def unsupervised_analysis(df, nu, size, percent):
stream = DataStream(df)
stream.prepare_for_use()
stream_clf = HoeffdingTree()
stream_acc = []
stream_record = []
stream_true= 0
buffer = dataBuffer(size, stream.n_features, percent)
clf = svm.OneClassSVM(nu=nu, kernel="rbf", gamma='auto')
#
start = time.time()
X,y = stream.next_sample(size)
stream_clf.partial_fit(X,y, classes=stream.target_values)
clf.fit(X)
i=0
while(stream.has_more_samples()): #stream.has_more_samples()
X,y = stream.next_sample()
if buffer.isEmpty():
buffer.addInstance(X,y,clf.predict(X))
y_hat = stream_clf.predict(X)
stream_true = stream_true + check_true(y, y_hat)
stream_clf.partial_fit(X,y)
stream_acc.append(stream_true / (i+1))
stream_record.append(check_true(y,y_hat))
else:
if buffer.driftCheck(): #detected
#print("concept drift detected at {}".format(i))
#retrain the model
stream_clf.reset()
#stream_clf = HoeffdingTree()
stream_clf.partial_fit(buffer.getCurrentData(), buffer.getCurrentLabels(), classes=stream.target_values)
#update one-class SVM
clf.fit(buffer.getCurrentData())
#evaluate and update the model
y_hat = stream_clf.predict(X)
stream_true = stream_true + check_true(y, y_hat)
stream_clf.partial_fit(X,y)
stream_acc.append(stream_true / (i+1))
stream_record.append(check_true(y,y_hat))
#add new sample to the window
buffer.addInstance(X,y,clf.predict(X))
else:
#evaluate and update the model
y_hat = stream_clf.predict(X)
stream_true = stream_true + check_true(y, y_hat)
stream_clf.partial_fit(X,y)
stream_acc.append(stream_true / (i+1))
stream_record.append(check_true(y,y_hat))
#add new sample to the window
buffer.addInstance(X,y,clf.predict(X))
i = i + 1
#print(buffer.drift_count)
elapsed = format(time.time() - start, '.4f')
acc = format(stream_acc[-1] * 100, '.4f')
final_accuracy = "Parameters: {}, {}, {}, Final accuracy: {}, Elapsed time: {}".format(nu,size,percent,acc,elapsed)
return final_accuracy, stream_record
def test_data_stream(test_path, package_path):
test_file = os.path.join(package_path, 'src/skmultiflow/data/datasets/sea_stream.csv')
raw_data = pd.read_csv(test_file)
stream = DataStream(raw_data, name='Test')
assert not stream._Y_is_defined
stream.prepare_for_use()
assert stream.n_remaining_samples() == 40000
expected_names = ['attrib1', 'attrib2', 'attrib3']
assert stream.feature_names == expected_names
expected_targets = [0, 1]
assert stream.target_values == expected_targets
assert stream.target_names == ['class']
assert stream.n_features == 3
assert stream.n_cat_features == 0
assert stream.n_num_features == 3
assert stream.n_targets == 1
assert stream.get_data_info() == 'Test: 1 target(s), 2 classes'
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, 'sea_stream_file.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 = "DataStream(n_targets=-1, target_idx=1, cat_features=None, name='Test')"
assert stream.get_info() == expected_info
def test_data_stream_X_y(test_path, package_path):
test_file = os.path.join(package_path,
'src/skmultiflow/datasets/sea_stream.csv')
raw_data = pd.read_csv(test_file)
