def _vectorized_transform(self, X, X_input_mtype=None, y=None, inverse=False):
"""Vectorized application of transform or inverse, and convert back."""
if X_input_mtype is None:
X_input_mtype = mtype(X, as_scitype=["Series", "Panel"])
if y is not None:
ValueError(
"no default behaviour if _fit does not support Panel, "
" but X is Panel and y is not None"
)
X = convert_to(
X, to_type="df-list", as_scitype="Panel", store=self._converter_store_X
)
# depending on whether fitting happens, apply fitted or unfitted instances
if not self.get_tag("fit-in-transform"):
# these are the transformers-per-instanced, fitted in fit
transformers = self.transformers_
if len(transformers) != len(X):
raise RuntimeError(
"found different number of instances in transform than in fit"
)
if inverse:
Xt = [transformers[i].inverse_transform(X[i]) for i in range(len(X))]
else:
Xt = [transformers[i].transform(X[i]) for i in range(len(X))]
# now we have a list of transformed instances
else:
# if no fitting happens, just apply transform multiple times
if inverse:
Xt = [self.inverse_transform(X[i]) for i in range(len(X))]
else:
Xt = [self.transform(X[i]) for i in range(len(X))]
# convert to expected output format
###################################
if inverse:
output_scitype = self.get_tag("scitype:transform-input")
else:
output_scitype = self.get_tag("scitype:transform-output")
# if the output is Series, Xt is a Panel and we convert back
if output_scitype == "Series":
Xt = convert_to(
Xt,
to_type=X_input_mtype,
as_scitype="Panel",
store=self._converter_store_X,
)
# if the output is Primitives, we have a list of one-row dataframes
# we concatenate those and overwrite the index with that of X
elif output_scitype == "Primitives":
Xt = pd.concat(Xt)
Xt = Xt.reset_index(drop=True)
return Xt
def _convert_output(self, X, X_input_mtype=None, X_was_Series=False, inverse=False):
"""Convert transform output to expected format."""
Xt = X
X_input_scitype = mtype_to_scitype(X_input_mtype)
if inverse:
# the output of inverse transform is equal to input of transform
output_scitype = self.get_tag("scitype:transform-input")
else:
output_scitype = self.get_tag("scitype:transform-output")
# if we converted Series to "one-instance-Panel", revert that
if X_was_Series and output_scitype == "Series":
Xt = convert_to(
Xt, to_type=["pd-multiindex", "numpy3D", "df-list"], as_scitype="Panel"
)
Xt = convert_Panel_to_Series(Xt)
if output_scitype == "Series":
# output mtype is input mtype
X_output_mtype = X_input_mtype
# exception to this: if the transformer outputs multivariate series,
# we cannot convert back to pd.Series, do pd.DataFrame instead then
# this happens only for Series, not Panel
if X_input_scitype == "Series":
_, _, metadata = check_is_mtype(
Xt,
["pd.DataFrame", "pd.Series", "np.ndarray"],
return_metadata=True,
)
if not metadata["is_univariate"] and X_input_mtype == "pd.Series":
X_output_mtype = "pd.DataFrame"
Xt = convert_to(
Xt,
to_type=X_output_mtype,
as_scitype=X_input_scitype,
store=self._converter_store_X,
)
elif output_scitype == "Primitives":
# we "abuse" the Series converter to ensure df output
# & reset index to have integers for instances
if isinstance(Xt, (pd.DataFrame, pd.Series)):
Xt = Xt.reset_index(drop=True)
Xt = convert_to(
Xt,
to_type="pd.DataFrame",
as_scitype="Series",
# no converter store since this is not a "1:1 back-conversion"
)
# else output_scitype is "Panel" and no need for conversion
return Xt
def _convert_X_y(self, X, y):
"""Convert X, y to inner type."""
X_inner_mtype = _coerce_to_list(self.get_tag("X_inner_mtype"))
X_inner_scitypes = mtype_to_scitype(X_inner_mtype, return_unique=True)
y_inner_mtype = _coerce_to_list(self.get_tag("y_inner_mtype"))
X_mtype = mtype(X, as_scitype=["Series", "Panel"])
X_scitype = mtype_to_scitype(X_mtype)
y_mtype = mtype(y, as_scitype=["Series", "Panel"])
y_scitype = mtype_to_scitype(y_mtype)
# for debugging, exception if the conversion fails (this should never happen)
if X_scitype not in X_inner_scitypes:
raise RuntimeError(
"conversion of X to X_inner unsuccessful, unexpected")
# convert X/y to supported inner type, if necessary
###################################################
# subset to the mtypes that are of the same scitype as X/y
X_inner_mtype = [
mt for mt in X_inner_mtype if mtype_to_scitype(mt) == X_scitype
]
# convert X and y to a supported internal type
# if X/y type is already supported, no conversion takes place
X_inner = convert_to(
X,
to_type=X_inner_mtype,
as_scitype=X_scitype,
store=self._converter_store_X,
)
if y_inner_mtype != ["None"]:
y_inner_mtype = [
mt for mt in y_inner_mtype if mtype_to_scitype(mt) == y_scitype
]
y_inner = convert_to(
y,
to_type=y_inner_mtype,
as_scitype=y_scitype,
)
else:
y_inner = None
return X_inner, y_inner
def _pairwise_table_x_check(self, X, var_name="X"):
"""Check and coerce input data.
Method used to check the input and convert Table input
to internally used format, as defined in X_inner_mtype tag
Parameters
----------
X: pd.DataFrame, pd.Series, numpy 1D or 2D, list of dicts
sktime data container compliant with the Table scitype
The value to be checked and coerced
var_name: str, variable name to print in error messages
Returns
-------
X: Panel data container of a supported format in X_inner_mtype
usually a 2D np.ndarray or a pd.DataFrame, unless overridden
"""
X_valid = check_is_scitype(X,
"Table",
return_metadata=False,
var_name=var_name)
if not X_valid:
msg = (
"X and X2 must be in an sktime compatible format, of scitype Table, "
"for instance a pandas.DataFrame or a 2D numpy.ndarray. "
"See the data format tutorial examples/AA_datatypes_and_datasets.ipynb"
)
raise TypeError(msg)
X_inner_mtype = self.get_tag("X_inner_mtype")
X_coerced = convert_to(X, to_type=X_inner_mtype, as_scitype="Table")
return X_coerced
def plot_series(X: TimeSeriesInstances):
_check_soft_dependencies("matplotlib")
import matplotlib.patches as mpatches
import matplotlib.pyplot as plt
if isinstance(X, pd.DataFrame):
X = convert_to(X, "numpy3D")
plt.figure(figsize=(5, 10))
plt.rcParams["figure.dpi"] = 100
fig, axes = plt.subplots(nrows=len(X), ncols=1)
for i in range(len(X)):
curr = X[i][0]
curr_axes = axes[i]
curr_axes.plot(curr, color="b")
blue_patch = mpatches.Patch(color="blue",
label="Series that belong to the cluster")
plt.legend(
handles=[blue_patch],
loc="upper center",
bbox_to_anchor=(0.5, -0.40),
fancybox=True,
shadow=True,
ncol=5,
)
plt.tight_layout()
plt.show()
def create_test_distance_numpy(
n_instance: int,
n_columns: int = None,
n_timepoints: int = None,
random_state: int = 1,
):
"""Create a test numpy distance.
