import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import precision_recall_curve, f1_score

# Generate synthetic data with make_classification
X, y_true = make_classification(n_samples=1000, n_features=20, random_state=42)

# Create a Logistic Regression model
model = LogisticRegression()

# Fit the model on the data
model.fit(X, y_true)

# Predict probabilities for the positive class
y_scores = model.predict_proba(X)[:, 1]

# Compute precision, recall, and F-score
precision, recall, thresholds = precision_recall_curve(y_true, y_scores)
f_scores = 2 * (precision * recall) / (precision + recall)

# Find the threshold with the maximal F-score
max_f_score_idx = np.argmax(f_scores)
max_f_score_threshold = thresholds[max_f_score_idx]

# Create the PR curve plot
plt.figure(figsize=(8, 6))
plt.scatter(recall[:-1], precision[:-1], c=thresholds)
plt.scatter(recall[max_f_score_idx], precision[max_f_score_idx], c='red', marker='o', label=f'Max F-score ({max_f_score_threshold:.2f})', s=100)
plt.colorbar()
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Precision-Recall Curve')
plt.legend()
plt.grid(True)
plt.show()