train_model.py

from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

## logistic regression parameter config
parameters = {
    "penalty":"l2",
    "C":1.0,
    "max_iter": 100
}

## use a standard scaler and logistic regression
scaler = StandardScaler()
logistic_regression = LogisticRegression(
    penalty=parameters["penalty"],
    C=parameters["C"],
    max_iter=parameters["max_iter"],
)

## make a pipeline out of them
pipeline = make_pipeline(scaler, logistic_regression)

## get our data from the feature store and create a train/test split
data = feature_store.get_all_data()
X_train, X_test, y_train, y_test = train_test_split(data[["feature_1","feature_2","feature_3"]], data["target"])

## fit the model
pipeline.fit(X_train, y_train)

## get the test score 
score = pipeline.score(X_test, y_test)

## record it
record_model(pipeline, score, parameters)

## view the output
pd.read_csv("metadata_store.csv")