Parameters
----------
n_instance: int
Number of instances to create.
n_columns: int
Number of columns to create.
n_timepoints: int, defaults = None
Number of timepoints to create in each column.
random_state: int, defaults = 1
Random state to initialise with.
Returns
-------
np.ndarray 2D or 3D numpy
Numpy array of shape specific. If 1 instance then 2D array returned,
if > 1 instance then 3D array returned.
"""
num_dims = 3
if n_timepoints is None:
n_timepoints = 1
num_dims -= 1
if n_columns is None:
n_columns = 1
num_dims -= 1
df = _create_test_distances(
n_instance=n_instance,
n_columns=n_columns,
n_timepoints=n_timepoints,
random_state=random_state,
)
if num_dims == 3:
return convert_to(df, to_type="numpy3D")
elif num_dims == 2:
return convert_to(df, to_type="numpy3D")[:, :, 0]
else:
return convert_to(df, to_type="numpy3D")[:, 0, 0]
def test_center_init(center_init_callable: Callable[[np.ndarray], np.ndarray]):
"""Test center initialisation algorithms."""
k = 5
X, y = load_arrow_head(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y)
X_train = convert_to(X_train, "numpy3D")
random_state = check_random_state(1)
test_centers = center_init_callable(X_train, k, random_state)
assert len(test_centers) == k
assert len(np.unique(test_centers, axis=1)) == k
def _check_clusterer_input(
self, X: TimeSeriesInstances, enforce_min_instances: int = 1
) -> TimeSeriesInstances:
"""Validate the input and prepare for _fit.
Parameters
----------
X : np.ndarray (2d or 3d array of shape (n_instances, series_length) or shape
(n_instances,n_dimensions,series_length)) or nested pd.DataFrame (
n_instances,n_dimensions).
Training time series instances to cluster.
Returns
-------
X : np.ndarray (3d of shape (n_instances,n_dimensions,series_length)) or
pd.Dataframe (n_instances,n_dimensions).
Converted X ready for _fit.
Raises
------
ValueError
If y or X is invalid input data type, or there is not enough data.
"""
X = self._initial_conversion(X)
X_valid, _, X_metadata = check_is_scitype(
X, scitype="Panel", return_metadata=True
)
if not X_valid:
raise TypeError(
f"X is not of a supported input data type."
f"X must be of type np.ndarray or pd.DataFrame, found {type(X)}"
f"Use datatypes.check_is_mtype to check conformance with "
f"specifications."
)
n_cases = X_metadata["n_instances"]
if n_cases < enforce_min_instances:
raise ValueError(
f"Minimum number of cases required is {enforce_min_instances} but X "
f"has : {n_cases}"
)
missing = X_metadata["has_nans"]
multivariate = not X_metadata["is_univariate"]
unequal = not X_metadata["is_equal_length"]
self._check_capabilities(missing, multivariate, unequal)
return convert_to(
X,
to_type=self.get_tag("X_inner_mtype"),
as_scitype="Panel",
)
def _pairwise_panel_x_check(self, X, var_name="X"):
"""Check and coerce input data.
Method used to check the input and convert Series/Panel input
to internally used format, as defined in X_inner_mtype tag
Parameters
----------
X: List of dfs, Numpy of dfs, 3d numpy
sktime data container compliant with the Series or Panel scitype
The value to be checked
var_name: str, variable name to print in error messages
Returns
-------
X: Panel data container of a supported format in X_inner_mtype
usually df-list, list of pd.DataFrame, unless overridden
"""
check_res = check_is_scitype(X, ["Series", "Panel"],
return_metadata=True,
var_name=var_name)
X_valid = check_res[0]
metadata = check_res[2]
X_scitype = metadata["scitype"]
if not X_valid:
msg = (
"X and X2 must be in an sktime compatible format, "
"of scitype Series or Panel, "
"for instance a pandas.DataFrame with sktime compatible time indices, "
"or with MultiIndex and lowest level a sktime compatible time index. "
"See the data format tutorial examples/AA_datatypes_and_datasets.ipynb"
)
raise TypeError(msg)
# if the input is a single series, convert it to a Panel
if X_scitype == "Series":
X = convert_Series_to_Panel(X)
# can't be anything else if check_is_scitype is working properly
elif X_scitype != "Panel":
raise RuntimeError(
"Unexpected error in check_is_scitype, check validity")
X_inner_mtype = self.get_tag("X_inner_mtype")
X_coerced = convert_to(X, to_type=X_inner_mtype, as_scitype="Panel")
return X_coerced
def _transform(self, X, y=None):
"""Transform nested pandas dataframe into tabular dataframe.
Parameters
----------
X : pandas DataFrame or 3D np.ndarray
panel of time series to transform
y : ignored argument for interface compatibility
Returns
-------
Xt : pandas DataFrame
Transformed dataframe with only primitives in cells.
"""
Xt = convert_to(X, to_type="numpyflat", as_scitype="Panel")
return Xt
def plot_cluster_algorithm(model: TimeSeriesLloyds, X: TimeSeriesInstances,
k: int):
"""Plot the results from a univariate partitioning algorithm.
Parameters
----------
model: BaseClusterer
Clustering model to plot
predict_series: np.ndarray or pd.Dataframe or List[pd.Dataframe]
The series to predict the values for
k: int
Number of centers
"""
_check_soft_dependencies("matplotlib")
import matplotlib.patches as mpatches
import matplotlib.pyplot as plt
if isinstance(X, pd.DataFrame):
predict_series = convert_to(X, "numpy3D")
plt.figure(figsize=(5, 10))
plt.rcParams["figure.dpi"] = 100
indexes = model.predict(predict_series)
centers = model.cluster_centers_
series_values = _get_cluster_values(indexes, predict_series, k)
fig, axes = plt.subplots(nrows=k, ncols=1)
for i in range(k):
_plot(series_values[i], centers[i], axes[i])
blue_patch = mpatches.Patch(color="blue",
label="Series that belong to the cluster")
red_patch = mpatches.Patch(color="red", label="Cluster centers")
plt.legend(
handles=[red_patch, blue_patch],
loc="upper center",
bbox_to_anchor=(0.5, -0.40),
fancybox=True,
shadow=True,
ncol=5,
)
plt.tight_layout()
plt.show()
def _pairwise_panel_x_check(self, X, var_name="X"):
"""Check and coerce input data.
