Update app.py

app.py

@@ -82,6 +82,16 @@ def single_answer(df):
     friquency_dataframe.loc[len(friquency_dataframe)] = ['Sample_size', len(df.dropna()), 1]
     return friquency_dataframe
 
+def score_answer(df):
+    counter = df.value_counts().sort_index()
+
+    friquency_dataframe = pd.DataFrame({
+        'Value': list(counter.index)+["Meen", "Variance"],
+        'Frequency': list(counter.values)+[df.mean(), df.var()], 
+        'Percentage': list((counter.values / counter.sum()) * 100)+["", ""]})
+    
+    return friquency_dataframe
+
 def two_variable_ss(df, var1, var2):
 
     counter = df.groupby(var1)[var2].value_counts()
@@ -162,6 +172,24 @@ def z_testes(n1, n2, p1, p2):
     except ZeroDivisionError:
         return np.nan
 
+def z_test_data(df):
+
+    rows, cols = df.shape
+
+    for i in range(rows-2):
+        for j in range(cols-2):
+            n1 = df.iloc[-1, -1]  # x_IJ
+            n2 = df.iloc[-1, j]  # x_Ij
+            p1 = df.iloc[i, -1]  # x_1J
+            p2 = df.iloc[i, j]  # x_ij
+            p_value = z_testes(n1, n2, p1, p2)
+            if p_value < 0.05:
+                df.iloc[i, j] = f'<span style="background-color:lightgreen">{df.iloc[i, j]}</span>'
+            else:
+                df.iloc[i, j] = f'<span style="background-color:lightgray">{df.iloc[i, j]}</span>'
+
+    return df
+
 def Z_test_dataframes(sheets_data):
     """Processes each sheet's DataFrame and computes new DataFrames with Z-test results."""
     result_dataframes = {}
@@ -255,7 +283,7 @@ if main_option == "Tabulation":
             if tabulation_option == "All":
                 st.info("This section of the program is under development.")
             elif tabulation_option == "Univariate":
-                uni_option = st.selectbox("Select the type of univariate analysis:", ["Multiple answer", "Single answer"])
+                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:")
@@ -284,6 +312,21 @@ if main_option == "Tabulation":
                             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')
+                        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:")
@@ -296,7 +339,7 @@ if main_option == "Tabulation":
                     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.dataframe(percentile_df)
+                        st.dataframe(z_test_data(percentile_df))
 
                         st.subheader("Frequency Table")
                         st.dataframe(frequency_df)
@@ -309,7 +352,7 @@ if main_option == "Tabulation":
                         if matching_cols:
                             percentile_df, frequency_df = two_variable_sm(df[[var1] + matching_cols], var1, matching_cols)
                             st.subheader("Percentage Table")
-                            st.dataframe(percentile_df)
+                            st.dataframe(z_test_data(percentile_df))
 
                             st.subheader("Frequency Table")
                             st.dataframe(frequency_df)
@@ -326,7 +369,7 @@ if main_option == "Tabulation":
                         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.dataframe(percentile_df)
+                            st.dataframe(z_test_data(percentile_df))
 
                             st.subheader("Frequency Table")
                             st.dataframe(frequency_df)