def test_regular_df_X_y():
# autofeat with df without column names
X, target = get_random_data()
afreg = AutoFeatRegressor(verbose=1, feateng_steps=3)
df = afreg.fit_transform(pd.DataFrame(X), pd.DataFrame(target))
# score once with original, once with transformed data
assert afreg.score(pd.DataFrame(X), target) >= 0.999, "R^2 should be 1."
assert afreg.score(df, target) >= 0.999, "R^2 should be 1."
assert list(df.columns)[:3] == ["0", "1", "2"], "Wrong column names"
def test_regular_X_y():
# autofeat with numpy arrays
X, target = get_random_data()
afreg = AutoFeatRegressor(verbose=1, feateng_steps=3)
df = afreg.fit_transform(X, target)
assert afreg.score(X, target) >= 0.999, "R^2 should be 1."
assert afreg.score(df, target) >= 0.999, "R^2 should be 1."
assert list(df.columns)[:3] == ["x000", "x001",
"x002"], "Wrong column names"
def test_weird_colnames():
# autofeat with df with weird column names
X, target = get_random_data()
afreg = AutoFeatRegressor(verbose=1, feateng_steps=3)
df = afreg.fit_transform(pd.DataFrame(X, columns=["x 1.1", 2, "x/3"]),
pd.DataFrame(target))
assert afreg.score(pd.DataFrame(X, columns=["x 1.1", 2, "x/3"]),
target) >= 0.999, "R^2 should be 1."
assert list(df.columns)[:3] == ["x 1.1", "2", "x/3"], "Wrong column names"
# error if the column names aren't the same as before
try:
afreg.score(pd.DataFrame(X, columns=["x 11", 2, "x/3"]), target)
except ValueError:
pass
else:
raise AssertionError("Should throw error on mismatch column names")
def test_categorical_cols():
np.random.seed(15)
x1 = np.random.rand(1000)
x2 = np.random.randn(1000)
x3 = np.random.rand(1000)
x4 = np.array(200 * [4] + 300 * [5] + 500 * [2], dtype=int)
target = 2 + 15 * x1 + 3 / (x2 - 1 / x3) + 5 * (x2 + np.log(x1))**3 + x4
X = np.vstack([x1, x2, x3, x4]).T
afreg = AutoFeatRegressor(verbose=1,
categorical_cols=["x4", "x5"],
feateng_steps=3)
try:
df = afreg.fit_transform(
pd.DataFrame(X, columns=["x1", "x2", "x3", "x4"]), target)
except ValueError:
pass
else:
raise AssertionError(
"categorical_cols not in df should throw an error")
afreg = AutoFeatRegressor(verbose=1,
categorical_cols=["x4"],
feateng_steps=3)
df = afreg.fit_transform(pd.DataFrame(X, columns=["x1", "x2", "x3", "x4"]),
target)
assert list(df.columns)[3:6] == [
"cat_x4_2.0", "cat_x4_4.0", "cat_x4_5.0"
], "categorical_cols were not transformed correctly"
assert "x4" not in df.columns, "categorical_cols weren't deleted from df"
df = afreg.transform(pd.DataFrame(X, columns=["x1", "x2", "x3", "x4"]))
assert list(df.columns)[3:6] == [
"cat_x4_2.0", "cat_x4_4.0", "cat_x4_5.0"
], "categorical_cols were not transformed correctly"
assert "x4" not in df.columns, "categorical_cols weren't deleted from df"
assert afreg.score(pd.DataFrame(X, columns=["x1", "x2", "x3", "x4"]),
target) >= 0.999, "R^2 should be 1."
def test_units():
np.random.seed(15)
x1 = np.random.rand(1000)
x2 = np.random.randn(1000)
x3 = np.random.rand(1000)
target = 2 + 15 * x1 + 3 / (x2 - 1 / x3) + 5 * (x2 * np.log(x1))**3
X = np.vstack([x1, x2, x3]).T
units = {"x2": "m/sec", "x3": "min/mm"}
afreg = AutoFeatRegressor(verbose=1, units=units, feateng_steps=3)
_ = afreg.fit_transform(pd.DataFrame(X, columns=["x1", "x2", "x3"]),
target)
assert afreg.score(pd.DataFrame(X, columns=["x1", "x2", "x3"]),
target) >= 0.999, "R^2 should be 1."
from autofeat import FeatureSelector, AutoFeatRegressor
from sklearn.pipeline import make_pipeline
import pickle
def main():
# Get the dataset from the users GitHub repository
dataset_path = "https://raw.githubusercontent.com/" + os.environ["GITHUB_REPOSITORY"] +"/master/dataset.csv"
df = pd.read_csv(dataset_path)
print()
print(df.describe())
for steps in range(5):
np.random.seed(55)
print("### AutoFeat with %i feateng_steps" % steps)
afreg = AutoFeatRegressor(verbose=1, feateng_steps=steps)
df = afreg.fit_transform(df_org, target)
r2 = afreg.score(df_org, target)
print("## Final R^2: %.4f" % r2)
plt.figure()
plt.scatter(afreg.predict(df_org), target, s=2);
plt.title("%i FE steps (R^2: %.4f; %i new features)" % (steps, r2, len(afreg.new_feat_cols_)))
afreg = AutoFeatRegressor(verbose=1, feateng_steps=3)
# train on noisy data
df = afreg.fit_transform(df_org, target_noisy)
# test on real targets
print("Final R^2: %.4f" % afreg.score(df, target))
plt.figure()
plt.scatter(afreg.predict(df), target, s=2);
afreg = AutoFeatRegressor(verbose=1, feateng_steps=3)
# train on noisy data
df = afreg.fit_transform(df_org, target_very_noisy)
# test on real targets