Method used to check the input and convert Series/Panel input
to internally used format, as defined in X_inner_mtype tag
Parameters
----------
X: List of dfs, Numpy of dfs, 3d numpy
The value to be checked
var_name: str, variable name to print in error messages
Returns
-------
X: Panel data container of a supported format in X_inner_mtype
usually df-list, list of pd.DataFrame, unless overridden
"""
check_res = check_is_scitype(X, ["Series", "Panel"],
return_metadata=True,
var_name=var_name)
X_valid = check_res[0]
metadata = check_res[2]
X_scitype = metadata["scitype"]
if not X_valid:
raise TypeError("X/X2 must be of Series or Panel scitype")
# if the input is a single series, convert it to a Panel
if X_scitype == "Series":
X = convert_Series_to_Panel(X)
# can't be anything else if check_is_scitype is working properly
elif X_scitype != "Panel":
raise RuntimeError(
"Unexpected error in check_is_scitype, check validity")
X_inner_mtype = self.get_tag("X_inner_mtype")
X_coerced = convert_to(X, to_type=X_inner_mtype, as_scitype="Panel")
return X_coerced
def _convert_X(self, X):
"""Convert equal length series from DataFrame to numpy array or vice versa.
Parameters
----------
self : this classifier
X : pd.DataFrame or np.ndarray. Input attribute data
Returns
-------
X : pd.DataFrame or np.array
Checked and possibly converted input data
"""
inner_type = self.get_tag("X_inner_mtype")
# convert pd.DataFrame
X = convert_to(
X,
to_type=inner_type,
as_scitype="Panel",
)
return X
def make_clustering_problem(
n_instances=20,
n_columns=1,
n_timepoints=20,
return_numpy=False,
random_state=None,
):
"""Make Clustering Problem."""
# Can only currently support univariate so converting
# to univaritate for the time being
X = _make_panel_X(
n_instances=n_instances,
n_columns=n_columns,
n_timepoints=n_timepoints,
return_numpy=return_numpy,
random_state=random_state,
)
if return_numpy:
return convert_to(X, "numpy3D")
else:
return X
def plot_dba_example():
"""Plot dba."""
import matplotlib.pyplot as plt
X_train, y_train = load_arrow_head(split="train")
X_train = convert_to(X_train, "numpy3D")
def plot_helper(barycenter):
for series in X_train:
plt.plot(series.ravel(), "k-", alpha=0.2)
plt.plot(barycenter.ravel(), "r-", linewidth=2)
ax1 = plt.subplot()
plt.subplot(4, 1, 1, sharex=ax1)
plt.title("Sktime DBA (using dtw)")
plot_helper(
dba(X_train, distance_metric="dtw", medoids_distance_metric="dtw"))
plt.subplot(4, 1, 2, sharex=ax1)
plt.title("Sktime DBA (using wdtw)")
plot_helper(
dba(X_train, distance_metric="wdtw", medoids_distance_metric="wdtw"))
plt.subplot(4, 1, 3, sharex=ax1)
plt.title("Sktime DBA (using lcss)")
plot_helper(
dba(X_train, distance_metric="lcss", medoids_distance_metric="lcss"))
plt.subplot(4, 1, 4, sharex=ax1)
plt.title("Sktime DBA (using msm)")
plot_helper(dba(X_train, distance_metric="msm"))
ax1.set_xlim([0, X_train.shape[2]])
# show the plot(s)
plt.tight_layout()
plt.show()
def convert_Hierarchical_to_Panel(obj, store=None):
"""Convert single-series hierarchical object to a series.
Removes one dimensions to obtain a panel, by removing 1 level from MultiIndex.
Assumes input is conformant with Hierarchical mtype.
This method does not perform full mtype checks, use mtype or check_is_mtype for
checks.
Parameters
----------
obj: an object of scitype Hierarchical.
Returns
-------
returns a data container of mtype pd-multiindex, of scitype Panel
"""
obj_df = convert_to(obj,
to_type="pd_multiindex_hier",
as_scitype="Hierarchical")
obj_df = obj_df.copy()
obj_df.index = obj_df.index.get_level_values([-2, -1])
return obj_df
def convert_Panel_to_Hierarchical(obj, store=None):
"""Convert panel to a single-panel hierarchical object.
Adds a dimensions to the panel to obtain a 3-level MultiIndex, 1 level is added.
Assumes input is conformant with one of the Panel mtypes.
This method does not perform full mtype checks, use mtype or check_is_mtype for
checks.
Parameters
----------
obj: an object of scitype Panel.
Returns
-------
returns a data container of mtype pd_multiindex_hier
"""
obj_df = convert_to(obj, to_type="pd-multiindex", as_scitype="Panel")
obj_df = obj_df.copy()
obj_df["__level2"] = 0
obj_df = obj_df.set_index(["__level2"], append=True)
obj_df = obj_df.reorder_levels([2, 0, 1])
return obj_df
def convert_Series_to_Hierarchical(obj, store=None):
"""Convert series to a single-series hierarchical object.
Adds two dimensions to the series to obtain a 3-level MultiIndex, 2 levels added.
Assumes input is conformant with one of the three Series mtypes.
This method does not perform full mtype checks, use mtype or check_is_mtype for
checks.
Parameters
----------
obj: an object of scitype Series, of mtype pd.DataFrame, pd.Series, or np.ndarray.
Returns
-------
returns a data container of mtype pd_multiindex_hier
"""
obj_df = convert_to(obj, to_type="pd.DataFrame", as_scitype="Series")
obj_df = obj_df.copy()
obj_df["__level1"] = 0
obj_df["__level2"] = 0
obj_df = obj_df.set_index(["__level1", "__level2"], append=True)
obj_df = obj_df.reorder_levels([1, 2, 0])
return obj_df
def update(self, X, y=None, Z=None, update_params=True):
"""Update transformer with X, optionally y.
State required:
Requires state to be "fitted".
Accesses in self:
Fitted model attributes ending in "_".
self._is_fitted
Writes to self:
May update fitted model attributes ending in "_".
Parameters
----------
X : Series or Panel, any supported mtype
Data to fit transform to, of python type as follows:
Series: pd.Series, pd.DataFrame, or np.ndarray (1D or 2D)
Panel: pd.DataFrame with 2-level MultiIndex, list of pd.DataFrame,
nested pd.DataFrame, or pd.DataFrame in long/wide format
subject to sktime mtype format specifications, for further details see
examples/AA_datatypes_and_datasets.ipynb
y : Series or Panel, default=None
Additional data, e.g., labels for transformation
Z : possible alias for X; should not be passed when X is passed
alias Z will be deprecated in version 0.10.0
update_params : bool, default=True
whether the model is updated. Yes if true, if false, simply skips call.
argument exists for compatibility with forecasting module.
