def _get_random_walk():
numpy.random.seed(0)
# Generate a random walk time series
n_ts, sz, d = 1, 100, 1
dataset = random_walks(n_ts=n_ts, sz=sz, d=d)
scaler = TimeSeriesScalerMeanVariance(mu=0., std=1.)
return scaler.fit_transform(dataset)
def perform_sax(dataset, gram_number, symbols, segments):
scaler = TimeSeriesScalerMeanVariance(
mu=0., std=np.std(dataset)) # Rescale time series
dataset = scaler.fit_transform(dataset)
# SAX transform
sax = SymbolicAggregateApproximation(n_segments=segments,
alphabet_size_avg=symbols)
sax_dataset_inv = sax.inverse_transform(sax.fit_transform(dataset))
# print(pd.DataFrame(sax_dataset_inv[0])[0].value_counts())
# sax_dataset_inv = sax.fit_transform(dataset)
# print(len(sax_dataset_inv[0]))
# Convert result to strings
df_sax = pd.DataFrame(sax_dataset_inv[0])
sax_series = df_sax[0]
# Convert sax from numeric to characters
sax_values = sax_series.unique()
alphabet = 'abcdefghijklmnopqrstuvw'
sax_dict = {x: alphabet[i] for i, x in enumerate(sax_values)}
sax_list = [sax_dict[x] for x in sax_series]
# Convert the list of characters to n_grams based on input parameter
tri = n_grams(gram_number, sax_list)
# print(Counter(tri))
return tri
def getNormalize(data_baseline):
data_baseline = TimeSeriesScalerMeanVariance().fit_transform(data_baseline)
data_baseline = data_baseline.reshape(
(data_baseline.shape[0], data_baseline.shape[1]))
return data_baseline
def _update_centroids(self, X):
for k in range(self.n_clusters):
self.cluster_centers_[k] = self._shape_extraction(X, k)
self.cluster_centers_ = TimeSeriesScalerMeanVariance(
mu=0., std=1.).fit_transform(self.cluster_centers_)
self._norms_centroids = numpy.linalg.norm(self.cluster_centers_,
axis=(1, 2))
def reshape_data(self):
ts_value = self.input_df.T.values
ts_value = ts_value.reshape(ts_value.shape[0], ts_value.shape[1], 1)
scaler = TimeSeriesScalerMeanVariance(mu=0., std=1.)
data_scaled = scaler.fit_transform(ts_value)
data_scaled = np.nan_to_num(data_scaled)
self.data_scaled = data_scaled
def test_single_value_ts_no_nan():
X = to_time_series_dataset([[1, 1, 1, 1]])
standard_scaler = TimeSeriesScalerMeanVariance()
assert np.sum(np.isnan(standard_scaler.fit_transform(X))) == 0
minmax_scaler = TimeSeriesScalerMinMax()
assert np.sum(np.isnan(minmax_scaler.fit_transform(X))) == 0
def getStdData(originData):
n_paa_segments = 120 #一天分成4份，每6个小时整合为一段
paa_data = PiecewiseAggregateApproximation(
n_segments=n_paa_segments).fit_transform(originData)
#进行平均值归一化
scaler = TimeSeriesScalerMeanVariance(mu=0., std=1.)
dataset = scaler.fit_transform(paa_data)
dataset = dataset.reshape(dataset.shape[0], dataset.shape[1])
return dataset
def normalize(df):
df_normalized = df.copy()
df_normalized = df_normalized
normalize = TimeSeriesScalerMeanVariance(mu=0, std=1)
for col in df:
df_normalized[col] = normalize.fit_transform(df_normalized[col])[0]
return df_normalized
def _transform(self, X, y=None):
n_ts, sz, d = X.shape
if d > 1:
raise NotImplementedError("We currently don't support using "
"multi-dimensional matrix profiles "
"from the stumpy library.")
