def test_numeric_columns(self):
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path, sep=',',
numeric_dtype=np.float32)
xf = OneHotHashVectorizer(
columns={
'edu': 'education',
'in': 'induced',
'sp': 'spontaneous'},
number_of_bits=2)
xf.fit_transform(data)
xf = OneHotHashVectorizer(
columns=[
'education',
'induced',
'spontaneous'],
number_of_bits=2)
xf.fit_transform(data)
True, False, True, False, True, False, True
]))
test_reviews = pandas.DataFrame(data=dict(review=[
"This is great", "I hate it", "Love it", "Really like it", "I hate it",
"I like it a lot", "I love it", "I do like it", "I really hate it",
"I love it"
]))
# OneHotHashVectorizer transform: the entire string is treated as a category.
# if output column name is same as input column, original input column values
# are replaced. number_of_bits=6 will hash into 2^6 -1 dimensions
y = train_reviews['like']
X = train_reviews.loc[:, train_reviews.columns != 'like']
cat = OneHotHashVectorizer(number_of_bits=6) << 'review'
X = cat.fit_transform(X)
# view the transformed numerical values and column names
print(X)
mymodel = LogisticRegressionBinaryClassifier().fit(X, y)
X_test = cat.transform(test_reviews)
scores = mymodel.predict(cat.transform(test_reviews))
# view the scores
print(scores)
###############################################################################
# OneHotHashVectorizer
from nimbusml import FileDataStream
from nimbusml.datasets import get_dataset
from nimbusml.feature_extraction.categorical import OneHotHashVectorizer
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path, sep=',',
dtype={'spontaneous': str
}) # Error with numeric input for ohhv
print(data.head())
# age case education induced parity ... row_num spontaneous ...
# 0 26 1 0-5yrs 1 6 ... 1 2 ...
# 1 42 1 0-5yrs 1 1 ... 2 0 ...
# 2 39 1 0-5yrs 2 6 ... 3 0 ...
# 3 34 1 0-5yrs 2 4 ... 4 0 ...
# 4 35 1 6-11yrs 1 3 ... 5 1 ...
xf = OneHotHashVectorizer(columns={'edu': 'education', 'sp': 'spontaneous'})
# fit and transform
features = xf.fit_transform(data)
print(features.head())
# age case edu.0 edu.1003 ... sp.995 ... spontaneous stratum
# 0 26 1 0.0 0.0 ... 0.0 ... 2.0 1.0
# 1 42 1 0.0 0.0 ... 0.0 ... 0.0 2.0
# 2 39 1 0.0 0.0 ... 0.0 ... 0.0 3.0