Returns
-------
self : a fitted instance of the estimator
"""
X = _handle_alias(X, Z)
# skip everything if update_params is False
if not update_params:
return self
# skip everything if fit-in-transform is True
if self.get_tag("fit-in-transform"):
return self
# input checks and minor coercions on X, y
###########################################
valid, msg, X_metadata = check_is_mtype(
X, mtype=self.ALLOWED_INPUT_MTYPES, return_metadata=True, var_name="X"
)
if not valid:
raise ValueError(msg)
# checking X
enforce_univariate = self.get_tag("univariate-only")
if enforce_univariate and not X_metadata["is_univariate"]:
raise ValueError("X must be univariate but is not")
# retrieve mtypes/scitypes of all objects
#########################################
X_input_scitype = X_metadata["scitype"]
X_inner_mtype = _coerce_to_list(self.get_tag("X_inner_mtype"))
X_inner_scitypes = mtype_to_scitype(X_inner_mtype, return_unique=True)
# treating Series vs Panel conversion for X
###########################################
# there are three cases to treat:
# 1. if the internal _fit supports X's scitype, move on to mtype conversion
# 2. internal only has Panel but X is Series: consider X as one-instance Panel
# 3. internal only has Series but X is Panel: auto-vectorization over instances
# currently, this is enabled by conversion to df-list mtype
# auto-vectorization is not supported if y is passed
# individual estimators that vectorize over y must implement individually
# 1. nothing to do - simply don't enter any of the ifs below
# 2. internal only has Panel but X is Series: consider X as one-instance Panel
if X_input_scitype == "Series" and "Series" not in X_inner_scitypes:
X = convert_Series_to_Panel(X)
# 3. internal only has Series but X is Panel: loop over instances
elif X_input_scitype == "Panel" and "Panel" not in X_inner_scitypes:
if y is not None:
raise ValueError(
"no default behaviour if _fit does not support Panel, "
" but X is Panel and y is not None"
)
X = convert_to(
X, to_type="df-list", as_scitype="Panel", store=self._converter_store_X
)
# this fits one transformer per instance
self.transformers_ = [clone(self).fit(Xi) for Xi in X]
# recurse and leave function - recursion does input checks/conversion
# also set is_fitted flag to True since we leave function here
self._is_fitted = True
return self
X_inner, y_inner = self._convert_X_y(X, y)
# todo: uncomment this once Z is completely gone
# self._update(X=X_inner, y=y_inner)
# less robust workaround until then
self._update(X_inner, y_inner)
return self
def _check_X_y(self, X=None, y=None):
"""Check and coerce X/y for fit/predict/update functions.
Parameters
----------
y : pd.Series, pd.DataFrame, or np.ndarray (1D or 2D), optional (default=None)
Time series to check.
X : pd.DataFrame, or 2D np.array, optional (default=None)
Exogeneous time series.
Returns
-------
y_inner : Series compatible with self.get_tag("y_inner_mtype") format
converted/coerced version of y, mtype determined by "y_inner_mtype" tag
None if y was None
X_inner : Series compatible with self.get_tag("X_inner_mtype") format
converted/coerced version of y, mtype determined by "X_inner_mtype" tag
None if X was None
Raises
------
TypeError if y or X is not one of the permissible Series mtypes
TypeError if y is not compatible with self.get_tag("scitype:y")
if tag value is "univariate", y must be univariate
if tag value is "multivariate", y must be bi- or higher-variate
if tag vaule is "both", y can be either
TypeError if self.get_tag("X-y-must-have-same-index") is True
and the index set of X is not a super-set of the index set of y
Writes to self
--------------
_y_mtype_last_seen : str, mtype of y
_converter_store_y : dict, metadata from conversion for back-conversion
"""
# input checks and minor coercions on X, y
###########################################
enforce_univariate = self.get_tag("scitype:y") == "univariate"
enforce_multivariate = self.get_tag("scitype:y") == "multivariate"
enforce_index_type = self.get_tag("enforce_index_type")
# checking y
if y is not None:
check_y_args = {
"enforce_univariate": enforce_univariate,
"enforce_multivariate": enforce_multivariate,
"enforce_index_type": enforce_index_type,
"allow_None": False,
"allow_empty": True,
}
y = check_series(y, **check_y_args, var_name="y")
self._y_mtype_last_seen = mtype(y, as_scitype="Series")
# end checking y
# checking X
if X is not None:
X = check_series(X, enforce_index_type=enforce_index_type, var_name="X")
if self.get_tag("X-y-must-have-same-index"):
check_equal_time_index(X, y)
# end checking X
# convert X & y to supported inner type, if necessary
#####################################################
# retrieve supported mtypes
# convert X and y to a supported internal mtype
# it X/y mtype is already supported, no conversion takes place
# if X/y is None, then no conversion takes place (returns None)
y_inner_mtype = self.get_tag("y_inner_mtype")
y_inner = convert_to(
y,
to_type=y_inner_mtype,
as_scitype="Series", # we are dealing with series
store=self._converter_store_y,
)
X_inner_mtype = self.get_tag("X_inner_mtype")
X_inner = convert_to(
X,
to_type=X_inner_mtype,
as_scitype="Series", # we are dealing with series
)
return X_inner, y_inner
def predict(
self,
fh=None,
X=None,
return_pred_int=False,
alpha=DEFAULT_ALPHA,
keep_old_return_type=True,
):
"""Forecast time series at future horizon.
State required:
Requires state to be "fitted".
Accesses in self:
Fitted model attributes ending in "_".
self.cutoff, self._is_fitted
Writes to self:
Stores fh to self.fh if fh is passed and has not been passed previously.
Parameters
----------
fh : int, list, np.ndarray or ForecastingHorizon
Forecasting horizon
X : pd.DataFrame, or 2D np.ndarray, optional (default=None)
Exogeneous time series to predict from
if self.get_tag("X-y-must-have-same-index"), X.index must contain fh.index
return_pred_int : bool, optional (default=False)
If True, returns prediction intervals for given alpha values.
alpha : float or list, optional (default=0.95)
Returns
-------
y_pred : pd.Series, pd.DataFrame, or np.ndarray (1D or 2D)
Point forecasts at fh, with same index as fh
y_pred has same type as y passed in fit (most recently)
y_pred_int : pd.DataFrame - only if return_pred_int=True
in this case, return is 2-tuple (otherwise a single y_pred)
Prediction intervals
"""
# handle inputs
self.check_is_fitted()
self._set_fh(fh)
# todo deprecate NotImplementedError in v 10.0.1
if return_pred_int and not self.get_tag("capability:pred_int"):
raise NotImplementedError(
f"{self.__class__.__name__} does not have the capability to return "
"prediction intervals. Please set return_pred_int=False. If you "
"think this estimator should have the capability, please open "
"an issue on sktime."
