def setUpClass(cls):
from sklearn.datasets import load_iris
irisArr = load_iris()
cls._irisArr = {"X": irisArr.data, "y": irisArr.target}
from lale.datasets import sklearn_to_pandas
(train_X, train_y), (test_X, test_y) = sklearn_to_pandas.load_iris_df()
cls._irisDf = {"X": train_X, "y": train_y}
(train_X, train_y), (test_X, test_y) = sklearn_to_pandas.digits_df()
cls._digits = {"X": train_X, "y": train_y}
(train_X,
train_y), (test_X,
test_y) = sklearn_to_pandas.california_housing_df()
cls._housing = {"X": train_X, "y": train_y}
from lale.datasets import openml
(train_X, train_y), (test_X, test_y) = openml.fetch("credit-g",
"classification",
preprocess=False)
cls._creditG = {"X": train_X, "y": train_y}
from lale.datasets import load_movie_review
train_X, train_y = load_movie_review()
cls._movies = {"X": train_X, "y": train_y}
from lale.datasets.uci.uci_datasets import fetch_drugscom
train_X, train_y, test_X, test_y = fetch_drugscom()
cls._drugRev = {"X": train_X, "y": train_y}
def test_text_and_structured(self):
from lale.datasets.uci.uci_datasets import fetch_drugscom
from sklearn.model_selection import train_test_split
train_X_all, train_y_all, test_X, test_y = fetch_drugscom()
#subset to speed up debugging
train_X, train_X_ignore, train_y, train_y_ignore = train_test_split(
train_X_all, train_y_all, train_size=0.01, random_state=42)
from lale.lib.lale import Project
from lale.lib.lale import ConcatFeatures as Cat
from lale.lib.sklearn import TfidfVectorizer as Tfidf
from lale.lib.sklearn import LinearRegression as LinReg
from lale.lib.sklearn import RandomForestRegressor as Forest
prep_text = Project(columns=['review']) >> Tfidf(max_features=100)
prep_nums = Project(columns={'type': 'number'})
planned = (prep_text & prep_nums) >> Cat >> (LinReg | Forest)
from lale.lib.lale import Hyperopt
hyperopt_classifier = Hyperopt(estimator=planned, max_evals=1, scoring='r2')
best_found = hyperopt_classifier.fit(train_X, train_y)