dadams/california-equity-git
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

library packages

Browse Source
This commit is contained in:
David Adams
2024-09-28 22:56:00 -07:00
parent 64d9b78b3a
commit 1973934e95
4893 changed files with 1184173 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.venv/lib/python3.12/site-packages/sklearn/impute/__init__.py Normal file
View File

@@ -0,0 +1,25 @@
"""Transformers for missing value imputation."""
import typing
from ._base import MissingIndicator, SimpleImputer
from ._knn import KNNImputer
if typing.TYPE_CHECKING:
# Avoid errors in type checkers (e.g. mypy) for experimental estimators.
# TODO: remove this check once the estimator is no longer experimental.
from ._iterative import IterativeImputer # noqa
__all__ = ["MissingIndicator", "SimpleImputer", "KNNImputer"]
# TODO: remove this check once the estimator is no longer experimental.
def __getattr__(name):
if name == "IterativeImputer":
raise ImportError(
f"{name} is experimental and the API might change without any "
"deprecation cycle. To use it, you need to explicitly import "
"enable_iterative_imputer:\n"
"from sklearn.experimental import enable_iterative_imputer"
)
raise AttributeError(f"module {__name__} has no attribute {name}")

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/__pycache__/_base.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/__pycache__/_iterative.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/__pycache__/_knn.cpython-312.pyc Normal file
View File

Binary file not shown.

1095
.venv/lib/python3.12/site-packages/sklearn/impute/_base.py Normal file
View File

File diff suppressed because it is too large Load Diff

960
.venv/lib/python3.12/site-packages/sklearn/impute/_iterative.py Normal file
View File

