Update app.py

app.py

@@ -1,5 +1,4 @@
 import os
-import shutil
 import zipfile
 import pandas as pd
 import nltk
@@ -12,28 +11,27 @@ import plotly.express as px
 import gradio as gr
 import tempfile
 
-# Download NLTK assets
+# NLTK setup
 nltk.download('punkt')
 nltk.download('stopwords')
 stop_words = set(stopwords.words('english'))
 
-# Global variable
+# Global variable to store embeddings dataframe
 embed_df = pd.DataFrame()
 
 def analyze_bigrams(zip_file, perplexity):
     global embed_df
     if zip_file is None:
-        return "Please upload a ZIP file containing .txt files.", None
+        return "Please upload a ZIP file containing .txt files.", None, None
 
-    # Extract uploaded zip to a temporary directory
+    # Extract to temp dir
     with tempfile.TemporaryDirectory() as tmpdir:
-        with zipfile.ZipFile(zip_file.name, 'r') as zip_ref:
+        with zipfile.ZipFile(zip_file, 'r') as zip_ref:
             zip_ref.extractall(tmpdir)
 
-        # Gather all .txt files
         txt_files = [os.path.join(tmpdir, f) for f in os.listdir(tmpdir) if f.endswith(".txt")]
         if not txt_files:
-            return "No .txt files found in the ZIP file.", None
+            return "No .txt files found in the ZIP file.", None, None
 
         all_texts = []
         for file_path in txt_files:
@@ -69,37 +67,34 @@ def analyze_bigrams(zip_file, perplexity):
                          size='count', title="Bigram Embeddings", template='plotly_white')
         fig.update_layout(dragmode='lasso')
 
-        return "Bigram analysis complete. Select points on the plot below.", fig
+        return "Bigram analysis complete.", fig, embed_df
 
-def generate_bar_plot(selected_indices):
-    global embed_df
-    if not embed_df.empty and selected_indices:
-        selected_df = embed_df.iloc[selected_indices]
-        fig = px.bar(selected_df.sort_values("count", ascending=False),
-                     x="count", y="bigram", orientation="h",
-                     title="Selected Bigram Frequencies")
-        return fig
-    return None
+def generate_bar_plot(selected_df):
+    if selected_df is None or selected_df.empty:
+        return None
+    fig = px.bar(selected_df.sort_values("count", ascending=False),
+                 x="count", y="bigram", orientation="h",
+                 title="Selected Bigram Frequencies")
+    return fig
 
 with gr.Blocks() as demo:
     gr.Markdown("## 📦 Upload a ZIP of .txt files to Analyze Bigrams")
 
-    
-    zip_input = gr.File(label="Upload ZIP File of .txt Files", type="filepath")  # ✅ FIXED
-
+    zip_input = gr.File(label="Upload ZIP File of .txt Files", type="filepath")
     perplexity_input = gr.Number(label="t-SNE Perplexity", value=30)
-
     generate_btn = gr.Button("Generate Scatter Plot")
+
     status_output = gr.Label()
     scatter_plot = gr.Plot()
+    bigram_table = gr.Dataframe(label="Top Bigrams", interactive=True)
     bar_plot = gr.Plot()
 
     generate_btn.click(fn=analyze_bigrams,
                        inputs=[zip_input, perplexity_input],
-                       outputs=[status_output, scatter_plot])
+                       outputs=[status_output, scatter_plot, bigram_table])
 
-    scatter_plot.select(fn=generate_bar_plot,
-                        inputs=[],
+    bigram_table.change(fn=generate_bar_plot,
+                        inputs=bigram_table,
                         outputs=bar_plot)
 
 demo.launch()