def test_transformer_wrapper_function():
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler as StandardScaler
from foreshadow.concrete import StandardScaler as CustomScaler
boston_path = get_file_path("data", "boston_housing.csv")
df = pd.read_csv(boston_path)
custom = CustomScaler()
sklearn = StandardScaler()
custom.fit(df[["crim"]])
sklearn.fit(df[["crim"]])
custom_tf = custom.transform(df[["crim"]])
sklearn_tf = sklearn.transform(df[["crim"]])
assert np.array_equal(custom_tf.values, sklearn_tf)
custom_tf = custom.fit_transform(df[["crim"]])
sklearn_tf = sklearn.fit_transform(df[["crim"]])
assert np.array_equal(custom_tf.values, sklearn_tf)
def test_smarttransformer_function(smart_child):
"""Test overall SmartTransformer functionality
Args:
smart_child: A subclass of SmartTransformer.
"""
import numpy as np
import pandas as pd
from foreshadow.concrete import StandardScaler
boston_path = get_file_path("data", "boston_housing.csv")
df = pd.read_csv(boston_path)
smart = smart_child(cache_manager=CacheManager())
smart_data = smart.fit_transform(df[["crim"]])
std = StandardScaler()
std_data = std.fit_transform(df[["crim"]])
assert smart_data.equals(std_data)
smart.fit(df[["crim"]])
smart_data = smart.transform(df[["crim"]])
std.fit(df[["crim"]])
std_data = std.transform(df[["crim"]])
# TODO, remove when SmartTransformer is no longer wrapped
# Column names will be different, thus np.allclose() is used
assert np.allclose(smart_data, std_data)
def test_transformer_keep_cols():
import pandas as pd
from foreshadow.concrete import StandardScaler as CustomScaler
boston_path = get_file_path("data", "boston_housing.csv")
df = pd.read_csv(boston_path)
custom = CustomScaler(keep_columns=True)
custom_tf = custom.fit_transform(df[["crim"]])
assert custom_tf.shape[1] == 2
def test_transformer_naming_default():
from foreshadow.concrete import StandardScaler
import pandas as pd
boston_path = get_file_path("data", "boston_housing.csv")
df = pd.read_csv(boston_path)
scaler = StandardScaler(keep_columns=False)
out = scaler.fit_transform(df[["crim"]])
assert out.iloc[:, 0].name == "crim"