def __init__(self, concept_id=0, seed=None, noise=0):
self.cf = concept_id
self.seed = seed
stream = AGRAWALGenerator(concept_id,
random_state=seed,
perturbation=noise)
stream.prepare_for_use()
super().__init__(stream)
def test_agrawal_generator_all_functions(test_path):
for f in range(10):
stream = AGRAWALGenerator(classification_function=f, random_state=1)
# Load test data corresponding to first 10 instances
test_file = os.path.join(test_path, 'agrawal_stream_{}.npz'.format(f))
data = np.load(test_file)
X_expected = data['X']
y_expected = data['y']
X, y = stream.next_sample(10)
assert np.alltrue(X == X_expected)
assert np.alltrue(y == y_expected)
def test_agrawal_drift(test_path):
stream = AGRAWALGenerator(random_state=1)
stream.prepare_for_use()
X, y = stream.next_sample(10)
stream.generate_drift()
X_drift, y_drift = stream.next_sample(10)
# Load test data corresponding to first 10 instances
test_file = os.path.join(test_path, 'agrawal_stream_drift.npz')
data = np.load(test_file)
X_expected = data['X']
y_expected = data['y']
X = np.concatenate((X, X_drift))
y = np.concatenate((y, y_drift))
assert np.alltrue(X == X_expected)
assert np.alltrue(y == y_expected)
def test_agrawal_generator(test_path):
stream = AGRAWALGenerator(classification_function=2,
random_state=112,
balance_classes=False,
perturbation=0.28)
assert stream.n_remaining_samples() == -1
expected_names = [
"salary", "commission", "age", "elevel", "car", "zipcode", "hvalue",
"hyears", "loan"
]
assert stream.feature_names == expected_names
expected_targets = [0, 1]
assert stream.target_values == expected_targets
assert stream.target_names == ['target']
assert stream.n_features == 9
assert stream.n_cat_features == 3
assert stream.n_num_features == 6
assert stream.n_targets == 1
assert stream.get_data_info(
) == 'AGRAWAL Generator - 1 target(s), 2 classes, 9 features'
assert stream.has_more_samples() is True
assert stream.is_restartable() is True
# Load test data corresponding to first 10 instances
test_file = os.path.join(test_path, 'agrawal_stream.npz')
data = np.load(test_file)
X_expected = data['X']
y_expected = data['y']
X, y = stream.next_sample()
assert np.alltrue(X[0] == X_expected[0])
assert np.alltrue(y[0] == y_expected[0])
X, y = stream.last_sample()
assert np.alltrue(X[0] == X_expected[0])
assert np.alltrue(y[0] == y_expected[0])
stream.restart()
X, y = stream.next_sample(10)
assert np.alltrue(X == X_expected)
assert np.alltrue(y == y_expected)
assert stream.n_targets == np.array(y).ndim
assert stream.n_features == X.shape[1]
assert 'stream' == stream._estimator_type
expected_info = "AGRAWALGenerator(balance_classes=False, classification_function=2,\n" \
" perturbation=0.28, random_state=112)"
assert stream.get_info() == expected_info
def main():
usedSynthData = [[
"synthData/cess_data.csv", "synthData/cess_targets.csv"
], ["synthData/move_square_data.csv", "synthData/move_square_targets.csv"],
["synthData/sea_data.csv", "synthData/sea_targets.csv"]]
#Name of the datastreams
synthDataStreams_names = [
"Cess_data",
"Move_squares",
"Sea_data",
]
realDataFiles = [
["realData/electric_data.csv", "realData/electric_targets.csv"],
["realData/poker_data.csv", "realData/poker_targets.csv"],
["realData/weather_data.csv", "realData/weather_targets.csv"],
["realData/rialto_data.csv", "realData/rialto_targets.csv"]
]
#Name of the datastreams
realDataStreams_names = ["Electric", "Poker", "Weather", "Rialto"]
#fixe the poker dataset
#dfX=pd.read_csv("realData/poker_data_broken.csv")
#dfY=pd.read_csv(realTargetFiles[1])
#print(dfX.dtypes)
#remove the false columns
#dfX = dfX.drop(columns = ['feat_11', 'feat_12'])
#print(dfX.dtypes)
#save fixed data as csv
#dfX.to_csv(r'realData/poker_data.csv', index = None, header=True)
#check if saved correctly
#X=pd.read_csv(realDataFiles[1])
#print(X.dtypes)
#fix electirc dataset
#dfX=pd.read_csv("realData/electric_data_broken.csv")
#print(dfX.dtypes)
#remove the false columns
#dfX = dfX.drop(columns = ['feat_1', 'feat_2'])
#print(dfX.dtypes)
#dfX.to_csv(r'realData/electric_data.csv', index = None, header=True)
#check if saved correctly
#X=pd.read_csv(realDataFiles[0])
#print(X.dtypes)
