def test_class_distribution():
y = np.array([[1, 0, 0, 1],
[2, 2, 0, 1],
[1, 3, 0, 1],
[4, 2, 0, 1],
[2, 0, 0, 1],
[1, 3, 0, 1]])
# Define the sparse matrix with a mix of implicit and explicit zeros
data = np.array([1, 2, 1, 4, 2, 1, 0, 2, 3, 2, 3, 1, 1, 1, 1, 1, 1])
indices = np.array([0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 5, 0, 1, 2, 3, 4, 5])
indptr = np.array([0, 6, 11, 11, 17])
y_sp = sp.csc_matrix((data, indices, indptr), shape=(6, 4))
classes, n_classes, class_prior = class_distribution(y)
classes_sp, n_classes_sp, class_prior_sp = class_distribution(y_sp)
classes_expected = [[1, 2, 4],
[0, 2, 3],
[0],
[1]]
n_classes_expected = [3, 3, 1, 1]
class_prior_expected = [[3/6, 2/6, 1/6],
[1/3, 1/3, 1/3],
[1.0],
[1.0]]
for k in range(y.shape[1]):
assert_array_almost_equal(classes[k], classes_expected[k])
assert_array_almost_equal(n_classes[k], n_classes_expected[k])
assert_array_almost_equal(class_prior[k], class_prior_expected[k])
assert_array_almost_equal(classes_sp[k], classes_expected[k])
assert_array_almost_equal(n_classes_sp[k], n_classes_expected[k])
assert_array_almost_equal(class_prior_sp[k], class_prior_expected[k])
# Test again with explicit sample weights
(classes,
n_classes,
class_prior) = class_distribution(y, [1.0, 2.0, 1.0, 2.0, 1.0, 2.0])
(classes_sp,
n_classes_sp,
class_prior_sp) = class_distribution(y, [1.0, 2.0, 1.0, 2.0, 1.0, 2.0])
class_prior_expected = [[4/9, 3/9, 2/9],
[2/9, 4/9, 3/9],
[1.0],
[1.0]]
for k in range(y.shape[1]):
assert_array_almost_equal(classes[k], classes_expected[k])
assert_array_almost_equal(n_classes[k], n_classes_expected[k])
assert_array_almost_equal(class_prior[k], class_prior_expected[k])
assert_array_almost_equal(classes_sp[k], classes_expected[k])
assert_array_almost_equal(n_classes_sp[k], n_classes_expected[k])
assert_array_almost_equal(class_prior_sp[k], class_prior_expected[k])
def test_class_distribution():
y = np.array([[1, 0, 0, 1],
[2, 2, 0, 1],
[1, 3, 0, 1],
[4, 2, 0, 1],
[2, 0, 0, 1],
[1, 3, 0, 1]])
# Define the sparse matrix with a mix of implicit and explicit zeros
data = np.array([1, 2, 1, 4, 2, 1, 0, 2, 3, 2, 3, 1, 1, 1, 1, 1, 1])
indices = np.array([0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 5, 0, 1, 2, 3, 4, 5])
indptr = np.array([0, 6, 11, 11, 17])
y_sp = sp.csc_matrix((data, indices, indptr), shape=(6, 4))
classes, n_classes, class_prior = class_distribution(y)
classes_sp, n_classes_sp, class_prior_sp = class_distribution(y_sp)
classes_expected = [[1, 2, 4],
[0, 2, 3],
[0],
[1]]
n_classes_expected = [3, 3, 1, 1]
class_prior_expected = [[3/6, 2/6, 1/6],
[1/3, 1/3, 1/3],
[1.0],
[1.0]]
for k in range(y.shape[1]):
assert_array_almost_equal(classes[k], classes_expected[k])
assert_array_almost_equal(n_classes[k], n_classes_expected[k])
assert_array_almost_equal(class_prior[k], class_prior_expected[k])
assert_array_almost_equal(classes_sp[k], classes_expected[k])
assert_array_almost_equal(n_classes_sp[k], n_classes_expected[k])
assert_array_almost_equal(class_prior_sp[k], class_prior_expected[k])
# Test again with explicit sample weights
(classes,
n_classes,
class_prior) = class_distribution(y, [1.0, 2.0, 1.0, 2.0, 1.0, 2.0])
(classes_sp,
n_classes_sp,
class_prior_sp) = class_distribution(y, [1.0, 2.0, 1.0, 2.0, 1.0, 2.0])
class_prior_expected = [[4/9, 3/9, 2/9],
[2/9, 4/9, 3/9],
[1.0],
[1.0]]
for k in range(y.shape[1]):
assert_array_almost_equal(classes[k], classes_expected[k])
assert_array_almost_equal(n_classes[k], n_classes_expected[k])
assert_array_almost_equal(class_prior[k], class_prior_expected[k])
assert_array_almost_equal(classes_sp[k], classes_expected[k])
assert_array_almost_equal(n_classes_sp[k], n_classes_expected[k])
assert_array_almost_equal(class_prior_sp[k], class_prior_expected[k])
def fit(self, X, y):
"""Fit a single boss classifier on n_instances cases (X,y).
