def test_pass_decision_function_multiclass_3class(self):
clf = FastLinearClassifier(number_of_threads=1)
clf.fit(X_train_3class, y_train_3class)
s = clf.decision_function(X_test_3class).sum()
assert_almost_equal(s,
38.0,
decimal=4,
err_msg=invalid_decision_function_output)
assert_equal(set(clf.classes_), {'Blue', 'Green', 'Red'})
def test_pass_predict_proba_multiclass_3class(self):
clf = FastLinearClassifier(number_of_threads=1)
clf.fit(X_train_3class, y_train_3class, verbose=0)
s = clf.predict_proba(X_test_3class).sum()
assert_almost_equal(s,
38.0,
decimal=4,
err_msg=invalid_predict_proba_output)
assert_equal(set(clf.classes_), {'Blue', 'Green', 'Red'})
def test_pass_predict_proba_multiclass_3class_retains_classes_type(self):
clf = FastLinearClassifier(number_of_threads=1)
clf.fit(X_train_3class_int, y_train_3class_int)
s = clf.predict_proba(X_test_3class_int).sum()
assert_almost_equal(s,
38.0,
decimal=4,
err_msg=invalid_predict_proba_output)
assert_equal(set(clf.classes_), {0, 1, 2})
def test_text_label(self):
X, y = get_iris()
ap = FastLinearClassifier(
feature=[
'Sepal_Width',
'Sepal_Length',
'Petal_Width',
'Petal_Length'])
ap.fit(X, y)
scores = ap.predict(X)
assert str(scores.dtype) == "object"
def test_unseen_classes(self):
# Create a dataset such that cv splits miss some of the classes
X = random_df()
y = random_series()
y[95:] = range(5)
msg = 'CV didn\'t raise Warning exception b/c of minority class issue'
with self.assertRaises(Warning, msg=msg):
cv = CV([FastLinearClassifier()])
cv.fit(X, y, cv=3)
def test_pass_predict_proba_multiclass_with_pipeline(self):
algos = [
LogisticRegressionClassifier(),
FastLinearClassifier(),
LightGbmClassifier()
]
for algo in algos:
assert_almost_equal(proba_sum(Pipeline([algo])),
38.0,
decimal=3,
err_msg=invalid_predict_proba_output)
def setUpClass(self):
adult_path = get_dataset('uciadult_train').as_filepath()
self.classification_data = FileDataStream.read_csv(adult_path)
binary_pipeline = Pipeline([
OneHotVectorizer(columns=['education']),
LogisticRegressionBinaryClassifier(feature=['age', 'education'],
label='label',
number_of_threads=1)
])
self.binary_model = binary_pipeline.fit(self.classification_data)
self.binary_pfi = self.binary_model.permutation_feature_importance(
self.classification_data)
classifier_pipeline = Pipeline([
OneHotVectorizer(columns=['education']),
FastLinearClassifier(feature=['age', 'education'],
label='label',
number_of_threads=1,
shuffle=False)
])
self.classifier_model = classifier_pipeline.fit(
self.classification_data)
self.classifier_pfi = self.classifier_model.permutation_feature_importance(
self.classification_data)
infert_path = get_dataset('infert').as_filepath()
self.regression_data = FileDataStream.read_csv(infert_path)
regressor_pipeline = Pipeline([
OneHotVectorizer(columns=['education']),
FastLinearRegressor(feature=['induced', 'education'],
label='age',
number_of_threads=1,
shuffle=False)
])
self.regressor_model = regressor_pipeline.fit(self.regression_data)
self.regressor_pfi = self.regressor_model.permutation_feature_importance(
self.regression_data)
ticket_path = get_dataset('gen_tickettrain').as_filepath()
self.ranking_data = FileDataStream.read_csv(ticket_path)
ranker_pipeline = Pipeline([
ToKey(columns=['group']),
LightGbmRanker(feature=['Class', 'dep_day', 'duration'],
label='rank',
group_id='group',
random_state=0,
number_of_threads=1)
])
self.ranker_model = ranker_pipeline.fit(self.ranking_data)
self.ranker_pfi = self.ranker_model.permutation_feature_importance(
self.ranking_data)
def test_decision_function_multiclass_3class_no_y_input_implies_no_classes_attribute(
self):
X_train = X_train_3class_int.join(y_train_3class_int)
X_test = X_test_3class_int.join(y_test_3class_int)
clf = FastLinearClassifier(number_of_threads=1, label='Label')
clf.fit(X_train)
if hasattr(clf, 'classes_'):
# The classes_ attribute is currently not supported
# when fitting when there is no y input specified.
self.fail("classes_ attribute not expected.")
