repo representation visualization

display_representations.py

@@ -0,0 +1,105 @@
+import gradio as gr
+import pandas as pd
+import logging
+import re
+
+
+logging.basicConfig(level=logging.INFO)
+
+
+def load_repo_df(data_path="data/repo_representations.jsonl"):
+    data = pd.read_json(data_path, lines=True, orient="records")
+    return data.assign(
+        text=data["text"]
+        .str.replace(r"<img.*\/>", "", regex=True)
+        .str.replace("│", "\n")
+        .str.replace("⋮", "\n")
+    )
+
+
+def display_representations(repo, representation1, representation2):
+    repo_data = repos_df[repos_df["repo_name"] == repo]
+    logging.info(f"repo_data: {repo_data}")
+    text1 = (
+        repo_data[repo_data["representation"] == representation1]["text"].iloc[0]
+        if not repo_data[repo_data["representation"] == representation1].empty
+        else "No data available"
+    )
+    text2 = (
+        repo_data[repo_data["representation"] == representation2]["text"].iloc[0]
+        if not repo_data[repo_data["representation"] == representation2].empty
+        else "No data available"
+    )
+
+    return text1, text2
+
+
+if __name__ == "__main__":
+    repos_df = load_repo_df()
+    repos = list(repos_df["repo_name"].unique())
+    representation_types = list(repos_df["representation"].unique())
+    logging.info(f"found {len(repos)} repositories")
+    logging.info(f"representation types: {representation_types}")
+
+    with gr.Blocks() as demo:
+        gr.Markdown("# Repository Representations Viewer")
+        gr.Markdown("Select a repository and two representation types to compare them.")
+
+        with gr.Row():
+            repo = gr.Dropdown(choices=repos, label="Repository", value=repos[0])
+            representation1 = gr.Dropdown(
+                choices=representation_types, label="Representation 1", value="readme"
+            )
+            representation2 = gr.Dropdown(
+                choices=representation_types,
+                label="Representation 2",
+                value="generated_readme",
+            )
+
+        with gr.Row():
+            with gr.Box(elem_id="box1"):
+                text1 = gr.Markdown()
+            with gr.Box(elem_id="box2"):
+                text2 = gr.Markdown()
+
+        # Add custom CSS
+        gr.Markdown(
+            """
+            <style>
+            #box1, #box2 {
+                border: 2px solid #ddd;
+                border-radius: 10px;
+                padding: 10px;
+                margin: 10px;
+                background-color: #f9f9f9;
+            }
+            #box1 {
+                border-color: #007bff;
+            }
+            #box2 {
+                border-color: #28a745;
+            }
+            </style>
+            """
+        )
+
+        def update_representations(*args):
+            text1_content, text2_content = display_representations(*args)
+            return (
+                f"### Representation 1\n\n{text1_content}",
+                f"### Representation 2\n\n{text2_content}",
+            )
+
+        # Initial call to populate textboxes with default values
+        text1.value, text2.value = update_representations(
+            repos[0], "readme", "generated_readme"
+        )
+
+        for component in [repo, representation1, representation2]:
+            component.change(
+                fn=update_representations,
+                inputs=[repo, representation1, representation2],
+                outputs=[text1, text2],
+            )
+
+    demo.launch()

requirements.txt

@@ -0,0 +1 @@
+gradio==3.48.0