@@ -0,0 +1,960 @@
import warnings
from collections import namedtuple
from numbers import Integral, Real
from time import time
import numpy as np
from scipy import stats
from ..base import _fit_context, clone
from ..exceptions import ConvergenceWarning
from ..preprocessing import normalize
from ..utils import _safe_indexing, check_array, check_random_state
from ..utils._indexing import _safe_assign
from ..utils._mask import _get_mask
from ..utils._missing import is_scalar_nan
from ..utils._param_validation import HasMethods, Interval, StrOptions
from ..utils.metadata_routing import (
MetadataRouter,
MethodMapping,
_raise_for_params,
process_routing,
)
from ..utils.validation import FLOAT_DTYPES, _check_feature_names_in, check_is_fitted
from ._base import SimpleImputer, _BaseImputer, _check_inputs_dtype
_ImputerTriplet = namedtuple(
"_ImputerTriplet", ["feat_idx", "neighbor_feat_idx", "estimator"]
)
def _assign_where(X1, X2, cond):
"""Assign X2 to X1 where cond is True.
Parameters
----------
X1 : ndarray or dataframe of shape (n_samples, n_features)
Data.
X2 : ndarray of shape (n_samples, n_features)
Data to be assigned.
cond : ndarray of shape (n_samples, n_features)
Boolean mask to assign data.
"""
if hasattr(X1, "mask"): # pandas dataframes
X1.mask(cond=cond, other=X2, inplace=True)
else: # ndarrays
X1[cond] = X2[cond]
class IterativeImputer(_BaseImputer):
"""Multivariate imputer that estimates each feature from all the others.
A strategy for imputing missing values by modeling each feature with
missing values as a function of other features in a round-robin fashion.
Read more in the :ref:`User Guide <iterative_imputer>`.
.. versionadded:: 0.21
.. note::
This estimator is still **experimental** for now: the predictions
and the API might change without any deprecation cycle. To use it,
you need to explicitly import `enable_iterative_imputer`::
>>> # explicitly require this experimental feature
>>> from sklearn.experimental import enable_iterative_imputer # noqa
>>> # now you can import normally from sklearn.impute
>>> from sklearn.impute import IterativeImputer
Parameters
----------
estimator : estimator object, default=BayesianRidge()
The estimator to use at each step of the round-robin imputation.
If `sample_posterior=True`, the estimator must support
`return_std` in its `predict` method.
missing_values : int or np.nan, default=np.nan
The placeholder for the missing values. All occurrences of
`missing_values` will be imputed. For pandas' dataframes with
nullable integer dtypes with missing values, `missing_values`
should be set to `np.nan`, since `pd.NA` will be converted to `np.nan`.
sample_posterior : bool, default=False
Whether to sample from the (Gaussian) predictive posterior of the
fitted estimator for each imputation. Estimator must support
`return_std` in its `predict` method if set to `True`. Set to
`True` if using `IterativeImputer` for multiple imputations.
max_iter : int, default=10
Maximum number of imputation rounds to perform before returning the
imputations computed during the final round. A round is a single
imputation of each feature with missing values. The stopping criterion
is met once `max(abs(X_t - X_{t-1}))/max(abs(X[known_vals])) < tol`,
where `X_t` is `X` at iteration `t`. Note that early stopping is only
applied if `sample_posterior=False`.
tol : float, default=1e-3
Tolerance of the stopping condition.
n_nearest_features : int, default=None
Number of other features to use to estimate the missing values of
each feature column. Nearness between features is measured using
the absolute correlation coefficient between each feature pair (after
initial imputation). To ensure coverage of features throughout the
imputation process, the neighbor features are not necessarily nearest,
but are drawn with probability proportional to correlation for each
imputed target feature. Can provide significant speed-up when the
number of features is huge. If `None`, all features will be used.
initial_strategy : {'mean', 'median', 'most_frequent', 'constant'}, \
default='mean'
Which strategy to use to initialize the missing values. Same as the
`strategy` parameter in :class:`~sklearn.impute.SimpleImputer`.
fill_value : str or numerical value, default=None
When `strategy="constant"`, `fill_value` is used to replace all
occurrences of missing_values. For string or object data types,
`fill_value` must be a string.
If `None`, `fill_value` will be 0 when imputing numerical
data and "missing_value" for strings or object data types.
.. versionadded:: 1.3
imputation_order : {'ascending', 'descending', 'roman', 'arabic', \
'random'}, default='ascending'
The order in which the features will be imputed. Possible values:
- `'ascending'`: From features with fewest missing values to most.
- `'descending'`: From features with most missing values to fewest.
- `'roman'`: Left to right.
- `'arabic'`: Right to left.
- `'random'`: A random order for each round.
skip_complete : bool, default=False
If `True` then features with missing values during :meth:`transform`
