How to choose the optimal threshold for imbalanced classification

threshold_simulation.py

# Import module for data manipulation
import pandas as pd
# Import module for linear algebra
import numpy as np
# Import module for data simulation
from sklearn.datasets import make_classification     # Create a synthetic dataframe
from sklearn.linear_model import LogisticRegression  # Classification model
from sklearn.model_selection import train_test_split # Split the dataframe
from sklearn.metrics import roc_curve                # Calculate the ROC curve
from sklearn.metrics import precision_recall_curve   # Calculate the Precision-Recall curve
from sklearn.metrics import f1_score                 # Calculate the F-score
# Import module for data visualization
from plotnine import *
import plotnine

# Generate the dataset
X, y = make_classification(n_samples = 10000, n_features = 2, n_redundant = 0,
                           n_clusters_per_class = 1, weights = [0.99], flip_y = 0, random_state = 0)

# Data partitioning
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0, stratify=y)

# Fit the model
reglogModel = LogisticRegression(random_state = 0)
reglogModel.fit(X_train, y_train)

# Predict the probabilities
y_pred = reglogModel.predict_proba(X_test)

# Get the probabilities for positive class
y_pred = y_pred[:, 1]