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):
self.n_instances_, self.n_dims_, self.series_length_ = X.shape
if self.base_estimator.lower() == "dtc":
self._base_estimator = DecisionTreeClassifier(criterion="entropy")
elif self.base_estimator.lower() == "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._threads_to_use)(
delayed(self._fit_estimator)(
X,
y,
i,
) for i in range(self.n_estimators))
self.estimators_, self.intervals_, self.dims_, self.atts_ = zip(*fit)
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]
time_limit = self.time_limit_in_minutes * 60
start_time = time.time()
train_time = 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.")
X_p = np.zeros(
(
self.n_instances,
self.n_dims,
int(
math.pow(2, math.ceil(math.log(self.series_length, 2)))
- self.series_length
),
)
)
X_p = np.concatenate((X, X_p), axis=2)
X_p = np.abs(np.fft.fft(X_p)[:, :, : int(X_p.shape[2] / 2)])
X_d = np.diff(X, 1)
if self.n_intervals is None:
self._n_intervals = [None, None, None]
self._n_intervals[0] = 4 + int(
(math.sqrt(self.series_length) * math.sqrt(self.n_dims)) / 3
)
self._n_intervals[1] = 4 + int(
(math.sqrt(X_p.shape[2]) * math.sqrt(self.n_dims)) / 3
)
self._n_intervals[2] = 4 + int(
(math.sqrt(X_d.shape[2]) * math.sqrt(self.n_dims)) / 3
)
elif isinstance(self.n_intervals, int):
self._n_intervals = [self.n_intervals, self.n_intervals, self.n_intervals]
elif isinstance(self.n_intervals, list) and len(self.n_intervals) == 3:
self._n_intervals = self.n_intervals
else:
raise ValueError("DrCIF n_intervals must be an int or list of length 3.")
for i, n in enumerate(self._n_intervals):
if n <= 0:
self._n_intervals[i] = 1
if self.att_subsample_size > 25:
self._att_subsample_size = 25
if isinstance(self.min_interval, int):
self._min_interval = [
self.min_interval,
self.min_interval,
self.min_interval,
]
elif isinstance(self.min_interval, list) and len(self.min_interval) == 3:
self._min_interval = self.min_interval
else:
raise ValueError("DrCIF min_interval must be an int or list of length 3.")
if self.series_length < self._min_interval[0]:
self._min_interval[0] = self.series_length
if X_p.shape[2] < self._min_interval[1]:
self._min_interval[1] = X_p.shape[2]
if X_d.shape[2] < self._min_interval[2]:
self._min_interval[2] = X_d.shape[2]
if self.max_interval is None:
self._max_interval = [
self.series_length / 2,
X_p.shape[2] / 2,
X_d.shape[2] / 2,
]
elif isinstance(self.max_interval, int):
self._max_interval = [
self.max_interval,
self.max_interval,
self.max_interval,
]
elif isinstance(self.max_interval, list) and len(self.max_interval) == 3:
self._max_interval = self.max_interval
else:
raise ValueError("DrCIF max_interval must be an int or list of length 3.")
for i, n in enumerate(self._max_interval):
if n < self._min_interval[i]:
self._max_interval[i] = self._min_interval[i]
self.total_intervals = sum(self._n_intervals)
if time_limit > 0:
self._n_estimators = 0
self.estimators_ = []
self.intervals = []
self.atts = []
self.dims = []
self.transformed_data = []
while (
train_time < time_limit
and self._n_estimators < self.contract_max_n_estimators
):
fit = Parallel(n_jobs=self._n_jobs)(
delayed(self._fit_estimator)(
X,
X_p,
X_d,
y,
i,
)
for i in range(self._n_jobs)
)
(
estimators,
intervals,
dims,
atts,
transformed_data,
) = zip(*fit)
self.estimators_ += estimators
self.intervals += intervals
self.atts += atts
self.dims += dims
self.transformed_data += transformed_data
self._n_estimators += self._n_jobs
train_time = time.time() - start_time
else:
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.estimators_,
self.intervals,
self.dims,
self.atts,
self.transformed_data,
) = zip(*fit)
def _fit(self, X, y):
self.n_instances_, self.n_dims_, self.series_length_ = X.shape
time_limit = self.time_limit_in_minutes * 60
start_time = time.time()
train_time = 0
if self.base_estimator.lower() == "dtc":
self._base_estimator = DecisionTreeClassifier(criterion="entropy")
elif self.base_estimator.lower() == "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.")