which did not have any missing values during :meth:`fit` will be
imputed with the initial imputation method only. Set to `True` if you
have many features with no missing values at both :meth:`fit` and
:meth:`transform` time to save compute.
min_value : float or array-like of shape (n_features,), default=-np.inf
Minimum possible imputed value. Broadcast to shape `(n_features,)` if
scalar. If array-like, expects shape `(n_features,)`, one min value for
each feature. The default is `-np.inf`.
.. versionchanged:: 0.23
Added support for array-like.
max_value : float or array-like of shape (n_features,), default=np.inf
Maximum possible imputed value. Broadcast to shape `(n_features,)` if
scalar. If array-like, expects shape `(n_features,)`, one max value for
each feature. The default is `np.inf`.
.. versionchanged:: 0.23
Added support for array-like.
verbose : int, default=0
Verbosity flag, controls the debug messages that are issued
as functions are evaluated. The higher, the more verbose. Can be 0, 1,
or 2.
random_state : int, RandomState instance or None, default=None
The seed of the pseudo random number generator to use. Randomizes
selection of estimator features if `n_nearest_features` is not `None`,
the `imputation_order` if `random`, and the sampling from posterior if
`sample_posterior=True`. Use an integer for determinism.
See :term:`the Glossary <random_state>`.
add_indicator : bool, default=False
If `True`, a :class:`MissingIndicator` transform will stack onto output
of the imputer's transform. This allows a predictive estimator
to account for missingness despite imputation. If a feature has no
missing values at fit/train time, the feature won't appear on
the missing indicator even if there are missing values at
transform/test time.
keep_empty_features : bool, default=False
If True, features that consist exclusively of missing values when
`fit` is called are returned in results when `transform` is called.
The imputed value is always `0` except when
`initial_strategy="constant"` in which case `fill_value` will be
used instead.
.. versionadded:: 1.2
Attributes
----------
initial_imputer_ : object of type :class:`~sklearn.impute.SimpleImputer`
Imputer used to initialize the missing values.
imputation_sequence_ : list of tuples
Each tuple has `(feat_idx, neighbor_feat_idx, estimator)`, where
`feat_idx` is the current feature to be imputed,
`neighbor_feat_idx` is the array of other features used to impute the
current feature, and `estimator` is the trained estimator used for
the imputation. Length is `self.n_features_with_missing_ *
self.n_iter_`.
n_iter_ : int
Number of iteration rounds that occurred. Will be less than
`self.max_iter` if early stopping criterion was reached.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
n_features_with_missing_ : int
Number of features with missing values.
indicator_ : :class:`~sklearn.impute.MissingIndicator`
Indicator used to add binary indicators for missing values.
`None` if `add_indicator=False`.
random_state_ : RandomState instance
RandomState instance that is generated either from a seed, the random
number generator or by `np.random`.
See Also
--------
SimpleImputer : Univariate imputer for completing missing values
with simple strategies.
KNNImputer : Multivariate imputer that estimates missing features using
nearest samples.
Notes
-----
To support imputation in inductive mode we store each feature's estimator
during the :meth:`fit` phase, and predict without refitting (in order)
during the :meth:`transform` phase.
Features which contain all missing values at :meth:`fit` are discarded upon
:meth:`transform`.
Using defaults, the imputer scales in :math:`\\mathcal{O}(knp^3\\min(n,p))`
where :math:`k` = `max_iter`, :math:`n` the number of samples and
:math:`p` the number of features. It thus becomes prohibitively costly when
the number of features increases. Setting
`n_nearest_features << n_features`, `skip_complete=True` or increasing `tol`
can help to reduce its computational cost.
Depending on the nature of missing values, simple imputers can be
preferable in a prediction context.
References
----------
.. [1] `Stef van Buuren, Karin Groothuis-Oudshoorn (2011). "mice:
Multivariate Imputation by Chained Equations in R". Journal of
Statistical Software 45: 1-67.
<https://www.jstatsoft.org/article/view/v045i03>`_
.. [2] `S. F. Buck, (1960). "A Method of Estimation of Missing Values in
Multivariate Data Suitable for use with an Electronic Computer".
Journal of the Royal Statistical Society 22(2): 302-306.
<https://www.jstor.org/stable/2984099>`_
Examples
--------
>>> import numpy as np
>>> from sklearn.experimental import enable_iterative_imputer
>>> from sklearn.impute import IterativeImputer
>>> imp_mean = IterativeImputer(random_state=0)
>>> imp_mean.fit([[7, 2, 3], [4, np.nan, 6], [10, 5, 9]])
IterativeImputer(random_state=0)
>>> X = [[np.nan, 2, 3], [4, np.nan, 6], [10, np.nan, 9]]
>>> imp_mean.transform(X)
array([[ 6.9584..., 2. , 3. ],
[ 4. , 2.6000..., 6. ],
[10. , 4.9999..., 9. ]])
For a more detailed example see
:ref:`sphx_glr_auto_examples_impute_plot_missing_values.py` or
