def demo(output_file=None, instances=50000):
""" _test_sam_knn_prequential
This demo shows how to produce a prequential evaluation.
The first thing needed is a stream. For this case we use a file stream
which gets its samples from the movingSquares.csv file, inside the datasets
folder.
Then we need to setup a classifier, which in this case is an instance
of scikit-multiflow's SAMKNN. Then, optionally we create a
pipeline structure, initialized on that classifier.
The evaluation is then run.
Parameters
----------
output_file: string
The name of the csv output file
instances: int
The evaluation's max number of instances
"""
# Setup the File Stream
# opt = FileOption("FILE", "OPT_NAME", "../datasets/covtype.csv", "CSV", False)
opt = FileOption("FILE", "OPT_NAME", "../datasets/movingSquares.csv",
"CSV", False)
stream = FileStream(opt, -1, 1)
# stream = WaveformGenerator()
stream.prepare_for_use()
# Setup the classifier
# classifier = SGDClassifier()
# classifier = KNNAdwin(k=8, max_window_size=2000,leaf_size=40, categorical_list=None)
# classifier = OzaBaggingAdwin(h=KNN(k=8, max_window_size=2000, leaf_size=30, categorical_list=None))
classifier = SAMKNN(n_neighbors=5,
knnWeights='distance',
maxSize=1000,
STMSizeAdaption='maxACCApprox',
useLTM=False)
# classifier = SGDRegressor()
# classifier = PerceptronMask()
# Setup the pipeline
#pipe = Pipeline([('Classifier', classifier)])
# Setup the evaluator
eval = EvaluatePrequential(pretrain_size=0,
max_instances=instances,
batch_size=1,
n_wait=100,
max_time=1000,
output_file=output_file,
task_type='classification',
show_plot=True,
plot_options=['performance'])
# Evaluate
eval.eval(stream=stream, classifier=classifier)
def demo_parameterized(h, dset="sea_stream.csv", show_plot=True):
# Setup Stream
opt = FileOption("FILE", "OPT_NAME", "../datasets/"+dset, "CSV", False)
stream = FileStream(opt, -1, 1)
stream.prepare_for_use()
# For each classifier, e...
T_init = 100
eval = EvaluatePrequential(pretrain_size=T_init, output_file='output.csv', max_instances=10000, batch_size=1, n_wait=1000, task_type='classification', show_plot=show_plot, plot_options=['performance'])
eval.eval(stream=stream, classifier=h)
def demo(output_file=None, instances=40000):
""" _test_prequential_mol
This demo shows the evaluation process of a MOL classifier, initialized
with sklearn's SGDClassifier.
Parameters
----------
output_file: string
The name of the csv output file
instances: int
The evaluation's max number of instances
"""
# Setup the File Stream
#opt = FileOption("FILE", "OPT_NAME", "../datasets/music.csv", "CSV", False)
#stream = FileStream(opt, 0, 6)
stream = MultilabelGenerator(n_samples=instances)
#stream = WaveformGenerator()
stream.prepare_for_use()
# Setup the classifier
classifier = MultiOutputLearner(SGDClassifier(n_iter=100))
#classifier = SGDClassifier()
#classifier = PassiveAggressiveClassifier()
#classifier = SGDRegressor()
#classifier = PerceptronMask()
# Setup the pipeline
pipe = Pipeline([('Classifier', classifier)])
# Setup the evaluator
eval = EvaluatePrequential(
pretrain_size=5000,
max_instances=instances - 10000,
batch_size=1,
n_wait=200,
max_time=1000,
output_file=output_file,
task_type='multi_output',
show_plot=True,
plot_options=['hamming_score', 'j_index', 'exact_match'])
# Evaluate
eval.eval(stream=stream, classifier=pipe)
def demo(output_file=None, instances=40000):
""" _test_prequential_bagging
This demo shows the evaluation process of a LeverageBagging classifier,
initialized with KNN classifiers.
