scikit-learn/isolation_forest/predict.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import joblib
import numpy as np

from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# Load the model from disk
model = joblib.load('isolation_forest.joblib')

# Set the random seed
random_seed = 0
np.random.seed(random_seed)

# Load the dataset
dataset_name = "cardiotocography"
dataset = fetch_openml(name=dataset_name, version=1, as_frame=False)
X, y = dataset.data, dataset.target
s = y == "3"
y = s.astype(int)

# Split the dataset into training and testing sets
_, X_test, _, y_test = train_test_split(X, y, test_size=0.25, random_state=random_seed)
print(f'X_test:\n{X_test[0]}')
print(f'y_test:\n{y_test[0]}')

# Use the model to make predictions on the test data
y_pred = model.predict(X_test)
# Mapping 1->0 and -1->1
y_pred = np.where(y_pred == 1, 0, 1)
print(f'y_pred:\n{y_pred[0]}')

# Score the model using accuracy classification score
acc = accuracy_score(y_test, y_pred)
print(f'Accuracy classification score: {acc}')