import matplotlib

matplotlib.use("Agg")

import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import RocCurveDisplay
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler


cancer = load_breast_cancer()
X = cancer.data
y = (cancer.target_names[cancer.target] == "malignant").astype(int)

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.25,
    stratify=y,
    random_state=42,
)

model = make_pipeline(
    StandardScaler(),
    LogisticRegression(max_iter=1000),
)
model.fit(X_train, y_train)

display = RocCurveDisplay.from_estimator(
    model,
    X_test,
    y_test,
    name="Logistic regression",
    pos_label=1,
    plot_chance_level=True,
    despine=True,
)
display.ax_.set_title("ROC curve for malignant cancer class")
display.figure_.set_size_inches(7, 5)
display.figure_.tight_layout()
display.figure_.savefig("roc-curve-plot.png", dpi=160)
plt.close(display.figure_)

print(f"train rows: {X_train.shape[0]}")
print(f"test rows: {X_test.shape[0]}")
print("positive class: malignant")
print(f"roc auc: {display.roc_auc:.3f}")
print(f"curve points: {len(display.fpr)}")
print("plot saved: roc-curve-plot.png")