Parameters
----------
X : pd.DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, enforce_univariate=True, coerce_to_numpy=True)
sfa = self.transformer.fit_transform(X)
self.transformed_data = sfa[0]
self.class_vals = y
self.num_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
self._is_fitted = True
return self
def fit(self, X, y, **kwargs):
self.nb_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for itr in range(self.nb_iterations):
# each construction shall have a different random initialisation
y_cur, fit_time_cur, predict_time_cur = self.load_network_probs(
self.network_name,
itr,
self.res_path,
self.dataset_name,
self.random_seed,
)
if itr == 0:
self.y_pred = y_cur
self.fit_time = fit_time_cur
self.predict_time = predict_time_cur
else:
self.y_pred = self.y_pred + y_cur
self.fit_time = self.fit_time + fit_time_cur
self.predict_time = self.predict_time + predict_time_cur
self.y_pred = self.y_pred / self.nb_iterations
# check if binary classification
if self.y_pred.shape[1] == 1:
# first column is probability of class 0 and second is of class 1
self.y_pred = np.hstack([1 - self.y_pred, self.y_pred])
self._is_fitted = True
return self
def fit(self, X, y):
"""Perform a shapelet transform then builds a random forest.
Contract default for ST is 5 hours
----------
X : array-like or sparse matrix of shape = [n_instances,
series_length] or shape = [n_instances,n_columns]
The training input samples. If a Pandas data frame is passed it
must have a single column (i.e. univariate
classification. RISE has no bespoke method for multivariate
classification as yet.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, enforce_univariate=True)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.classifier.fit(X, y)
# self.shapelet_transform.fit(X,y)
# print("Shapelet Search complete")
# self.st_X =self.shapelet_transform.transform(X)
# print("Transform complete")
# X = np.asarray([a.values for a in X.iloc[:, 0]])
# self.classifier.fit(X,y)
# print("Build classifier complete")
self._is_fitted = True
return self
def fit(self, X, y):
"""Fit a random catch22 feature forest classifier.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X = check_X(X, enforce_univariate=False, coerce_to_numpy=True)
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
c22 = Catch22(outlier_norm=self.outlier_norm)
c22_list = c22.fit_transform(X)
self.classifier = RandomForestClassifier(
n_jobs=self.n_jobs,
n_estimators=self.n_estimators,
random_state=self.random_state,
)
X_c22 = np.nan_to_num(np.array(c22_list, dtype=np.float32), False, 0,
0, 0)
self.classifier.fit(X_c22, y)
self._is_fitted = True
return self
def fit(self, X, y):
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.constituent_build_times = np.zeros(len(self.classifiers))
self.train_accs_by_classifier = np.zeros(len(self.classifiers))
self.training_preds = np.empty((len(self.classifiers), len(y)),dtype=type(y[0]))
self.training_probas = np.empty((len(self.classifiers), len(y), len(self.classes_)))
# build each classifier
for c_id in range(len(self.classifiers)):
if self.verbose > 0:
print("Building "+self.classifier_names[c_id])
start_time = time.time()
self.classifiers[c_id].random_state=self.random_state
if self.classifier_param_grids is None or self.classifier_param_grids[c_id] is None:
pass
else:
grid = GridSearchCV(estimator=self.classifiers[c_id], param_grid=self.classifier_param_grids[c_id],
scoring='accuracy', cv=self.param_cv_folds, verbose=self.verbose)
self.classifiers[c_id] = grid.fit(X, y).best_estimator_
self.training_probas[c_id] = cross_val_predict(self.classifiers[c_id], X=X, y=y, cv=self.cv_folds, method='predict_proba')
end_time = time.time()
self.training_preds[c_id] = np.array([self.classes_[np.argmax(x)] for x in self.training_probas[c_id]])
self.train_accs_by_classifier[c_id] = accuracy_score(y, self.training_preds[c_id])
self.constituent_build_times[c_id] = end_time-start_time
self.classifiers[c_id].fit(train_x, train_y)
def fit(self, X, y):
"""Build a pipeline containing the ROCKET transformer and RidgeClassifierCV.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
self.classifier = rocket_pipeline = make_pipeline(
Rocket(
num_kernels=self.num_kernels,
random_state=self.random_state,
n_jobs=self.n_jobs,
),
RidgeClassifierCV(alphas=np.logspace(-3, 3, 10), normalize=True),
)
rocket_pipeline.fit(X, y)
self._is_fitted = True
return self
def fit(self, X, y):
"""Build a forest of trees from the training set (X, y) using supervised
intervals and summary features
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,
series_length] or shape = [n_instances,n_columns]
The training input samples. If a Pandas data frame is passed it
must have a single column (i.e. univariate
classification. STSF has no bespoke method for multivariate
classification as yet.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(
X,
y,
enforce_univariate=True,
coerce_to_numpy=True,
)
X = X.squeeze(1)
n_instances, _ = X.shape
rng = check_random_state(self.random_state)
cls, class_counts = np.unique(y, return_counts=True)
self.n_classes = class_counts.shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.intervals_ = [[[] for _ in range(3)]
for _ in range(self.n_estimators)]
_, X_p = signal.periodogram(X)
X_d = np.diff(X, 1)
balance_cases = np.zeros(0, dtype=np.int32)
average = math.floor(n_instances / self.n_classes)
for i, c in enumerate(cls):
if class_counts[i] < average:
cls_idx = np.where(y == c)[0]
balance_cases = np.concatenate(
(rng.choice(cls_idx, size=average - class_counts[i]),
balance_cases))
self.estimators_ = Parallel(n_jobs=self.n_jobs)(
delayed(self._fit_estimator)(
X,
X_p,
X_d,
y,
np.concatenate((rng.choice(n_instances, size=n_instances),
balance_cases)),
i,
) for i in range(self.n_estimators))
self._is_fitted = True
return self
def _fit(self, X, y):
"""Fit an estimator using transformed data from the Catch22 transformer.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, n_dims]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.n_classes = np.unique(y).shape[0]
self._transformer = Catch22(outlier_norm=self.outlier_norm)
self._estimator = _clone_estimator(
RandomForestClassifier(n_estimators=200)
if self.estimator is None else self.estimator,
self.random_state,
)
m = getattr(self._estimator, "n_jobs", None)
if m is not None:
self._estimator.n_jobs = self.n_jobs
X_t = self._transformer.fit_transform(X, y)
X_t = np.nan_to_num(X_t, False, 0, 0, 0)
self._estimator.fit(X_t, y)
return self
def fit(self, X, y):
"""Build a forest of trees from the training set (X, y).
