def load_basic_motions(split=None, return_X_y=True, return_type=None):
"""
Load the BasicMotions time series classification problem and returns X and y.
This is an equal length multivariate time series classification problem. It loads a
4 class classification problem with number of cases, n, where n = 80 (if
split is None) or 40 (if split is "train"/"test") of series length m = 100.
Parameters
----------
split: None or str{"train", "test"}, optional (default=None)
Whether to load the train or test partition of the problem. By
default it loads both.
return_X_y: bool, optional (default=True)
If True, returns (time series, target) separately as X and y instead of a single
data structure.
return_type: None or str{"numpy3d", "nested_univ"},
optional (default=None). Controls the returned data structure.
Returns
-------
X: The time series data for the problem. If return_type is either
"numpy2d"/"numpyflat", it returns 2D numpy array of shape (n,m), if "numpy3d" it
returns 3D numpy array of shape (n,6,m) and if "nested_univ" or None it returns
a nested pandas DataFrame of shape (n,6), where each cell is a pd.Series of
length m.
y: (optional) numpy array shape (n,1). The class labels for each case in X.
If return_X_y is False, y is appended to X.
Raises
------
ValueError if argument "numpy2d"/"numpyflat" is passed as return_type
Notes
-----
Dimensionality: multivariate, 6
Series length: 100
Train cases: 40
Test cases: 40
Number of classes: 4
The data was generated as part of a student project where four students performed
four activities whilst wearing a smart watch. The watch collects 3D accelerometer
and a 3D gyroscope It consists of four classes, which are walking, resting,
running and badminton. Participants were required to record motion a total of
five times, and the data is sampled once every tenth of a second, for a ten second
period.
Dataset details: http://www.timeseriesclassification.com/description.php?Dataset
=BasicMotions
"""
name = "BasicMotions"
if return_type == "numpy2d" or return_type == "numpyflat":
raise ValueError(
f"{name} loader: Error, attempting to load into a numpy2d "
f"array, but cannot because it is a multivariate problem. Use "
f"numpy3d instead")
return _load_provided_dataset(name=name,
split=split,
return_X_y=return_X_y,
return_type=return_type)
def load_arrow_head(split=None, return_X_y=True, return_type="nested_univ"):
"""
Load the ArrowHead time series classification problem and returns X and y.
Parameters
----------
split: None or str{"train", "test"}, optional (default=None)
Whether to load the train or test partition of the problem. By
default it loads both.
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for
features and the target.
Returns
-------
X: pd.DataFrame with m rows and c columns
The time series data for the problem with m cases and c dimensions
y: numpy array
The class labels for each case in X
Examples
--------
>>> from sktime.datasets import load_arrow_head
>>> X, y = load_arrow_head()
Notes
-----
Dimensionality: univariate
Series length: 251
Train cases: 36
Test cases: 175
Number of classes: 3
The arrowhead data consists of outlines of the images of arrowheads. The
shapes of the
projectile points are converted into a time series using the angle-based
method. The
classification of projectile points is an important topic in
anthropology. The classes
are based on shape distinctions such as the presence and location of a
notch in the
arrow. The problem in the repository is a length normalised version of
that used in
Ye09shapelets. The three classes are called "Avonlea", "Clovis" and "Mix"."
Dataset details: http://timeseriesclassification.com/description.php
?Dataset=ArrowHead
"""
name = "ArrowHead"
return _load_provided_dataset(name=name,
split=split,
return_X_y=return_X_y,
return_type=return_type)
def load_unit_test(split=None, return_X_y=True, return_type=None):
"""
Load UnitTest data.
This is an equal length univariate time series classification problem. It is a
stripped down version of the ChinaTown problem that is used in correctness tests
for classification. It loads a two class classification problem with number of
cases, n, where n = 42 (if split is None) or 20/22 (if split is "train"/"test")
of series length m = 24
Parameters
----------
split: None or str{"train", "test"}, optional (default=None)
Whether to load the train or test partition of the problem. By default it
loads both.
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a concatenated data
structure.
return_type: None or str{"numpy2d", "numpyflat", "numpy3d", "nested_univ"},
optional (default=None). Controls the returned data structure.
Returns
-------
X: The time series data for the problem. If return_type is either
"numpy2d"/"numpyflat", it returns 2D numpy array of shape (n,m), if "numpy3d" it
returns 3D numpy array of shape (n,1,m) and if "nested_univ" or None it returns
a nested pandas DataFrame of shape (n,1), where each cell is a pd.Series of
length m.
y: (optional) numpy array shape (n,1). The class labels for each case in X.
If return_X_y is False, y is appended to X.
Examples
--------
>>> from sktime.datasets import load_unit_test
>>> X, y = load_unit_test()
Details
-------
This is the Chinatown problem with a smaller test set, useful for rapid tests.
Dimensionality: univariate
Series length: 24
Train cases: 20
Test cases: 22 (full dataset has 345)
Number of classes: 2
See
http://timeseriesclassification.com/description.php?Dataset=Chinatown
for the full dataset
"""
name = "UnitTest"
return _load_provided_dataset(name, split, return_X_y, return_type)
def load_basic_motions(split=None, return_X_y=True, return_type="nested_univ"):
"""
Load the BasicMotions time series classification problem and returns X and y.
Parameters
----------
split: None or str{"train", "test"}, optional (default=None)
Whether to load the train or test partition of the problem. By
default it loads both.
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for
features and the target.
Returns
-------
X: pandas DataFrame with m rows and c columns
The time series data for the problem with m cases and c dimensions
y: numpy array
The class labels for each case in X
Notes
-----
Dimensionality: multivariate, 6
Series length: 100
Train cases: 40
Test cases: 40
Number of classes: 4
The data was generated as part of a student project where four students performed
four activities whilst wearing a smart watch. The watch collects 3D accelerometer
and a 3D gyroscope It consists of four classes, which are walking, resting,
running and badminton. Participants were required to record motion a total of
five times, and the data is sampled once every tenth of a second, for a ten second
period.
Dataset details: http://www.timeseriesclassification.com/description.php?Dataset
=BasicMotions
"""
name = "BasicMotions"
return _load_provided_dataset(name=name,
split=split,
return_X_y=return_X_y,
return_type=return_type)
def load_unit_test(split=None, return_X_y=True):
"""
Load UnitTest time series classification problem.
This problem is a stripped down version of the ChinaTown problem that is used in
correctness tests for classification.
Parameters
----------
split: None or str{"train", "test"}, optional (default=None)
Whether to load the train or test partition of the problem. By
default it loads both.
return_X_y: bool, optional (default=True)
If True, returns (features, target) separately instead of a single
dataframe with columns for
features and the target.
Returns
-------
X: pandas DataFrame with m rows and c columns
The time series data for the problem with m cases and c dimensions
y: numpy array
The class labels for each case in X
Details
-------
This is the Chinatown problem with a smaller test set, useful for rapid tests. See
http://timeseriesclassification.com/description.php?Dataset=Chinatown
for the full dataset
Dimensionality: univariate
Series length: 24
Train cases: 20
Test cases: 22 (full dataset has 345)
Number of classes: 2
"""
name = "UnitTest"
return _load_provided_dataset(name, split, return_X_y)