y = raw_data.iloc[:, -1:]
X = raw_data.iloc[:, :-1]
stream = DataStream(X, y)
assert stream._Y_is_defined == True
stream.prepare_for_use()
assert stream.n_remaining_samples() == 40000
expected_names = ['attrib1', 'attrib2', 'attrib3']
assert stream.feature_names == expected_names
expected_targets = [0, 1]
assert stream.target_values == expected_targets
assert stream.target_names == ['class']
assert stream.n_features == 3
assert stream.n_cat_features == 0
assert stream.n_num_features == 3
assert stream.n_targets == 1
assert stream.get_data_info() == '1 target(s), 2 target_values'
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, 'sea_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]
def NSE_run (dataset_name, batch, num_copy):
data = load_arff(path, dataset_name, num_copy)
# data transform
stream = DataStream(data)
#print(stream)
# Setup variables to control loop and track performance
n_samples = 0
max_samples = data.shape[0]
# Train the classifier with the samples provided by the data stream
pred = np.empty(0)
np.random.seed(0)
model = LearnPPNSEClassifier()
while n_samples < max_samples and stream.has_more_samples():
X, y = stream.next_sample(batch)
y_pred = model.predict(X)
pred = np.hstack((pred,y_pred))
model.partial_fit(X, y,stream.target_values)
n_samples += batch
# evaluate
data = data.values
Y = data[:,-1]
acc = accuracy_score(Y[batch:], pred[batch:])
f1 = f1_score(Y[batch:], pred[batch:], average='macro')
#print (Y[batch:].shape, pred[batch:].shape)
print("acc:",acc)
print("f1:",f1)
# save results
result = np.zeros([pred[batch:].shape[0], 2])
result[:, 0] = pred[batch:]
result[:, 1] = Y[batch:]
def InnerCycle_Train(X, y, inject_drift, perc_train):
# get number of training samples
ntrain = int(perc_train * X.shape[0])
if inject_drift:
# pick a point between 0.7 and 0.9 of the stream
dpoints = Driftpoints(X)
dpoints["cleanrun"] = dpoints["row"] - ntrain
# contaminate X after that point
X = Swapcols(df=X,
class_vec=y,
ids=dpoints["cols"],
t_change=dpoints["row"])
else:
dpoints = dict({"row": X.shape[0], "cols": 0})
# cast data as DataStream class
stream = DataStream(X, y)
stream.prepare_for_use()
# call incr model (main classifier, teacher model)
stream_clf = ARF(n_estimators=25) #,
#drift_detection_method=None,
#warning_detection_method=None
#)
# get training data... first ntrain rows
Xtrain, ytrain = stream.next_sample(ntrain)
# partial fit of the incre model using training data
stream_clf.fit(Xtrain, ytrain, classes=stream.target_values)
yhat_train = stream_clf.predict(Xtrain)
yhat_train_prob = stream_clf.predict_proba(
Xtrain) ### needs warnings!!!!!!!!!
yhat_tr_max_prob = np.array([np.max(x) for x in yhat_train_prob])
# fit student model
student_clf = ARF(n_estimators=25) #,
#drift_detection_method=None,
#warning_detection_method=None)
student_clf.fit(Xtrain, yhat_train, classes=stream.target_values)
student_regr = RHT()
student_regr.fit(Xtrain, yhat_tr_max_prob)
results = dict()
results["Teacher"] = stream_clf
results["Student"] = student_clf