Uses random intervals and catch22/tsf summary features.
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,n_dimensions,
series_length] or shape = [n_instances,series_length]
The training input samples.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, coerce_to_numpy=True)
self.n_instances, self.n_dims, self.series_length = X.shape
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
if self.base_estimator is None or self.base_estimator == "DTC":
self.tree = DecisionTreeClassifier(criterion="entropy")
elif self.base_estimator == "CIT":
self.tree = ContinuousIntervalTree()
elif isinstance(self.base_estimator, BaseEstimator):
self.tree = self.base_estimator
else:
raise ValueError("DrCIF invalid base estimator given.")
if self.n_intervals is None:
self.__n_intervals = int(
math.sqrt(self.series_length) * math.sqrt(self.n_dims)
)
if self.__n_intervals <= 0:
self.__n_intervals = 1
if self.series_length < self.min_interval:
self.min_interval = self.series_length
if self.max_interval is None:
self.__max_interval = self.series_length / 2
if self.__max_interval < self.min_interval:
self.__max_interval = self.min_interval
fit = Parallel(n_jobs=self.n_jobs)(
delayed(self._fit_estimator)(
X,
y,
i,
)
for i in range(self.n_estimators)
)
self.classifiers, self.intervals, self.dims, self.atts = zip(*fit)
self._is_fitted = True
return self
def fit(self, X, y):
"""Fit a single TD classifier on n_instances cases (X,y).
Parameters
----------
X : pd.DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, coerce_to_numpy=True)
self.n_instances, self.n_dims, self.series_length = X.shape
self.class_vals = y
self.num_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
# select dimensions using accuracy estimate if multivariate
if self.n_dims > 1:
self.dims, self.transformers = self._select_dims(X, y)
words = [defaultdict(int) for _ in range(self.n_instances)]
for i, dim in enumerate(self.dims):
X_dim = X[:, dim, :].reshape(self.n_instances, 1,
self.series_length)
dim_words = self.transformers[i].transform(X_dim, y)
dim_words = dim_words[0]
for i in range(self.n_instances):
for word, count in dim_words[i].items():
words[i][word << self.highest_dim_bit | dim] = count
self.transformed_data = words
else:
self.transformers.append(
SFA(
word_length=self.word_length,
alphabet_size=self.alphabet_size,
window_size=self.window_size,
norm=self.norm,
levels=self.levels,
binning_method="information-gain"
if self.igb else "equi-depth",
bigrams=self.bigrams,
remove_repeat_words=True,
save_words=False,
n_jobs=self.n_jobs,
))
sfa = self.transformers[0].fit_transform(X, y)
self.transformed_data = sfa[0]
self._is_fitted = True
return self
def fit(self, X, y):
sfa = self.transform.fit_transform(X)
self.transformed_data = [series.to_dict() for series in sfa.iloc[:, 0]]
self.class_vals = y
self.num_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
def fit(self, X, y):
X, y = check_X_y(X, y, enforce_univariate=True, coerce_to_numpy=True)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
cv_size = 10
_, counts = np.unique(y, return_counts=True)
min_class = np.min(counts)
if min_class < cv_size:
cv_size = min_class
self.stc = ShapeletTransformClassifier(
random_state=self.random_state,
time_contract_in_mins=60,
)
self.stc.fit(X, y)
train_preds = cross_val_predict(
ShapeletTransformClassifier(
random_state=self.random_state,
time_contract_in_mins=60,
),
X=X,
y=y,
cv=cv_size,
)
self.stc_weight = accuracy_score(y, train_preds)**4
self.tsf = TimeSeriesForest(random_state=self.random_state)
self.tsf.fit(X, y)
train_preds = cross_val_predict(
TimeSeriesForest(random_state=self.random_state),
X=X,
y=y,
cv=cv_size,
)
self.tsf_weight = accuracy_score(y, train_preds)**4
self.rise = RandomIntervalSpectralForest(
random_state=self.random_state)
self.fit(X, y)
train_preds = cross_val_predict(
RandomIntervalSpectralForest(random_state=self.random_state),
X=X,
y=y,
cv=cv_size,
)
self.rise_weight = accuracy_score(y, train_preds)**4
