""" predict.py - analyzes a local repo and predicts the technical debt per file Uses model v3: tabular features (Radon + AST + relative git activity) combined with PCA-reduced code embeddings (see docs/decisions/004-embeddings-tradeoff.md). """ import argparse import sys import os import shutil import stat import tempfile import re from pathlib import Path from datetime import datetime import joblib import numpy as np import pandas as pd from git import Repo from git.exc import InvalidGitRepositoryError, NoSuchPathError from sentence_transformers import SentenceTransformer from feature_lib import ( features_ats, features_radon, feature_git_raw, normalization_relative_to_repo, embedding_extract_functions, ) SRC_DIR = Path(__file__).resolve().parent MODELS_DIR = SRC_DIR.parent / "models" REPORTS_DIR = SRC_DIR.parent / "temp_reports" if str(SRC_DIR) not in sys.path: sys.path.insert(0, str(SRC_DIR)) # Oficial Artifacts: v3 (embeddings + PCA) feat_list = joblib.load(MODELS_DIR / "features_v3.pkl") MODEL = joblib.load(MODELS_DIR / "random_forest_v3.pkl") PCA_MODEL = joblib.load(MODELS_DIR / "pca_v3.pkl") EMBED_MODEL = SentenceTransformer("all-MiniLM-L6-v2") CONFIG = { "skip_dirs": ["test", ".venv"], } def validate_repo(path: str) -> tuple[Path, Repo]: repo_path = Path(path).resolve() if not repo_path.exists(): print(f"Error: the path '{repo_path}' does not exist.") sys.exit(1) try: repo_git = Repo(repo_path) except (InvalidGitRepositoryError, NoSuchPathError): print(f"Error: '{repo_path}' is not a valid git repository.") sys.exit(1) return repo_path, repo_git def find_python_files(repo_path: Path) -> list[str]: return [ str(f.relative_to(repo_path)) for f in repo_path.rglob("*.py") if not any(part in CONFIG["skip_dirs"] for part in f.parts) ] def print_summary(repo_path: Path, files: list[str]): print("\n" + "=" * 60) print(f" FILES FOUND IN {repo_path.name}") print("=" * 60) print(f" Total: {len(files)} .py files") print("=" * 60) for file in files[:15]: print(f" {file}") if len(files) > 15: print(f" ... and {len(files) - 15} more") print("=" * 60) def feature_extraction(path, files, repo_git, repo_name): resultados = {} todas_las_funciones = [] indice_por_archivo = [] for archivo in files: try: with open(path / archivo, "r", encoding="utf-8") as f: feat_file = f.read() features = {} features.update(features_radon(feat_file)) features.update(features_ats(feat_file)) features.update(feature_git_raw(archivo, repo_git)) features["repo"] = repo_name # Ruta normalizada — evita el desajuste backslash/forward-slash # entre este dict y las claves de embeddings_por_archivo. clave = f"{repo_name}/{archivo}".replace("\\", "/") resultados[clave] = features funciones_archivo = embedding_extract_functions(feat_file) indice_por_archivo.append((clave, len(funciones_archivo))) todas_las_funciones.extend(funciones_archivo) except Exception as e: print(f"corrupted file: {archivo} , {e}") continue return resultados, todas_las_funciones, indice_por_archivo def generar_embeddings_reducidos(todas_las_funciones, indice_por_archivo): """Genera embeddings por función (batched), hace mean pooling por archivo. NO aplica PCA aquí — eso ocurre en full_report, sobre la matriz completa.""" if todas_las_funciones: embeddings_funciones = EMBED_MODEL.encode(todas_las_funciones, batch_size=64) else: embeddings_funciones = np.empty((0, 384)) embeddings_por_archivo = {} cursor = 0 for clave, cantidad in indice_por_archivo: if cantidad == 0: embeddings_por_archivo[clave] = np.zeros(384) continue bloque = embeddings_funciones[cursor: cursor + cantidad] embeddings_por_archivo[clave] = bloque.mean(axis=0) cursor += cantidad return embeddings_por_archivo def full_report(results: dict, embeddings_por_archivo: dict) -> pd.DataFrame: """Combina features tabulares (normalizados relativo al