mlflowtst.py

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
import onnx
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):
#    print(data.shape[0]])
    initial_type = [('float_input', FloatTensorType([None, 11]))]
    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(lr, test_x)
        mlflow.onnx.log_model(onnx_model, "onnx-model")

teston.py

!pip3 install scikit-learn pandas numpy onnx==1.13.1 onnxruntime skl2onnx
import mlflow
from sklearn.model_selection import train_test_split

import numpy as np
import mlflow.onnx
import onnx
import onnxruntime as rt
from skl2onnx import convert_sklearn
from skl2onnx.common.data_types import FloatTensorType

def score(model, data_ndarray):
    sess = rt.InferenceSession(model.SerializeToString(), providers=['CPUExecutionProvider'])
    input_name = sess.get_inputs()[0].name
    print(sess.get_inputs()[0])
    return sess.run(None,{input_name: data_ndarray})
#    return sess.run(None, {input_name: data_ndarray.astype(np.float32)})[0]


logged_model = '/home/cdsw/.experiments/2hrm-o9a9-1qwd-qb17/9l7r-lz3a-tast-9pfy/artifacts/onnx-model'

model=mlflow.onnx.load_model("runs:/11yt-wh5d-d36y-13hy/onnx-model")
# Predict on a Pandas DataFrame.

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)

train, test = train_test_split(data,test_size=1)
print(test.shape[0])
print(test[:1])
data=np.array([6.2, 0.66, 0.48, 1.2, 0.029, 29, 75, 0.98, 3.33, 0.39, 12.8], dtype='float')
train_x = train.drop(["quality"], axis=1)
test_x = test.drop(["quality"], axis=1)
print(test_x)
score(model, data)