)
# input check and conversion for X
X_inner = self._check_X(X=X)
# this is how it is supposed to be after the refactor is complete and effective
if not return_pred_int:
y_pred = self._predict(
self.fh,
X=X_inner,
)
# convert to output mtype, identical with last y mtype seen
y_out = convert_to(
y_pred,
self._y_mtype_last_seen,
as_scitype="Series",
store=self._converter_store_y,
)
return y_out
# keep following code for downward compatibility,
# todo: can be deleted once refactor is completed and effective,
# todo: deprecate in v 10
else:
warn(
"return_pred_int in predict() will be deprecated;"
"please use predict_interval() instead to generate "
"prediction intervals.",
FutureWarning,
)
if not self._has_predict_quantiles_been_refactored():
# this means the method is not refactored
y_pred = self._predict(
self.fh,
X=X_inner,
return_pred_int=return_pred_int,
alpha=alpha,
)
# returns old return type anyways
pred_int = y_pred[1]
y_pred = y_pred[0]
else:
# it's already refactored
# opposite definition previously vs. now
coverage = [1 - a for a in alpha]
pred_int = self.predict_interval(fh=fh, X=X_inner, coverage=coverage)
if keep_old_return_type:
pred_int = _convert_new_to_old_pred_int(pred_int, alpha)
# convert to output mtype, identical with last y mtype seen
y_out = convert_to(
y_pred,
self._y_mtype_last_seen,
as_scitype="Series",
store=self._converter_store_y,
)
return (y_out, pred_int)
np.argmax,
np.any,
]
X1_list_df = make_transformer_problem(n_instances=4,
n_columns=4,
n_timepoints=5,
random_state=1,
return_numpy=False)
X2_list_df = make_transformer_problem(n_instances=5,
n_columns=4,
n_timepoints=5,
random_state=2,
return_numpy=False)
X1_num_pan = convert_to(X1_list_df, to_type="numpy3D")
X2_num_pan = convert_to(X2_list_df, to_type="numpy3D")
def test_aggr():
"""Test that AggrDist produces expected pre-computed result on fixtures."""
# test 3d numpy
_run_aggr_dist_test(X1_num_pan, X2_num_pan)
# test list of df
_run_aggr_dist_test(X1_list_df, X2_list_df)
def _run_aggr_dist_test(x, y):
# default parametersc
default_params = AggrDist(transformer=ScipyDist())
def plot_correlations(
series,
lags=24,
alpha=0.05,
zero_lag=True,
acf_fft=False,
acf_adjusted=True,
pacf_method="ywadjusted",
suptitle=None,
series_title=None,
acf_title="Autocorrelation",
pacf_title="Partial Autocorrelation",
):
"""Plot series and its ACF and PACF values.
Parameters
----------
series : pd.Series
A time series.
lags : int, default = 24
Number of lags to include in ACF and PACF plots
alpha : int, default = 0.05
Alpha value used to set confidence intervals. Alpha = 0.05 results in
95% confidence interval with standard deviation calculated via
Bartlett's formula.
zero_lag : bool, default = True
If True, start ACF and PACF plots at 0th lag
acf_fft : bool, = False
Whether to compute ACF via FFT.
acf_adjusted : bool, default = True
If True, denonimator of ACF calculations uses n-k instead of n, where
n is number of observations and k is the lag.
pacf_method : str, default = 'ywadjusted'
Method to use in calculation of PACF.
suptitle : str, default = None
The text to use as the Figure's suptitle.
series_title : str, default = None
Used to set the title of the series plot if provided. Otherwise, series
plot has no title.
acf_title : str, default = 'Autocorrelation'
Used to set title of ACF plot.
pacf_title : str, default = 'Partial Autocorrelation'
Used to set title of PACF plot.
Returns
-------
fig : matplotlib.figure.Figure
axes : np.ndarray
Array of the figure's Axe objects
"""
_check_soft_dependencies("matplotlib")
import matplotlib.pyplot as plt
series = check_y(series)
series = convert_to(series, "pd.Series", "Series")
# Setup figure for plotting
fig = plt.figure(constrained_layout=True, figsize=(12, 8))
gs = fig.add_gridspec(2, 2)
f_ax1 = fig.add_subplot(gs[0, :])
if series_title is not None:
f_ax1.set_title(series_title)
f_ax2 = fig.add_subplot(gs[1, 0])
f_ax3 = fig.add_subplot(gs[1, 1])
# Create expected plots on their respective Axes
plot_series(series, ax=f_ax1)
plot_acf(
series,
ax=f_ax2,
lags=lags,
zero=zero_lag,
alpha=alpha,
title=acf_title,
adjusted=acf_adjusted,
fft=acf_fft,
)
plot_pacf(
series,
ax=f_ax3,
lags=lags,
zero=zero_lag,
alpha=alpha,
title=pacf_title,
method=pacf_method,
)
if suptitle is not None:
fig.suptitle(suptitle, size="xx-large")
return fig, np.array(fig.get_axes())
def transform(self, X, y=None, Z=None):
"""Transform X and return a transformed version.
State required:
Requires state to be "fitted".
Accesses in self:
Fitted model attributes ending in "_".
self._is_fitted
Parameters
----------
X : Series or Panel, any supported mtype
Data to be transformed, of python type as follows:
Series: pd.Series, pd.DataFrame, or np.ndarray (1D or 2D)
Panel: pd.DataFrame with 2-level MultiIndex, list of pd.DataFrame,
nested pd.DataFrame, or pd.DataFrame in long/wide format
subject to sktime mtype format specifications, for further details see
examples/AA_datatypes_and_datasets.ipynb
y : Series or Panel, default=None
Additional data, e.g., labels for transformation
Z : possible alias for X; should not be passed when X is passed
alias Z will be deprecated in version 0.10.0
Returns
-------
transformed version of X
type depends on type of X and scitype:transform-output tag:
| | `transform` | |
| `X` | `-output` | type of return |
|----------|--------------|------------------------|
| `Series` | `Primitives` | `pd.DataFrame` (1-row) |
| `Panel` | `Primitives` | `pd.DataFrame` |
| `Series` | `Series` | `Series` |
| `Panel` | `Series` | `Panel` |
| `Series` | `Panel` | `Panel` |
instances in return correspond to instances in `X`
combinations not in the table are currently not supported
Explicitly, with examples:
if `X` is `Series` (e.g., `pd.DataFrame`) and `transform-output` is `Series`
then the return is a single `Series` of the same mtype
Example: detrending a single series
if `X` is `Panel` (e.g., `pd-multiindex`) and `transform-output` is `Series`
then the return is `Panel` with same number of instances as `X`
(the transformer is applied to each input Series instance)
Example: all series in the panel are detrended individually
if `X` is `Series` or `Panel` and `transform-output` is `Primitives`
then the return is `pd.DataFrame` with as many rows as instances in `X`
Example: i-th row of the return has mean and variance of the i-th series
if `X` is `Series` and `transform-output` is `Panel`
then the return is a `Panel` object of type `pd-multiindex`
Example: i-th instance of the output is the i-th window running over `X`
"""
X = _handle_alias(X, Z)
# check whether is fitted, unless fit-in-transform is true
if self.get_tag("fit-in-transform"):
self.fit(X=X, y=y, Z=Z)
else:
self.check_is_fitted()
# input checks and minor coercions on X, y
###########################################
valid, msg, metadata = check_is(X,
mtype=self.ALLOWED_INPUT_MTYPES,
return_metadata=True,
var_name="X")
if not valid:
ValueError(msg)
