def test_holidays(self):
df = pandas.DataFrame(
data=dict(tokens1=[1, 2, 3, 157161600], tokens2=[10, 11, 12, 13]))
cols_to_drop = [
'dtHour12', 'dtDayOfWeek', 'dtDayOfQuarter', 'dtDayOfYear',
'dtWeekOfMonth', 'dtQuarterOfYear', 'dtHalfOfYear', 'dtWeekIso',
'dtYearIso', 'dtMonthLabel', 'dtAmPmLabel', 'dtDayOfWeekLabel',
'dtIsPaidTimeOff'
]
dts = DateTimeSplitter(prefix='dt', country='Canada') << 'tokens1'
pipeline = Pipeline([dts, ColumnSelector(drop_columns=cols_to_drop)])
y = pipeline.fit_transform(df)
self.assertEqual(y.loc[3, 'dtHolidayName'], 'Christmas Day')
from nimbusml import Pipeline
from nimbusml.preprocessing import DateTimeSplitter
from nimbusml.preprocessing.schema import ColumnSelector
df = pandas.DataFrame(data=dict(
tokens1=[1, 2, 3, 157161600],
tokens2=[10, 11, 12, 13]
))
cols_to_drop = [
'dtHour12', 'dtDayOfWeek', 'dtDayOfQuarter',
'dtDayOfYear', 'dtWeekOfMonth', 'dtQuarterOfYear',
'dtHalfOfYear', 'dtWeekIso', 'dtYearIso', 'dtMonthLabel',
'dtAmPmLabel', 'dtDayOfWeekLabel', 'dtIsPaidTimeOff'
]
dts = DateTimeSplitter(prefix='dt', country='Canada') << 'tokens1'
pipeline = Pipeline([dts, ColumnSelector(drop_columns=cols_to_drop)])
y = pipeline.fit_transform(df)
# view the three columns
pandas.set_option('display.max_columns', None)
pandas.set_option('display.width', 1000)
print(y)
# tokens1 tokens2 dtYear dtMonth dtDay dtHour dtMinute dtSecond dtAmPm dtHolidayName
# 0 1 10 1970 1 1 0 0 1 0 New Year's Day
# 1 2 11 1970 1 1 0 0 2 0 New Year's Day
# 2 3 12 1970 1 1 0 0 3 0 New Year's Day
# 3 157161600 13 1974 12 25 0 0 0 0 Christmas Day
INSTANCES = {
'AveragedPerceptronBinaryClassifier': AveragedPerceptronBinaryClassifier(
feature=['education_str.0-5yrs', 'education_str.6-11yrs', 'education_str.12+ yrs']),
'Binner': Binner(num_bins=3),
'CharTokenizer': CharTokenizer(columns={'SentimentText_Transform': 'SentimentText'}),
'ColumnConcatenator': ColumnConcatenator(columns={'Features': [
'Sepal_Length',
'Sepal_Width',
'Petal_Length',
'Petal_Width',
'Setosa']}),
'ColumnSelector': ColumnSelector(columns=['Sepal_Width', 'Sepal_Length']),
'ColumnDuplicator': ColumnDuplicator(columns={'dup': 'Sepal_Width'}),
'CountSelector': CountSelector(count=5, columns=['Sepal_Width']),
'DateTimeSplitter': DateTimeSplitter(prefix='dt'),
'FastForestBinaryClassifier': FastForestBinaryClassifier(feature=['Sepal_Width', 'Sepal_Length'],
label='Setosa'),
'FastLinearBinaryClassifier': FastLinearBinaryClassifier(feature=['Sepal_Width', 'Sepal_Length'],
label='Setosa'),
'FastTreesTweedieRegressor': FastTreesTweedieRegressor(label='Ozone'),
'Filter': Filter(columns=[ 'Petal_Length', 'Petal_Width']),
'FromKey': Pipeline([
ToKey(columns=['Sepal_Length']),
FromKey(columns=['Sepal_Length'])
]),
# GlobalContrastRowScaler currently requires a vector input to work
'GlobalContrastRowScaler': Pipeline([
ColumnConcatenator() << {
'concated_columns': [
'Petal_Length',
###############################################################################
# DateTimeSplitter
import pandas as pd
from nimbusml import FileDataStream
from nimbusml.datasets import get_dataset
from nimbusml.preprocessing import DateTimeSplitter
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path, sep=',')
# transform usage
xf = DateTimeSplitter(prefix='dt_') << 'age'
# fit and transform
features = xf.fit_transform(data)
features = features.drop([
'row_num', 'education', 'parity', 'induced', 'case', 'spontaneous',
'stratum', 'pooled.stratum'
],
axis=1)
# print features
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 1000)
print(features.head())
# age dt_Year dt_Month dt_Day dt_Hour dt_Minute dt_Second dt_AmPm dt_Hour12 dt_DayOfWeek dt_DayOfQuarter dt_DayOfYear dt_WeekOfMonth dt_QuarterOfYear dt_HalfOfYear dt_WeekIso dt_YearIso dt_MonthLabel dt_AmPmLabel dt_DayOfWeekLabel dt_HolidayName dt_IsPaidTimeOff
# 0 26 1970 1 1 0 0 26 0 0 4 1 0 0 1 1 1 1970 January am Thursday None 0
# 1 42 1970 1 1 0 0 42 0 0 4 1 0 0 1 1 1 1970 January am Thursday None 0
'check_estimators_pickle')
OMITTED_CHECKS_ALWAYS = 'check_estimators_nan_inf'
NOBINARY_CHECKS = [
'check_estimator_sparse_data', 'check_dtype_object',
'check_fit_score_takes_y', 'check_fit2d_predict1d', 'check_fit1d_1feature',
'check_dont_overwrite_parameters', 'check_supervised_y_2d',
'check_estimators_fit_returns_self', 'check_estimators_overwrite_params',
'check_estimators_dtypes', 'check_classifiers_classes',
'check_classifiers_train'
]
INSTANCES = {
'DateTimeSplitter':
DateTimeSplitter(prefix='dt', columns=['F0']),
'EnsembleClassifier':
EnsembleClassifier(num_models=3),
'EnsembleRegressor':
EnsembleRegressor(num_models=3),
'FactorizationMachineBinaryClassifier':
FactorizationMachineBinaryClassifier(shuffle=False),
'KMeansPlusPlus':
KMeansPlusPlus(n_clusters=2),
'LightGbmBinaryClassifier':
LightGbmBinaryClassifier(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'LightGbmClassifier':
LightGbmClassifier(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'LightGbmRegressor':
def test_check_estimator_DateTimeSplitter(self):
df = pandas.DataFrame(data=dict(dt=[i for i in range(8)]))
dt = DateTimeSplitter(prefix='dt_') << 'dt'
result = dt.fit_transform(df)
assert_equal(result['dt_Year'][0], 1970,
"it should have been year of 1970")