# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
OnlineGradientDescentRegressor(feature=['parity', 'edu'], label='age')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# Score
# 0 28.103731
# 1 21.805904
# 2 28.103731
# 3 25.584600
# 4 33.743286
# print evaluation metrics
}
if show_individual_predictions:
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r1.fit(train_df)
result = r1.predict(test_df)
print(result)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r2.fit(train_df)
result = r2.predict(test_df)
print(result)
r3 = LightGbmRegressor(**lgbmArgs)
r3.fit(train_df)
result = r3.predict(test_df)
print(result)
# Perform a prediction using an ensemble
# of all three of the above predictors.
r1 = OrdinaryLeastSquaresRegressor(**olsrArgs)
r2 = OnlineGradientDescentRegressor(**ogdArgs)
r3 = LightGbmRegressor(**lgbmArgs)
pipeline = Pipeline(
[VotingRegressor(estimators=[r1, r2, r3], combiner='Average')])
pipeline.fit(train_df)
result = pipeline.predict(test_df)
print(result)
sep=',',
numeric_dtype=numpy.float32,
names={
0: 'row_num',
5: 'case'
})
print(data.head())
# age case education induced parity pooled.stratum row_num ...
# 0 26.0 1.0 0-5yrs 1.0 6.0 3.0 1.0 ...
# 1 42.0 1.0 0-5yrs 1.0 1.0 1.0 2.0 ...
# 2 39.0 1.0 0-5yrs 2.0 6.0 4.0 3.0 ...
# 3 34.0 1.0 0-5yrs 2.0 4.0 2.0 4.0 ...
# 4 35.0 1.0 6-11yrs 1.0 3.0 32.0 5.0 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
FastForestBinaryClassifier(feature=['age', 'edu', 'induced'], label='case')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score
# 0 0.0 -26.985743
# 1 0.0 -26.562090
# 2 0.0 -24.832508
# 3 0.0 -23.799389
# 4 0.0 -19.612534
# print evaluation metrics
def test_example_success(self):
like = [
True, False, True, False, True, False, True, False, True, False,
True, False, True, False, True, False, True, False, True, False,
True, False, True, False, True
]
x1 = [(5. if _ else 4.) for _ in like]
x2 = [(-5. if _ else -4.) for _ in like]
x1[0] = 50
x2[1] = 50
x2[2] = 50
train_data = pandas.DataFrame(data=dict(like=like, x1=x2, x2=x2),
dtype=numpy.float32)
X = train_data.drop('like', axis=1)
y = train_data[['like']]
transform_2 = MutualInformationSelector()
exp = Pipeline([transform_2])
res = exp.fit_transform(X, y)
assert res is not None
transform_2 = MutualInformationSelector(slots_in_output=2)
pipe = Pipeline([transform_2])
res = pipe.fit_transform(X, y)
assert res is not None
transform_2 = MutualInformationSelector() << {
Role.Feature: ['x1', 'x2'],
Role.Label: 'like'
}
assert transform_2._allowed_roles == {'Label'}
assert transform_2.label_column == 'like'
assert transform_2.input == ['x1', 'x2']
assert transform_2.output == ['Feature']
exp = Pipeline([transform_2])
res = exp.fit_transform(train_data)
assert res is not None
transform_2 = MutualInformationSelector() << {
"zoo": ['x1', 'x2'],
Role.Label: 'like'
}
assert transform_2._allowed_roles == {'Label'}
assert transform_2.label_column == 'like'
assert transform_2.input == ['x1', 'x2']
assert transform_2.output == ['zoo']
exp = Pipeline([transform_2])
res = exp.fit_transform(train_data)
assert res is not None
transform_2 = MutualInformationSelector() << {
"zoo": ['x1'],
Role.Label: 'like'
}
assert transform_2._allowed_roles == {'Label'}
assert transform_2.label_column == 'like'
