Update app.py

app.py

@@ -2,12 +2,14 @@ import gradio as gr
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.cluster import KMeans
-from sklearn.preprocessing import normalize
-from wordcloud import WordCloud
 import matplotlib.pyplot as plt
-from io import BytesIO
+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)
@@ -15,6 +17,19 @@ def preprocess_data(df):
     df['texts'] = df['texts'].str.lower()
     df['texts'] = df['texts'].apply(lambda text: re.sub(r'https?://\S+|www\.\S+', '', text))
 
+    def remove_emoji(string):
+        emoji_pattern = re.compile("["
+                               u"\U0001F600-\U0001F64F"
+                               u"\U0001F300-\U0001F5FF"
+                               u"\U0001F680-\U0001F6FF"
+                               u"\U0001F1E0-\U0001F1FF"
+                               u"\U00002702-\U000027B0"
+                               u"\U000024C2-\U0001F251"
+                               "]+", flags=re.UNICODE)
+        return emoji_pattern.sub(r'', string) if isinstance(string, str) else string
+
+    df['texts'] = df['texts'].apply(remove_emoji)
+
     custom_synonyms = {
         'application': ['form'],
         'apply': ['fill', 'applied'],
@@ -35,73 +50,136 @@ def preprocess_data(df):
             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"]
+
+    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)
+
+    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'].str.strip()
+
+    df['texts'] = df['texts'].apply(lambda x: x.strip())
+    df = df[df['texts'] != '']
+
     return df
 
 def cluster_data(df, num_clusters):
     vectorizer = TfidfVectorizer(stop_words='english')
     X = vectorizer.fit_transform(df['texts'])
-    X = normalize(X)
 
     kmeans = KMeans(n_clusters=num_clusters, random_state=0)
     kmeans.fit(X)
     df['Cluster'] = kmeans.labels_
 
-    return df
+    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
 
-def generate_wordcloud(texts):
-    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(" ".join(texts))
+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)
-    return buf
-
-def main(file, num_clusters, 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 = cluster_data(df, num_clusters)
-    
-    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')
-
-    wordclouds = []
-    for cluster in filtered_clusters:
-        texts = df[df['Cluster'] == cluster]['texts'].tolist()
-        wordcloud_image = generate_wordcloud(texts)
-        wordclouds.append((f"Cluster {cluster}", wordcloud_image))
-
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
-        df.to_csv(tmpfile.name, index=False)
-        csv_file_path = tmpfile.name
-
-    return wordclouds, csv_file_path
+    img = Image.open(buf)
+    return img
+
+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_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')
+
+        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,
     inputs=[
         gr.File(label="Upload CSV File (.csv)"),
-        gr.Slider(label="Number of Clusters", minimum=2, maximum=20, step=1, value=5),
         gr.Slider(label="Number of Categories to Display", minimum=1, maximum=10, step=1, value=5)
     ],
     outputs=[
-        gr.Gallery(label="Word Clouds of Clusters"),
-        gr.File(label="Clustered Data CSV")
+        gr.File(label="Clustered Data CSV"),
+        gr.Image(label="Word Cloud")
     ],
     title="Unanswered User Queries Clustering",
     description="Unanswered User Query Categorization"