:ref:`sphx_glr_auto_examples_impute_plot_iterative_imputer_variants_comparison.py`.
"""
_parameter_constraints: dict = {
**_BaseImputer._parameter_constraints,
"estimator": [None, HasMethods(["fit", "predict"])],
"sample_posterior": ["boolean"],
"max_iter": [Interval(Integral, 0, None, closed="left")],
"tol": [Interval(Real, 0, None, closed="left")],
"n_nearest_features": [None, Interval(Integral, 1, None, closed="left")],
"initial_strategy": [
StrOptions({"mean", "median", "most_frequent", "constant"})
],
"fill_value": "no_validation", # any object is valid
"imputation_order": [
StrOptions({"ascending", "descending", "roman", "arabic", "random"})
],
"skip_complete": ["boolean"],
"min_value": [None, Interval(Real, None, None, closed="both"), "array-like"],
"max_value": [None, Interval(Real, None, None, closed="both"), "array-like"],
"verbose": ["verbose"],
"random_state": ["random_state"],
}
def __init__(
self,
estimator=None,
*,
missing_values=np.nan,
sample_posterior=False,
max_iter=10,
tol=1e-3,
n_nearest_features=None,
initial_strategy="mean",
fill_value=None,
imputation_order="ascending",
skip_complete=False,
min_value=-np.inf,
max_value=np.inf,
verbose=0,
random_state=None,
add_indicator=False,
keep_empty_features=False,
):
super().__init__(
missing_values=missing_values,
add_indicator=add_indicator,
keep_empty_features=keep_empty_features,
)
self.estimator = estimator
self.sample_posterior = sample_posterior
self.max_iter = max_iter
self.tol = tol
self.n_nearest_features = n_nearest_features
self.initial_strategy = initial_strategy
self.fill_value = fill_value
self.imputation_order = imputation_order
self.skip_complete = skip_complete
self.min_value = min_value
self.max_value = max_value
self.verbose = verbose
self.random_state = random_state
def _impute_one_feature(
self,
X_filled,
mask_missing_values,
feat_idx,
neighbor_feat_idx,
estimator=None,
fit_mode=True,
params=None,
):
"""Impute a single feature from the others provided.
This function predicts the missing values of one of the features using
the current estimates of all the other features. The `estimator` must
support `return_std=True` in its `predict` method for this function
to work.
Parameters
----------
X_filled : ndarray
Input data with the most recent imputations.
mask_missing_values : ndarray
Input data's missing indicator matrix.
feat_idx : int
Index of the feature currently being imputed.
neighbor_feat_idx : ndarray
Indices of the features to be used in imputing `feat_idx`.
estimator : object
The estimator to use at this step of the round-robin imputation.
If `sample_posterior=True`, the estimator must support
`return_std` in its `predict` method.
If None, it will be cloned from self._estimator.
fit_mode : boolean, default=True
Whether to fit and predict with the estimator or just predict.
params : dict
Additional params routed to the individual estimator.
Returns
-------
X_filled : ndarray
Input data with `X_filled[missing_row_mask, feat_idx]` updated.
estimator : estimator with sklearn API
The fitted estimator used to impute
`X_filled[missing_row_mask, feat_idx]`.
"""
if estimator is None and fit_mode is False:
raise ValueError(
"If fit_mode is False, then an already-fitted "
"estimator should be passed in."
)
if estimator is None:
estimator = clone(self._estimator)
missing_row_mask = mask_missing_values[:, feat_idx]
if fit_mode:
X_train = _safe_indexing(
_safe_indexing(X_filled, neighbor_feat_idx, axis=1),
~missing_row_mask,
axis=0,
)
y_train = _safe_indexing(
_safe_indexing(X_filled, feat_idx, axis=1),
~missing_row_mask,
axis=0,
)
estimator.fit(X_train, y_train, **params)
# if no missing values, don't predict
if np.sum(missing_row_mask) == 0:
return X_filled, estimator
# get posterior samples if there is at least one missing value
X_test = _safe_indexing(
_safe_indexing(X_filled, neighbor_feat_idx, axis=1),
missing_row_mask,
axis=0,
)
if self.sample_posterior:
mus, sigmas = estimator.predict(X_test, return_std=True)
imputed_values = np.zeros(mus.shape, dtype=X_filled.dtype)
# two types of problems: (1) non-positive sigmas
# (2) mus outside legal range of min_value and max_value
# (results in inf sample)
positive_sigmas = sigmas > 0
imputed_values[~positive_sigmas] = mus[~positive_sigmas]
mus_too_low = mus < self._min_value[feat_idx]
imputed_values[mus_too_low] = self._min_value[feat_idx]
mus_too_high = mus > self._max_value[feat_idx]
imputed_values[mus_too_high] = self._max_value[feat_idx]
# the rest can be sampled without statistical issues
inrange_mask = positive_sigmas & ~mus_too_low & ~mus_too_high
mus = mus[inrange_mask]
sigmas = sigmas[inrange_mask]
a = (self._min_value[feat_idx] - mus) / sigmas
b = (self._max_value[feat_idx] - mus) / sigmas
truncated_normal = stats.truncnorm(a=a, b=b, loc=mus, scale=sigmas)
imputed_values[inrange_mask] = truncated_normal.rvs(
random_state=self.random_state_
)
else:
imputed_values = estimator.predict(X_test)
imputed_values = np.clip(
imputed_values, self._min_value[feat_idx], self._max_value[feat_idx]
)
# update the feature
_safe_assign(
