        default=[]
-    )
-
-    matching_cols1 = []
-    for i in multi_list:
-        matching_cols1 += [col for col in df.columns if is_matching_pattern(col, i)]
-
-    df_clean = process_dataframe(df[single_list + matching_cols1])
-    st.subheader("Selected Table")
-        st.dataframe(df_clean)
-
-        linkage_method = st.sidebar.selectbox("Select the Linkage Method of Segmentation Analysis:", ['average', 'single', 'complete', 'weighted', 'centroid', 'median', 'ward'])
+    elif main_option == "Segmentation Analysis":
+        st.header("Segmentation Analysis")
         
-        df_cluster = hierarchical_clustering_with_plotly(df_clean, linkage_method)
-
-        st.subheader("Cluster Table")
-        st.dataframe(df_clean)
-
-elif main_option == "Hypothesis test":
-    st.header("Hypothesis Testing")
-    hypothesis_option = st.selectbox("Please select the type of hypothesis test:", ["Z test", "T test", "Chi-Square test", "ANOVA test"])
-
-    if hypothesis_option != "Z test":
+        st.sidebar.header("Selection of questions")
+            single_list = st.sidebar.multiselect(
+                'Single answer questions', 
+                cols,
+                default=[]
+            )
+        
+            multi_list = st.sidebar.multiselect(
+                'Multi answer questions', 
+                cols,
+                default=[]
+            )
+        
+            score_list = st.sidebar.multiselect(
+                'Score answer questions', 
+                cols,
+                default=[]
+            )
+        
+            matching_cols1 = []
+            for i in multi_list:
+                matching_cols1 += [col for col in df.columns if is_matching_pattern(col, i)]
+        
+            df_clean = process_dataframe(df[single_list + matching_cols1])
+            st.subheader("Selected Table")
+            st.dataframe(df_clean)
+    
+            linkage_method = st.sidebar.selectbox("Select the Linkage Method of Segmentation Analysis:", ['average', 'single', 'complete', 'weighted', 'centroid', 'median', 'ward'])
+            
+            df_cluster = hierarchical_clustering_with_plotly(df_clean, linkage_method)
+    
+            st.subheader("Cluster Table")
+            st.dataframe(df_clean)
+    
+    elif main_option == "Hypothesis test":
+        st.header("Hypothesis Testing")
+        hypothesis_option = st.selectbox("Please select the type of hypothesis test:", ["Z test", "T test", "Chi-Square test", "ANOVA test"])
+    
+        if hypothesis_option != "Z test":
+            st.info("This section of the program is under development.")
+        else:
+            uploaded_file = st.file_uploader("Please upload your Excel file for Z-Test", type=["xlsx", "xls"])
+            if uploaded_file:
+                result = analyze_z_test(uploaded_file)
+                if result:
+                    st.success("Z-Test analysis completed successfully.")
+    
+    elif main_option in ["Machine Learning", "Coding"]:
         st.info("This section of the program is under development.")
-    else:
-        uploaded_file = st.file_uploader("Please upload your Excel file for Z-Test", type=["xlsx", "xls"])
-        if uploaded_file:
-            result = analyze_z_test(uploaded_file)
-            if result:
-                st.success("Z-Test analysis completed successfully.")
-
-elif main_option in ["Machine Learning", "Coding"]:
-    st.info("This section of the program is under development.")
+
+except Exception as e:
+        st.error(f"❌ Error: {e}")