Update app.py

app.py

@@ -11,8 +11,103 @@ import tempfile
 import numpy as np
 
 def preprocess_data(df):
-    # Your preprocessing code here
-    pass
+    df.rename(columns={'Question Asked': 'texts'}, inplace=True)
+    df['texts'] = df['texts'].astype(str)
+    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'],
+        'work': ['job'],
+        'salary': ['stipend', 'pay', 'payment', 'paid'],
+        'test': ['online test', 'amcat test', 'exam', 'assessment'],
+        'pass': ['clear', 'selected', 'pass or not'],
+        'result': ['outcome', 'mark', 'marks'],
+        'thanks': ["thanks a lot to you", "thankyou so much", "thank you so much", "tysm", "thank you",
+                   "okaythank", "thx", "ty", "thankyou", "thank", "thank u"],
+        'interview': ["pi"]
+    }
+
+    for original_word, synonym_list in custom_synonyms.items():
+        for synonym in synonym_list:
+            pattern = r"\b" + synonym + r"\b(?!\s*\()"
+            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"]
+
+    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')