Преемник Neuraxle RandomSearch () - PullRequest
Новая
       82

Преемник Neuraxle RandomSearch ()

0 голосов
/ 18 марта 2020

Я обновил Neuraxle до последней версии (3.4).

Я заметил, что весь auto_ml.py был переделан. Я проверил документацию, но там ничего нет. На git кажется, что метод RandomSearch() долгое время заменялся go на AutoML() метод. Однако параметры разные.

Кто-нибудь знает, как я могу направить пример конвейера Boston Housing на автоматический поиск параметров c в последней версии Neuraxle (3.4)? 

import numpy as np
from sklearn.cluster import KMeans
from sklearn.datasets import load_boston
from sklearn.decomposition import PCA, FastICA
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.linear_model import Ridge
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle

from neuraxle.hyperparams.distributions import RandInt, LogUniform, Boolean
from neuraxle.hyperparams.space import HyperparameterSpace
from neuraxle.metaopt.auto_ml import RandomSearch
from neuraxle.metaopt.random import KFoldCrossValidationWrapper
from neuraxle.pipeline import Pipeline
from neuraxle.steps.numpy import NumpyTranspose
from neuraxle.steps.sklearn import SKLearnWrapper
from neuraxle.union import AddFeatures, ModelStacking


def main():
    boston = load_boston()
    X, y = shuffle(boston.data, boston.target, random_state=13)
    X = X.astype(np.float32)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, shuffle=False)

    # Note that the hyperparameter spaces are defined here during the pipeline definition, but it could be already set
    # within the classes ar their definition if using custom classes, or also it could be defined after declaring the
    # pipeline using a flat dict or a nested dict.

    p = Pipeline([
        AddFeatures([
            SKLearnWrapper(
                PCA(n_components=2),
                HyperparameterSpace({"n_components": RandInt(1, 3)})
            ),
            SKLearnWrapper(
                FastICA(n_components=2),
                HyperparameterSpace({"n_components": RandInt(1, 3)})
            ),
        ]),
        ModelStacking([
            SKLearnWrapper(
                GradientBoostingRegressor(),
                HyperparameterSpace({
                    "n_estimators": RandInt(50, 600), "max_depth": RandInt(1, 10),
                    "learning_rate": LogUniform(0.07, 0.7)
                })
            ),
            SKLearnWrapper(
                KMeans(),
                HyperparameterSpace({"n_clusters": RandInt(5, 10)})
            ),
        ],
            joiner=NumpyTranspose(),
            judge=SKLearnWrapper(
                Ridge(),
                HyperparameterSpace({"alpha": LogUniform(0.7, 1.4), "fit_intercept": Boolean()})
            ),
        )
    ])
    print("Meta-fitting on train:")
    p = p.meta_fit(X_train, y_train, metastep=RandomSearch(
        n_iter=10,
        higher_score_is_better=True,
        validation_technique=KFoldCrossValidationWrapper(scoring_function=r2_score, k_fold=10)
    ))
    # Here is an alternative way to do it, more "pipeliney":
    # p = RandomSearch(
    #     p,
    #     n_iter=15,
    #     higher_score_is_better=True,
    #     validation_technique=KFoldCrossValidation(scoring_function=r2_score, k_fold=3)
    # ).fit(X_train, y_train)

    print("")

    print("Transforming train and test:")
    y_train_predicted = p.predict(X_train)
    y_test_predicted = p.predict(X_test)

    print("")

    print("Evaluating transformed train:")
    score_transform = r2_score(y_train_predicted, y_train)
    print('R2 regression score:', score_transform)

    print("")

    print("Evaluating transformed test:")
    score_test = r2_score(y_test_predicted, y_test)
    print('R2 regression score:', score_test)


if __name__ == "__main__":
    main()
...