from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler


iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data,
    iris.target,
    test_size=0.25,
    stratify=iris.target,
    random_state=42,
)

model = make_pipeline(
    StandardScaler(),
    LogisticRegression(max_iter=200),
)
model.fit(X_train, y_train)

predictions = model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
classifier = model.named_steps["logisticregression"]

sample_prediction = model.predict(X_test[[0]])[0]
sample_probability = model.predict_proba(X_test[[0]])[0]
sample_probabilities = {
    str(iris.target_names[index]): round(float(probability), 3)
    for index, probability in enumerate(sample_probability)
}

print(f"train rows: {X_train.shape[0]}")
print(f"test rows: {X_test.shape[0]}")
print(f"accuracy: {accuracy:.3f}")
print(f"classes: {', '.join(iris.target_names[classifier.classes_])}")
print(f"coefficient shape: {classifier.coef_.shape}")
print(f"first prediction: {iris.target_names[sample_prediction]}")
print(f"first probabilities: {sample_probabilities}")