Update app.py

app.py

@@ -6,6 +6,7 @@ import plotly.graph_objects as go
 from scipy.stats import norm, t
 from scipy.cluster.hierarchy import linkage, dendrogram, fcluster
 import plotly.figure_factory as ff
+from sklearn.cluster import KMeans
 
 def sorting(df):
     df.index = list(map(float, df.index))
@@ -499,6 +500,18 @@ def hierarchical_clustering_with_plotly(df, linkage_method):
 
     return df
 
+from sklearn.cluster import KMeans
+
+def kmeans_clustering(df, k):
+
+  numeric_df = df.select_dtypes(include=['number'])
+
+  if numeric_df.empty:
+    raise ValueError("DataFrame does not contain any numeric columns for clustering.")
+    
+  kmeans = KMeans(n_clusters=k, random_state=0) # You can modify random_state
+  df['cluster'] = kmeans.fit_predict(numeric_df)
+  return df
 
 def upload_and_select_dataframe():
   st.sidebar.title("File Upload")
@@ -766,7 +779,6 @@ try:
         
         funnel_percentage_cleaned = funnel_percentage.dropna(axis=0, how='all')
         
-        # اضافه کردن انتخاب ترتیب مرتب‌سازی
         columns = st.sidebar.multiselect('Sort by which questions?', sorted(funnel_percentage_cleaned.columns))
         sort_order = st.sidebar.radio('Sort Order', ['Ascending', 'Descending'])
         
@@ -826,6 +838,46 @@ try:
         
         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, 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:", ["Hierarchical Clustering"])
+        
+        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")