output_size = sz - self.subsequence_length + 1
X_transformed = np.empty((n_ts, output_size, 1))
if self.implementation == "stump":
if not STUMPY_INSTALLED:
raise ImportError(stumpy_msg)
for i_ts in range(n_ts):
result = stumpy.stump(T_A=X[i_ts, :, 0].ravel(),
m=self.subsequence_length)
X_transformed[i_ts, :, 0] = result[:, 0].astype(np.float)
elif self.implementation == "gpu_stump":
if not STUMPY_INSTALLED:
raise ImportError(stumpy_msg)
for i_ts in range(n_ts):
result = stumpy.gpu_stump(T_A=X[i_ts, :, 0].ravel(),
m=self.subsequence_length)
X_transformed[i_ts, :, 0] = result[:, 0].astype(np.float)
elif self.implementation == "numpy":
scaler = TimeSeriesScalerMeanVariance()
band_width = int(np.ceil(self.subsequence_length / 4))
for i_ts in range(n_ts):
segments = _series_to_segments(X[i_ts],
self.subsequence_length)
if self.scale:
segments = scaler.fit_transform(segments)
n_segments = segments.shape[0]
segments_2d = segments.reshape(
(-1, self.subsequence_length * d))
dists = squareform(pdist(segments_2d, "euclidean"))
band = (np.tri(
n_segments, n_segments, band_width, dtype=np.bool
) & ~np.tri(
n_segments, n_segments, -(band_width + 1), dtype=np.bool))
dists[band] = np.inf
X_transformed[i_ts] = dists.min(axis=1, keepdims=True)
else:
available_implementations = ["numpy", "stump", "gpu_stump"]
raise ValueError(
'This "{}" matrix profile implementation is not'
' recognized. Available implementations are {}.'.format(
self.implementation, available_implementations))
return X_transformed
def cor(x, y):
"""
Correlation-based distance (COR) between two multivariate time series given as arrays of shape (timesteps, dim)
"""
scaler = TimeSeriesScalerMeanVariance()
x_norm = scaler.fit_transform(x)
y_norm = scaler.fit_transform(y)
pcc = np.mean(x_norm * y_norm) # Pearson correlation coefficients
d = np.sqrt(2.0 * (1.0 - pcc + 1e-9)) # correlation-based similarities
return np.sum(d)
def saa_pax(dataset, title):
"""
Show the graph of PAA and SAX of time series data
:param dataset: time series of a stock
:return:
"""
n_ts, sz, d = 1, 100, 1
scaler = TimeSeriesScalerMeanVariance(mu=0., std=1.) # Rescale time series
dataset = scaler.fit_transform(dataset)
# PAA transform (and inverse transform) of the data
n_paa_segments = 10
paa = PiecewiseAggregateApproximation(n_segments=n_paa_segments)
paa_dataset_inv = paa.inverse_transform(paa.fit_transform(dataset))
# SAX transform
n_sax_symbols = 8
sax = SymbolicAggregateApproximation(n_segments=n_paa_segments,
alphabet_size_avg=n_sax_symbols)
sax_dataset_inv = sax.inverse_transform(sax.fit_transform(dataset))
# 1d-SAX transform
n_sax_symbols_avg = 8
n_sax_symbols_slope = 8
one_d_sax = OneD_SymbolicAggregateApproximation(
n_segments=n_paa_segments,
alphabet_size_avg=n_sax_symbols_avg,
alphabet_size_slope=n_sax_symbols_slope)
one_d_sax_dataset_inv = one_d_sax.inverse_transform(
one_d_sax.fit_transform(dataset))
plt.figure()
plt.subplot(2, 2, 1) # First, raw time series
plt.plot(dataset[0].ravel(), "b-")
plt.title("Raw time series " + title)
plt.subplot(2, 2, 2) # Second, PAA
plt.plot(dataset[0].ravel(), "b-", alpha=0.4)
plt.plot(paa_dataset_inv[0].ravel(), "b-")
