Add network correlations

page_shopping.py

@@ -4,6 +4,7 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import pandas as pd
 import numpy as np
+import networkx as nx
 from fields.likert_flat_fields import likert_flat_fields
 #from fields.boolean_fields import boolean_fields
 
@@ -16,6 +17,7 @@ def show(df):
                 f"<h2 style='text-align: center;'>Boycott Count (Overall)</h2>", unsafe_allow_html=True)
     show_boycott_count(df, font_prop=chinese_font)
     #generate_correlation_chart(df, chinese_font)
+    create_correlation_network(df, 0.4, chinese_font)
 
 def show_boycott_count(df, font_prop):
     # Count the number of people who have invested and who have not
@@ -40,6 +42,42 @@ def show_boycott_count(df, font_prop):
     # Display the chart in Streamlit
     st.pyplot(plt)
 
+def create_correlation_network(df, threshold, chinese_font):
+    
+    filtered_df = df[likert_flat_fields]
+    filtered_df = filtered_df.apply(pd.to_numeric, errors='coerce')
+
+    # Now you can calculate the correlation matrix and create the network
+    corr_matrix = filtered_df.corr()
+
+    # Create a graph
+    graph = nx.Graph()
+
+    # Iterate over the correlation matrix and add edges
+    for i in range(len(corr_matrix.columns)):
+        for j in range(i):
+            if abs(corr_matrix.iloc[i, j]) > threshold:  # only consider strong correlations
+                graph.add_edge(corr_matrix.columns[i], corr_matrix.columns[j], weight=corr_matrix.iloc[i, j])
+
+    # Draw the network
+    pos = nx.spring_layout(graph, k=0.1, iterations=20)
+    edges = graph.edges()
+    weights = [graph[u][v]['weight'] for u, v in edges]  # Use the weights for edge width
+
+    plt.figure(figsize=(10, 10))
+    nx.draw_networkx_nodes(graph, pos, node_size=500, node_color='lightblue', edgecolors='black')
+    nx.draw_networkx_edges(graph, pos, edgelist=edges, width=weights, alpha=0.5, edge_color='gray')
+
+    # Set Chinese font
+    for label in graph.nodes():
+        x, y = pos[label]
+        plt.text(x, y, label, fontsize=9, fontproperties=chinese_font, ha='center', va='center')
+
+    plt.title('Correlation Network', fontproperties=chinese_font)
+    plt.axis('off')  # Turn off the axis
+
+    # Use Streamlit to render the plot
+    st.pyplot(plt)
 
 def generate_correlation_chart(df, chinese_font):
 

requirements.txt

@@ -7,4 +7,5 @@ scipy
 scikit-learn
 squarify
 kmodes
-adjustText
+adjustText
+networkx