assert transform_2.input == ['x1']
assert transform_2.output == ['zoo']
exp = Pipeline([transform_2])
res = exp.fit_transform(train_data)
assert res is not None
transform_2 = MutualInformationSelector(slots_in_output=1,
columns=['x1'],
label='like')
assert transform_2._allowed_roles == {'Label'}
assert transform_2.label_column == 'like'
assert transform_2.input == ['x1']
assert transform_2.output == ['x1']
pipe = Pipeline([transform_2])
pipe.fit(train_data)
res = pipe.transform(train_data)
assert res is not None
from nimbusml import Pipeline
from nimbusml.datasets.image import get_RevolutionAnalyticslogo, get_Microsoftlogo
from nimbusml.feature_extraction.image import Loader, Resizer, PixelExtractor
from nimbusml.linear_model import FastLinearBinaryClassifier
data = pandas.DataFrame(
data=dict(Path=[get_RevolutionAnalyticslogo(),
get_Microsoftlogo()],
Label=[True, False]))
X = data[['Path']]
y = data[['Label']]
# define the training pipeline
pipeline = Pipeline([
Loader(columns={'ImgPath': 'Path'}),
Resizer(image_width=32, image_height=32, columns={'ImgResize': 'ImgPath'}),
PixelExtractor(columns={'ImgPixels': 'ImgResize'}),
FastLinearBinaryClassifier(feature='ImgPixels')
])
# train
pipeline.fit(X, y)
# predict
scores = pipeline.predict(X)
print("Predicted Labels:", scores.PredictedLabel.values)
# Predicted Labels : [True False]
print("Accuracy:", np.mean(y.Label.values == scores.PredictedLabel.values))
# Accuracy : 1
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
LightGbmBinaryClassifier(feature=['induced', 'edu'],
label='case',
booster=Goss(top_rate=0.9))
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data, 'case').test(data,
output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Probability Score
# 0 1 0.612220 0.913309
# 1 1 0.612220 0.913309
# 2 0 0.334486 -1.375929
# 3 0 0.334486 -1.375929
# 4 0 0.421264 -0.635176
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
KMeansPlusPlus(n_clusters=5, feature=['induced', 'edu', 'parity'])
])
# train, predict, and evaluate
metrics, predictions = pipeline \
.fit(data) \
.test(data, 'induced', output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score.0 Score.1 Score.2 Score.3 Score.4
# 0 4 2.732253 2.667988 2.353899 2.339244 0.092014
# 1 4 2.269290 2.120064 2.102576 2.222578 0.300347
# 2 4 3.482253 3.253153 2.425328 2.269245 0.258680
# 3 4 3.130401 2.867317 2.158132 2.055911 0.175347
# 4 2 0.287809 2.172567 0.036439 2.102578 2.050347
def test_pipeline_clone_dataframe_transforms(self):
pipe = Pipeline([
OneHotVectorizer(columns={'onehot': 'group_2'})
])
fit_transform_clone_and_check(pipe, df)
def test_pipeline_clone_filedatastream_transforms(self):
pipe = Pipeline([
OneHotVectorizer(columns={'onehot': 'group_2'})
])
fit_transform_clone_and_check(pipe, fds)
# data input (as a FileDataStream)
path = get_dataset('timeseries').as_filepath()
data = FileDataStream.read_csv(path)
print(data.head())
# t1 t2 t3
# 0 0.01 0.01 0.0100
# 1 0.02 0.02 0.0200
# 2 0.03 0.03 0.0200
# 3 0.03 0.03 0.0250
# 4 0.03 0.03 0.0005
# define the training pipeline
pipeline = Pipeline([
SsaChangePointDetector(columns={'t2_cp': 't2'},
change_history_length=4,
training_window_size=8,
seasonal_window_size=3)
])
result = pipeline.fit_transform(data)
print(result)
