Update app.py

app.py

@@ -2,113 +2,19 @@ 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
 
 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'].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 = 15  # Set the number of clusters
+    # Your preprocessing code here
+    pass
+
+def cluster_data(df, num_clusters):
     vectorizer = TfidfVectorizer(stop_words='english')
     X = vectorizer.fit_transform(df['texts'])
 
@@ -121,7 +27,7 @@ def cluster_data(df):
     df['PCA1'] = principal_components[:, 0]
     df['PCA2'] = principal_components[:, 1]
 
-    return df
+    return df, X, kmeans
 
 def visualize_clusters(df):
     plt.figure(figsize=(10, 6))
@@ -132,6 +38,35 @@ def visualize_clusters(df):
     plt.ylabel('PCA Component 2')
     plt.show()
 
+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, len(X) + (num_clusters + 1) * 10])
+    
+    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
+    
+    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)])
+    
+    return fig
+
 def main(file, num_clusters_to_display):
     try:
         df = pd.read_csv(file)
@@ -140,24 +75,33 @@ def main(file, num_clusters_to_display):
         df = df[(df['Answer'] == 'Fallback Message shown')]
         
         df = preprocess_data(df)
-        df = cluster_data(df)
+        df, X, kmeans = cluster_data(df, num_clusters=15)
         visualize_clusters(df)
 
         cluster_sizes = df['Cluster'].value_counts()
         sorted_clusters = cluster_sizes.index.tolist()
-        
-        # Exclude the largest cluster
-        largest_cluster = sorted_clusters[0]
-        filtered_clusters = [cluster for cluster in sorted_clusters if cluster != largest_cluster]
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=sorted_clusters, ordered=True)
+        df = df.sort_values('Cluster')
+
+        # Filter out base cluster and get the largest clusters
+        filtered_clusters = [cluster for cluster in sorted_clusters if cluster != 10]
         top_clusters = filtered_clusters[:num_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')
 
+        silhouette_avg = silhouette_score(X, kmeans.labels_)
+        silhouette_plot = silhouette_analysis(X, kmeans.labels_, num_clusters=15)
+
         with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
             df.to_csv(tmpfile.name, index=False)
-            return tmpfile.name
+
+        return {
+            "Clustered Data CSV": tmpfile.name,
+            "Silhouette Score": silhouette_avg,
+            "Silhouette Plot": silhouette_plot
+        }
     except Exception as e:
         return str(e)
 
@@ -167,7 +111,11 @@ interface = gr.Interface(
         gr.File(label="Upload CSV File (.csv)"),
         gr.Slider(label="Number of Categories to Display", minimum=1, maximum=10, step=1, value=5)
     ],
-    outputs=gr.File(label="Clustered Data CSV"),
+    outputs=[
+        gr.File(label="Clustered Data CSV"),
+        gr.Number(label="Silhouette Score"),
+        gr.Plot(label="Silhouette Plot")
+    ],
     title="Unanswered User Queries Clustering",
     description="Unanswered User Query Categorization"
 )