self.cboss = ContractableBOSS(random_state=self.random_state)
self.cboss.fit(X, y)
train_probs = self.cboss._get_train_probs(X)
train_preds = self.cboss.classes_[np.argmax(train_probs, axis=1)]
self.cboss_weight = accuracy_score(y, train_preds)**4
return self
def fit(self, X, y):
"""Build a forest of trees from the training set (X, y) using random
intervals and summary features
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,
series_length] or shape = [n_instances,n_columns]
The training input samples. If a Pandas data frame is passed it
must have a single column (i.e. univariate
classification. TSF has no bespoke method for multivariate
classification as yet.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(
X,
y,
enforce_univariate=not TimeSeriesForest.capabilities["multivariate"],
coerce_to_numpy=True,
)
X = X.squeeze(1)
n_instances, self.series_length = X.shape
rng = check_random_state(self.random_state)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.n_intervals = int(math.sqrt(self.series_length))
if self.n_intervals == 0:
self.n_intervals = 1
if self.series_length < self.min_interval:
self.min_interval = self.series_length
self.intervals_ = [
_get_intervals(self.n_intervals, self.min_interval, self.series_length, rng)
for _ in range(self.n_estimators)
]
self.estimators_ = Parallel(n_jobs=self.n_jobs)(
delayed(_fit_estimator)(
X,
y,
self.base_estimator,
self.intervals_[i],
self.random_state,
)
for i in range(self.n_estimators)
)
self._is_fitted = True
return self
def fit(self, X, y, sample_weight=None):
"""Build a forest of trees from the training set (X, y) using random intervals and summary measures.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samps, num_atts]
The training input samples. If a Pandas data frame is passed, the column _dim_to_use is extracted
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The class labels.
Returns
-------
self : object
"""
if isinstance(X, pd.DataFrame):
if isinstance(X.iloc[0,self.dim_to_use], pd.Series):
X = np.asarray([a.values for a in X.iloc[:,0]])
else:
raise TypeError("Input should either be a 2d numpy array, or a pandas dataframe containing Series objects")
n_samps, self.series_length = X.shape
self.num_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.intervals=np.zeros((self.num_trees, 2), dtype=int)
self.intervals[0][0] = 0
self.intervals[0][1] = self.series_length
for i in range(1, self.num_trees):
self.intervals[i][0]=random.randint(self.series_length - self.min_interval)
self.intervals[i][1]=random.randint(self.intervals[i][0] + self.min_interval, self.series_length)
# Check lag against global properties
if self.acf_lag > self.series_length-self.acf_min_values:
self.acf_lag = self.series_length - self.acf_min_values
if self.acf_lag < 0:
self.acf_lag = 1
self.lags=np.zeros(self.num_trees, dtype=int)
for i in range(0, self.num_trees):
temp_lag=self.acf_lag
if temp_lag > self.intervals[i][1]-self.intervals[i][0]-self.acf_min_values:
temp_lag = self.intervals[i][1] - self.intervals[i][0] - self.acf_min_values
if temp_lag < 0:
temp_lag = 1
self.lags[i] = int(temp_lag)
acf_x = np.empty(shape=(n_samps,self.lags[i]))
ps_len = (self.intervals[i][1] - self.intervals[i][0]) / 2
ps_x = np.empty(shape=(n_samps,int(ps_len)))
for j in range(0, n_samps):
acf_x[j] = acf(X[j,self.intervals[i][0]:self.intervals[i][1]], temp_lag)
ps_x[j] = ps(X[j, self.intervals[i][0]:self.intervals[i][1]])
transformed_x = np.concatenate((acf_x,ps_x),axis=1)
# transformed_x=acf_x
tree = deepcopy(self.base_estimator)
tree.fit(transformed_x, y)
self.classifiers.append(tree)
return self
def fit(self, X, y):
"""Build a forest of trees from the training set (X, y) using random
intervals and catch22/tsf summary features
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,
series_length] or shape = [n_instances,series_length]
The training input samples. If a Pandas data frame is passed it
must have a single column (i.e. univariate
classification).