# checking X
enforce_univariate = self.get_tag("univariate-only")
if enforce_univariate and not metadata["is_univariate"]:
ValueError("X must be univariate but is not")
# retrieve mtypes/scitypes of all objects
#########################################
X_input_mtype = mtype(X)
X_input_scitype = mtype_to_scitype(X_input_mtype)
y_input_mtype = mtype(y)
y_input_scitype = mtype_to_scitype(y_input_mtype)
output_scitype = self.get_tag("scitype:transform-output")
X_inner_mtype = self.get_tag("X_inner_mtype")
if not isinstance(X_inner_mtype, list):
X_inner_mtype = [X_inner_mtype]
X_inner_scitypes = list(
set([mtype_to_scitype(mt) for mt in X_inner_mtype]))
y_inner_mtype = self.get_tag("y_inner_mtype")
if not isinstance(y_inner_mtype, list):
y_inner_mtype = [y_inner_mtype]
# y_inner_scitypes = list(set([mtype_to_scitype(mt) for mt in y_inner_mtype]))
# treating Series vs Panel conversion for X
###########################################
# there are three cases to treat:
# 1. if the internal _fit supports X's scitype, move on to mtype conversion
# 2. internal only has Panel but X is Series: consider X as one-instance Panel
# 3. internal only has Series but X is Panel: loop over instances
# currently this is enabled by conversion to df-list mtype
# and this does not support y (unclear what should happen here)
# 1. nothing to do - simply don't enter any of the ifs below
# the "ifs" for case 2 and 3 below are skipped under the condition
# X_input_scitype in X_inner_scitypes
# case 2 has an "else" which remembers that it wasn't entered
# 2. internal only has Panel but X is Series: consider X as one-instance Panel
if (X_input_scitype == "Series" and "Series" not in X_inner_scitypes
and "Panel" in X_inner_scitypes):
# convert the Series X to a one-element Panel
X = convert_Series_to_Panel(X)
# remember that we converted the Series to a one-element Panel
X_was_Series = True
else:
# remember that we didn't convert a Series to a one-element Panel
X_was_Series = False
# 3. internal only has Series but X is Panel: loop over instances
if (X_input_scitype == "Panel" and "Panel" not in X_inner_scitypes
and "Series" in X_inner_scitypes):
if y is not None:
ValueError(
"no default behaviour if _fit does not support Panel, "
" but X is Panel and y is not None")
X = convert_to(X, to_type="df-list", as_scitype="Panel")
if self.get_tag("fit-in-transform"):
Xt = [clone(self).transform(Xi) for Xi in X]
else:
transformers = self.transformers_
if len(transformers) != len(X):
raise RuntimeError(
"found different number of instances in transform than in fit"
)
else:
Xt = [
transformers[i].transform(X[i]) for i in range(len(X))
]
# now we have a list of transformed instances
# if the output is Series, Xt is a Panel and we convert back
if output_scitype == "Series":
Xt = convert_to(Xt, to_type=X_input_mtype, as_scitype="Panel")
# if the output is Primitives, we have a list of one-row dataframes
# we concatenate those and overwrite the index with that of X
elif output_scitype == "Primitives":
Xt = pd.concat(Xt)
Xt.index = X.index
return Xt
# convert X/y to supported inner type, if necessary
###################################################
# variables for the scitype of the current X (possibly converted)
# y wasn't converted so we can use y_input_scitype
X_mtype = mtype(X)
X_scitype = mtype_to_scitype(X_mtype)
# subset to the mtypes that are of the same scitype as X/y
X_inner_mtype = [
mt for mt in X_inner_mtype if mtype_to_scitype(mt) == X_scitype
]
y_inner_mtype = [
mt for mt in y_inner_mtype
if mtype_to_scitype(mt) == y_input_scitype
]
# convert X and y to a supported internal type
# if X/y type is already supported, no conversion takes place
X_inner = convert_to(
X,
to_type=X_inner_mtype,
as_scitype=X_scitype,
)
y_inner = convert_to(
y,
to_type=y_inner_mtype,
as_scitype=y_input_scitype,
)
# carry out the transformation
###################################################
# todo: uncomment this once Z is completely gone
# Xt = self._transform(X=X_inner, y=y_inner)
# less robust workaround until then
Xt = self._transform(X_inner, y_inner)
# convert transformed X back to input mtype
###########################################
# if we converted Series to "one-instance-Panel", revert that
if X_was_Series and output_scitype == "Series":
Xt = convert_Panel_to_Series(Xt)
if output_scitype == "Series":
Xt = convert_to(
Xt,
to_type=X_input_mtype,
as_scitype=X_input_scitype,
)
elif output_scitype == "Primitives":
# we "abuse" the Series converter to ensure df output
Xt = convert_to(
Xt,
to_type="pd.DataFrame",
as_scitype="Series",
)
else:
# output_scitype is "Panel" and no need for conversion
pass
return Xt
def fit(self, X, y=None, Z=None):
"""Fit transformer to X, optionally to y.
State change:
Changes state to "fitted".
Writes to self:
Sets is_fitted flag to True.
Sets fitted model attributes ending in "_".
Parameters
----------
X : Series or Panel, any supported mtype
Data to fit transform to, of python type as follows:
Series: pd.Series, pd.DataFrame, or np.ndarray (1D or 2D)
Panel: pd.DataFrame with 2-level MultiIndex, list of pd.DataFrame,
nested pd.DataFrame, or pd.DataFrame in long/wide format
subject to sktime mtype format specifications, for further details see
examples/AA_datatypes_and_datasets.ipynb
y : Series or Panel, default=None
Additional data, e.g., labels for transformation
Z : possible alias for X; should not be passed when X is passed
alias Z will be deprecated in version 0.10.0
Returns
-------
self : a fitted instance of the estimator
"""
X = _handle_alias(X, Z)
self._is_fitted = False
# skip everything if fit-in-transform is True
if self.get_tag("fit-in-transform"):
self._is_fitted = True
return self
# input checks and minor coercions on X, y
###########################################
valid, msg, metadata = check_is(X,
mtype=self.ALLOWED_INPUT_MTYPES,
return_metadata=True,
var_name="X")
if not valid:
raise ValueError(msg)
# checking X
enforce_univariate = self.get_tag("univariate-only")
if enforce_univariate and not metadata["is_univariate"]:
raise ValueError("X must be univariate but is not")
# retrieve mtypes/scitypes of all objects
#########################################
X_input_mtype = mtype(X)
X_input_scitype = mtype_to_scitype(X_input_mtype)
y_input_mtype = mtype(y)
y_input_scitype = mtype_to_scitype(y_input_mtype)
X_inner_mtype = self.get_tag("X_inner_mtype")
if not isinstance(X_inner_mtype, list):
X_inner_mtype = [X_inner_mtype]
X_inner_scitypes = list(
set([mtype_to_scitype(mt) for mt in X_inner_mtype]))
y_inner_mtype = self.get_tag("y_inner_mtype")
if not isinstance(y_inner_mtype, list):
y_inner_mtype = [y_inner_mtype]
# y_inner_scitypes = list(set([mtype_to_scitype(mt) for mt in y_inner_mtype]))
# treating Series vs Panel conversion for X
###########################################
