init_repo_MLstructureMining.py

import json
import os
import pickle
from pathlib import Path
from tempfile import mkdtemp, mkstemp
from uuid import uuid4

import numpy as np
import xgboost
import sklearn
from huggingface_hub import HfApi
from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import HistGradientBoostingClassifier
from sklearn.experimental import enable_halving_search_cv  # noqa
from sklearn.model_selection import HalvingGridSearchCV, train_test_split
import shutil
from skops import card, hub_utils

# Data
X, y = load_breast_cancer(as_frame=True, return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42
)
print("X's summary: ", X.describe())
print("y's summary: ", y.describe())

# # Train model
param_grid = {
    "max_leaf_nodes": [5, 10, 15],
    "max_depth": [2, 5, 10],
}

model = HalvingGridSearchCV(
    estimator=HistGradientBoostingClassifier(),
    param_grid=param_grid,
    random_state=42,
    n_jobs=-1,
).fit(X_train, y_train)
model.score(X_test, y_test)# The file name is not significant, here we choose to save it with a `pkl`
# extension.

_, pkl_name = mkstemp(prefix="skops-", suffix=".pkl")
with open(pkl_name, mode="bw") as f:
    pickle.dump(model, file=f)



local_repo = mkdtemp(prefix="skops-")
hub_utils.init(
    #model=pkl_name,
    model="xgb_model_bayse_optimization_00000.bin",
    requirements=[f"scikit-learn={sklearn.__version__}", f"xgboost={xgboost.__version__}"],
    dst=local_repo,
    task="tabular-classification",
    data=X_test,
)
if "__file__" in locals():  # __file__ not defined during docs built
    # Add this script itself to the files to be uploaded for reproducibility
    hub_utils.add_files(__file__, dst=local_repo)

print(os.listdir(local_repo))

model_card = card.Card(model, metadata=card.metadata_from_config(Path(local_repo)))
model_card.save(Path(local_repo) / "README.md")


# you can put your own token here, or set it as an environment variable before
# running this script.
token = os.environ["HF_HUB_TOKEN"]

repo_name = f"MLstructureMining"
user_name = HfApi().whoami(token=token)["name"]
repo_id = f"{user_name}/{repo_name}"
print(f"Creating and pushing to repo: {repo_id}")


hub_utils.push(
    repo_id=repo_id,
    source=local_repo,
    token=token,
    commit_message="pushing files to the repo from the example!",
    create_remote=True,
    private=True,
)