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, coerce_to_numpy=True)
self.n_instances, self.n_dims, self.series_length = X.shape
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
if self.n_intervals is None:
self.__n_intervals = 4 + int(
(math.sqrt(self.series_length) * math.sqrt(self.n_dims)) / 3)
if self.__n_intervals <= 0:
self.__n_intervals = 1
if self.series_length < self.min_interval:
self.min_interval = self.series_length
if self.max_interval is None:
self.__max_interval = self.series_length / 2
if self.__max_interval < self.min_interval:
self.__max_interval = self.min_interval
_, X_p = signal.periodogram(X)
X_d = np.diff(X, 1)
self.total_intervals = self.__n_intervals * 2 + int(
self.__n_intervals / 2)
fit = Parallel(n_jobs=self.n_jobs)(delayed(self._fit_estimator)(
X,
X_p,
X_d,
y,
i,
) for i in range(self.n_estimators))
self.classifiers, self.intervals, self.dims, self.atts = zip(*fit)
self._is_fitted = True
return self
def fit(self, X, y):
"""Build a forest of trees from the training set (X, y) using random intervals and summary features
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,series_length] or shape = [n_instances,n_columns]
The training input samples. If a Pandas data frame is passed it must have a single column (i.e. univariate
classification. RISE has no bespoke method for multivariate classification as yet.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
if isinstance(X, pd.DataFrame):
if X.shape[1] > 1:
raise TypeError("TSF cannot handle multivariate problems yet")
elif isinstance(X.iloc[0,0], pd.Series):
X = np.asarray([a.values for a in X.iloc[:,0]])
else:
raise TypeError("Input should either be a 2d numpy array, or a pandas dataframe with a single column of Series objects (TSF cannot yet handle multivariate problems")
n_samps, self.series_length = X.shape
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.n_intervals = int(math.sqrt(self.series_length))
if self.n_intervals==0:
self.n_intervals = 1
if self.series_length <self.min_interval:
self.min_interval=self.series_length
self.intervals=np.zeros((self.n_trees, 3 * self.n_intervals, 2), dtype=int)
for i in range(0, self.n_trees):
transformed_x = np.empty(shape=(3 * self.n_intervals, n_samps))
# Find the random intervals for classifier i and concatentate features
for j in range(0, self.n_intervals):
self.intervals[i][j][0]=random.randint(self.series_length - self.min_interval)
length=random.randint(self.series_length - self.intervals[i][j][0] - 1)
if length < self.min_interval:
length = self.min_interval
self.intervals[i][j][1] = self.intervals[i][j][0] + length
# Transforms here, just hard coding it, so not configurable
means = np.mean(X[:, self.intervals[i][j][0]:self.intervals[i][j][1]], axis=1)
std_dev = np.std(X[:, self.intervals[i][j][0]:self.intervals[i][j][1]], axis=1)
slope = self.lsq_fit(X[:, self.intervals[i][j][0]:self.intervals[i][j][1]])
transformed_x[3*j]=means
transformed_x[3*j+1]=std_dev
transformed_x[3*j+2]=slope
tree = deepcopy(self.base_estimator)
transformed_x=transformed_x.T
tree.fit(transformed_x, y)
self.classifiers.append(tree)
return self
def fit(self, X, y):
X, y = check_X_y(X, y, enforce_univariate=True, coerce_to_numpy=True)
sfa = self.transformer.fit_transform(X, y)
self.transformed_data = sfa[0] # .iloc[:, 0]
self.class_vals = y
self.num_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
self._is_fitted = True
return self
def _fit(self, X, y):
self._n_jobs = check_n_jobs(self.n_jobs)
self.n_instances, self.n_dims, self.series_length = X.shape
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
if self.time_limit_in_minutes > 0:
# contracting 2/3 transform (with 1/5 of that taken away for final
# transform), 1/3 classifier
third = self.time_limit_in_minutes / 3
self._classifier_limit_in_minutes = third
self._transform_limit_in_minutes = (third * 2) / 5 * 4
elif self.transform_limit_in_minutes > 0:
self._transform_limit_in_minutes = self.transform_limit_in_minutes
self._transformer = RandomShapeletTransform(
n_shapelet_samples=self.n_shapelet_samples,
max_shapelets=self.max_shapelets,
max_shapelet_length=self.max_shapelet_length,
time_limit_in_minutes=self._transform_limit_in_minutes,
contract_max_n_shapelet_samples=self.
contract_max_n_shapelet_samples,
n_jobs=self.n_jobs,
batch_size=self.batch_size,
random_state=self.random_state,
)
self._estimator = _clone_estimator(
RotationForest() if self.estimator is None else self.estimator,
self.random_state,
)
if isinstance(self._estimator, RotationForest):
self._estimator.save_transformed_data = self.save_transformed_data
m = getattr(self._estimator, "n_jobs", None)
if m is not None:
self._estimator.n_jobs = self._n_jobs
m = getattr(self._estimator, "time_limit_in_minutes", None)
if m is not None and self.time_limit_in_minutes > 0:
self._estimator.time_limit_in_minutes = self._classifier_limit_in_minutes
X_t = self._transformer.fit_transform(X, y).to_numpy()
if self.save_transformed_data:
self.transformed_data = X_t
self._estimator.fit(X_t, y)
def fit(self, X, y):
"""Build a forest of trees from the training set (X, y).
Parameters
----------
Xt: np.ndarray or pd.DataFrame
Panel training data.
y : np.ndarray
The class labels.
