Update app.py

app.py

@@ -2,19 +2,17 @@ import gradio as gr
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.cluster import KMeans
-from sklearn.metrics import silhouette_score, silhouette_samples
 import matplotlib.pyplot as plt
-from sklearn.decomposition import PCA
 import re
 from io import BytesIO
 import tempfile
 import numpy as np
 from PIL import Image
+from wordcloud import WordCloud
 
 def preprocess_data(df):
     df.rename(columns={'Question Asked': 'texts'}, inplace=True)
-    df['texts'] = df['texts'].astype(str)
-    df['texts'] = df['texts'].str.lower()
+    df['texts'] = df['texts'].astype(str).str.lower()
     df['texts'] = df['texts'].apply(lambda text: re.sub(r'https?://\S+|www\.\S+', '', text))
 
     def remove_emoji(string):
@@ -26,7 +24,7 @@ def preprocess_data(df):
                                u"\U00002702-\U000027B0"
                                u"\U000024C2-\U0001F251"
                                "]+", flags=re.UNICODE)
-        return emoji_pattern.sub(r'', string) if isinstance(string, str) else string
+        return emoji_pattern.sub(r'', string)
 
     df['texts'] = df['texts'].apply(remove_emoji)
 
@@ -45,67 +43,22 @@ def preprocess_data(df):
 
     for original_word, synonym_list in custom_synonyms.items():
         for synonym in synonym_list:
-            pattern = r"\b" + synonym + r"\b(?!\s*\()"
+            pattern = r"\b" + synonym + r"\b"
             df['texts'] = df['texts'].str.replace(pattern, original_word, regex=True)
-            pattern = r"\b" + synonym + r"\s+you" + r"\b(?!\s*\()"
-            df['texts'] = df['texts'].str.replace(pattern, original_word + ' ', regex=True)
 
     spam_list = ["click here", "free", "recharge", "limited", "discount", "money back guarantee", "aaj", "kal", "mein",
                  "how can i help you", "how can we help you", "how we can help you", "follow", "king", "contacting", "gar",
-                 "kirke", "subscribe", "youtube", "jio", "insta", "make money", "b2b","sent using truecaller"]
+                 "kirke", "subscribe", "youtube", "jio", "insta", "make money", "b2b", "sent using truecaller"]
 
-    rows_to_remove = set()
     for spam_phrase in spam_list:
         pattern = r"\b" + re.escape(spam_phrase) + r"\b"
-        spam_rows = df['texts'].str.contains(pattern)
-        rows_to_remove.update(df.index[spam_rows].tolist())
-
-    df = df.drop(rows_to_remove)
-
-    greet_variations = ["hello", "hy", "hey", "hii", "hi", "heyyy", "bie", "bye"]
-    for greet_var in greet_variations:
-        pattern = r"(?<!\S)" + greet_var + r"(?!\S)|\b" + greet_var + r"\b"
-        df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
-
-    okay_variations = ["ok", "k", "kay", "okay", "okie", "kk", "ohhhk","t","r"]
-    for okay_var in okay_variations:
-        pattern = r"(?<!\S)" + okay_var + r"(?!\S)|\b" + okay_var + r"\b"
-        df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
-
-    yes_variations = ["yes", "yeah", "yep", "yup", "yuh", "ya", "yes got it", "yeah it is", "yesss", "yea","no"]
-    for yes_var in yes_variations:
-        pattern = r"(?<!\S)" + yes_var + r"(?!\S)|\b" + yes_var + r"\b"
-        df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
-
-    remove_phrases = ["i'm all set","ask a question","apply the survey","videos (2-8 min)","long reads (> 8 min)",
-                      "short reads (3-8 min)","not a student alumni","mock","share feedback","bite size (< 2 min)",
-                      "actually no","next steps","i'm a student alumni","i have questions"]
-
-    for phrase in remove_phrases:
-        df['texts'] = df['texts'].str.replace(phrase, '')
-
-    general_variations = ["good morning", "good evening", "good afternoon", "good night", "done", "sorry", "top", "query",
-                          "stop", "sir", "sure", "oh", "wow", "aaa", "maam", "mam", "ma&#39;am","i'm all set","ask a question","apply the survey",
-                          "videos (2-8 min)","long reads (> 8 min)","short reads (3-8 min)","not a student alumni","mock","share feedback","bite size (< 2 min)",
-                          "actually no","next steps","i'm a student alumni","i have questions"]
-    for gen_var in general_variations:
-        pattern = r"(?<!\S)" + gen_var + r"(?!\S)|\b" + gen_var + r"\b(?=\W|$)"
-        df['texts'] = df['texts'].str.replace(pattern, '', regex=True)
+        df = df[~df['texts'].str.contains(pattern)]
 
     def remove_punctuations(text):
         return re.sub(r'[^\w\s]', '', text)
-    df['texts'] = df['texts'].apply(remove_punctuations)
-
-    remove_morephrases = ["short reads 38 min","bite size  2 min","videos 28 min","long reads  8 min"]
-
-    for phrase in remove_morephrases:
-        df['texts'] = df['texts'].str.replace(phrase, '')
-
-    df = df[~df['texts'].str.contains(r'\b\d{10}\b')]
 