plt.title("PAA " + title)
plt.subplot(2, 2, 3) # Then SAX
plt.plot(dataset[0].ravel(), "b-", alpha=0.4)
plt.plot(sax_dataset_inv[0].ravel(), "b-")
plt.title("SAX, %d symbols" % n_sax_symbols)
plt.subplot(2, 2, 4) # Finally, 1d-SAX
plt.plot(dataset[0].ravel(), "b-", alpha=0.4)
plt.plot(one_d_sax_dataset_inv[0].ravel(), "b-")
plt.title("1d-SAX, %d symbols (%dx%d)" %
(n_sax_symbols_avg * n_sax_symbols_slope, n_sax_symbols_avg,
n_sax_symbols_slope))
plt.tight_layout()
plt.show()
def ApplyPaa(n_paa_segments, df, ckt):
circuito = ckt
print("Quantidade de segmentos de PAA: {}".format(n_paa_segments))
paa = PiecewiseAggregateApproximation(n_paa_segments)
scaler = TimeSeriesScalerMeanVariance()
dadosPaa = df
for i in range(0, len(df)):
dataset = scaler.fit_transform(df[i])
dadosPaa[i] = paa.inverse_transform(paa.fit_transform(dataset))[0]
dadosPaa = dadosPaa.T
return dadosPaa
def standardize(self, data):
"""
Standardize des TS, moyenne: 0 et ecart type: 1
Data: dataframe
"""
# prepare data for standardization
values = data["Valeur"]
values = values.values.reshape((len(values), 1))
# train the standardization
t = TimeSeriesScalerMeanVariance().fit_transform(values)
print(t)
data["valeur"] = TimeSeriesScalerMeanVariance().fit_transform(values)
return data
def check_classifiers_classes(name, classifier_orig):
# Case of shapelet models
if name == 'SerializableShapeletModel':
raise SkipTest('Skipping check_classifiers_classes for shapelets'
' due to convergence issues...')
elif name == 'ShapeletModel':
X_multiclass, y_multiclass = _create_large_ts_dataset()
classifier_orig = clone(classifier_orig)
classifier_orig.max_iter = 1000
else:
X_multiclass, y_multiclass = _create_small_ts_dataset()
X_multiclass, y_multiclass = shuffle(X_multiclass,
y_multiclass,
random_state=7)
scaler = TimeSeriesScalerMeanVariance()
X_multiclass = scaler.fit_transform(X_multiclass)
X_multiclass = np.reshape(X_multiclass,
(X_multiclass.shape[0], X_multiclass.shape[1]))
X_binary = X_multiclass[y_multiclass != 2]
y_binary = y_multiclass[y_multiclass != 2]
X_multiclass = pairwise_estimator_convert_X(X_multiclass, classifier_orig)
X_binary = pairwise_estimator_convert_X(X_binary, classifier_orig)
labels_multiclass = ["one", "two", "three"]
labels_binary = ["one", "two"]
y_names_multiclass = np.take(labels_multiclass, y_multiclass)
y_names_binary = np.take(labels_binary, y_binary)
problems = [(X_binary, y_binary, y_names_binary)]
if not classifier_orig._get_tags()['binary_only']:
problems.append((X_multiclass, y_multiclass, y_names_multiclass))
for X, y, y_names in problems:
for y_names_i in [y_names, y_names.astype('O')]:
y_ = choose_check_classifiers_labels(name, y, y_names_i)
check_classifiers_predictions(X, y_, name, classifier_orig)
labels_binary = [-1, 1]
y_names_binary = np.take(labels_binary, y_binary)
y_binary = choose_check_classifiers_labels(name, y_binary, y_names_binary)
check_classifiers_predictions(X_binary, y_binary, name, classifier_orig)
def fit(self, X, y=None):
"""Compute k-Shape clustering.
Parameters
----------
X : array-like of shape=(n_ts, sz, d)
Time series dataset.