s = clf.decision_function(X_test).sum()
assert_almost_equal(s,
38.0,
decimal=4,
err_msg=invalid_decision_function_output)
if hasattr(clf, 'classes_'):
# The classes_ attribute is currently not supported
# when predicting when there was no y input specified
# during fitting.
self.fail("classes_ attribute not expected.")
def test_label_column_for_classifier_specified_as_argument(self):
train_data = {
'c1': [2, 3, 4, 5],
'c2': [3, 4, 5, 6],
'c3': [4, 5, 6, 7],
'd1': [0, 1, 2, 1]
}
train_df = pd.DataFrame(train_data)
predictor = FastLinearClassifier(label='d1')
pipeline = Pipeline([predictor])
result = json.loads(pipeline.fit(train_df, dry_run=True))
self.verify_classifier_nodes(
result, "d1", ['c1', 'c2', 'c3'],
"Trainers.StochasticDualCoordinateAscentClassifier")
def test_default_label_for_classifier_without_label_column(self):
train_data = {
'c1': [2, 3, 4, 5],
'c2': [3, 4, 5, 6],
'c3': [4, 5, 6, 7],
'c4': [0, 1, 2, 1]
}
train_df = pd.DataFrame(train_data)
predictor = FastLinearClassifier()
pipeline = Pipeline([predictor])
result = json.loads(pipeline.fit(train_df, dry_run=True))
self.verify_classifier_nodes(
result, "Label", ['c1', 'c2', 'c3', 'c4'],
"Trainers.StochasticDualCoordinateAscentClassifier")
def test_pass_predict_proba_multiclass_with_pipeline_adds_classes(self):
clf = FastLinearClassifier(number_of_threads=1)
pipeline = Pipeline([clf])
pipeline.fit(X_train_3class, y_train_3class)
expected_classes = {'Blue', 'Green', 'Red'}
assert_equal(set(clf.classes_), expected_classes)
assert_equal(set(pipeline.classes_), expected_classes)
s = pipeline.predict_proba(X_test_3class).sum()
assert_almost_equal(s,
38.0,
decimal=4,
err_msg=invalid_predict_proba_output)
assert_equal(set(clf.classes_), expected_classes)
assert_equal(set(pipeline.classes_), expected_classes)
###############################################################################
# FastLinearClassifier
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.linear_model import FastLinearClassifier
from sklearn.model_selection import train_test_split
# use 'iris' data set to create test and train data
# Sepal_Length Sepal_Width Petal_Length Petal_Width Label Species Setosa
# 0 5.1 3.5 1.4 0.2 0 setosa 1.0
# 1 4.9 3.0 1.4 0.2 0 setosa 1.0
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = FastLinearClassifier().fit(X_train, y_train)
scores = lr.predict(X_test)
# evaluate the model
print('Accuracy:', np.mean(y_test == [i for i in scores]))
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(),
OrdinaryLeastSquaresRegressor(),
PoissonRegressionRegressor()
]
learners_not_supported = [
NaiveBayesClassifier(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
KMeansPlusPlus(),
# fix in nimbusml, needs to implement ICanGetSummaryAsIDataView
# 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'}),
FastLinearClassifier(feature=['age', 'edu', 'parity'], label='induced')
])
# 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 Score.1 Score.2
# 0 2 0.015312 0.058199 0.926489
# 1 0 0.892915 0.097093 0.009991
# 2 2 0.058976 0.123581 0.817444
# 3 2 0.287882 0.245397 0.466721
# 4 0 0.404075 0.362293 0.233632
def test_FastLinearClassifier(self):
acc = get_accuracy(self, FastLinearClassifier())
assert_almost_equal(acc,
0.97368421052,
decimal=8,
err_msg="Sum should be %s" % 0.97368421052)
# FeatureName AreaUnderRocCurve AreaUnderRocCurve.StdErr ...
# 0 age -0.081604 0.0 ...
# 6 education.Prof-school -0.012964 0.0 ...
# 10 education.Doctorate -0.012863 0.0 ...
# 8 education.Bachelors -0.010593 0.0 ...
# 2 education.HS-grad -0.005918 0.0 ...
###############################
# PFI for Classification models
###############################
# define the training pipeline with a classifier
# use 1 thread and no shuffling to force determinism
multiclass_pipeline = Pipeline([
OneHotVectorizer(columns=['education']),
FastLinearClassifier(feature=['age', 'education'],
label='label',
number_of_threads=1,
shuffle=False)
])
# train the model
multiclass_model = multiclass_pipeline.fit(classification_data)
# get permutation feature importance
multiclass_pfi = multiclass_model.permutation_feature_importance(
classification_data)
# Print PFI for each feature, ordered by most important features w.r.t. Macro
# accuracy. Since Macro accuracy is an increasing metric, the highest negative
# changes indicate the most important features.
print("================== PFI for Classification Model ==================")
print(multiclass_pfi.sort_values('MacroAccuracy').head())