# there are three cases to treat:
# 1. if the internal _fit supports X's scitype, move on to mtype conversion
# 2. internal only has Panel but X is Series: consider X as one-instance Panel
# 3. internal only has Series but X is Panel: auto-vectorization over instances
# currently, this is enabled by conversion to df-list mtype
# auto-vectorization is not supported if y is passed
# individual estimators that vectorize over y must implement individually
# 1. nothing to do - simply don't enter any of the ifs below
# 2. internal only has Panel but X is Series: consider X as one-instance Panel
if X_input_scitype == "Series" and "Series" not in X_inner_scitypes:
X = convert_Series_to_Panel(X)
# 3. internal only has Series but X is Panel: loop over instances
elif X_input_scitype == "Panel" and "Panel" not in X_inner_scitypes:
if y is not None:
raise ValueError(
"no default behaviour if _fit does not support Panel, "
" but X is Panel and y is not None")
X = convert_to(X, to_type="df-list", as_scitype="Panel")
# this fits one transformer per instance
self.transformers_ = [clone(self).fit(Xi) for Xi in X]
# recurse and leave function - recursion does input checks/conversion
# also set is_fitted flag to True since we leave function here
self._is_fitted = True
return self
X_mtype = mtype(X)
X_scitype = mtype_to_scitype(X_mtype)
# for debugging, exception if the conversion fails (this should never happen)
if X_scitype not in X_inner_scitypes:
raise RuntimeError(
"conversion of X to X_inner unsuccessful, unexpected")
# convert X/y to supported inner type, if necessary
###################################################
# subset to the mtypes that are of the same scitype as X/y
X_inner_mtype = [
mt for mt in X_inner_mtype if mtype_to_scitype(mt) == X_scitype
]
y_inner_mtype = [
mt for mt in y_inner_mtype
if mtype_to_scitype(mt) == y_input_scitype
]
# convert X and y to a supported internal type
# if X/y type is already supported, no conversion takes place
X_inner = convert_to(
X,
to_type=X_inner_mtype,
as_scitype=X_scitype,
)
y_inner = convert_to(
y,
to_type=y_inner_mtype,
as_scitype=y_input_scitype,
)
# todo: uncomment this once Z is completely gone
# self._fit(X=X_inner, y=y_inner)
# less robust workaround until then
self._fit(X_inner, y_inner)
self._is_fitted = True
return self
def get_window(obj, window_length=None, lag=0):
"""Slice obj to the time index window with given length and lag.
Returns time series or time series panel with time indices
strictly greater than cutoff - lag - window_length, and
equal or less than cutoff - lag.
Cutoff if of obj, as determined by get_cutoff.
Parameters
----------
obj : sktime compatible time series data container or None
if not None, must be of one of the following mtypes:
pd.Series, pd.DataFrame, np.ndarray, of Series scitype
pd.multiindex, numpy3D, nested_univ, df-list, of Panel scitype
pd_multiindex_hier, of Hierarchical scitype
window_length : int or timedelta, optional, default=-inf
must be int if obj is int indexed, timedelta if datetime indexed
length of the window to slice to. Default = window of infinite size
lag : int or timedelta, optional, default = 0
must be int if obj is int indexed, timedelta if datetime indexed
lag of the latest time in the window, with respect to cutoff of obj
Returns
-------
obj sub-set to time indices in the semi-open interval
(cutoff - window_length - lag, cutoff - lag)
None if obj was None
"""
from sktime.datatypes import check_is_scitype, convert_to
if window_length is None or obj is None:
return obj
valid, _, metadata = check_is_scitype(
obj, scitype=["Series", "Panel", "Hierarchical"], return_metadata=True)
if not valid:
raise ValueError(
"obj must be of Series, Panel, or Hierarchical scitype")
obj_in_mtype = metadata["mtype"]
obj = convert_to(obj, GET_LATEST_WINDOW_SUPPORTED_MTYPES)
# numpy3D (Panel) or np.npdarray (Series)
if isinstance(obj, np.ndarray):
obj_len = len(obj)
window_start = max(-window_length - lag, -obj_len)
window_end = max(-lag, -obj_len)
if window_end == 0:
return obj[window_start:]
else:
return obj[window_start:window_end]
# pd.DataFrame(Series), pd-multiindex (Panel) and pd_multiindex_hier (Hierarchical)
if isinstance(obj, pd.DataFrame):
cutoff = get_cutoff(obj)
win_start_excl = cutoff - window_length - lag
win_end_incl = cutoff - lag
if not isinstance(obj.index, pd.MultiIndex):
time_indices = obj.index
else:
time_indices = obj.index.get_level_values(-1)
win_select = (time_indices > win_start_excl) & (time_indices <=
win_end_incl)
obj_subset = obj.iloc[win_select]
return convert_to(obj_subset, obj_in_mtype)
raise ValueError(
"bug in get_latest_window, unreachable condition, ifs should be exhaustive"
)
def _transform(self, X, y=None):
"""Transform X.
Transform X, segments time-series in each column into random
intervals using interval indices generated
during `fit` and extracts features from each interval.
Parameters
----------
X : nested pandas.DataFrame of shape [n_instances, n_features]
Nested dataframe with time-series in cells.
Returns
-------
Xt : pandas.DataFrame
Transformed pandas DataFrame with n_instances rows and one
column for each generated interval.
"""
# Check input of feature calculators, i.e list of functions to be
# applied to time-series
features = _check_features(self.features)
X = convert_to(X, "numpy3D")
# Check that the input is of the same shape as the one passed
# during fit.
if X.shape[1] != self.input_shape_[1]:
raise ValueError(
"Number of columns of input is different from what was seen in `fit`"
)
# Input validation
# if not all([np.array_equal(fit_idx, trans_idx) for trans_idx,
# fit_idx in zip(check_equal_index(X),
# raise ValueError('Indexes of input time-series are different
# from what was seen in `fit`')
n_instances, _, _ = X.shape
n_features = len(features)
intervals = self.intervals_
n_intervals = len(intervals)
# Compute features on intervals.
Xt = np.zeros((n_instances, n_features * n_intervals)) # Allocate output array
# for transformed data
columns = []
i = 0
for func in features:
# TODO generalise to series-to-series functions and function kwargs
for start, end in intervals:
interval = X[:, :, start:end]
# Try to use optimised computations over axis if possible,
# otherwise iterate over rows.
try:
Xt[:, i] = func(interval, axis=-1).squeeze()
except TypeError as e:
if (
str(e) == f"{func.__name__}() got an unexpected "
f"keyword argument 'axis'"
):
Xt[:, i] = np.apply_along_axis(
func, axis=2, arr=interval
).squeeze()
else:
raise
i += 1
columns.append(f"{start}_{end}_{func.__name__}")
Xt = pd.DataFrame(Xt)
Xt.columns = columns
return Xt
def transform_single_feature(self, X, feature, case_id=None):
"""Transform data into a specified catch22 feature.
Parameters
----------
X : np.ndarray, 3D, in numpy3D mtype format
or other sktime data container of Panel scitype
feature : int, catch22 feature id or String, catch22 feature
name.
case_id : int, identifier for the current set of cases. If the case_id is not
None and the same as the previously used case_id, calculations from
previous features will be reused.