"""
X_ = to_time_series_dataset(X)
X_ = TimeSeriesScalerMeanVariance(mu=0., std=1.).fit_transform(X_)
assert X_.shape[-1] == 1, "kShape is supposed to work on monomodal data, provided data has dimension %d" % \
X_.shape[-1]
rs = check_random_state(self.random_state)
best_correct_centroids = None
min_inertia = numpy.inf
n_successful = 0
n_attempts = 0
while n_successful < self.n_init and n_attempts < self.max_attempts:
try:
if self.verbose and self.n_init > 1:
print("Init %d" % (n_successful + 1))
n_attempts += 1
self._fit_one_init(X_, rs)
if self.inertia_ < min_inertia:
best_correct_centroids = self.cluster_centers_.copy()
min_inertia = self.inertia_
n_successful += 1
except EmptyClusterError:
if self.verbose:
print("Resumed because of empty cluster")
self._post_fit(X_, best_correct_centroids, min_inertia)
return self
def load_casas(dataset, fixed_length):
# X = np.load('./npy/{}-x.npy'.format(dataset), allow_pickle=True); X=X[:-1*(X.shape[0]%fixed_length)].reshape(-1, fixed_length, 1); print(X.shape)
# Y = np.load('./npy/{}-y.npy'.format(dataset), allow_pickle=True); Y=Y[:-1*(Y.shape[0]%fixed_length)].reshape(-1, fixed_length, 1); print(Y.shape); Y=np.array(Y, dtype=int)
X = np.load('./npy/{}-x-noidle.npy'.format(dataset), allow_pickle=True)
if -1*(X.shape[0]%fixed_length)!=0:
X=X[:-1*(X.shape[0]%fixed_length)]
X=X.reshape(-1, fixed_length, 1); print(X.shape)
Y = np.load('./npy/{}-y-noidle.npy'.format(dataset), allow_pickle=True)
if -1*(Y.shape[0]%fixed_length)!=0:
Y=Y[:-1*(Y.shape[0]%fixed_length)]
Y=Y.reshape(-1, fixed_length, 1); print(Y.shape); Y=np.array(Y, dtype=int)
y=[]
for i in range(X.shape[0]):
y.append(np.argmax(np.bincount(Y[i].flatten())))
print(Counter(y))
X=np.array(X, dtype=object)
y=np.array(y, dtype=object); y = y.reshape(-1,1)
label_encoder = LabelEncoder()
y = label_encoder.fit_transform(y)
dictActivities = np.load('./npy/{}-labels-noidle.npy'.format(dataset), allow_pickle=True).item()
X_scaled=TimeSeriesScalerMeanVariance().fit_transform(X)
return X_scaled, y, dictActivities
def preprocessing(lc_data, windowSize=50):
lc_nor = TimeSeriesScalerMeanVariance(mu=0., std=1.).fit_transform(
[lc_data['instances']])
lc_data['lc_nor'] = lc_nor
paa = ut_gen.genListPAA(instances_nor=lc_nor,
windowSize=windowSize,
timestamp=lc_data['timestamp'])
lc_data['paa'] = paa
sax = ut_gen.genListSAX(instances_nor=lc_nor,
windowSize=windowSize,
timestamp=lc_data['timestamp'],
n_sax_symbols=n_sax_symbols)
lc_data['sax'] = sax
one_sax = ut_gen.genList1D_SAX(instances_nor=lc_nor,
windowSize=windowSize,
timestamp=lc_data['timestamp'],
n_sax_symbols_slope=n_sax_symbols_slope,
n_sax_symbols_avg=n_sax_symbols_avg)
lc_data['one_sax'] = one_sax
corePlot = sketchDyBinService(windowSize=windowSize,
initialBin=5,
isOnline=False)
sketchInstances = corePlot.sketchMode(instances=list(lc_nor[0].ravel()))
lc_data['dy_bin'] = {
'sketchInstances': sketchInstances,
'timestamp': lc_data['timestamp']
}
print("a")
def processData(self, transmission: Transmission):
self.t = transmission
self.set_data_column_combo_box()
if not self.ctrls['Apply'].isChecked():
return
self.t = transmission.copy()