# t1 t2 t3 t2_cp.Alert t2_cp.Raw Score t2_cp.P-Value Score t2_cp.Martingale Score
# 0 0.01 0.01 0.0100 0.0 -0.111334 5.000000e-01 0.001213
# 1 0.02 0.02 0.0200 0.0 -0.076755 4.862075e-01 0.001243
# 2 0.03 0.03 0.0200 0.0 -0.034871 3.856320e-03 0.099119
# 3 0.03 0.03 0.0250 0.0 -0.012559 8.617091e-02 0.482400
# 4 0.03 0.03 0.0005 0.0 -0.015723 2.252377e-01 0.988788
# 5 0.03 0.05 0.0100 0.0 -0.001133 1.767711e-01 2.457946
# 6 0.05 0.07 0.0500 0.0 0.006265 9.170460e-02 0.141898
# 7 0.07 0.09 0.0900 0.0 0.002383 2.701134e-01 0.050747
from nimbusml.datasets import get_dataset
from nimbusml.feature_extraction.text import NGramFeaturizer
from nimbusml.feature_extraction.text.extractor import Ngram
from nimbusml.naive_bayes import NaiveBayesClassifier
from nimbusml.utils import get_X_y
from sklearn.model_selection import train_test_split
# use 'wiki_detox_train' data set to create test and train data
# Sentiment SentimentText
# 1 ==RUDE== Dude, you are rude upload that carl picture back, or else.
# 1 == OK! == IM GOING TO VANDALIZE WILD ONES WIKI THEN!!!
np.random.seed(0)
train_file = get_dataset("wiki_detox_train").as_filepath()
(train, label) = get_X_y(train_file, label_column='Sentiment', sep='\t')
X_train, X_test, y_train, y_test = train_test_split(train, label)
# map text reviews to vector space
texttransform = NGramFeaturizer(
word_feature_extractor=Ngram(),
vector_normalizer='None') << 'SentimentText'
nb = NaiveBayesClassifier(feature=['SentimentText'])
ppl = Pipeline([texttransform, nb])
ppl.fit(X_train, y_train)
# evaluate the model
metrics, scores = ppl.test(X_test, y_test, output_scores=True)
print(metrics)
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
SgdBinaryClassifier(feature=['parity', 'edu'], label='case')
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Probability Score
# 0 0 0.363427 -0.560521
# 1 0 0.378848 -0.494439
# 2 0 0.363427 -0.560521
# 3 0 0.369564 -0.534088
# 4 0 0.336350 -0.679603
# print evaluation metrics
print(metrics)
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
LightGbmClassifier(feature=['parity', 'edu'],
label='induced',
booster=Dart(reg_lambda=0.1))
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score.0 Score.1 Score.2
# 0 2 0.070722 0.145439 0.783839
# 1 0 0.737733 0.260116 0.002150
# 2 2 0.070722 0.145439 0.783839
# 3 0 0.490715 0.091749 0.417537
# 4 0 0.562419 0.197818 0.239763
# print evaluation metrics
# LightGbmRanker
import numpy as np
from nimbusml import Pipeline, FileDataStream
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import LightGbmRanker
# data input (as a FileDataStream)
path = get_dataset('gen_tickettrain').as_filepath()
# LightGbmRanker requires key type for group column
data = FileDataStream.read_csv(path, dtype={'group': np.uint32})
# define the training pipeline
pipeline = Pipeline([
LightGbmRanker(feature=['Class', 'dep_day', 'duration'],
label='rank',
group_id='group')
])
# train, predict, and evaluate.
metrics, predictions = pipeline \
.fit(data) \
.test(data, output_scores=True)
# print predictions
print(predictions.head())
# Score
# 0 -0.124121
# 1 -0.124121
# 2 -0.124121
# 3 -0.376062
def test_pass_decision_function_multiclass_with_pipeline(self):
assert_almost_equal(decfun_sum(Pipeline([NaiveBayesClassifier()])),
-96.87325,
decimal=4,
err_msg=invalid_decision_function_output)
def test_pipeline_clone_filedatastream_transforms_shift_operator(self):
pipe = Pipeline([
OneHotVectorizer() << {'onehot': 'group_2'}
])
fit_transform_clone_and_check(pipe, fds)
def test_fail_decision_function_multiclass_with_pipeline(self):
check_unsupported_decision_function(
self, Pipeline([LogisticRegressionClassifier()]), X_train, y_train,
X_test)