Returns
-------
Numpy array containing a catch22 feature for each input series.
"""
if isinstance(feature,
(int, np.integer)) or isinstance(feature,
(float, float)):
if feature > 21 or feature < 0:
raise ValueError("Invalid catch22 feature ID")
elif isinstance(feature, str):
if feature in feature_names:
feature = feature_names.index(feature)
else:
raise ValueError("Invalid catch22 feature name")
else:
raise ValueError("catch22 feature name or ID required")
if isinstance(X, pd.DataFrame):
X = convert_to(X, "numpy3D")
if len(X.shape) > 2:
n_instances, n_dims, series_length = X.shape
if n_dims > 1:
raise ValueError(
"transform_single_feature can only handle univariate series "
"currently.")
X = np.reshape(X, (n_instances, -1))
else:
n_instances, series_length = X.shape
if case_id is not None:
if case_id != self._case_id:
self._case_id = case_id
self._st_n_instances = n_instances
self._st_series_length = series_length
self._outlier_series = [None] * n_instances
self._smin = [None] * n_instances
self._smax = [None] * n_instances
self._smean = [None] * n_instances
self._fft = [None] * n_instances
self._ac = [None] * n_instances
self._acfz = [None] * n_instances
else:
if (n_instances != self._st_n_instances
or series_length != self._st_series_length):
raise ValueError(
"Catch22: case_is the same, but n_instances and "
"series_length do not match last seen for single "
"feature transform.")
c22_list = Parallel(n_jobs=self.n_jobs)(
delayed(self._transform_case_single)(
X[i],
feature,
case_id,
i,
) for i in range(n_instances))
if self.replace_nans:
c22_list = np.nan_to_num(c22_list, False, 0, 0, 0)
return np.asarray(c22_list)
def plot_series(*series,
labels=None,
markers=None,
x_label=None,
y_label=None,
ax=None):
"""Plot one or more time series.
Parameters
----------
series : pd.Series or iterable of pd.Series
One or more time series
labels : list, default = None
Names of series, will be displayed in figure legend
markers: list, default = None
Markers of data points, if None the marker "o" is used by default.
The length of the list has to match with the number of series.
Returns
-------
fig : plt.Figure
ax : plt.Axis
"""
_check_soft_dependencies("matplotlib", "seaborn")
import matplotlib.pyplot as plt
from matplotlib.ticker import FuncFormatter, MaxNLocator
from matplotlib.cbook import flatten
import seaborn as sns
for y in series:
check_y(y)
series = list(series)
series = [convert_to(y, "pd.Series", "Series") for y in series]
n_series = len(series)
_ax_kwarg_is_none = True if ax is None else False
# labels
if labels is not None:
if n_series != len(labels):
raise ValueError("""There must be one label for each time series,
but found inconsistent numbers of series and
labels.""")
legend = True
else:
labels = ["" for _ in range(n_series)]
legend = False
# markers
if markers is not None:
if n_series != len(markers):
raise ValueError("""There must be one marker for each time series,
but found inconsistent numbers of series and
markers.""")
else:
markers = ["o" for _ in range(n_series)]
# create combined index
index = series[0].index
for y in series[1:]:
# check index types
check_consistent_index_type(index, y.index)
index = index.union(y.index)
# generate integer x-values
xs = [np.argwhere(index.isin(y.index)).ravel() for y in series]
# create figure if no Axe provided for plotting
if _ax_kwarg_is_none:
fig, ax = plt.subplots(1, figsize=plt.figaspect(0.25))
colors = sns.color_palette("colorblind", n_colors=n_series)
# plot series
for x, y, color, label, marker in zip(xs, series, colors, labels, markers):
# scatter if little data is available or index is not complete
if len(x) <= 3 or not np.array_equal(np.arange(x[0], x[-1] + 1), x):
plot_func = sns.scatterplot
else:
plot_func = sns.lineplot
plot_func(x=x, y=y, ax=ax, marker=marker, label=label, color=color)
# combine data points for all series
xs_flat = list(flatten(xs))
# set x label of data point to the matching index
def format_fn(tick_val, tick_pos):
if int(tick_val) in xs_flat:
return index[int(tick_val)]
else:
return ""
# dynamically set x label ticks and spacing from index labels
ax.xaxis.set_major_formatter(FuncFormatter(format_fn))
ax.xaxis.set_major_locator(MaxNLocator(integer=True))
# Label the x and y axes
if x_label is not None:
ax.set_xlabel(x_label)
_y_label = y_label if y_label is not None else series[0].name
ax.set_ylabel(_y_label)
if legend:
ax.legend()
if _ax_kwarg_is_none:
return fig, ax
else:
return ax
def predict(self,
fh=None,
X=None,
return_pred_int=False,
alpha=DEFAULT_ALPHA):
"""Forecast time series at future horizon.
State required:
Requires state to be "fitted".
Accesses in self:
Fitted model attributes ending in "_".
self.cutoff, self._is_fitted
Writes to self:
Stores fh to self.fh if fh is passed and has not been passed in _fit.
Parameters
----------
fh : int, list, np.ndarray or ForecastingHorizon
Forecasting horizon
X : pd.DataFrame, or 2D np.ndarray, optional (default=None)
Exogeneous time series to predict from
if self.get_tag("X-y-must-have-same-index"), X.index must contain fh.index
return_pred_int : bool, optional (default=False)
If True, returns prediction intervals for given alpha values.
alpha : float or list, optional (default=0.95)
Returns
-------
y_pred : pd.Series, pd.DataFrame, or np.ndarray (1D or 2D)
Point forecasts at fh, with same index as fh
y_pred has same type as y passed in fit (most recently)
y_pred_int : pd.DataFrame - only if return_pred_int=True
in this case, return is 2-tuple (otherwise a single y_pred)
Prediction intervals
"""
# handle inputs
self.check_is_fitted()
self._set_fh(fh)
if return_pred_int and not self.get_tag("capability:pred_int"):
raise NotImplementedError(
f"{self.__class__.__name__} does not have the capability to return "
"prediction intervals. Please set return_pred_int=False. If you "
"think this estimator should have the capability, please open "
"an issue on sktime.")
# input check and conversion for X
X_inner = self._check_X(X=X)
# this should be here, but it breaks the ARIMA forecasters
# that is because check_alpha converts to list, but ARIMA forecaster
# doesn't do the check, and needs it as a float or it breaks
# todo: needs fixing in ARIMA and AutoARIMA
# alpha = check_alpha(alpha)
y_pred = self._predict(
self.fh,
X=X_inner,
return_pred_int=return_pred_int,
alpha=alpha,
)
# todo: clean this up, predictive intervals should be returned by other method
if return_pred_int:
pred_int = y_pred[1]
y_pred = y_pred[0]
# convert to output mtype, identical with last y mtype seen
y_out = convert_to(
y_pred,
self._y_mtype_last_seen,
as_scitype="Series",
store=self._converter_store_y,
)
if return_pred_int:
return (y_out, pred_int)
else:
return y_out