mu = self.ctrls['mu'].value()
std = self.ctrls['std'].value()
params = {
'data_column': self.data_column,
'mu': mu,
'std': std,
'units': self.t.last_unit
}
output_column = '_SCALER_MEAN_VARIANCE'
self.t.df[output_column] = self.t.df[self.data_column].apply(
lambda a: TimeSeriesScalerMeanVariance(mu=mu, std=std
).fit_transform(a)[:, :, 0])
self.t.history_trace.add_operation(data_block_id='all',
operation='scaler_mean_variance',
parameters=params)
self.t.last_output = output_column
return self.t
def update_plot_means(self, *args, **kwargs):
"""Update the means plot"""
padded = self.pad_input_data(self.input_arrays, 'fill-size')
scaled = TimeSeriesScalerMeanVariance().fit_transform(padded)[:, :, 0]
if self.control_widget.ui.radioButtonXZeroZero.isChecked():
xzero = 'zero'
elif self.control_widget.ui.radioButtonXZeroMaxima.isChecked():
xzero = 'maxima'
else:
raise ValueError('Must select an option for set x = 0 at')
if self.control_widget.ui.comboBoxErrorBand.currentText(
) == 'standard deviation':
ci = 'sd'
elif self.control_widget.ui.comboBoxErrorBand.currentText(
) == 'confidence interval':
ci = 95
elif self.control_widget.ui.comboBoxErrorBand.currentText() == 'None':
ci = None
self.plot_means.set_plots(scaled,
self.n_clusters,
self.y_pred,
xzero_pos=xzero,
error_band=ci)
self.plot_means.show()
def check_clustering(name, clusterer_orig, readonly_memmap=False):
clusterer = clone(clusterer_orig)
X, y = _create_small_ts_dataset()
X, y = shuffle(X, y, random_state=7)
X = TimeSeriesScalerMeanVariance().fit_transform(X)
rng = np.random.RandomState(42)
X_noise = X + (rng.randn(*X.shape) / 5)
n_samples, n_features, dim = X.shape
# catch deprecation and neighbors warnings
if hasattr(clusterer, "n_clusters"):
clusterer.set_params(n_clusters=3)
set_random_state(clusterer)
# fit
clusterer.fit(X)
# with lists
clusterer.fit(X.tolist())
pred = clusterer.labels_
assert_equal(pred.shape, (n_samples,))
assert_greater(adjusted_rand_score(pred, y), 0.4)
if clusterer._get_tags()['non_deterministic']:
return
set_random_state(clusterer)
with warnings.catch_warnings(record=True):
pred2 = clusterer.fit_predict(X)
assert_array_equal(pred, pred2)
# fit_predict(X) and labels_ should be of type int
assert pred.dtype in [np.dtype('int32'), np.dtype('int64')]
assert pred2.dtype in [np.dtype('int32'), np.dtype('int64')]
# Add noise to X to test the possible values of the labels
labels = clusterer.fit_predict(X_noise)
# There should be at least one sample in every original cluster
labels_sorted = np.unique(labels)
assert_array_equal(labels_sorted, np.arange(0, 3))
# Labels should be less than n_clusters - 1
if hasattr(clusterer, 'n_clusters'):
n_clusters = getattr(clusterer, 'n_clusters')
assert_greater_equal(n_clusters - 1, labels_sorted[-1])
def load_tslearn_data():
""" Time series data with variable length """
X_train, y_train, X_test, y_test = CachedDatasets().load_dataset("Trace")
X_train = X_train[y_train < 4] # Keep first 3 classes
np.random.shuffle(X_train)
X_train = TimeSeriesScalerMeanVariance().fit_transform(X_train[:50]) # Keep only 50 time series
