import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_curve

data = pd.read_csv('/datasets/travel_insurance_preprocessed.csv')

target = data['Claim']
features = data.drop('Claim', axis=1)
features_train, features_valid, target_train, target_valid = train_test_split(
    features, target, test_size=0.25, random_state=12345)

model = LogisticRegression(random_state=12345, solver='liblinear')
model.fit(features_train, target_train)

probabilities_valid = model.predict_proba(features_valid)
probabilities_one_valid = probabilities_valid[:, 1]
fpr, tpr, thresholds = roc_curve(target_valid, probabilities_one_valid)

plt.figure()
plt.plot(fpr, tpr)
plt.plot([0, 1], [0, 1], linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.0])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC-кривая')
plt.show()