repo) con embeddings reducidos por PCA (ya ajustado en entrenamiento — aquí solo .transform()).""" df = pd.DataFrame.from_dict(results, orient="index") df.index.name = "file" df = normalization_relative_to_repo(df, repo_col="repo") X_tabular = df[feat_list].values matriz_embeddings = np.array([embeddings_por_archivo[clave] for clave in df.index]) X_embeddings_reducido = PCA_MODEL.transform(matriz_embeddings) # transform, NUNCA fit_transform X_final = np.hstack([X_tabular, X_embeddings_reducido]) df.insert(0, "danger", MODEL.predict_proba(X_final)[:, 1].round(3)) return df.sort_values("danger", ascending=False).reset_index() def save_csv_report(report: pd.DataFrame, repo_name: str, destination: Path = REPORTS_DIR) -> Path: destination.mkdir(parents=True, exist_ok=True) clean_name = re.sub(r"[^A-Za-z0-9._-]", "_", repo_name) or "repo" timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") csv_path = destination / f"report_{clean_name}_{timestamp}.csv" report.to_csv(csv_path, index=False, encoding="utf-8") return csv_path def _delete_tree(path: Path): def _remove_readonly(func, path, _exc_info): os.chmod(path, stat.S_IWRITE) func(path) shutil.rmtree(path, onerror=_remove_readonly) def fetch_and_clone_repo(max_attempts: int = 5): try: from repo_search import get_random_repo except EnvironmentError as e: print(f"Error: {e}") return None tried_urls = set() for attempt in range(1, max_attempts + 1): repo_info = get_random_repo() if repo_info is None: print(f" [{attempt}/{max_attempts}] No repo was obtained. Retrying...") continue clone_url = repo_info["clone_url"] if clone_url in tried_urls: continue tried_urls.add(clone_url) tmp_dir = Path(tempfile.mkdtemp(prefix="techdebt_")) dest = tmp_dir / repo_info["name"] try: print(f" [{attempt}/{max_attempts}] Cloning {repo_info['full_name']} ...") repo_git = Repo.clone_from(clone_url, dest) except Exception as e: print(f" Clone failed: {e}") _delete_tree(tmp_dir) continue files = find_python_files(dest) if not files: print(" The repo has no usable .py files. Trying another one...") repo_git.close() _delete_tree(tmp_dir) continue return tmp_dir, dest, repo_git, repo_info["name"], files return None def main(): parser = argparse.ArgumentParser( description="Analyzes a repository and predicts the technical debt per file. " "Without arguments, it looks for and clones a random GitHub repo." ) parser.add_argument( "repo_path", nargs="?", default=None, help="Path to a local repo (optional). If omitted, a random GitHub repo " "is looked up and cloned.", ) args = parser.parse_args() tmp_dir = None repo_git = None try: if args.repo_path: repo_path, repo_git = validate_repo(args.repo_path) repo_name = repo_path.name files = find_python_files(repo_path) if not files: print(f"No .py files were found in '{repo_path}'.") return else: print("Looking for a random repo on GitHub...") result = fetch_and_clone_repo() if result is None: print("Could not obtain a valid GitHub repo after several attempts.") return tmp_dir, repo_path, repo_git, repo_name, files = result print_summary(repo_path, files) results, functions_list, index_list = feature_extraction( repo_path, files, repo_git, repo_name ) print(f"\nFeatures extracted from {len(results)} files.") if not results: print("Could not extract features from any file.") return embeddings_por_archivo = generar_embeddings_reducidos(functions_list, index_list) report = full_report(results, embeddings_por_archivo) print("\n" + "=" * 60) print(" RISK + RAW VALUES (highest to lowest risk)") print("=" * 60) print(report.to_string(index=False)) csv_path = save_csv_report(report, repo_name) print(f"\nReport saved to: {csv_path}") finally: if repo_git is not None: repo_git.close() if tmp_dir is not None: _delete_tree(tmp_dir) print("\nTemporary repo deleted.") if __name__ == "__main__": main()