def test_factorize():
fact = DateFactorizer(cols=['b'], features=("year", "month"))
trans = fact.fit_transform(df)
assert trans.columns.tolist() == ['a', 'b_year', 'b_month']
# Assert that the transform function works independent of fit_transform
assert trans.equals(fact.transform(df))
def test_factorize_attribute_error():
# also show we can handle a non-iterable in features
factorizer = DateFactorizer(cols=['b'], features="yr")
assert_raises(AttributeError, factorizer.fit, df)
def test_factorize_preserve_original():
# keep the original columns
trans = DateFactorizer(cols=['b'],
features=("year", "month"),
drop_original=False).fit_transform(df)
assert trans.columns.tolist() == ['a', 'b', 'b_year', 'b_month']
def test_non_date_factorize():
# Fails since not a date time
assert_raises(ValueError, DateFactorizer(cols=["a", "b"]).fit, df)
def test_date_factorizer_asdf():
assert_transformer_asdf(DateFactorizer(cols=['b']), df)
def test_date_factorizer_persistable():
assert_persistable(DateFactorizer(cols=['b']), location="loc.pkl", X=df)
from datetime import datetime as dt
# #############################################################################
# create data
data = [[1, dt.strptime("06-01-2018 12:00:05", "%m-%d-%Y %H:%M:%S")],
[2, dt.strptime("06-02-2018 13:19:12", "%m-%d-%Y %H:%M:%S")],
[3, dt.strptime("06-03-2018 06:04:17", "%m-%d-%Y %H:%M:%S")],
[4, dt.strptime("06-04-2018 03:56:32", "%m-%d-%Y %H:%M:%S")],
[5, None]]
df = pd.DataFrame.from_records(data, columns=["transaction_id", "time"])
# We can extract a multitude of features from date fields. The default will
# grab the year, month, day and hour
print("Default features:")
print(DateFactorizer(cols=['time']).fit_transform(df))
# we can specify more if we'd like:
print("\n+Minutes, +Seconds:")
print(
DateFactorizer(cols=['time'],
features=("year", "month", "day", "hour", "minute",
"second")).fit_transform(df))
# And we can retain the old (pre-transform) time features if we wanted
print("\nSame as above, but retain old time column:")
print(
DateFactorizer(cols=['time'],
drop_original=False,
features=("year", "month", "day", "hour", "minute",
"second")).fit_transform(df))