automl.py

import autosklearn.classification
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
import numpy as np

classes = {
    "CYT": 0,
    "NUC": 1,
    "MIT": 2,
    "ME3": 3,
    "ME2": 4,
    "ME1": 5,
    "EXC": 6,
    "VAC": 7,
    "POX": 8,
    "ERL": 9
}

v = np.genfromtxt("./yeast.data", dtype="|U5", autostrip=True)

X = np.asarray(v[:, 1:-1], dtype=np.float64)
y = [classes[k] for k in v[:, -1]]

X_train, X_test, y_train, y_test = \
sklearn.model_selection.train_test_split(X, y, random_state=1)
automl = autosklearn.classification.AutoSklearnClassifier(time_left_for_this_task=60 * 5)
automl.fit(X_train, y_train)
y_hat = automl.predict(X_test)
print(automl.show_models())
print("Accuracy score", sklearn.metrics.accuracy_score(y_test, y_hat))