X_p = np.zeros((
self.n_instances_,
self.n_dims_,
int(
math.pow(2, math.ceil(math.log(self.series_length_, 2))) -
self.series_length_),
))
X_p = np.concatenate((X, X_p), axis=2)
X_p = np.abs(np.fft.fft(X_p)[:, :, :int(X_p.shape[2] / 2)])
X_d = np.diff(X, 1)
if self.n_intervals is None:
self._n_intervals = [None, None, None]
self._n_intervals[0] = 4 + int(
(math.sqrt(self.series_length_) * math.sqrt(self.n_dims_)) / 3)
self._n_intervals[1] = 4 + int(
(math.sqrt(X_p.shape[2]) * math.sqrt(self.n_dims_)) / 3)
self._n_intervals[2] = 4 + int(
(math.sqrt(X_d.shape[2]) * math.sqrt(self.n_dims_)) / 3)
elif isinstance(self.n_intervals, int):
self._n_intervals = [
self.n_intervals, self.n_intervals, self.n_intervals
]
elif isinstance(self.n_intervals, list) and len(self.n_intervals) == 3:
self._n_intervals = self.n_intervals
else:
raise ValueError(
"DrCIF n_intervals must be an int or list of length 3.")
for i, n in enumerate(self._n_intervals):
if n <= 0:
self._n_intervals[i] = 1
if self.att_subsample_size > 29:
self._att_subsample_size = 29
if isinstance(self.min_interval, int):
self._min_interval = [
self.min_interval,
self.min_interval,
self.min_interval,
]
elif isinstance(self.min_interval, list) and len(
self.min_interval) == 3:
self._min_interval = self.min_interval
else:
raise ValueError(
"DrCIF min_interval must be an int or list of length 3.")
if self.series_length_ < self._min_interval[0]:
self._min_interval[0] = self.series_length_
if X_p.shape[2] < self._min_interval[1]:
self._min_interval[1] = X_p.shape[2]
if X_d.shape[2] < self._min_interval[2]:
self._min_interval[2] = X_d.shape[2]
if self.max_interval is None:
self._max_interval = [
int(self.series_length_ / 2),
int(X_p.shape[2] / 2),
int(X_d.shape[2] / 2),
]
elif isinstance(self.max_interval, int):
self._max_interval = [
self.max_interval,
self.max_interval,
self.max_interval,
]
elif isinstance(self.max_interval, list) and len(
self.max_interval) == 3:
self._max_interval = self.max_interval
else:
raise ValueError(
"DrCIF max_interval must be an int or list of length 3.")
for i, n in enumerate(self._max_interval):
if n < self._min_interval[i]:
self._max_interval[i] = self._min_interval[i]
self.total_intervals_ = sum(self._n_intervals)
if time_limit > 0:
self._n_estimators = 0
self.estimators_ = []
self.intervals_ = []
self.atts_ = []
self.dims_ = []
self.transformed_data_ = []
while (train_time < time_limit
and self._n_estimators < self.contract_max_n_estimators):
fit = Parallel(n_jobs=self._threads_to_use)(
delayed(self._fit_estimator)(
X,
X_p,
X_d,
y,
i,
) for i in range(self._threads_to_use))
(
estimators,
intervals,
dims,
atts,
transformed_data,
) = zip(*fit)
self.estimators_ += estimators
self.intervals_ += intervals
self.atts_ += atts
self.dims_ += dims
self.transformed_data_ += transformed_data
self._n_estimators += self._threads_to_use
train_time = time.time() - start_time
else:
fit = Parallel(n_jobs=self._threads_to_use)(
delayed(self._fit_estimator)(
X,
X_p,
X_d,
y,
i,
) for i in range(self._n_estimators))
(
self.estimators_,
self.intervals_,
self.dims_,
self.atts_,
self.transformed_data_,
) = zip(*fit)
return self