def transform(self, X, y=None):
"""Concatenate multivariate time series/panel data into long
univariate time series/panel
data by simply concatenating times series in time.
Parameters
----------
X : nested pandas DataFrame of shape [n_samples, n_features]
Nested dataframe with time-series in cells.
Returns
-------
Xt : pandas DataFrame
Transformed pandas DataFrame with same number of rows and single
column
"""
self.check_is_fitted()
X = check_X(X)
# We concatenate by tabularizing all columns and then detabularizing
# them into a single column
if isinstance(X, pd.DataFrame):
Xt = from_nested_to_2d_array(X)
else:
Xt = from_3d_numpy_to_2d_array(X)
return from_2d_array_to_nested(Xt)
def transform(self, X, y=None):
"""
Transform X, transforms univariate time-series using sklearn's PCA
class
Parameters
----------
X : nested pandas DataFrame of shape [n_samples, 1]
Nested dataframe with univariate time-series in cells.
Returns
-------
Xt : pandas DataFrame
Transformed pandas DataFrame with the same number of rows and the
(potentially reduced) PCA transformed
column. Time indices of the original column are replaced with 0:(
n_components - 1).
"""
self.check_is_fitted()
X = check_X(X, enforce_univariate=True, coerce_to_numpy=True)
X = X.squeeze(1)
# Transform X using the fitted PCA
Xpca = pd.DataFrame(data=self.pca.transform(X))
# Back-transform into time series data format
Xt = from_2d_array_to_nested(Xpca)
return Xt
def inverse_transform(self, X, y=None):
"""Transform tabular pandas dataframe into nested dataframe.
Parameters
----------
X : pandas DataFrame
Tabular dataframe with primitives in cells.
y : array-like, optional (default=None)
Returns
-------
Xt : pandas DataFrame
Transformed dataframe with series in cells.
"""
self.check_is_fitted()
if len(self._columns) > 1:
raise NotImplementedError(f"`inverse-transform` currently only "
f"handles univariate data, but found: "
f"{len(self._columns)} columns in `fit`")
# we expect a tabular pd.DataFrame or np.array here, hence we use
# scikit-learn's input validation function
X = check_array(X)
Xt = from_2d_array_to_nested(X, time_index=self._time_index)
Xt.columns = self._columns
return Xt
def test_pca_results(n_components):
np.random.seed(42)
# sklearn
X = pd.DataFrame(data=np.random.randn(10, 5))
pca = PCA(n_components=n_components)
Xt1 = pca.fit_transform(X)
# sktime
Xs = from_2d_array_to_nested(X)
pca_transform = PCATransformer(n_components=n_components)
Xt2 = pca_transform.fit_transform(Xs)
assert np.allclose(np.asarray(Xt1), np.asarray(from_nested_to_2d_array(Xt2)))
def test_output_format_dim(len_series, n_instances, n_components):
np.random.seed(42)
X = from_2d_array_to_nested(
pd.DataFrame(data=np.random.randn(n_instances, len_series)))
trans = PCATransformer(n_components=n_components)
Xt = trans.fit_transform(X)
# Check number of rows and output type.
assert isinstance(Xt, pd.DataFrame)
assert Xt.shape[0] == X.shape[0]
# Check number of principal components in the output.
assert from_nested_to_2d_array(Xt).shape[1] == min(
n_components,
from_nested_to_2d_array(X).shape[1])
def inverse_transform(self, X, y=None):
"""Transform tabular pandas dataframe into nested dataframe.
Parameters
----------
X : pandas DataFrame
Tabular dataframe with primitives in cells.
y : array-like, optional (default=None)
Returns
-------
Xt : pandas DataFrame
Transformed dataframe with series in cells.
"""
self.check_is_fitted()
# We expect a tabular pd.DataFrame or np.array here, hence we use
# scikit-learn's input validation function.
X = check_array(X)
return from_2d_array_to_nested(X)
def test_pca_kwargs(kwargs):
np.random.seed(42)
X = from_2d_array_to_nested(pd.DataFrame(data=np.random.randn(10, 5)))
pca = PCATransformer(n_components=1, **kwargs)
pca.fit_transform(X)