###############################################################################
# Pipeline
import numpy as np
import pandas as pd
from nimbusml import Pipeline, FileDataStream
from nimbusml.linear_model import FastLinearRegressor
from nimbusml.preprocessing.normalization import MeanVarianceScaler
X = np.array([[1, 2.0], [2, 4], [3, 0.7]])
Y = np.array([2, 3, 1.5])
df = pd.DataFrame(dict(y=Y, x1=X[:, 0], x2=X[:, 1]))
pipe = Pipeline([
MeanVarianceScaler(),
FastLinearRegressor()
])
# fit with pandas dataframe
pipe.fit(X, Y)
# Fit with FileDataStream
df.to_csv('data.csv', index=False)
ds = FileDataStream.read_csv('data.csv', sep=',')
pipe = Pipeline([
MeanVarianceScaler(),
FastLinearRegressor()
])
pipe.fit(ds, 'y')
print(pipe.summary())
from nimbusml.linear_model import AveragedPerceptronBinaryClassifier
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
AveragedPerceptronBinaryClassifier(
feature=['age', 'parity', 'spontaneous'], label='case')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score
# 0 0 -0.285667
# 1 0 -1.304729
# 2 0 -2.651955
# 3 0 -2.111450
# 4 0 -0.660658
# print evaluation metrics
from nimbusml.timeseries import IidChangePointDetector
# data input (as a FileDataStream)
path = get_dataset('timeseries').as_filepath()
data = FileDataStream.read_csv(path)
print(data.head())
# t1 t2 t3
# 0 0.01 0.01 0.0100
# 1 0.02 0.02 0.0200
# 2 0.03 0.03 0.0200
# 3 0.03 0.03 0.0250
# 4 0.03 0.03 0.0005
# define the training pipeline
pipeline = Pipeline(
[IidChangePointDetector(columns={'t2_cp': 't2'}, change_history_length=4)])
result = pipeline.fit_transform(data)
print(result)
# t1 t2 t3 t2_cp.Alert t2_cp.Raw Score t2_cp.P-Value Score t2_cp.Martingale Score
# 0 0.01 0.01 0.0100 0.0 0.01 5.000000e-01 1.212573e-03
# 1 0.02 0.02 0.0200 0.0 0.02 4.960106e-01 1.221347e-03
# 2 0.03 0.03 0.0200 0.0 0.03 1.139087e-02 3.672914e-02
# 3 0.03 0.03 0.0250 0.0 0.03 2.058296e-01 8.164447e-02
# 4 0.03 0.03 0.0005 0.0 0.03 2.804577e-01 1.373786e-01
# 5 0.03 0.05 0.0100 1.0 0.05 1.448886e-06 1.315014e+04
# 6 0.05 0.07 0.0500 0.0 0.07 2.616611e-03 4.941587e+04
# 7 0.07 0.09 0.0900 0.0 0.09 3.053187e-02 2.752614e+05
# 8 0.09 99.00 99.0000 0.0 99.00 1.000000e-08 1.389396e+12
# 9 1.10 0.10 0.1000 1.0 0.10 3.778296e-01 1.854344e+07
from nimbusml.feature_extraction.categorical import OneHotVectorizer
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
FastTreesRegressor(feature=['induced', 'edu'], label='age')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# Score
# 0 35.171112
# 1 35.171112
# 2 34.118595
# 3 34.118595
# 4 32.484325
# print evaluation metrics
from nimbusml.linear_model import LinearSvmBinaryClassifier
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
LinearSvmBinaryClassifier(feature=['age', 'parity', 'spontaneous'],
label='case')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score Probability
# 0 1 0.688481 0.607060
# 1 0 -2.514992 0.203312
# 2 0 -3.479344 0.129230
# 3 0 -3.016621 0.161422
# 4 0 -0.825512 0.397461
# print evaluation metrics
from nimbusml.preprocessing.schema import ColumnConcatenator
data = pd.DataFrame({'month': ['Jan', 'Feb'], 'year': ['1988', '1978']})
# not concatenated
xf = OneHotVectorizer()
features = xf.fit_transform(data)
print(features.head())
#
# month.Feb month.Jan year.1978 year.1988
# 0 0.0 1.0 0.0 1.0
# 1 1.0 0.0 1.0 0.0
# input columns concatenated into vector type
pipe = Pipeline([
ColumnConcatenator(columns={'f': ['month', 'year']}),
OneHotVectorizer(columns=['f']),
])
features2 = pipe.fit_transform(data)
print(features2.head())
# f.month.1978 f.month.1988 f.month.Feb f.month.Jan f.year.1978 \
# 0 0.0 0.0 0.0 1.0 0.0
# 1 0.0 0.0 1.0 0.0 1.0
#
# f.year.1988 f.year.Feb f.year.Jan month year
# 0 1.0 0.0 0.0 Jan 1988
# 1 0.0 0.0 0.0 Feb 1978
# input columns concatenated, output_kind = "Bag"
pipe = Pipeline([