#Stream with synth generated data from generators, synth data stream that were used in other works and real data streams
synthDataStreams = [
[AGRAWALGenerator(random_state=112, perturbation=0.1), "Agrawal"],
[
ConceptDriftStream(stream=AGRAWALGenerator(random_state=112),
drift_stream=AGRAWALGenerator(random_state=112,
perturbation=0.1),
position=40000,
width=10000), "Agrawal_drift"
],
[
HyperplaneGenerator(mag_change=0.001, noise_percentage=0.1),
"Hyperplane"
],
[
ConceptDriftStream(stream=HyperplaneGenerator(),
drift_stream=HyperplaneGenerator(),
position=40000,
width=10000), "Hyperplane_drift"
], [SineGenerator(random_state=112), "Sine"],
[
ConceptDriftStream(stream=SineGenerator(random_state=112),
drift_stream=SineGenerator(random_state=112),
position=40000,
width=10000), "Sine_drift"
]
]
synthDataStreamsUsed = []
for i in range(len(usedSynthData)):
synthDataStreamsUsed.append([
DataStream(pd.read_csv(usedSynthData[i][0]),
pd.read_csv(usedSynthData[i][1])),
synthDataStreams_names[i]
])
realDataStreams = []
for i in range(len(realDataFiles)):
realDataStreams.append([
DataStream(pd.read_csv(realDataFiles[i][0]),
pd.read_csv(realDataFiles[i][1])),
realDataStreams_names[i]
])
clfs = [[RSLVQSgd(), 'RSLVQ_SGD'], [RSLVQAdadelta(), 'RSLVQ_Adadelta'],
[RSLVQRMSprop(), 'RSLVQ_RMSprop'], [RSLVQAdam(), 'RSLVQ_Adam']]
max_items = 40000
#insert the dataset array that should be evaluated, if the reform exception occurs, set the dataset
#that is effected by it as the first one in the array and run again
for i in range(len(synthDataStreams)):
for j in range(len(clfs)):
#print('bla')
#custom_evaluation(synthDataStreams[i], clfs[j], max_items, False)
custom_evaluation(synthDataStreams[i], clfs[j], max_items, True)
def init_standard_streams_naive_bayes(
): # RBF Stream beinhaltet negative Werte daher muss dieser beim Naive Bayes Algortihmus weggelassen werden
"""Initialize standard data streams
Standard streams are inspired by the experiment settings of
Gomes, Heitor Murilo & Bifet, Albert & Read, Jesse & Barddal, Jean Paul &
Enembreck, Fabrício & Pfahringer, Bernhard & Holmes, Geoff &
Abdessalem, Talel. (2017). Adaptive random forests for evolving data
stream classification. Machine Learning. 1-27. 10.1007/s10994-017-5642-8.
"""
agrawal_a = ConceptDriftStream(stream=AGRAWALGenerator(random_state=112,
perturbation=0.1),
drift_stream=AGRAWALGenerator(
random_state=112,
classification_function=2,
perturbation=0.1),
random_state=None,
alpha=90.0,
position=21000000)
agrawal_a.name = "agrawal_a"
agrawal_g = ConceptDriftStream(stream=AGRAWALGenerator(random_state=112,
perturbation=0.1),
drift_stream=AGRAWALGenerator(
random_state=112,
classification_function=1,
perturbation=0.1),
random_state=None,
position=21000000,
width=1000000)
agrawal_g.name = "agrawal_g"
hyper = HyperplaneGenerator(mag_change=0.001, noise_percentage=0.1)
led_a = ConceptDriftStream(
stream=LEDGeneratorDrift(has_noise=False,
noise_percentage=0.0,
n_drift_features=3),
drift_stream=LEDGeneratorDrift(has_noise=False,
noise_percentage=0.0,
n_drift_features=7),
random_state=None,
alpha=90.0, # angle of change grade 0 - 90
position=21000000,
width=1)
led_a.name = "led_a"
led_g = ConceptDriftStream(stream=LEDGeneratorDrift(has_noise=False,
noise_percentage=0.0,
n_drift_features=3),
drift_stream=LEDGeneratorDrift(
has_noise=False,
noise_percentage=0.0,
n_drift_features=7),
random_state=None,
position=21000000,
width=1000000)
led_g.name = "led_g"
rand_tree = RandomTreeGenerator()
rand_tree.name = "rand_tree"
#rbf_if = RandomRBFGeneratorDrift(change_speed=0.001)
#rbf_if.name = "rbf_if"
#rbf_im = RandomRBFGeneratorDrift(change_speed=0.0001)
#rbf_im.name = "rbf_im"
sea_a = ConceptDriftStream(stream=SEAGenerator(random_state=112,
noise_percentage=0.1),
drift_stream=SEAGenerator(
random_state=112,
classification_function=2,
noise_percentage=0.1),
alpha=90.0,
random_state=None,
position=21000000,
width=1)
sea_a.name = "sea_a"
sea_g = ConceptDriftStream(stream=SEAGenerator(random_state=112,
noise_percentage=0.1),
drift_stream=SEAGenerator(
random_state=112,
classification_function=1,
noise_percentage=0.1),
random_state=None,
position=21000000,
width=1000000)
sea_g.name = "sea_g"
return [agrawal_a, agrawal_g, hyper, led_a, led_g, rand_tree, sea_a, sea_g]