Update app.py

app.py

@@ -107,22 +107,8 @@ def preprocess_data(df):
 
     return df
 
-def elbow_method(X):
-    distortions = []
-    K = range(1, 20)
-    for k in K:
-        kmeanModel = KMeans(n_clusters=k)
-        kmeanModel.fit(X)
-        distortions.append(kmeanModel.inertia_)
-
-    plt.figure(figsize=(10, 6))
-    plt.plot(K, distortions, 'bx-')
-    plt.xlabel('k')
-    plt.ylabel('Distortion')
-    plt.title('The Elbow Method showing the optimal k')
-    plt.show()
-
-def cluster_data(df, num_clusters=15):
+def cluster_data(df):
+    num_clusters = 20  # Set the number of clusters to 15
     vectorizer = TfidfVectorizer(stop_words='english')
     X = vectorizer.fit_transform(df['texts'])
 
@@ -131,45 +117,54 @@ def cluster_data(df, num_clusters=15):
     df['Cluster'] = kmeans.labels_
 
     pca = PCA(n_components=2)
-    scatter_plot_points = pca.fit_transform(X.toarray())
-    colors = ['r', 'b', 'c', 'y', 'm', 'g']
+    principal_components = pca.fit_transform(X.toarray())
+    df['PCA1'] = principal_components[:, 0]
+    df['PCA2'] = principal_components[:, 1]
 
-    x_axis = [o[0] for o in scatter_plot_points]
-    y_axis = [o[1] for o in scatter_plot_points]
+    return df
 
+def visualize_clusters(df):
     plt.figure(figsize=(10, 6))
-    plt.scatter(x_axis, y_axis, c=[colors[d] for d in kmeans.labels_])
+    scatter = plt.scatter(df['PCA1'], df['PCA2'], c=df['Cluster'], cmap='viridis')
+    plt.legend(*scatter.legend_elements(), title="Clusters")
+    plt.title('Clusters of User Queries')
+    plt.xlabel('PCA Component 1')
+    plt.ylabel('PCA Component 2')
     plt.show()
 
-    return df
-
-def sort_and_filter_clusters(df, num_display_clusters):
-    cluster_sizes = df['Cluster'].value_counts().sort_values(ascending=False)
-    largest_clusters = cluster_sizes[cluster_sizes.index != 0].head(num_display_clusters).index
-    filtered_df = df[df['Cluster'].isin(largest_clusters)]
+def main(file, num_clusters_to_display):
+    try:
+        df = pd.read_excel(file)
+        df = preprocess_data(df)
+        df = cluster_data(df)
+        visualize_clusters(df)
 
-    return filtered_df
+        cluster_sizes = df['Cluster'].value_counts()
+        sorted_clusters = cluster_sizes.index.tolist()
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=sorted_clusters, ordered=True)
+        df = df.sort_values('Cluster')
 
-def main(file, num_display_clusters):
-    df = pd.read_excel(file)
-    df = preprocess_data(df)
-    df = cluster_data(df, num_clusters=15)
-    df = sort_and_filter_clusters(df, num_display_clusters)
-    
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp:
-        df.to_csv(tmp.name, index=False)
-        tmp.seek(0)
-        return tmp.name
+        # Filter out cluster 0 and get the largest clusters
+        filtered_clusters = [cluster for cluster in sorted_clusters if cluster != 0]
+        top_clusters = filtered_clusters[:num_clusters_to_display]
 
-input_file = gr.inputs.File(label="Upload an Excel file (.xlsx)")
-num_display_clusters = gr.inputs.Slider(minimum=1, maximum=10, step=1, default=5, label="Number of Largest Clusters to Display")
+        df = df[df['Cluster'].isin(top_clusters)]
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=top_clusters, ordered=True)
+        df = df.sort_values('Cluster')
 
-output_file = gr.outputs.File(label="Clustered Data CSV")
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
+            df.to_csv(tmpfile.name, index=False)
+            return tmpfile.name
+    except Exception as e:
+        return str(e)
 
 interface = gr.Interface(
     fn=main,
-    inputs=[input_file, num_display_clusters],
-    outputs=output_file,
+    inputs=[
+        gr.File(label="Upload Excel File (.xlsx)"),
+        gr.Slider(1, 10, step=1, label="Number of Categories to Display")
+    ],
+    outputs=gr.File(label="Clustered Data CSV"),
     title="Unanswered User Queries Clustering",
     description="Upload an Excel file (.xlsx) and select the number of largest clusters to display (excluding cluster 0)"
 )