ColumnConcatenator(columns={'f': ['month', 'year']}),
OneHotVectorizer(columns=['f'], output_kind="Bag"),
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
OrdinaryLeastSquaresRegressor(feature=['parity', 'edu'], label='age')
])
# train, predict, and evaluate
# TODO: Replace with CV
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# Score
# 0 35.188782
# 1 35.363689
# 2 35.188782
# 3 35.258743
# 4 32.818516
def accuracy(ovr):
pipe = Pipeline([ovr])
pipe.fit(X_train, y_train)
metrics, _ = pipe.test(X_train, y_train)
return metrics
def test_fail_predict_proba_multiclass_with_pipeline(self):
check_unsupported_predict_proba(self,
Pipeline([NaiveBayesClassifier()]),
X_train, y_train, X_test)
import pandas as pd
from nimbusml import Pipeline
from nimbusml.ensemble import FastTreesBinaryClassifier
from nimbusml.feature_extraction.categorical import OneHotHashVectorizer, \
OneHotVectorizer
from sklearn.model_selection import GridSearchCV
df = pd.DataFrame(
dict(education=['A', 'A', 'A', 'A', 'B', 'A', 'B'],
workclass=['X', 'Y', 'X', 'X', 'X', 'Y', 'Y'],
y=[1, 0, 1, 1, 0, 1, 0]))
X = df.drop('y', axis=1)
y = df['y']
pipe = Pipeline([
('cat', OneHotVectorizer() << 'education'),
# unnamed step, stays same in grid search
OneHotHashVectorizer() << 'workclass',
# this instance of FastTreesBinaryClassifier with number_of_trees 0 will be
# never run by grid search as its not a part of param_grid below
('learner', FastTreesBinaryClassifier(number_of_trees=0,
number_of_leaves=2))
])
param_grid = dict(cat__output_kind=['Indicator', 'Binary'],
learner__number_of_trees=[1, 2, 3])
grid = GridSearchCV(pipe, param_grid, cv=3, iid='warn')
grid.fit(X, y)
print(grid.best_params_)
# {'cat__output_kind': 'Indicator', 'learner__number_of_trees': 1}
def test_pass_decision_function_binary_with_pipeline(self):
assert_almost_equal(decfun_sum(
Pipeline([FactorizationMachineBinaryClassifier()])),
-30.2316,
decimal=4,
err_msg=invalid_decision_function_output)
data = FileDataStream.read_csv(path)
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 ...
# define the training pipeline
pipeline = Pipeline([
OneHotVectorizer(columns={'edu': 'education'}),
OneVsRestClassifier(
# using a binary classifier + OVR for multiclass dataset
FastTreesBinaryClassifier(),
# True = class probabilities will sum to 1.0
# False = raw scores, unknown range
use_probabilities=True,
feature=['age', 'edu'],
label='induced')
])
# train, predict, and evaluate
metrics, predictions = pipeline.fit(data).test(data, output_scores=True)
# print predictions
print(predictions.head())
# PredictedLabel Score.0 Score.1 Score.2
# 0 2 0.084504 0.302600 0.612897
# 1 0 0.620235 0.379226 0.000538
# 2 2 0.077734 0.061426 0.860840
# data input (as a FileDataStream)
path = get_dataset('timeseries').as_filepath()
data = FileDataStream.read_csv(path)
print(data.head())
# t1 t2 t3
# 0 0.01 0.01 0.0100
# 1 0.02 0.02 0.0200
# 2 0.03 0.03 0.0200
# 3 0.03 0.03 0.0250
# 4 0.03 0.03 0.0005
# define the training pipeline
pipeline = Pipeline([
SsaSpikeDetector(columns={'t2_spikes': 't2'},
pvalue_history_length=4,
training_window_size=8,
seasonal_window_size=3)
])
result = pipeline.fit_transform(data)
print(result)
# t1 t2 t3 t2_spikes.Alert t2_spikes.Raw Score t2_spikes.P-Value Score
# 0 0.01 0.01 0.0100 0.0 -0.111334 5.000000e-01
# 1 0.02 0.02 0.0200 0.0 -0.076755 4.862075e-01
# 2 0.03 0.03 0.0200 0.0 -0.034871 3.856320e-03
# 3 0.03 0.03 0.0250 0.0 -0.012559 8.617091e-02
# 4 0.03 0.03 0.0005 0.0 -0.015723 2.252377e-01
# 5 0.03 0.05 0.0100 0.0 -0.001133 1.767711e-01
# 6 0.05 0.07 0.0500 0.0 0.006265 9.170460e-02
# 7 0.07 0.09 0.0900 0.0 0.002383 2.701134e-01
