Update app.py

app.py

@@ -2,13 +2,12 @@ import gradio as gr
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.cluster import KMeans
-import matplotlib.pyplot as plt
 import re
 from io import BytesIO
 import tempfile
-import numpy as np
-from PIL import Image
 from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+from PIL import Image
 
 def preprocess_data(df):
     df.rename(columns={'Question Asked': 'texts'}, inplace=True)
@@ -75,7 +74,7 @@ def cluster_data(df, num_clusters):
 
 def generate_wordcloud(df):
     text = " ".join(df['texts'].tolist())
-    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
+    wordcloud = WordCloud(width=800, height=400, background_color='white', max_words=200, collocations=False).generate(text)
     plt.figure(figsize=(10, 5))
     plt.imshow(wordcloud, interpolation='bilinear')
     plt.axis('off')
@@ -86,32 +85,37 @@ def generate_wordcloud(df):
     return img
 
 def main(file, num_clusters_to_display):
-    df = pd.read_csv(file)
-    
-    # Filter by 'Fallback Message shown'
-    df = df[df['Answer'] == 'Fallback Message shown']
-    
-    df = preprocess_data(df)
-    df, kmeans = cluster_data(df, num_clusters=20)
-    
-    cluster_sizes = df['Cluster'].value_counts()
-    sorted_clusters = cluster_sizes.index.tolist()
-
-    # Filter out the largest cluster and get the next largest clusters
-    largest_cluster = sorted_clusters[0]
-    filtered_clusters = sorted_clusters[1:num_clusters_to_display+1]
-
-    df = df[df['Cluster'].isin(filtered_clusters)]
-    df['Cluster'] = pd.Categorical(df['Cluster'], categories=filtered_clusters, ordered=True)
-    df = df.sort_values('Cluster')
-
-    wordcloud_img = generate_wordcloud(df)
-
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
-        df.to_csv(tmpfile.name, index=False)
-        csv_file_path = tmpfile.name
-
-    return csv_file_path, wordcloud_img
+    try:
+        df = pd.read_csv(file)
+        
+        # Filter by 'Fallback Message shown'
+        df = df[df['Answer'] == 'Fallback Message shown']
+        
+        df = preprocess_data(df)
+        df, kmeans = cluster_data(df, num_clusters=15)
+        
+        cluster_sizes = df['Cluster'].value_counts()
+        sorted_clusters = cluster_sizes.index.tolist()
+
+        # Filter out the largest cluster and get the next largest clusters
+        largest_cluster = sorted_clusters[0]
+        filtered_clusters = sorted_clusters[1:num_clusters_to_display+1]
+
+        df = df[df['texts'] != '']
+        df = df[df['Cluster'].isin(filtered_clusters)]
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=filtered_clusters, ordered=True)
+        df = df.sort_values('Cluster')
+
+        wordcloud_img = generate_wordcloud(df)
+
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
+            df.to_csv(tmpfile.name, index=False)
+            csv_file_path = tmpfile.name
+
+        return csv_file_path, wordcloud_img
+    except Exception as e:
+        print(f"Error: {e}")
+        return str(e), None
 
 interface = gr.Interface(
     fn=main,