+    df['texts'] = df['texts'].apply(remove_punctuations)
     df['texts'] = df['texts'].str.strip()
-
-    df['texts'] = df['texts'].apply(lambda x: x.strip())
     df = df[df['texts'] != '']
 
     return df
@@ -118,96 +71,47 @@ def cluster_data(df, num_clusters):
     kmeans.fit(X)
     df['Cluster'] = kmeans.labels_
 
-    pca = PCA(n_components=2)
-    principal_components = pca.fit_transform(X.toarray())
-    df['PCA1'] = principal_components[:, 0]
-    df['PCA2'] = principal_components[:, 1]
-
-    return df, X, kmeans
+    return df, kmeans
 
-def visualize_clusters(df):
-    plt.figure(figsize=(10, 6))
-    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')
+def generate_wordcloud(df):
+    text = " ".join(df['texts'].tolist())
+    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
+    plt.figure(figsize=(10, 5))
+    plt.imshow(wordcloud, interpolation='bilinear')
+    plt.axis('off')
     buf = BytesIO()
     plt.savefig(buf, format='png')
     buf.seek(0)
     img = Image.open(buf)
     return img
 
-def silhouette_analysis(X, labels, num_clusters):
-    fig, ax1 = plt.subplots(1, 1)
-    fig.set_size_inches(10, 6)
-    
-    ax1.set_xlim([-0.1, 1])
-    ax1.set_ylim([0, X.shape[0] + (num_clusters + 1) * 10])
+def main(file, num_clusters_to_display):
+    df = pd.read_csv(file)
     
-    sample_silhouette_values = silhouette_samples(X, labels)
-    y_lower = 10
-    for i in range(num_clusters):
-        ith_cluster_silhouette_values = sample_silhouette_values[labels == i]
-        ith_cluster_silhouette_values.sort()
-        size_cluster_i = ith_cluster_silhouette_values.shape[0]
-        y_upper = y_lower + size_cluster_i
-        color = plt.cm.nipy_spectral(float(i) / num_clusters)
-        ax1.fill_betweenx(np.arange(y_lower, y_upper), 0, ith_cluster_silhouette_values,
-                          facecolor=color, edgecolor=color, alpha=0.7)
-        ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
-        y_lower = y_upper + 10
+    # Filter by 'Fallback Message shown'
+    df = df[df['Answer'] == 'Fallback Message shown']
     
-    ax1.set_title("The silhouette plot for the various clusters.")
-    ax1.set_xlabel("The silhouette coefficient values")
-    ax1.set_ylabel("Cluster label")
-    ax1.axvline(x=np.mean(sample_silhouette_values), color="red", linestyle="--")
-    ax1.set_yticks([])
-    ax1.set_xticks([i/10.0 for i in range(-1, 11)])
+    df = preprocess_data(df)
+    df, kmeans = cluster_data(df, num_clusters=15)
     
-    buf = BytesIO()
-    plt.savefig(buf, format='png')
-    buf.seek(0)
-    img = Image.open(buf)
-    return img
+    cluster_sizes = df['Cluster'].value_counts()
+    sorted_clusters = cluster_sizes.index.tolist()
 
-def main(file, num_clusters_to_display):
-    try:
-        df = pd.read_csv(file)
-        
-        # Filter by 'Fallback Message shown'
-        df = df[(df['Answer'] == 'Fallback Message shown')]
-        
-        df = preprocess_data(df)
-        df, X, kmeans = cluster_data(df, num_clusters=15)
-        
-        cluster_plot = visualize_clusters(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')
-
-        # 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')
-
-        silhouette_avg = silhouette_score(X, kmeans.labels_)
-        silhouette_plot = silhouette_analysis(X, kmeans.labels_, num_clusters=15)
-
-        # Convert silhouette score to percentage
-        silhouette_percentage = (silhouette_avg + 1) * 50
-
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
-            df.to_csv(tmpfile.name, index=False)
-            return tmpfile.name, silhouette_percentage, cluster_plot, silhouette_plot
-    except Exception as e:
-        print(f"Error: {e}")
-        return str(e), None, None, None
+    # 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
 
 interface = gr.Interface(
     fn=main,
@@ -217,13 +121,10 @@ interface = gr.Interface(
     ],
     outputs=[
         gr.File(label="Clustered Data CSV"),
-        gr.Number(label="Clustering Quality (%)"),
-        gr.Image(label="Cluster Plot"),
-        gr.Image(label="Silhouette Plot")
+        gr.Image(label="Word Cloud")
     ],
     title="Unanswered User Queries Clustering",
     description="Unanswered User Query Categorization"
 )
 
-interface.launch()
-
+interface.launch(share=True)