Update app.py

app.py

@@ -486,6 +486,11 @@ def all_tabulation(df, main_dict, follow_dict):
         st.subheader(j)
         st.dataframe(join_dataframes(name_list, dataframe_list))
 
+def process_dataframe(df):
+  df = df.fillna(0)
+  for col in df.columns:
+    df[col] = pd.Categorical(df[col])
+  return df
 
 empty_col1, main_col, empty_col2 = st.columns([1.6, 2.8, 1.6])
 
@@ -512,7 +517,7 @@ if uploaded_file:
         st.subheader("Displaying the first few rows of the DataFrame")
         st.dataframe(df.head())
 
-        main_option = st.selectbox("Please select an option:", ["Tabulation", "Funnel", "Hypothesis test", "Machine Learning", "Coding"])
+        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")
@@ -692,7 +697,7 @@ if uploaded_file:
                     else:
                         st.info("This section of the program is under development.")
 
-        elif main_option == "Funnel":
+        elif main_option == "Funnel Analysis":
             st.header("Funnel")
         
             cols = edit_strings(df.columns)
@@ -776,6 +781,38 @@ if uploaded_file:
             
             st.plotly_chart(fig)
 
+        elif main_option == "Segmentation Analysis":
+            st.header("Segmentation Analysis")
+
+            cols = edit_strings(df.columns)
+            cols = sorted(list(set(cols)))
+            
+            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, var1)]
+
+            df_clean = process_dataframe(df[single_list + matching_cols1])
+            st.dataframe(df_clean)
+
 
         elif main_option == "Hypothesis test":
             st.header("Hypothesis Testing")