Tpot-使用遗传编程优化机器学习管道的Python自动机器学习工具

from tpot import TPOTClassifier from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split digits = load_digits()
X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target,
                                                    train_size=0.75, test_size=0.25, random_state=42)

tpot = TPOTClassifier(generations=5, population_size=50, verbosity=2, random_state=42)
tpot.fit(X_train, y_train)
print(tpot.score(X_test, y_test))
tpot.export('tpot_digits_pipeline.py')

import numpy as np import pandas as pd from sklearn.ensemble import RandomForestClassifier from sklearn.linear_model import LogisticRegression from sklearn.model_selection import train_test_split from sklearn.pipeline import make_pipeline, make_union from sklearn.preprocessing import PolynomialFeatures from tpot.builtins import StackingEstimator from tpot.export_utils import set_param_recursive # NOTE: Make sure that the outcome column is labeled 'target' in the data file tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1)
training_features, testing_features, training_target, testing_target = \
            train_test_split(features, tpot_data['target'], random_state=42)

# Average CV score on the training set was: 0.9799428471757372 exported_pipeline = make_pipeline(
    PolynomialFeatures(degree=2, include_bias=False, interaction_only=False),
    StackingEstimator(estimator=LogisticRegression(C=0.1, dual=False, penalty="l1")),
    RandomForestClassifier(bootstrap=True, criterion="entropy", max_features=0.35000000000000003, min_samples_leaf=20, min_samples_split=19, n_estimators=100)
)
# Fix random state for all the steps in exported pipeline set_param_recursive(exported_pipeline.steps, 'random_state', 42)

exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)

from tpot import TPOTRegressor from sklearn.datasets import load_boston from sklearn.model_selection import train_test_split housing = load_boston()
X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target,
                                                    train_size=0.75, test_size=0.25, random_state=42)

tpot = TPOTRegressor(generations=5, population_size=50, verbosity=2, random_state=42)
tpot.fit(X_train, y_train)
print(tpot.score(X_test, y_test))
tpot.export('tpot_boston_pipeline.py')

import numpy as np import pandas as pd from sklearn.ensemble import ExtraTreesRegressor from sklearn.model_selection import train_test_split from sklearn.pipeline import make_pipeline from sklearn.preprocessing import PolynomialFeatures from tpot.export_utils import set_param_recursive # NOTE: Make sure that the outcome column is labeled 'target' in the data file tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1)
training_features, testing_features, training_target, testing_target = \
            train_test_split(features, tpot_data['target'], random_state=42)

# Average CV score on the training set was: -10.812040755234403 exported_pipeline = make_pipeline(
    PolynomialFeatures(degree=2, include_bias=False, interaction_only=False),
    ExtraTreesRegressor(bootstrap=False, max_features=0.5, min_samples_leaf=2, min_samples_split=3, n_estimators=100)
)
# Fix random state for all the steps in exported pipeline set_param_recursive(exported_pipeline.steps, 'random_state', 42)

exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)