def test_ovr_accuracy(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(number_of_threads=1),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1,
number_of_threads=1),
GamBinaryClassifier(number_of_threads=1),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1,
number_of_threads=1),
FastLinearBinaryClassifier(number_of_threads=1),
SgdBinaryClassifier(number_of_threads=1),
# SymSgdBinaryClassifier(number_of_threads=1),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=True)
metrics = accuracy(ovr)
accu = metrics['Accuracy(micro-avg)'][0]
# algos will have wide range of accuracy, so use low bar. Also
# checks Pipeline + Ova + clf
assert_greater(
accu, 0.65,
"{} accuracy is too low {}".format(clf.__class__, accu))
def test_failing_predict_proba_called_with_use_probabilites_false(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=False)
check_predict_proba_when_trained_with_use_probabilites_false(
self, ovr, clf)
def test_failing_decision_function_called_with_use_probabilites_true(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(min_split=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(min_split=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=True)
check_decision_function_when_trained_with_use_probabilites_true(
self, ovr, clf)
def test_decision_function_produces_distribution_not_sum_to_1(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf, use_probabilities=False)
scoremean = decfun_average(ovr)
assert_not_equal(
scoremean, 1.0,
'{} raw scores should not sum to 1.0 over 3 classes'.format(
clf.__class__))
def test_predict_proba_produces_distribution_sum_to_1(self):
clfs = [
# TODO: BUG 231482 , why doesnt FM work
# FactorizationMachineBinaryClassifier(),
LogisticRegressionBinaryClassifier(),
FastForestBinaryClassifier(minimum_example_count_per_leaf=1),
GamBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastTreesBinaryClassifier(minimum_example_count_per_leaf=1),
LightGbmBinaryClassifier(),
FastLinearBinaryClassifier(),
SgdBinaryClassifier(),
# TODO: why symsgd does not sum to 1.0
# SymSgdBinaryClassifier(),
]
for clf in clfs:
ovr = OneVsRestClassifier(classifier=clf)
probmean = proba_average(ovr)
assert_equal(
probmean, 1.0,
'{} probabilites {} do not sum to 1.0 over 3 classes'.format(
clf.__class__, probmean))
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',
'Sepal_Width',
'Sepal_Length']},
from nimbusml.multiclass import OneVsRestClassifier
from nimbusml.naive_bayes import NaiveBayesClassifier
from sklearn.utils.testing import assert_raises
train_file = get_dataset("uciadult_train").as_filepath()
categorical_columns = [
'workclass', 'education', 'marital-status', 'occupation', 'relationship',
'ethnicity', 'sex', 'native-country-region'
]
file_schema = 'sep=, col=label:R4:0 col=Features:R4:9-14 col=workclass:TX:1 ' \
'col=education:TX:2 col=marital-status:TX:3 ' \
'col=occupation:TX:4 col=relationship:TX:5 col=ethnicity:TX:6 ' \
'col=sex:TX:7 col=native-country-region:TX:8 header+'
label_column = 'label'
learners = [
FastForestBinaryClassifier(),
FastForestRegressor(),
FastTreesBinaryClassifier(),
FastTreesRegressor(),
FastTreesTweedieRegressor(),
LightGbmRegressor(),
LightGbmBinaryClassifier(),
AveragedPerceptronBinaryClassifier(),
FastLinearBinaryClassifier(),
FastLinearClassifier(),
FastLinearRegressor(),
LogisticRegressionBinaryClassifier(),
LogisticRegressionClassifier(),
OnlineGradientDescentRegressor(),
SgdBinaryClassifier(),
# SymSgdBinaryClassifier(),
# FastForestBinaryClassifier
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import FastForestBinaryClassifier
from nimbusml.feature_extraction.categorical import OneHotVectorizer
from sklearn.model_selection import train_test_split
# use the built-in data set 'infert' to create test and train data
# Unnamed: 0 education age parity induced case spontaneous stratum \
# 0 1 0.0 26.0 6.0 1.0 1.0 2.0 1.0
# 1 2 0.0 42.0 1.0 1.0 1.0 0.0 2.0
# pooled.stratum education_str
# 0 3.0 0-5yrs
# 1 1.0 0-5yrs
np.random.seed(0)
df = get_dataset("infert").as_df()
# remove : and ' ' from column names, and encode categorical column
df.columns = [i.replace(': ', '') for i in df.columns]
df = (OneHotVectorizer() << 'education_str').fit_transform(df)
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'case'], df['case'])
fforest = FastForestBinaryClassifier().fit(X_train, y_train)
scores = fforest.predict(X_test)
# evaluate the model
print('Accuracy:', np.mean(y_test == [i for i in scores]))
LogisticRegressionClassifier(),
OnlineGradientDescentRegressor(),
SgdBinaryClassifier(),
# Error on linux
# Unable to load shared library 'SymSgdNative' or one of its dependencies
#SymSgdBinaryClassifier(),
OrdinaryLeastSquaresRegressor(),
PoissonRegressionRegressor(),
OneVsRestClassifier(FastLinearBinaryClassifier()),
GamRegressor(),
GamBinaryClassifier(),
PcaAnomalyDetector(),
FactorizationMachineBinaryClassifier(),
KMeansPlusPlus(n_clusters=2),
NaiveBayesClassifier(),
FastForestBinaryClassifier(number_of_trees=2),
FastForestRegressor(number_of_trees=2),
FastTreesBinaryClassifier(number_of_trees=2),
FastTreesRegressor(number_of_trees=2),
FastTreesTweedieRegressor(number_of_trees=2),
LightGbmRegressor(number_of_iterations=2),
LightGbmClassifier(),
LightGbmBinaryClassifier(number_of_iterations=2)
]
learners_not_supported = [
#PcaTransformer(), # REVIEW: crashes
]
class TestModelSummary(unittest.TestCase):
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