def test_check_estimator_ColumnDuplicator_pairs(self):
df = pandas.DataFrame(
data=dict(tokens1=['one_' + str(i) for i in range(8)],
tokens2=['two_' + str(i) for i in range(8)]))
cd = ColumnDuplicator() << {'tokens3': 'tokens1', 'tokens4': 'tokens1'}
y = cd.fit_transform(df)
sum = 0
for v in y.values:
for c in str(v):
sum = sum + ord(c)
assert_equal(sum, 19920, "sum of chars should be %s" % 19920)
def test_averagedperceptron_unsupported_losses_syntax(self):
df = get_dataset("infert").as_df().drop('row_num', axis=1)
X = df
y = df['case']
pipeline = Pipeline([
OneHotVectorizer(columns={
'age1': 'age',
'parity1': 'parity',
'sp1': 'spontaneous'
}),
OneHotVectorizer(columns={'education_str': 'education_str'}),
ColumnDuplicator(columns={'case2': 'case'}),
AveragedPerceptronBinaryClassifier(
feature=['age1', 'education_str'], label='case')
])
try:
model = pipeline.fit(X, y, verbose=0)
raise AssertionError("same column name in X and y")
except RuntimeError as e:
assert "If any step in the pipeline has defined Label" in str(e)
X = X.drop('case', axis=1)
pipeline = Pipeline([
OneHotVectorizer(columns={
'age1': 'age',
'parity1': 'parity',
'sp1': 'spontaneous'
}),
OneHotVectorizer(columns={'education_str': 'education_str'}),
# ColumnDuplicator(columns={'case2': 'case'}), # does not work
AveragedPerceptronBinaryClassifier(
feature=['age1', 'education_str'], label='case')
])
info = pipeline.get_fit_info(df)[0]
assert info[-1]['inputs'] != ['Feature:Features', 'Label:case']
model = pipeline.fit(df)
y_pred_withpipeline = model.predict(X)
assert set(y_pred_withpipeline.columns) == {
'PredictedLabel', 'Probability', 'Score'
}
assert y_pred_withpipeline.shape == (248, 3)
'ColumnSelector'
}
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() << {
###############################################################################
# ColumnDuplicator
import pandas
from nimbusml.preprocessing.schema import ColumnDuplicator
df = pandas.DataFrame(data=dict(tokens1=['one_' + str(i) for i in range(8)],
tokens2=['two_' + str(i) for i in range(8)]))
# duplicate a column
cd = ColumnDuplicator() << {'tokens3': 'tokens1'}
y = cd.fit_transform(df)
# view the three columns
print(y)
###############################################################################
# ColumnDuplicator
from nimbusml import FileDataStream
from nimbusml.datasets import get_dataset
from nimbusml.preprocessing.schema import ColumnDuplicator
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path, sep=',')
# transform usage
xf = ColumnDuplicator(
columns={
'education_copy': 'education',
'age_copy': 'age'})
# fit and transform
features = xf.fit_transform(data)
# print features
print(features.head())
# age age_copy case education education_copy induced parity ...
# 0 26 26 1 0-5yrs 0-5yrs 1 6 ...
# 1 42 42 1 0-5yrs 0-5yrs 1 1 ...
# 2 39 39 1 0-5yrs 0-5yrs 2 6 ...
# 3 34 34 1 0-5yrs 0-5yrs 2 4 ...
# 4 35 35 1 6-11yrs 6-11yrs 1 3 ...