def test_foreshadow_param_optimize(): # TODO: Make this test faster
import pickle
import json
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV
from foreshadow.foreshadow import Foreshadow
from foreshadow.preparer import DataPreparer
from foreshadow.optimizers.param_mapping import param_mapping
boston_path = get_file_path("data", "boston_housing.csv")
test_json_path = get_file_path("configs", "optimizer_test.json")
truth_path = get_file_path("configs", "search_space_optimize.pkl")
data = pd.read_csv(boston_path)
js = json.load(open(test_json_path, "r"))
fs = Foreshadow(
DataPreparer(from_json=js),
False,
LinearRegression(),
ProblemType.REGRESSION,
GridSearchCV,
)
fs.pipeline = Pipeline([("preparer", fs.X_preparer),
("estimator", fs.estimator)])
x = data.drop(["medv"], axis=1, inplace=False)
y = data[["medv"]]
x_train, _, y_train, _ = train_test_split(x, y, test_size=0.25)
results = param_mapping(fs.pipeline, x_train, y_train)
# (If you change default configs) or file structure, you will need to
# verify the outputs are correct manually and regenerate the pickle
# truth file.
truth = pickle.load(open(truth_path, "rb"))
assert results[0].keys() == truth[0].keys()
def test_foreshadow_param_optimize_invalid_dict_key():
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from foreshadow.foreshadow import Foreshadow
from foreshadow.preparer import DataPreparer
from foreshadow.cachemanager import CacheManager
boston_path = get_file_path("data", "boston_housing.csv")
data = pd.read_csv(boston_path)
fs = Foreshadow(
DataPreparer(
cache_manager=CacheManager(),
from_json={"combinations": [{
"fake.fake": "[1,2]"
}]},
),
False,
LinearRegression(),
ProblemType.REGRESSION,
GridSearchCV,
)
fs.pipeline = Pipeline([("preprocessor", fs.X_preparer),
("estimator", fs.estimator)])
x = data.drop(["medv"], axis=1, inplace=False)
y = data[["medv"]]
x_train, _, y_train, _ = train_test_split(x, y, test_size=0.25)
with pytest.raises(ValueError) as e:
param_mapping(fs.pipeline, x_train, y_train) # noqa: F821
assert str(e.value) == "Invalid JSON Key fake in {}"
def test_foreshadow_param_optimize_invalid_array_idx():
import json
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from foreshadow.foreshadow import Foreshadow
from foreshadow.preparer import DataPreparer
from foreshadow.cachemanager import CacheManager
boston_path = get_file_path("data", "boston_housing.csv")
test_path = get_file_path("configs", "invalid_optimizer_config.json")
data = pd.read_csv(boston_path)
cfg = json.load(open(test_path, "r"))
fs = Foreshadow(
DataPreparer(CacheManager(), from_json=cfg),
False,
LinearRegression(),
ProblemType.REGRESSION,
GridSearchCV,
)
fs.pipeline = Pipeline([("preprocessor", fs.X_preparer),
("estimator", fs.estimator)])
x = data.drop(["medv"], axis=1, inplace=False)
y = data[["medv"]]
x_train, _, y_train, _ = train_test_split(x, y, test_size=0.25)
with pytest.raises(ValueError) as e:
param_mapping(fs.pipeline, x_train, y_train) # noqa: F821
assert str(e.value).startswith("Attempted to index list")
def test_foreshadow_param_optimize_no_combinations():
import pickle
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from foreshadow.foreshadow import Foreshadow
from foreshadow.preparer import DataPreparer
from foreshadow.cachemanager import CacheManager
boston_path = get_file_path("data", "boston_housing.csv")
test_path = get_file_path("configs", "search_space_no_combo.pkl")
data = pd.read_csv(boston_path)
fs = Foreshadow(
DataPreparer(cache_manager=CacheManager(), from_json={}),
False,
LinearRegression(),
ProblemType.REGRESSION,
GridSearchCV,
)
fs.pipeline = Pipeline([("preprocessor", fs.X_preparer),
("estimator", fs.estimator)])
x = data.drop(["medv"], axis=1, inplace=False)
y = data[["medv"]]
x_train, _, y_train, _ = train_test_split(x, y, test_size=0.25)
results = param_mapping(fs.pipeline, x_train, y_train) # noqa: F821
truth = pickle.load(open(test_path, "rb"))
assert results[0].keys() == truth[0].keys()