X_train = TimeSeriesResampler(sz=40).fit_transform(X_train) # Make time series shorter
X_train = X_train.reshape(50,-1)
return X_train
def test_variable_length_knn():
X = to_time_series_dataset([[1, 2, 3, 4], [1, 2, 3], [9, 8, 7, 6, 5, 2],
[8, 7, 6, 5, 3]])
y = [0, 0, 1, 1]
clf = KNeighborsTimeSeriesClassifier(metric="dtw", n_neighbors=1)
clf.fit(X, y)
assert_allclose(clf.predict(X), [0, 0, 1, 1])
clf = KNeighborsTimeSeriesClassifier(metric="softdtw", n_neighbors=1)
clf.fit(X, y)
assert_allclose(clf.predict(X), [0, 0, 1, 1])
scaler = TimeSeriesScalerMeanVariance()
clf = KNeighborsTimeSeriesClassifier(metric="sax",
n_neighbors=1,
metric_params={'n_segments': 2})
X_transf = scaler.fit_transform(X)
clf.fit(X_transf, y)
assert_allclose(clf.predict(X_transf), [0, 0, 1, 1])
def load_ucr(dataset='CBF'):
X_train, y_train, X_test, y_test = ucr.load_dataset(dataset)
X = np.concatenate((X_train, X_test))
y = np.concatenate((y_train, y_test))
if dataset == 'HandMovementDirection': # this one has special labels
y = [yy[0] for yy in y]
y = LabelEncoder().fit_transform(y) # sometimes labels are strings or start from 1
assert(y.min() == 0) # assert labels are integers and start from 0
# preprocess data (standardization)
X_scaled = TimeSeriesScalerMeanVariance().fit_transform(X)
return X_scaled, y
def get_distance_matrix(numpy_array):
sc = TimeSeriesScalerMeanVariance()
X_s = sc.fit_transform(to_time_series_dataset(numpy_array))
size = len(X_s)
idx = [(i, j) for i in range(0, size) for j in range(i + 1, size)]
def calc_dtw(my_idx):
i, j = my_idx
return dtw(X_s[i], X_s[j])
with mp.Pool(mp.cpu_count() - 1) as p:
distances = p.map(calc_dtw, idx)
dm = np.zeros(shape=(size, size))
for (i, j), v in zip(idx, distances):
dm[i, j] = v
dm[j, i] = v
return dm
def _transform(self, X, y=None):
n_ts, sz, d = X.shape
output_size = sz - self.subsequence_length + 1
X_transformed = numpy.empty((n_ts, output_size, 1))
scaler = TimeSeriesScalerMeanVariance()
for i_ts in range(n_ts):
Xi = X[i_ts]
elem_size = Xi.strides[0]
segments = as_strided(
Xi,
strides=(elem_size, elem_size, Xi.strides[1]),
shape=(Xi.shape[0] - self.subsequence_length + 1,
self.subsequence_length, d),
writeable=False)
if self.scale:
segments = scaler.fit_transform(segments)
segments_2d = segments.reshape((-1, self.subsequence_length * d))
dists = squareform(pdist(segments_2d, "euclidean"))
numpy.fill_diagonal(dists, numpy.inf)
X_transformed[i_ts] = dists.min(axis=1, keepdims=True)
return X_transformed
def approximate(self,
series: np.ndarray,
window: int = 1,
should_fit: bool = True) -> np.ndarray:
# series is already in batches
debug('TSLearnApproximatorWrapper.approximate: series shape {}'.format(
series.shape))
debug(
'TSLearnApproximatorWrapper.approximate: to_time_series shape {}'.
format(series.shape))
ts_representation = list()
debug(
f'TSLearnApproximatorWrapper.approximate: param series \n{series} '
)
for segment in series:
if isinstance(self.transformer,
SymbolicAggregateApproximation) or isinstance(
self.transformer,
OneD_SymbolicAggregateApproximation):
logger.info(
"Scaling the data so that they consist a normal distribution."
