def silhouette_score(X, labels, metric=None, sample_size=None,
metric_params=None, n_jobs=None, verbose=0,
random_state=None, **kwds):
"""Compute the mean Silhouette Coefficient of all samples (cf. [1]_ and
[2]_).
Read more in the `scikit-learn documentation
<http://scikit-learn.org/stable/modules/clustering.html\
#silhouette-coefficient>`_.
Parameters
----------
X : array [n_ts, n_ts] if metric == "precomputed", or, \
[n_ts, sz, d] otherwise
Array of pairwise distances between time series, or a time series
dataset.
labels : array, shape = [n_ts]
Predicted labels for each time series.
metric : string, callable or None (default: None)
The metric to use when calculating distance between time series.
Should be one of {'dtw', 'softdtw', 'euclidean'} or a callable distance
function or None.
If 'softdtw' is passed, a normalized version of Soft-DTW is used that
is defined as `sdtw_(x,y) := sdtw(x,y) - 1/2(sdtw(x,x)+sdtw(y,y))`.
If X is the distance array itself, use ``metric="precomputed"``.
If None, dtw is used.
sample_size : int or None (default: None)
The size of the sample to use when computing the Silhouette Coefficient
on a random subset of the data.
If ``sample_size is None``, no sampling is used.
metric_params : dict or None (default: None)
Parameter values for the chosen metric.
For metrics that accept parallelization of the cross-distance matrix
computations, `n_jobs` key passed in `metric_params` is overridden by
the `n_jobs` argument.
n_jobs : int or None, optional (default=None)
The number of jobs to run in parallel for cross-distance matrix
computations.
Ignored if the cross-distance matrix cannot be computed using
parallelization.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See scikit-learns'
`Glossary <https://scikit-learn.org/stable/glossary.html#term-n-jobs>`_
for more details.
verbose : int (default: 0)
If nonzero, print information about the inertia while learning
the model and joblib progress messages are printed.
random_state : int, RandomState instance or None, optional (default: None)
The generator used to randomly select a subset of samples. If int,
random_state is the seed used by the random number generator; If
RandomState instance, random_state is the random number generator; If
None, the random number generator is the RandomState instance used by
`np.random`. Used when ``sample_size is not None``.
**kwds : optional keyword parameters
Any further parameters are passed directly to the distance function,
just as for the `metric_params` parameter.
Returns
-------
silhouette : float
Mean Silhouette Coefficient for all samples.
References
----------
.. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the
Interpretation and Validation of Cluster Analysis". Computational
and Applied Mathematics 20: 53-65.
<http://www.sciencedirect.com/science/article/pii/0377042787901257>`_
.. [2] `Wikipedia entry on the Silhouette Coefficient
<https://en.wikipedia.org/wiki/Silhouette_(clustering)>`_
Examples
--------
>>> from tslearn.generators import random_walks
>>> from tslearn.metrics import cdist_dtw
>>> numpy.random.seed(0)
>>> X = random_walks(n_ts=20, sz=16, d=1)
>>> labels = numpy.random.randint(2, size=20)
>>> silhouette_score(X, labels, metric="dtw") # doctest: +ELLIPSIS
0.13383800...
>>> silhouette_score(X, labels, metric="euclidean") # doctest: +ELLIPSIS
0.09126917...
>>> silhouette_score(X, labels, metric="softdtw") # doctest: +ELLIPSIS
0.17953934...
>>> silhouette_score(X, labels, metric="softdtw",
... metric_params={"gamma": 2.}) \
# doctest: +ELLIPSIS
0.17591060...
>>> silhouette_score(cdist_dtw(X), labels,
... metric="precomputed") # doctest: +ELLIPSIS
0.13383800...
"""
sklearn_metric = None
if metric_params is None:
metric_params_ = {}
else:
metric_params_ = metric_params.copy()
for k in kwds.keys():
metric_params_[k] = kwds[k]
if "n_jobs" in metric_params_.keys():
del metric_params_["n_jobs"]
if metric == "precomputed":
sklearn_X = X
elif metric == "dtw" or metric is None:
sklearn_X = cdist_dtw(X, n_jobs=n_jobs, verbose=verbose,
**metric_params_)
elif metric == "softdtw":
sklearn_X = cdist_soft_dtw_normalized(X, **metric_params_)
elif metric == "euclidean":
X_ = to_time_series_dataset(X)
X_ = X_.reshape((X.shape[0], -1))
sklearn_X = cdist(X_, X_, metric="euclidean")
else:
X_ = to_time_series_dataset(X)
n, sz, d = X_.shape
sklearn_X = X_.reshape((n, -1))
def sklearn_metric(x, y):
return metric(to_time_series(x.reshape((sz, d)),
remove_nans=True),
to_time_series(y.reshape((sz, d)),
remove_nans=True))
metric = "precomputed" if sklearn_metric is None else sklearn_metric
return sklearn_silhouette_score(X=sklearn_X,
labels=labels,
metric=metric,
sample_size=sample_size,
random_state=random_state,
**kwds)
def silhouette_score(X,
labels,
metric=None,
sample_size=None,
metric_params=None,
random_state=None,
**kwds):
"""Compute the mean Silhouette Coefficient of all samples (cf. [1]_ and [2]_).
