test file to convert sklian to onnx

onnx.py

!pip install onnx==1.13.1 onnxruntime skl2onnx
import logging
import sys
import warnings
from urllib.parse import urlparse

import numpy as np
import pandas as pd
from sklearn.linear_model import ElasticNet
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from sklearn.model_selection import train_test_split

import mlflow
import mlflow.sklearn
from mlflow.models import infer_signature

from skl2onnx import convert_sklearn
from skl2onnx.common.data_types import FloatTensorType

logging.basicConfig(level=logging.WARN)
logger = logging.getLogger(__name__)




def convert_to_onnx(model, data):
    initial_type = [('float_input', FloatTensorType([None, data.shape[0]]))]
    onnx_model = convert_sklearn(model, initial_types=initial_type)
    print("onnx_model.type:",type(onnx_model))
    mlflow.set_tag("onnx_version",onnx.__version__)
    return onnx_model

def eval_metrics(actual, pred):
    rmse = np.sqrt(mean_squared_error(actual, pred))
    mae = mean_absolute_error(actual, pred)
    r2 = r2_score(actual, pred)
    return rmse, mae, r2


if __name__ == "__main__":
    warnings.filterwarnings("ignore")
    np.random.seed(40)

    # Read the wine-quality csv file from the URL
    csv_url = (
        "https://raw.githubusercontent.com/mlflow/mlflow/master/tests/datasets/winequality-red.csv"
    )
    try:
        data = pd.read_csv(csv_url, sep=";")
    except Exception as e:
        logger.exception(
            "Unable to download training & test CSV, check your internet connection. Error: %s", e
        )

    # Split the data into training and test sets. (0.75, 0.25) split.
    train, test = train_test_split(data)

    # The predicted column is "quality" which is a scalar from [3, 9]
    train_x = train.drop(["quality"], axis=1)
    test_x = test.drop(["quality"], axis=1)
    train_y = train[["quality"]]
    test_y = test[["quality"]]

    alpha = float(sys.argv[1]) if len(sys.argv) > 1 else 0.5
    l1_ratio = float(sys.argv[2]) if len(sys.argv) > 2 else 0.5

    with mlflow.start_run():
        lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42)
        lr.fit(train_x, train_y)

        predicted_qualities = lr.predict(test_x)

        (rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)

        print(f"Elasticnet model (alpha={alpha:f}, l1_ratio={l1_ratio:f}):")
        print(f"  RMSE: {rmse}")
        print(f"  MAE: {mae}")
        print(f"  R2: {r2}")

        mlflow.log_param("alpha", alpha)
        mlflow.log_param("l1_ratio", l1_ratio)
        mlflow.log_metric("rmse", rmse)
        mlflow.log_metric("r2", r2)
        mlflow.log_metric("mae", mae)

        predictions = lr.predict(train_x)
        signature = infer_signature(train_x, predictions)
        mlflow.sklearn.log_model(lr, "model", signature=signature)
        onnx_model = convert_to_onnx(dt, X_test)
        mlflow.onnx.log_model(onnx_model, "onnx-model")