Returns
-------
self : object
An fitted instance of the classifier
"""
X, y = check_X_y(
X,
y,
enforce_univariate=not self.capabilities["multivariate"],
coerce_to_numpy=True,
)
X = X.squeeze(1)
n_instances, self.series_length = X.shape
n_jobs = check_n_jobs(self.n_jobs)
rng = check_random_state(self.random_state)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.n_intervals = int(math.sqrt(self.series_length))
if self.n_intervals == 0:
self.n_intervals = 1
if self.series_length < self.min_interval:
self.min_interval = self.series_length
self.intervals_ = [
_get_intervals(self.n_intervals, self.min_interval,
self.series_length, rng)
for _ in range(self.n_estimators)
]
self.estimators_ = Parallel(n_jobs=n_jobs)(
delayed(_fit_estimator)(_clone_estimator(self.base_estimator, rng),
X, y, self.intervals_[i])
for i in range(self.n_estimators))
self._is_fitted = True
return self
def fit(self, X, y):
"""Perform a shapelet transform then builds a random forest.
Contract default for ST is 5 hours
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,
series_length] or shape = [n_instances,n_columns]
The training input samples. If a Pandas data frame is passed it
must have a single column (i.e. univariate
classification. RISE has no bespoke method for multivariate
classification as yet.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y, enforce_univariate=True)
# if y is a pd.series then convert to array.
if isinstance(y, pd.Series):
y = y.to_numpy()
# generate pipeline in fit so that random state can be propagated properly.
self.classifier_ = Pipeline([
(
"st",
ContractedShapeletTransform(
time_contract_in_mins=self.transform_contract_in_mins,
verbose=False,
random_state=self.random_state,
),
),
(
"rf",
RandomForestClassifier(n_estimators=self.n_estimators,
random_state=self.random_state),
),
])
self.n_classes_ = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.classifier_.fit(X, y)
self._is_fitted = True
return self
def fit(self, X, y):
"""Fit a tree on cases (X,y), where y is the target variable.
Build an information gain based tree for continuous attributes using the
margin gain metric for ties.
Parameters
----------
X : array-like or sparse matrix of shape = [n_instances,n_attributes]
The training input samples.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
if not isinstance(X, np.ndarray) or len(X.shape) > 2:
raise ValueError(
"ContinuousIntervalTree is not a time series classifier. "
"A 2d numpy array is required.")
X, y = check_X_y(X, y)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self._class_dictionary[classVal] = index
rng = check_random_state(self.random_state)
self.root = _TreeNode(random_state=rng)
thresholds = np.linspace(np.min(X, axis=0), np.max(X, axis=0), 20)
distribution_cls, distribution = unique_count(y)
e = _entropy(distribution, distribution.sum())
self.root.build_tree(
X,
y,
thresholds,
e,
distribution_cls,
distribution,
0,
self.max_depth,
False,
)
self._is_fitted = True
return self
def _fit(self, X, y):
self._n_jobs = check_n_jobs(self.n_jobs)
self.n_instances, self.n_dims, self.series_length = X.shape
self._class_vals = y
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self._class_dictionary[classVal] = index
# select dimensions using accuracy estimate if multivariate
if self.n_dims > 1:
self._dims, self._transformers = self._select_dims(X, y)
words = [defaultdict(int) for _ in range(self.n_instances)]
for i, dim in enumerate(self._dims):
X_dim = X[:, dim, :].reshape(self.n_instances, 1,
self.series_length)
dim_words = self._transformers[i].transform(X_dim, y)
dim_words = dim_words[0]
for n in range(self.n_instances):
for word, count in dim_words[n].items():
words[n][word << self._highest_dim_bit | dim] = count
self._transformed_data = words
else:
self._transformers.append(
SFA(
word_length=self.word_length,
alphabet_size=self.alphabet_size,
window_size=self.window_size,
norm=self.norm,
levels=self.levels,
binning_method="information-gain"
if self.igb else "equi-depth",
bigrams=self.bigrams,
remove_repeat_words=True,
lower_bounding=False,
save_words=False,
use_fallback_dft=True,
n_jobs=self._n_jobs,
))
sfa = self._transformers[0].fit_transform(X, y)
self._transformed_data = sfa[0]
def fit(self, X, y):
"""
Build a single or ensemble of pipelines containing the ROCKET transformer and
RidgeClassifierCV classifier.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
if self.ensemble:
for i in range(self.ensemble_size):
rocket_pipeline = make_pipeline(
Rocket(num_kernels=self.num_kernels,
random_state=self.random_state),
RidgeClassifierCV(alphas=np.logspace(-3, 3, 10),
normalize=True),
)
rocket_pipeline.fit(X, y)
self.classifiers.append(rocket_pipeline)
self.weights.append(rocket_pipeline.steps[1][1].best_score_)
self.weight_sum = self.weight_sum + self.weights[i]
else:
rocket_pipeline = make_pipeline(
Rocket(num_kernels=self.num_kernels,
random_state=self.random_state),
RidgeClassifierCV(alphas=np.logspace(-3, 3, 10),
normalize=True),
)
rocket_pipeline.fit(X, y)
self.classifiers.append(rocket_pipeline)
self._is_fitted = True
return self
def _fit(self, X, y):
self._n_jobs = check_n_jobs(self.n_jobs)
self.n_instances, self.n_dims, self.series_length = X.shape
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
if self.base_estimator == "DTC":
self._base_estimator = DecisionTreeClassifier(criterion="entropy")
elif self.base_estimator == "CIT":
self._base_estimator = ContinuousIntervalTree()
elif isinstance(self.base_estimator, BaseEstimator):
self._base_estimator = self.base_estimator
else:
raise ValueError("DrCIF invalid base estimator given.")
