AutoML Example

automl.py

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
import autosklearn.classification

from smac.tae import StatusType

from pathlib import Path
import shutil

if __name__ == "__main__":

    X, y = sklearn.datasets.load_digits(return_X_y=True)

    X_train, X_test, y_train, y_test = \
            sklearn.model_selection.train_test_split(X, y, random_state=1)
    print(f"Datasets loaded!")
    automl = autosklearn.classification.AutoSklearnClassifier(
        time_left_for_this_task=120,
        per_run_time_limit=120,
        n_jobs=4,
        memory_limit=3072,
        resampling_strategy='cv',
        resampling_strategy_arguments={'folds': 5},
        tmp_folder='/tmp/tmp_folder'

    )
    print(f"Training starts!")
    automl.fit(X_train, y_train)
    y_hat = automl.predict(X_test)

    print("Accuracy score", sklearn.metrics.accuracy_score(y_test, y_hat))
    

    poT = automl.performance_over_time_
    poT.plot(
        x='Timestamp',
        kind='line',
        legend=True,
        title='Auto-sklearn accuracy over time',
        grid=True,
    )
    plt.savefig('automl_run.png')

    print(f"Summary Statistics: {automl.sprint_statistics()}\n")
    print(f"Models: {automl.show_models()}\n")
    print(automl.leaderboard())