Parameters
----------
output_file: string
The name of the csv output file
instances: int
The evaluation's max number of instances
"""
# Setup the File Stream
# opt = FileOption("FILE", "OPT_NAME", "../datasets/sea_big.csv", "CSV", False)
# stream = FileStream(opt, -1, 1)
stream = SEAGenerator(classification_function=2,
instance_seed=755437,
noise_percentage=0.0)
stream.prepare_for_use()
# Setup the classifier
#classifier = OzaBaggingAdwin(h=KNN(k=8, max_window_size=2000, leaf_size=30, categorical_list=None))
classifier = LeverageBagging(h=KNN(k=8, max_window_size=2000,
leaf_size=30),
ensemble_length=1)
# Setup the pipeline
pipe = Pipeline([('Classifier', classifier)])
# Setup the evaluator
eval = EvaluatePrequential(
pretrain_size=2000,
max_instances=instances,
batch_size=1,
n_wait=200,
max_time=1000,
output_file=output_file,
task_type='classification',
show_plot=True,
plot_options=['kappa', 'kappa_t', 'performance'])
# Evaluate
eval.eval(stream=stream, classifier=pipe)
def demo(output_file=None, instances=40000):
""" _test_regression
This demo demonstrates how to evaluate a regressor. The data stream used
is an instance of the RegressionGenerator, which feeds an instance from
sklearn's SGDRegressor.
Parameters
----------
output_file: string
The name of the csv output file
instances: int
The evaluation's max number of instances
"""
# Setup the File Stream
#opt = FileOption("FILE", "OPT_NAME", "../datasets/covtype.csv", "CSV", False)
#stream = FileStream(opt, -1, 1)
#stream = WaveformGenerator()
#stream.prepare_for_use()
stream = RegressionGenerator(n_samples=40000)
# Setup the classifier
#classifier = SGDClassifier()
#classifier = PassiveAggressiveClassifier()
classifier = SGDRegressor()
#classifier = PerceptronMask()
# Setup the pipeline
pipe = Pipeline([('Classifier', classifier)])
# Setup the evaluator
eval = EvaluatePrequential(pretrain_size=1,
max_instances=instances,
batch_size=1,
n_wait=1,
max_time=1000,
output_file=output_file,
task_type='regression',
show_plot=True,
plot_options=['true_vs_predicts'])
# Evaluate
eval.eval(stream=stream, classifier=pipe)
def demo():
# The classifier we will use (other options: SAMKNN, LeverageBagging, SGD)
h = HoeffdingTree()
# Setup Stream
opt = FileOption("FILE", "OPT_NAME", "../datasets/sea_stream.csv", "CSV",
False)
stream = FileStream(opt, -1, 1)
stream.prepare_for_use()
T_init = 100
eval = EvaluatePrequential(pretrain_size=T_init,
output_file='output.csv',
max_instances=10000,
batch_size=1,
n_wait=1000,
task_type='classification',
show_plot=True,
plot_options=['performance'])
eval.eval(stream=stream, classifier=h)
def demo():
""" _test_pipeline
This demo demonstrates the Pipeline structure seemingly working as a
learner, while being passed as parameter to an EvaluatePrequential
object.