results["StudentRegression"] = student_regr
results["Driftpoints"] = dpoints
results["n"] = ntrain
results["Stream"] = stream
results["Xtrain"] = Xtrain
return (results)
def ARF_run (dataset_name, batch, random_seeds):
data = load_arff(path, dataset_name)
#print (data.shape)
# data transform
stream = DataStream(data)
#print(stream)
# Setup variables to control loop and track performance
n_samples = 0
max_samples = data.shape[0]
# Train the classifier with the samples provided by the data stream
pred = np.empty(0)
np.random.seed(0)
model = AdaptiveRandomForestClassifier(n_estimators=24, random_state=random_seeds)
while n_samples < max_samples and stream.has_more_samples():
X, y = stream.next_sample(batch)
y_pred = model.predict(X)
pred = np.hstack((pred,y_pred))
model.partial_fit(X, y,stream.target_values)
n_samples += batch
# evaluate
data = data.values
Y = data[:,-1]
acc = accuracy_score(Y[batch:], pred[batch:])
f1 = f1_score(Y[batch:], pred[batch:], average='macro')
#print (Y[batch:].shape, pred[batch:].shape)
print("acc:",acc)
print("f1:",f1)
# save results
result = np.zeros([pred[batch:].shape[0], 2])
result[:, 0] = pred[batch:]
result[:, 1] = Y[batch:]
np.savetxt(dataset_name +'_' + 'ARF' + str(random_seeds) +'.out', result, delimiter=',')
stream.prepare_for_use()
stream_clf = HoeffdingTree()
w = int(sys.argv[2])
rho = float(sys.argv[3])
auc = float(sys.argv[4])
# In[ ]:
D3_win = D3(w, rho, stream.n_features, auc)
stream_acc = []
stream_record = []
stream_true = 0
i = 0
start = time.time()
X, y = stream.next_sample(int(w * rho))
stream_clf.partial_fit(X, y, classes=stream.target_values)
while (stream.has_more_samples()):
X, y = stream.next_sample()
if D3_win.isEmpty():
D3_win.addInstance(X, y)
y_hat = stream_clf.predict(X)
stream_true = stream_true + check_true(y, y_hat)
stream_clf.partial_fit(X, y)
stream_acc.append(stream_true / (i + 1))
stream_record.append(check_true(y, y_hat))
else:
if D3_win.driftCheck(): #detected
#print("concept drift detected at {}".format(i))
#retrain the model
stream_clf.reset()
def InnerCycle(X, y, inject_drift, perc_train, window, delta, pval,
prob_instance, inst_delay):
# get number of training samples
ntrain = int(perc_train * X.shape[0])
if inject_drift:
# pick a point between 0.7 and 0.9 of the stream
dpoints = Driftpoints(X)
dpoints["cleanrun"] = dpoints["row"] - ntrain
# contaminate X after that point
X = Swapcols(df=X,
class_vec=y,
ids=dpoints["cols"],
t_change=dpoints["row"])
else:
dpoints = dict({"row": X.shape[0], "cols": 0})
# cast data as DataStream class
stream = DataStream(X, y)
stream.prepare_for_use()
# call incr model (main classifier, teacher model)
stream_clf = ARF(n_estimators=25,
drift_detection_method=None,
warning_detection_method=None)
# get training data... first ntrain rows
Xtrain, ytrain = stream.next_sample(ntrain)
# partial fit of the incre model using training data
stream_clf.fit(Xtrain, ytrain, classes=stream.target_values)
yhat_train = stream_clf.predict(Xtrain)
yhat_train_prob = stream_clf.predict_proba(
Xtrain) ### needs warnings!!!!!!!!!