if self.n_intervals is None:
self._n_intervals = int(
math.sqrt(self.series_length) * math.sqrt(self.n_dims)
)
if self._n_intervals <= 0:
self._n_intervals = 1
if self.att_subsample_size > 25:
self._att_subsample_size = 25
if self.series_length < self.min_interval:
self._min_interval = self.series_length
elif self.min_interval < 3:
self._min_interval = 3
if self.max_interval is None:
self._max_interval = self.series_length / 2
if self._max_interval < self._min_interval:
self._max_interval = self._min_interval
fit = Parallel(n_jobs=self._n_jobs)(
delayed(self._fit_estimator)(
X,
y,
i,
)
for i in range(self.n_estimators)
)
self.estimators_, self.intervals, self.dims, self.atts = zip(*fit)
def fit(self, X, y):
if isinstance(X, pd.Series) or isinstance(X, pd.DataFrame):
X, y = check_X_y(X, y, enforce_univariate=True)
X = tabularize(X, return_array=True)
sfa = self.transformer.fit_transform(X, y)
self.transformed_data = sfa[0] # .iloc[:, 0]
self.class_vals = y
self.num_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
self._is_fitted = True
return self
def fit(self, X, y):
"""Fit an estimator using transformed data from the Catch22 transformer.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, n_dims]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y)
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
self.n_classes = np.unique(y).shape[0]
self._transformer = (TSFreshRelevantFeatureExtractor(
default_fc_parameters=self.default_fc_parameters,
n_jobs=self.n_jobs,
chunksize=self.chunksize,
) if self.relevant_feature_extractor else TSFreshFeatureExtractor(
default_fc_parameters=self.default_fc_parameters,
n_jobs=self.n_jobs,
chunksize=self.chunksize,
))
self._estimator = _clone_estimator(
RandomForestClassifier(n_estimators=200)
if self.estimator is None else self.estimator,
self.random_state,
)
if self.verbose < 2:
self._transformer.show_warnings = False
if self.verbose < 1:
self._transformer.disable_progressbar = True
m = getattr(self._estimator, "n_jobs", None)
if callable(m):
self._estimator.n_jobs = self.n_jobs
X_t = self._transformer.fit_transform(X, y)
self._estimator.fit(X_t, y)
self._is_fitted = True
return self
def fit(self, X, y):
"""
Build an ensemble of pipelines containing the ROCKET transformer and
RidgeClassifierCV classifier.
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X, y = check_X_y(X, y)
n_jobs = check_n_jobs(self.n_jobs)
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self.class_dictionary[classVal] = index
base_estimator = _make_estimator(self.num_kernels, self.random_state)
self.estimators_ = Parallel(n_jobs=n_jobs)(
delayed(_fit_estimator)(_clone_estimator(base_estimator,
self.random_state), X, y)
for _ in range(self.n_estimators))
self.weights = []
self.weight_sum = 0
for rocket_pipeline in self.estimators_:
weight = rocket_pipeline.steps[1][1].best_score_
self.weights.append(weight)
self.weight_sum += weight
self._is_fitted = True
return self
def fit(self, X, y):
"""Fit a random catch22 feature forest classifier
Parameters
----------
X : nested pandas DataFrame of shape [n_instances, 1]
Nested dataframe with univariate time-series in cells.
y : array-like, shape = [n_instances] The class labels.
