Try to make a spider radar chart

fields/feature_translations.py

@@ -0,0 +1,17 @@
+# 14 fields
+feature_translations = [
+    "Eco Mat.\n在購買前了解產品的環保材料",
+    "Eco Pack.\n在購買前了解產品的環保包裝",
+    "Local Eco Biz.\n了解當地環保企業",
+    "CSR Review.\n投資前了解企業的CSR",
+    "Eco Friends\n用社交網絡認識環保朋友",
+    "Prod. Origin\n了解產品來源",
+    "Carbon Track.\n每月回顧個人碳足跡",
+    "Eco Services\n尋找環保服務",
+    "Eco News\n個性化環保新聞",
+    "Pre-buy CSR\n購買前了解企業的CSR",
+    "Eco Initiatives\n支持當地環保計劃",
+    "Eco Practices\n了解企業的環保實踐",
+    "No Extra Info\n不需要額外的環境資訊",
+    "CSR Compare\n投資前比較企業的CSR"
+]

fields/prod_feat_flat_fields.py

@@ -1,3 +1,4 @@
+# 14 fields
 prod_feat_flat_fields = [
     '想像一下AI陪伴能幫你/妳回答超多問題了。你/妳比較想知道的環保資訊是哪些? (買東西先查看產品的運輸距離（是不是當地食品）)',
     '想像一下AI陪伴能幫你/妳回答超多問題了。你/妳比較想知道的環保資訊是哪些? (買東西先查看公司生產過程多環保)',

page_shopping.py

@@ -1,12 +1,17 @@
 import streamlit as st
+from kmodes.kmodes import KModes
+from matplotlib.font_manager import FontProperties
+import matplotlib.pyplot as plt
 import pandas as pd
+from fields.prod_feat_flat_fields import prod_feat_flat_fields
+from fields.feature_translations import feature_translations
 
-
-@st.cache_data
+#@st.cache_data
 def show(df):
     st.write("Clustering Students based on Product Feature choices")
     show_boycott_count(df)
-
+    clusters = perform_kmodes_clustering(df, prod_feat_flat_fields)
+    show_radar_chart(clusters, feature_translations=feature_translations, font_path='mingliu.ttf')
 
 def show_boycott_count(df):
     # Count the number of people who have invested and who have not
@@ -18,3 +23,83 @@ def show_boycott_count(df):
 
     # Display the DataFrame as a table in Streamlit
     st.table(investment_table)
+
+
+def perform_kmodes_clustering(df, feature_columns, n_clusters=3):
+    # Extract the relevant fields for clustering
+    cluster_data = df[feature_columns]
+
+    # Convert boolean features to integer type
+    cluster_data_encoded = cluster_data.astype(int)
+
+    # Define the K-modes model
+    km = KModes(n_clusters=n_clusters, init='Huang', n_init=5, verbose=1)
+
+    # Fit the cluster model
+    clusters = km.fit_predict(cluster_data_encoded)
+
+    # Add the cluster labels to the original dataframe
+    df['Cluster'] = clusters
+
+    # Create a dictionary to store dataframes for each cluster
+    cluster_dict = {}
+    for cluster in df['Cluster'].unique():
+        cluster_df = df[df['Cluster'] == cluster]
+        cluster_dict[cluster] = cluster_df
+
+    return cluster_dict
+
+
+def show_radar_chart(clusters, feature_translations, font_path):
+
+    df_dict={
+        'Persona 1 (Cluster 0)': clusters[0],
+        'Persona 2 (Cluster 1)': clusters[1],
+        'Persona 3 (Cluster 2)': clusters[2]
+    }
+
+    feature_translations_dict = dict(zip(prod_feat_flat_fields, feature_translations))
+    persona_averages = [df[list(feature_translations_dict.keys())].mean().tolist() for df in df_dict.values()]
+      
+    # Append the first value at the end of each list for the radar chart
+    for averages in persona_averages:
+        averages += averages[:1]
+    
+    # Prepare the English labels for plotting
+    english_feature_labels = list(feature_translations.values())
+    english_feature_labels += [english_feature_labels[0]]  # Repeat the first label to close the loop
+    
+    # Number of variables we're plotting
+    num_vars = len(english_feature_labels)
+    
+    # Split the circle into even parts and save the angles
+    angles = np.linspace(0, 2 * np.pi, num_vars, endpoint=False).tolist()
+    angles += angles[:1]  # Complete the loop
+    
+    # Set up the font properties for using a custom font
+    font_properties = FontProperties(fname=font_path, size=12)
+    fig, ax = plt.subplots(figsize=(12, 12), subplot_kw=dict(polar=True))
+    fig.subplots_adjust(left=0.1, right=0.9, top=0.9, bottom=0.1)
+
+    # Draw one axe per variable and add labels
+    plt.xticks(angles[:-1], english_feature_labels, color='grey', size=12, fontproperties=font_properties)
+    
+    # Draw ylabels
+    ax.set_rlabel_position(0)
+    plt.yticks([0.2, 0.4, 0.6, 0.8, 1], ["0.2", "0.4", "0.6", "0.8", "1"], color="grey", size=7)
+    plt.ylim(0, 1)
+    
+    # Plot data and fill with color
+    for label, data in zip(df_dict.keys(), persona_averages):
+        data += data[:1]  # Complete the loop
+        ax.plot(angles, data, label=label, linewidth=1, linestyle='solid')
+        ax.fill(angles, data, alpha=0.25)
+    
+    # Add legend
+    plt.legend(loc='upper right', bbox_to_anchor=(0.1, 0.1))
+    
+    # Add a title
+    plt.title('Product Feature Preferences by Persona', size=20, color='grey', y=1.1, fontproperties=font_properties)
+    
+    # Display the radar chart
+    plt.show()