Create modules/clustering.py

modules/clustering.py

@@ -0,0 +1,53 @@
+# modules/clustering.py
+import logging
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+from sklearn.cluster import KMeans
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
+def perform_clustering(df: pd.DataFrame, numeric_cols: list, n_clusters: int):
+    if len(numeric_cols) < 2:
+        return go.Figure(), go.Figure(), "Clustering requires at least 2 numeric features."
+        
+    cluster_data = df[numeric_cols].dropna()
+    if len(cluster_data) < n_clusters:
+        return go.Figure(), go.Figure(), f"Not enough data ({len(cluster_data)}) for {n_clusters} clusters."
+
+    scaler = StandardScaler()
+    scaled_data = scaler.fit_transform(cluster_data)
+
+    # --- Elbow Method Plot ---
+    wcss = []
+    k_range = range(1, 11)
+    for i in k_range:
+        kmeans_elbow = KMeans(n_clusters=i, init='k-means++', random_state=42, n_init=10)
+        kmeans_elbow.fit(scaled_data)
+        wcss.append(kmeans_elbow.inertia_)
+    
+    fig_elbow = go.Figure()
+    fig_elbow.add_trace(go.Scatter(x=list(k_range), y=wcss, mode='lines+markers'))
+    fig_elbow.update_layout(title='<b>💡 The Elbow Method for Optimal K</b>',
+                          xaxis_title='Number of Clusters (K)',
+                          yaxis_title='Within-Cluster Sum of Squares (WCSS)')
+
+    # --- K-Means Clustering & Visualization ---
+    kmeans = KMeans(n_clusters=n_clusters, init='k-means++', random_state=42, n_init=10).fit(scaled_data)
+    cluster_data['Cluster'] = kmeans.labels_.astype(str)
+    
+    pca = PCA(n_components=2)
+    components = pca.fit_transform(scaled_data)
+    cluster_data['PCA1'], cluster_data['PCA2'] = components[:, 0], components[:, 1]
+    
+    fig_cluster = px.scatter(
+        cluster_data, x='PCA1', y='PCA2', color='Cluster',
+        title=f"<b>K-Means Clustering Visualization (K={n_clusters})</b>",
+        labels={'PCA1': 'Principal Component 1', 'PCA2': 'Principal Component 2'},
+        color_discrete_sequence=px.colors.qualitative.Vivid
+    )
+    
+    explained_variance = pca.explained_variance_ratio_.sum() * 100
+    summary = (f"**Features Used:** `{len(numeric_cols)}` | **Clusters (K):** `{n_clusters}`\n\n"
+               f"PCA explains **{explained_variance:.2f}%** of variance.")
+    return fig_cluster, fig_elbow, summary