Returns
-------
self : object
"""
X = check_X(X, enforce_univariate=False, coerce_to_numpy=True)
n_instances = X.shape[0]
X = np.reshape(X, (n_instances, -1))
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
c22_list = []
for i in range(n_instances):
series = X[i, :]
c22_dict = catch22_all(series)
c22_list.append(c22_dict["values"])
self.classifier = RandomForestClassifier(
n_jobs=self.n_jobs,
n_estimators=self.n_estimators,
random_state=self.random_state,
)
X_c22 = np.array(c22_list)
np.nan_to_num(X_c22, False, 0, 0, 0)
self.classifier.fit(X_c22, y)
self._is_fitted = True
return self
def _fit(self, X, y):
self._n_jobs = check_n_jobs(self.n_jobs)
if self.n_parameter_samples <= self.randomly_selected_params:
print( # noqa
"TDE Warning: n_parameter_samples <= randomly_selected_params, ",
"ensemble member parameters will be fully randomly selected.",
)
time_limit = self.time_limit_in_minutes * 60
self.n_instances, self.n_dims, self.series_length = X.shape
self.n_classes = np.unique(y).shape[0]
self.classes_ = class_distribution(np.asarray(y).reshape(-1, 1))[0][0]
for index, classVal in enumerate(self.classes_):
self._class_dictionary[classVal] = index
self.estimators_ = []
self.weights = []
self._prev_parameters_x = []
self._prev_parameters_y = []
# Window length parameter space dependent on series length
max_window_searches = self.series_length / 4
max_window = int(self.series_length * self.max_win_len_prop)
win_inc = int((max_window - self.min_window) / max_window_searches)
if win_inc < 1:
win_inc = 1
if self.min_window > max_window + 1:
raise ValueError(
f"Error in TemporalDictionaryEnsemble, min_window ="
f"{self.min_window} is bigger"
f" than max_window ={max_window},"
f" series length is {self.series_length}"
f" try set min_window to be smaller than series length in "
f"the constructor, but the classifier may not work at "
f"all with very short series")
possible_parameters = self._unique_parameters(max_window, win_inc)
num_classifiers = 0
subsample_size = int(self.n_instances * 0.7)
lowest_acc = 1
lowest_acc_idx = 0
time_limit = self.time_limit_in_minutes * 60
start_time = time.time()
train_time = 0
if time_limit > 0:
n_parameter_samples = 0
else:
n_parameter_samples = self.n_parameter_samples
rng = check_random_state(self.random_state)
if self.bigrams is None:
if self.n_dims > 1:
use_bigrams = False
else:
use_bigrams = True
else:
use_bigrams = self.bigrams
# use time limit or n_parameter_samples if limit is 0
while (train_time < time_limit or num_classifiers < n_parameter_samples
) and len(possible_parameters) > 0:
if num_classifiers < self.randomly_selected_params:
parameters = possible_parameters.pop(
rng.randint(0, len(possible_parameters)))
else:
scaler = preprocessing.StandardScaler()
scaler.fit(self._prev_parameters_x)
gp = KernelRidge(kernel="poly", degree=1)
gp.fit(scaler.transform(self._prev_parameters_x),
self._prev_parameters_y)
preds = gp.predict(scaler.transform(possible_parameters))
parameters = possible_parameters.pop(
rng.choice(np.flatnonzero(preds == preds.max())))
subsample = rng.choice(self.n_instances,
size=subsample_size,
replace=False)
X_subsample = X[subsample]
y_subsample = y[subsample]
tde = IndividualTDE(
*parameters,
alphabet_size=self._alphabet_size,
bigrams=use_bigrams,
dim_threshold=self.dim_threshold,
max_dims=self.max_dims,
random_state=self.random_state,
)
tde.fit(X_subsample, y_subsample)
tde._subsample = subsample
if self.save_train_predictions:
tde._train_predictions = np.zeros(subsample_size)
tde._accuracy = self._individual_train_acc(
tde,
y_subsample,
subsample_size,
0 if num_classifiers < self.max_ensemble_size else lowest_acc,
)
if tde._accuracy > 0:
weight = math.pow(tde._accuracy, 4)
else:
weight = 0.000000001
if num_classifiers < self.max_ensemble_size:
if tde._accuracy < lowest_acc:
lowest_acc = tde._accuracy
lowest_acc_idx = num_classifiers
self.weights.append(weight)
self.estimators_.append(tde)
elif tde._accuracy > lowest_acc:
self.weights[lowest_acc_idx] = weight
self.estimators_[lowest_acc_idx] = tde
lowest_acc, lowest_acc_idx = self._worst_ensemble_acc()
self._prev_parameters_x.append(parameters)
self._prev_parameters_y.append(tde._accuracy)
num_classifiers += 1
train_time = time.time() - start_time
self.n_estimators = len(self.estimators_)
self._weight_sum = np.sum(self.weights)
def fit(self, X, y, sample_weight=None):
"""Fit the random classifier.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
Target values.
sample_weight : array-like of shape = [n_samples], optional
Sample weights.
Returns
-------
self : object
Returns self.
"""
if self.strategy not in ("most_frequent", "stratified", "uniform",
"constant"):
raise ValueError("Unknown strategy type.")
if self.strategy == "uniform" and sp.issparse(y):
y = y.toarray()
warnings.warn('A local copy of the target data has been converted '
'to a numpy array. Predicting on sparse target data '
'with the uniform strategy would not save memory '
'and would be slower.',
UserWarning)
self.sparse_output_ = sp.issparse(y)
if not self.sparse_output_:
y = np.atleast_1d(y)
self.output_2d_ = y.ndim == 2
if y.ndim == 1:
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
if self.strategy == "constant":
if self.constant is None:
raise ValueError("Constant target value has to be specified "
"when the constant strategy is used.")
else:
constant = np.reshape(np.atleast_1d(self.constant), (-1, 1))
if constant.shape[0] != self.n_outputs_:
raise ValueError("Constant target value should have "
"shape (%d, 1)." % self.n_outputs_)
(self.classes_,
self.n_classes_,
self.class_prior_) = class_distribution(y, sample_weight)
if self.strategy == "constant":
for k in range(self.n_outputs_):
# Checking in case of constant strategy if the constant
# provided by the user is in y.
if constant[k] not in self.classes_[k]:
raise ValueError("The constant target value must be "
"present in training data")
if self.n_outputs_ == 1 and not self.output_2d_:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
self.class_prior_ = self.class_prior_[0]
return self