yhat_tr_max_prob = np.array([np.max(x) for x in yhat_train_prob])
# fit student model
student_clf = ARF(n_estimators=25,
drift_detection_method=None,
warning_detection_method=None)
student_clf.fit(Xtrain, yhat_train, classes=stream.target_values)
student_regr = RHT()
student_regr.fit(Xtrain, yhat_tr_max_prob)
####### Call drift detectors
## Supervised
# Supervised with ADWIN
S_ADWIN = ADWIN() #(delta=delta)
S_ADWIN_alarms = []
# Supervised with PHT
S_PHT = PHT() #(min_instances=window,delta=delta)
S_PHT_alarms = []
# Delayed Supervised with ADWIN
DS_ADWIN = ADWIN() #(delta=delta)
DS_ADWIN_alarms = []
# Delayed Supervised with PHT
DS_PHT = PHT() #(min_instances=window,delta=delta)
DS_PHT_alarms = []
## Semi-supervised
# Semi-Supervised with ADWIN
WS_ADWIN = ADWIN() #(delta=delta)
WS_ADWIN_alarms = []
# Supervised with PHT
WS_PHT = PHT() #(min_instances=window,delta=delta)
WS_PHT_alarms = []
# Delayed Supervised with ADWIN
DWS_ADWIN = ADWIN() #(delta=delta)
DWS_ADWIN_alarms = []
# Delayed Supervised with PHT
DWS_PHT = PHT() #(min_instances=window,delta=delta)
DWS_PHT_alarms = []
##### Unsupervised
# Student with ADWIN
U_ADWIN = ADWIN() #(delta=delta)
U_ADWIN_alarms = []
# Student with PHT
U_PHT = PHT() #(min_instances=window,delta=delta)
U_PHT_alarms = []
# Student with ADWIN
UR_ADWIN = ADWIN() #(delta=delta)
UR_ADWIN_alarms = []
# Student with PHT
UR_PHT = PHT() #(min_instances=window,delta=delta)
UR_PHT_alarms = []
# WRS with output
WRS_Output = HypothesisTestDetector(method="wrs", window=window, thr=pval)
WRS_Output_alarms = []
# WRS with class prob
WRS_Prob = HypothesisTestDetector(method="wrs", window=window, thr=pval)
WRS_Prob_alarms = []
# TT with output
TT_Output = HypothesisTestDetector(method="tt", window=window, thr=pval)
TT_Output_alarms = []
# TT with class prob
TT_Prob = HypothesisTestDetector(method="tt", window=window, thr=pval)
TT_Prob_alarms = []
# KS with output
KS_Output = HypothesisTestDetector(method="ks", window=window, thr=pval)
KS_Output_alarms = []
# KS with class prob
KS_Prob = HypothesisTestDetector(method="ks", window=window, thr=pval)
KS_Prob_alarms = []
Driftmodels = [
S_ADWIN, S_PHT, DS_ADWIN, DS_PHT, WS_ADWIN, WS_PHT, DWS_ADWIN, DWS_PHT,
U_ADWIN, U_PHT, UR_ADWIN, UR_PHT, WRS_Output, TT_Output, KS_Output,
WRS_Prob, TT_Prob, KS_Prob
]
Driftmodels_alarms = [
S_ADWIN_alarms, S_PHT_alarms, DS_ADWIN_alarms, DS_PHT_alarms,
WS_ADWIN_alarms, WS_PHT_alarms, DWS_ADWIN_alarms, DWS_PHT_alarms,
U_ADWIN_alarms, U_PHT_alarms, UR_ADWIN_alarms, UR_PHT_alarms,
WRS_Output_alarms, TT_Output_alarms, KS_Output_alarms, WRS_Prob_alarms,
TT_Prob_alarms, KS_Prob_alarms
]
S_driftmodels = Driftmodels[0:2]
DS_driftmodels = Driftmodels[2:4]
WS_driftmodels = Driftmodels[4:6]
DWS_driftmodels = Driftmodels[6:8]
Ustd_driftmodels = Driftmodels[8:10]
Ustdreg_driftmodels = Driftmodels[10:12]
Uoutput_driftmodels = Driftmodels[12:15]
Uprob_driftmodels = Driftmodels[15:18]
# always updated
S_clf = copy.deepcopy(stream_clf)
# always updated with delay
DS_clf = copy.deepcopy(stream_clf)
# updated immediately with some prob
WS_clf = copy.deepcopy(stream_clf)
# updated with delay with some prob
DWS_clf = copy.deepcopy(stream_clf)
# never updated
U_clf = copy.deepcopy(stream_clf)