Read more in the `scikit-learn documentation
<http://scikit-learn.org/stable/modules/clustering.html#silhouette-coefficient>`_.
Parameters
----------
X : array [n_ts, n_ts] if metric == "precomputed", or, \
[n_ts, sz, d] otherwise
Array of pairwise distances between time series, or a time series
dataset.
labels : array, shape = [n_ts]
Predicted labels for each time series.
metric : string, or callable
The metric to use when calculating distance between time series.
Should be one of {'dtw', 'softdtw', 'euclidean'} or a callable distance
function.
If 'softdtw' is passed, a normalized version of Soft-DTW is used that
is defined as `sdtw_(x,y) := sdtw(x,y) - 1/2(sdtw(x,x)+sdtw(y,y))`.
If X is the distance array itself, use ``metric="precomputed"``.
sample_size : int or None
The size of the sample to use when computing the Silhouette Coefficient
on a random subset of the data.
If ``sample_size is None``, no sampling is used.
metric_params : dict or None
Parameter values for the chosen metric. Value associated to the
`"gamma_sdtw"` key corresponds to the gamma parameter in Soft-DTW.
random_state : int, RandomState instance or None, optional (default=None)
The generator used to randomly select a subset of samples. If int,
random_state is the seed used by the random number generator; If
RandomState instance, random_state is the random number generator; If
None, the random number generator is the RandomState instance used by
`np.random`. Used when ``sample_size is not None``.
**kwds : optional keyword parameters
Any further parameters are passed directly to the distance function.
Returns
-------
silhouette : float
Mean Silhouette Coefficient for all samples.
References
----------
.. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the
Interpretation and Validation of Cluster Analysis". Computational
and Applied Mathematics 20: 53-65.
<http://www.sciencedirect.com/science/article/pii/0377042787901257>`_
.. [2] `Wikipedia entry on the Silhouette Coefficient
<https://en.wikipedia.org/wiki/Silhouette_(clustering)>`_
Examples
--------
>>> from tslearn.generators import random_walks
>>> from tslearn.metrics import cdist_dtw
>>> X = random_walks(n_ts=50, sz=32, d=1)
>>> labels = numpy.random.randint(2, size=50)
>>> s_sc = silhouette_score(X, labels, metric="dtw")
>>> s_sc2 = silhouette_score(X, labels, metric="euclidean")
>>> s_sc3 = silhouette_score(X, labels, metric="softdtw")
>>> s_sc3b = silhouette_score(X, labels, metric="softdtw", metric_params={"gamma_sdtw": 2.})
>>> s_sc4 = silhouette_score(cdist_dtw(X), labels, metric="precomputed")
"""
sklearn_metric = None
if metric_params is None:
metric_params = {}
if metric == "precomputed":
sklearn_X = X
elif metric == "dtw":
sklearn_X = cdist_dtw(X)
elif metric == "softdtw":
gamma = metric_params.get("gamma_sdtw", None)
if gamma is not None:
sklearn_X = cdist_soft_dtw_normalized(X, gamma=gamma)
else:
sklearn_X = cdist_soft_dtw_normalized(X)
elif metric == "euclidean":
X_ = to_time_series_dataset(X)
X_ = X_.reshape((X.shape[0], -1))
sklearn_X = cdist(X_, X_, metric="euclidean")
else:
X_ = to_time_series_dataset(X)
n, sz, d = X_.shape
sklearn_X = X_.reshape((n, -1))
if metric is None:
metric = dtw
sklearn_metric = lambda x, y: metric(
to_time_series(x.reshape((sz, d)), remove_nans=True),
to_time_series(y.reshape((sz, d)), remove_nans=True))
return sklearn_silhouette_score(
X=sklearn_X,
labels=labels,
metric="precomputed" if sklearn_metric is None else sklearn_metric,
sample_size=sample_size,
random_state=random_state,
**kwds)
PATH = "G:/Coding/ML/UCRArchive_2018/" # Change this value if necessary dataset = "CBF" file_train = PATH + str(dataset) + "/" + str(dataset) + "_TRAIN.tsv" file_test = PATH + str(dataset) + "/" + str(dataset) + "_TEST.tsv" train = np.genfromtxt(fname=file_train, delimiter="\t", skip_header=0) test = np.genfromtxt(fname=file_test, delimiter="\t", skip_header=0) X_train, y_train = train[:, 1:], train[:, 0] X_test, y_test = test[:, 1:], test[:, 0] #Feature extraction train_softdtw= cdist_soft_dtw_normalized(X_train,X_train) test_softdtw = cdist_soft_dtw_normalized(X_train, X_test) #train_dtw= cdist_dtw(X_train,X_train) # #train_dtw = np.transpose(train) #test_dtw = np.transpose(test) #train_softdtw = np.transpose(train) #test_softdtw = np.transpose(test) #test = np.vstack((test_softdtw,test_dtw)) #train = np.vstack((train_dtw,train_softdtw)) train = np.transpose(train_softdtw) test = np.transpose(test_softdtw)