def test_foreshadow_y_preparer(mocker):
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from foreshadow.foreshadow import Foreshadow
import pandas as pd
np.random.seed(0)
y_pipeline = Pipeline([("yohe", StandardScaler())])
setattr(y_pipeline, "pipeline", y_pipeline)
estimator = LinearRegression()
X = pd.DataFrame(np.array([0] * 50 + [1] * 50).reshape((-1, 1)),
columns=["col1"])
y = pd.DataFrame(np.random.normal(100, 10, 100).reshape((-1, 1)),
columns=["y"])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1)
# Let foreshadow set to defaults, we will overwrite them
y_preparer = mocker.PropertyMock(return_value=y_pipeline)
mocker.patch.object(Foreshadow, "y_preparer", y_preparer)
foreshadow = Foreshadow(problem_type=ProblemType.REGRESSION,
estimator=estimator)
foreshadow.fit(X_train, y_train)
foreshadow_predict = foreshadow.predict(X_test)
foreshadow_score = foreshadow.score(X_test, y_test)
expected_predict = np.array([
[102.19044770619593],
[102.19044770619593],
[102.19044770619593],
[100.05275170774354],
[102.19044770619593],
[102.19044770619593],
[102.19044770619593],
[102.19044770619593],
[100.05275170774354],
[100.05275170774354],
])
expected_score = -0.3576910440975052
assert np.allclose(foreshadow_predict, expected_predict)
assert np.allclose(foreshadow_score, expected_score)
def test_foreshadow_predict_before_fit():
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from foreshadow.foreshadow import Foreshadow
np.random.seed(0)
estimator = LinearRegression()
X = np.arange(200).reshape((-1, 2))
y = np.random.normal(0, 1, 100).reshape((-1, 1))
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1)
foreshadow = Foreshadow(problem_type=ProblemType.REGRESSION,
estimator=estimator)
with pytest.raises(ValueError) as e:
_ = foreshadow.predict(X_test)
assert str(e.value) == "Foreshadow has not been fit yet"
def test_core_foreshadow_example_regression():
import numpy as np
import pandas as pd
from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
from foreshadow.foreshadow import Foreshadow
np.random.seed(0)
boston = load_boston()
bostonX_df = pd.DataFrame(boston.data, columns=boston.feature_names)
bostony_df = pd.DataFrame(boston.target, columns=["target"])
X_train, X_test, y_train, y_test = train_test_split(bostonX_df,
bostony_df,
test_size=0.2)
model = Foreshadow(estimator=LinearRegression(),
problem_type=ProblemType.REGRESSION)
model.fit(X_train, y_train)
score = r2_score(y_test, model.predict(X_test))
print("Boston score: %f" % score)
def test_core_foreshadow_example_classification():
import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import f1_score
from sklearn.model_selection import train_test_split
from foreshadow.foreshadow import Foreshadow
np.random.seed(0)
iris = load_iris()
irisX_df = pd.DataFrame(iris.data, columns=iris.feature_names)
irisy_df = pd.DataFrame(iris.target, columns=["target"])
X_train, X_test, y_train, y_test = train_test_split(irisX_df,
irisy_df,
test_size=0.2)
model = Foreshadow(estimator=LogisticRegression(),
problem_type=ProblemType.CLASSIFICATION)
model.fit(X_train, y_train)
score = f1_score(y_test, model.predict(X_test), average="weighted")
print("Iris score: %f" % score)
