first version

app.py

@@ -0,0 +1,81 @@
+import pandas as pd
+import json
+import plotly.express as px
+import gradio as gr
+
+def load_data():
+    file_path = "causalquest_embeddings_tsne.json"
+    with open(file_path, 'r') as f:
+        data = json.load(f)
+    
+    df = pd.DataFrame({
+        'query_id': data['query_id'],
+        'query': data['query'],
+        'source': data['source'],
+        'is_causal': data['is_causal'],
+        'domain_class': data['domain_class'],
+        'action_class': data['action_class'],
+        'is_subjective': data['is_subjective'],
+        'x': data['tsne_x'],
+        'y': data['tsne_y']
+    })
+
+    # subsample data for faster visualization
+    df = df.sample(1000, random_state=42)
+    
+    return df
+
+def create_plot(df):
+    fig = px.scatter(df, x='x', y='y', hover_data=['query', 'source', 'is_causal', 'domain_class', 'action_class', 'is_subjective'])
+    
+    # Remove the hover box
+    fig.update_traces(hoverinfo='none', hovertemplate=None)
+    
+    # Function to wrap long text
+    def wrap_text(text, max_length=50):
+        if len(text) <= max_length:
+            return text
+        words = text.split()
+        lines = []
+        current_line = []
+        current_length = 0
+        for word in words:
+            if current_length + len(word) + 1 <= max_length:
+                current_line.append(word)
+                current_length += len(word) + 1
+            else:
+                lines.append(' '.join(current_line))
+                current_line = [word]
+                current_length = len(word)
+        if current_line:
+            lines.append(' '.join(current_line))
+        return '<br>'.join(lines)
+    
+    # Apply text wrapping to queries
+    df['wrapped_query'] = df['query'].apply(wrap_text)
+    
+    # Add custom hover text with wrapped query
+    fig.update_traces(
+        customdata=df[['wrapped_query', 'source', 'is_causal', 'domain_class', 'action_class', 'is_subjective']],
+        hovertemplate='Query: %{customdata[0]}<br>Source: %{customdata[1]}<br>Is Causal: %{customdata[2]}'
+    )
+    
+    return fig
+
+def visualize_data(processed_file):
+    df = load_data(processed_file)
+    fig = create_plot(df)
+    return fig
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=visualize_data,
+    outputs=gr.Plot(label="tsne Visualization"),
+    title="CausalQuest Visualization",
+    description="Visualize causalquest data using pre-computed embeddings and tsne coordinates",
+    allow_flagging="never",
+    fill_width=True
+)
+
+# Launch the app
+iface.launch()