)
scaler = TimeSeriesScalerMeanVariance(
mu=0., std=1.) # Rescale time series
segment = scaler.fit_transform(segment)
ts_representation.append(self.transformer.fit_transform(segment))
# debug('TSLearnApproximatorWrapper.approximate: ts_representation \n{}'.format(ts_representation))
debug(
'TSLearnApproximatorWrapper.approximate: ts_representation shape {}'
.format(np.shape(ts_representation)))
ts_representation = np.reshape(
ts_representation,
(np.shape(ts_representation)[0],
np.shape(ts_representation)[1] * np.shape(ts_representation)[2]))
debug('TSLearnApproximatorWrapper.approximate: ts_representation \n{}'.
format(ts_representation))
debug(
'TSLearnApproximatorWrapper.approximate: ts_representation shape {}'
.format(ts_representation.shape))
return ts_representation
def test_serialize_kshape():
n, sz, d = 15, 10, 3
rng = numpy.random.RandomState(0)
time_series = rng.randn(n, sz, d)
X = TimeSeriesScalerMeanVariance().fit_transform(time_series)
ks = KShape(n_clusters=3, verbose=True)
_check_not_fitted(ks)
ks.fit(X)
_check_params_predict(ks, X, ['predict'])
def ApplyPaa(n_paa_segments,df):
'''
Aplica o PAA no dataframe fornecido.
:param n_paa_segments: quantidade de segmento do PAA para redução de dados
:param df: dataframe com dados em que se deseja aplicar o PAA
:return: df após aplicação do PAA
'''
df = df.values.T.tolist()
scaler = TimeSeriesScalerMeanVariance(mu=0., std=1.)
dadosPaa = scaler.fit_transform(df)
print("Quantidade de segmentos de PAA: {}".format(n_paa_segments))
paa = PiecewiseAggregateApproximation(n_paa_segments)
dadosPaa = paa.inverse_transform(paa.fit_transform(dadosPaa))
df = pd.DataFrame()
for i in range(len(dadosPaa.T)):
for j in range(len(dadosPaa.T[0])):
df[j] = dadosPaa.T[i][j]
return df
def Preprocess(self, x=None):
"""
dataを(batch, len(data)//time_span)の形に整形する。
"""
if str(type(x)) == "<class 'NoneType'>":
self.n_data = len(self.data) // self.time_span
self.n_use = self.time_span * self.n_data
ts = self.data.loc[:self.data.index[self.n_use - 1]]
ts = np.array(ts.TEMPERATURE).reshape(1, -1)
ts = TimeSeriesScalerMeanVariance().fit_transform(ts)
ts = np.array(ts).reshape(self.n_data, -1)
ts = TimeSeriesResampler(sz=self.batch).fit_transform(ts)
self.ts = ts
else:
self.x_data = len(x) // self.time_span
self.x_use = self.time_span * self.x_data
ts = x.loc[:x.index[self.x_use - 1]]
ts = np.array(ts.TEMPERATURE).reshape(1, -1)
ts = TimeSeriesScalerMeanVariance().fit_transform(ts)
ts = np.array(ts).reshape(self.x_data, -1)
ts = TimeSeriesResampler(sz=self.batch).fit_transform(ts)
return ts
def test_kshape():
n, sz, d = 15, 10, 3
rng = np.random.RandomState(0)
time_series = rng.randn(n, sz, d)
time_series = TimeSeriesScalerMeanVariance().fit_transform(time_series)
ks = KShape(n_clusters=3, n_init=1, verbose=False,
random_state=rng).fit(time_series)
dists = ks._cross_dists(time_series)
np.testing.assert_allclose(ks.labels_, dists.argmin(axis=1))
np.testing.assert_allclose(ks.labels_, ks.predict(time_series))
assert KShape(n_clusters=101, verbose=False,
random_state=rng).fit(time_series)._X_fit is None