Spaces:
Runtime error
Runtime error
File size: 2,910 Bytes
b144cb7 045661d b144cb7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | """
Hugging Face Spaces entrypoint (Gradio).
Uses the same backend as the Reflex UI via `reflex_ui.backend_bridge.run_prediction`.
"""
from __future__ import annotations
import os
import sys
from pathlib import Path
import gradio as gr
import pandas as pd
REPO_ROOT = Path(__file__).resolve().parent
os.chdir(REPO_ROOT)
if str(REPO_ROOT) not in sys.path:
sys.path.insert(0, str(REPO_ROOT))
_reflex_pkg_parent = REPO_ROOT / "reflex_ui"
if str(_reflex_pkg_parent) not in sys.path:
sys.path.insert(0, str(_reflex_pkg_parent))
_reflex_pkg_nested = _reflex_pkg_parent / "reflex_ui"
if str(_reflex_pkg_nested) not in sys.path:
sys.path.insert(0, str(_reflex_pkg_nested))
from backend_bridge import run_prediction # noqa: E402
def _predict(code: str, language: str, top_k: float):
text = (code or "").strip()
if not text:
return (
"*Paste a non-empty code snippet.*",
"",
pd.DataFrame(),
"",
)
lang = (language or "python").lower()
if lang not in ("python", "java"):
lang = "python"
k = int(top_k) if top_k else 6
k = max(1, min(30, k))
try:
r = run_prediction(code=text, language=lang, top_k=k)
except Exception as e:
return (f"**{type(e).__name__}:** `{e}`", "", pd.DataFrame(), "")
label_md = f"## Prediction: **{r.label}**\n\nP(AI) = **{r.prob_ai:.4f}**"
grouped_lines = [
f"- **{name}:** {val:.4f}" for name, val in sorted(r.grouped_importance.items(), key=lambda x: -x[1])
]
grouped_md = "### Group importance\n" + ("\n".join(grouped_lines) if grouped_lines else "_n/a_")
df = pd.DataFrame(r.shap_rows)
if not df.empty and "impact" in df.columns:
show = df.drop(columns=["impact"], errors="ignore")
else:
show = df
return label_md, r.explanation, show, grouped_md
with gr.Blocks(title="AI vs Human Code Classifier") as demo:
gr.Markdown(
"# AI vs Human Code Classifier\n"
"Classifies snippets as **AI** or **Human** using XGBoost on statistical, AST, "
"stylometry, language, and **UnixCoder** semantic features, with **SHAP** attributions."
)
with gr.Row():
language = gr.Radio(choices=["python", "java"], value="python", label="Language")
top_k = gr.Slider(1, 20, value=6, step=1, label="Top SHAP features")
code = gr.Code(label="Code", language="python", lines=18)
run_btn = gr.Button("Run prediction", variant="primary")
out_head = gr.Markdown()
out_grouped = gr.Markdown()
out_expl = gr.Markdown(label="Narrative explanation")
out_table = gr.Dataframe(label="Top feature attributions", wrap=True)
run_btn.click(
_predict,
inputs=[code, language, top_k],
outputs=[out_head, out_expl, out_table, out_grouped],
)
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860)
|