"""
# # Setup the stream
# opt = FileOption("FILE", "OPT_NAME", "../datasets/covtype.csv", "CSV", False)
# stream = FileStream(opt, -1, 1)
# stream.prepare_for_use()
# # If used for Hoeffding Trees then need to pass indices for Nominal attributes
# Test with RandomTreeGenerator
# stream = RandomTreeGenerator(n_classes=2, n_numerical_attributes=5)
# stream.prepare_for_use()
# Test with WaveformGenerator
stream = WaveformGenerator()
stream.prepare_for_use()
# Setup the classifier
#classifier = PerceptronMask()
#classifier = NaiveBayes()
#classifier = PassiveAggressiveClassifier()
classifier = HoeffdingTree()
# Setup the pipeline
pipe = Pipeline([('Hoeffding Tree', classifier)])
# Setup the evaluator
eval = EvaluatePrequential(show_plot=True,
pretrain_size=1000,
max_instances=100000)
# Evaluate
eval.eval(stream=stream, classifier=pipe)
from skmultiflow.options.file_option import FileOption
from my_classifier import BatchClassifier
dataset = "elec"
# 1. Create a stream
opt = FileOption("FILE", "OPT_NAME", "./data/" + dataset + ".csv", "CSV",
False)
stream = FileStream(opt, -1, 1)
# 2. Prepare for use
stream.prepare_for_use()
# 2. Instantiate the HoeffdingTree classifier
h = [
KNN(k=10, max_window_size=100, leaf_size=30),
HoeffdingTree(),
BatchClassifier(window_size=100, max_models=10),
]
# 3. Setup the evaluator
eval = EvaluatePrequential(pretrain_size=1000,
output_file='result_' + dataset + '.csv',
max_instances=10000,
batch_size=1,
n_wait=500,
max_time=1000000000,
task_type='classification',
show_plot=True,
plot_options=['performance'])
# 4. Run
eval.eval(stream=stream, classifier=h)
from skmultiflow.evaluation.evaluate_prequential import EvaluatePrequential
# 1. Create a stream
stream = WaveformGenerator()
stream.prepare_for_use()
# 2. Instantiate the classifier
adf = AdaptiveRandomForest()
# 3. Setup the evaluator
eval = EvaluatePrequential(show_plot=True,
pretrain_size=100,
max_instances=10000)
# 4. Run evaluation
eval.eval(stream=stream, classifier=adf)
#
# # Eval Prequential with datasets.csv for ARF
#
# In[47]:
from skmultiflow.options.file_option import FileOption
from skmultiflow.data.file_stream import FileStream
from skmultiflow.evaluation.evaluate_prequential import EvaluatePrequential
# 1. Create a stream
#options = FileOption(option_value="../datasets/covtype.csv", file_extension="CSV")
#options = FileOption(option_value="../datasets/movingSquares.csv", file_extension="CSV")
options = FileOption(option_value="../datasets/sea_stream.csv",
def demo(instances=2000):
""" _test_comparison_prequential
This demo will test a prequential evaluation when more than one learner is
passed, which makes it a comparison task.
Parameters
----------
instances: int
The evaluation's maximum number of instances.
"""
# Stream setup
opt = FileOption("FILE", "OPT_NAME", "../datasets/covtype.csv", "CSV",
False)
#opt = FileOption("FILE", "OPT_NAME", "../datasets/sea_big.csv", "CSV", False)
stream = FileStream(opt, -1, 1)
#stream = SEAGenerator(classification_function=2, instance_seed=53432, balance_classes=False)
stream.prepare_for_use()
# Setup the classifier
clf = SGDClassifier()
# classifier = KNNAdwin(k=8, max_window_size=2000,leaf_size=40, categorical_list=None)
# classifier = OzaBaggingAdwin(h=KNN(k=8, max_window_size=2000, leaf_size=30, categorical_list=None))
clf_one = KNNAdwin(k=8, max_window_size=1000, leaf_size=30)
#clf_two = KNN(k=8, max_window_size=1000, leaf_size=30)
#clf_two = LeverageBagging(h=KNN(), ensemble_length=2)
t_one = OneHotToCategorical([[10, 11, 12, 13],
[
14, 15, 16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50, 51, 52, 53
]])
#t_two = OneHotToCategorical([[10, 11, 12, 13],
# [14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35,
# 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53]])
pipe_one = Pipeline([('one_hot_to_categorical', t_one), ('KNN', clf_one)])
#pipe_two = Pipeline([('one_hot_to_categorical', t_two), ('KNN', clf_two)])
classifier = [clf, pipe_one]
# classifier = SGDRegressor()
# classifier = PerceptronMask()
# Setup the pipeline
#pipe = Pipeline([('Classifier', classifier)])
# Setup the evaluator
eval = EvaluatePrequential(pretrain_size=2000,
output_file='teste.csv',
max_instances=instances,
batch_size=1,
n_wait=200,
max_time=1000,
task_type='classification',
show_plot=True,
plot_options=['performance', 'kappa_t'])
# Evaluate
eval.eval(stream=stream, classifier=classifier)