i = ntrain
k = 0
DWS_yhat_hist = []
DS_yhat_hist = []
X_hist = []
y_hist = []
while (stream.has_more_samples()):
print(i)
#i=3000
Xi, yi = stream.next_sample()
y_hist.append(yi[0])
X_hist.append(Xi)
ext_Xi = np.concatenate([Xtrain[-10:], Xi])
U_prob = U_clf.predict_proba(ext_Xi)[-1]
U_yhat = U_clf.predict(ext_Xi)[-1]
S_yhat = S_clf.predict(ext_Xi)[-1]
WS_yhat = WS_clf.predict(ext_Xi)[-1]
DS_yhat = DS_clf.predict(ext_Xi)[-1]
DWS_yhat = DWS_clf.predict(ext_Xi)[-1]
DWS_yhat_hist.append(DWS_yhat)
DS_yhat_hist.append(DS_yhat)
if len(U_prob) < 2:
U_yhat_prob_i = U_prob[0]
elif len(U_prob) == 2:
U_yhat_prob_i = U_prob[1]
else:
U_yhat_prob_i = np.max(U_prob)
y_meta_hat_i = student_clf.predict(ext_Xi)[-1]
y_meta_prob = student_regr.predict(ext_Xi)[-1]
# Updating student model
student_clf.partial_fit(Xi, [U_yhat])
# Updating supervised model
S_clf.partial_fit(Xi, yi)
# Computing loss
S_err_i = int(yi[0] != S_yhat)
student_err_i = int(y_meta_hat_i != U_yhat)
student_prob_err_i = U_yhat_prob_i - y_meta_prob
for model in S_driftmodels:
model.add_element(S_err_i)
for model in Ustd_driftmodels:
model.add_element(student_err_i)
for model in Ustdreg_driftmodels:
model.add_element(student_prob_err_i)
for model in Uoutput_driftmodels:
model.add_element(U_yhat)
for model in Uprob_driftmodels:
model.add_element(U_yhat_prob_i)
put_i_available = np.random.binomial(1, prob_instance)
if k >= inst_delay:
DS_err_i = int(
y_hist[k - inst_delay] != DS_yhat_hist[k - inst_delay])
DS_clf.partial_fit(X_hist[k - inst_delay],
[y_hist[k - inst_delay]])
for model in DS_driftmodels:
model.add_element(DS_err_i)
if put_i_available > 0:
DWS_err_i = int(
y_hist[k - inst_delay] != DWS_yhat_hist[k - inst_delay])
DWS_clf.partial_fit(X_hist[k - inst_delay],
[y_hist[k - inst_delay]])
for model in DWS_driftmodels:
model.add_element(DWS_err_i)
if put_i_available > 0:
WS_err_i = int(yi[0] != WS_yhat)
WS_clf.partial_fit(Xi, yi)
for model in WS_driftmodels:
model.add_element(WS_err_i)
# detect changes
for j, model in enumerate(Driftmodels):
has_change = model.detected_change()
if has_change:
Driftmodels_alarms[j].append(i)
i += 1
k += 1
return ([Driftmodels_alarms, dpoints])
def test_data_stream_X_y(test_path):
test_file = os.path.join(test_path, 'sea_stream_file.csv')
raw_data = pd.read_csv(test_file)
y = raw_data.iloc[:, -1:]
X = raw_data.iloc[:, :-1]
stream = DataStream(X, y)
assert stream._Y_is_defined
assert stream.n_remaining_samples() == 40
expected_names = ['attrib1', 'attrib2', 'attrib3']
assert stream.feature_names == expected_names
expected_targets = [0, 1]
assert stream.target_values == expected_targets
assert stream.target_names == ['class']
assert stream.n_features == 3
assert stream.n_cat_features == 0
assert stream.n_num_features == 3
assert stream.n_targets == 1
assert stream.get_data_info() == '1 target(s), 2 classes'
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, 'sea_stream_file.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]
# Ensure that the regression case is also covered
y = raw_data.iloc[:, -1:]
X = raw_data.iloc[:, :-1]
y = y.astype('float64')
stream = DataStream(X, y, name='Test')
assert stream.task_type == 'regression'
assert stream.get_data_info() == 'Test: 1 target(s)'