X_filled,
imputed_values,
row_indexer=missing_row_mask,
column_indexer=feat_idx,
)
return X_filled, estimator
def _get_neighbor_feat_idx(self, n_features, feat_idx, abs_corr_mat):
"""Get a list of other features to predict `feat_idx`.
If `self.n_nearest_features` is less than or equal to the total
number of features, then use a probability proportional to the absolute
correlation between `feat_idx` and each other feature to randomly
choose a subsample of the other features (without replacement).
Parameters
----------
n_features : int
Number of features in `X`.
feat_idx : int
Index of the feature currently being imputed.
abs_corr_mat : ndarray, shape (n_features, n_features)
Absolute correlation matrix of `X`. The diagonal has been zeroed
out and each feature has been normalized to sum to 1. Can be None.
Returns
-------
neighbor_feat_idx : array-like
The features to use to impute `feat_idx`.
"""
if self.n_nearest_features is not None and self.n_nearest_features < n_features:
p = abs_corr_mat[:, feat_idx]
neighbor_feat_idx = self.random_state_.choice(
np.arange(n_features), self.n_nearest_features, replace=False, p=p
)
else:
inds_left = np.arange(feat_idx)
inds_right = np.arange(feat_idx + 1, n_features)
neighbor_feat_idx = np.concatenate((inds_left, inds_right))
return neighbor_feat_idx
def _get_ordered_idx(self, mask_missing_values):
"""Decide in what order we will update the features.
As a homage to the MICE R package, we will have 4 main options of
how to order the updates, and use a random order if anything else
is specified.
Also, this function skips features which have no missing values.
Parameters
----------
mask_missing_values : array-like, shape (n_samples, n_features)
Input data's missing indicator matrix, where `n_samples` is the
number of samples and `n_features` is the number of features.
Returns
-------
ordered_idx : ndarray, shape (n_features,)
The order in which to impute the features.
"""
frac_of_missing_values = mask_missing_values.mean(axis=0)
if self.skip_complete:
missing_values_idx = np.flatnonzero(frac_of_missing_values)
else:
missing_values_idx = np.arange(np.shape(frac_of_missing_values)[0])
if self.imputation_order == "roman":
ordered_idx = missing_values_idx
elif self.imputation_order == "arabic":
ordered_idx = missing_values_idx[::-1]
elif self.imputation_order == "ascending":
n = len(frac_of_missing_values) - len(missing_values_idx)
ordered_idx = np.argsort(frac_of_missing_values, kind="mergesort")[n:]
elif self.imputation_order == "descending":
n = len(frac_of_missing_values) - len(missing_values_idx)
ordered_idx = np.argsort(frac_of_missing_values, kind="mergesort")[n:][::-1]
elif self.imputation_order == "random":
ordered_idx = missing_values_idx
self.random_state_.shuffle(ordered_idx)
return ordered_idx
def _get_abs_corr_mat(self, X_filled, tolerance=1e-6):
"""Get absolute correlation matrix between features.
Parameters
----------
X_filled : ndarray, shape (n_samples, n_features)
Input data with the most recent imputations.
tolerance : float, default=1e-6
`abs_corr_mat` can have nans, which will be replaced
with `tolerance`.
Returns
-------
abs_corr_mat : ndarray, shape (n_features, n_features)
Absolute correlation matrix of `X` at the beginning of the
current round. The diagonal has been zeroed out and each feature's
absolute correlations with all others have been normalized to sum
to 1.
"""
n_features = X_filled.shape[1]
if self.n_nearest_features is None or self.n_nearest_features >= n_features:
return None
with np.errstate(invalid="ignore"):
# if a feature in the neighborhood has only a single value
# (e.g., categorical feature), the std. dev. will be null and
# np.corrcoef will raise a warning due to a division by zero
abs_corr_mat = np.abs(np.corrcoef(X_filled.T))
# np.corrcoef is not defined for features with zero std
abs_corr_mat[np.isnan(abs_corr_mat)] = tolerance
# ensures exploration, i.e. at least some probability of sampling
np.clip(abs_corr_mat, tolerance, None, out=abs_corr_mat)
# features are not their own neighbors
np.fill_diagonal(abs_corr_mat, 0)
# needs to sum to 1 for np.random.choice sampling
abs_corr_mat = normalize(abs_corr_mat, norm="l1", axis=0, copy=False)
return abs_corr_mat
def _initial_imputation(self, X, in_fit=False):
"""Perform initial imputation for input `X`.
Parameters
----------
X : ndarray of shape (n_samples, n_features)
Input data, where `n_samples` is the number of samples and
`n_features` is the number of features.
in_fit : bool, default=False
Whether function is called in :meth:`fit`.
Returns
-------
Xt : ndarray of shape (n_samples, n_features)
Input data, where `n_samples` is the number of samples and
`n_features` is the number of features.
X_filled : ndarray of shape (n_samples, n_features)
Input data with the most recent imputations.
mask_missing_values : ndarray of shape (n_samples, n_features)
Input data's missing indicator matrix, where `n_samples` is the
number of samples and `n_features` is the number of features,
masked by non-missing features.
X_missing_mask : ndarray, shape (n_samples, n_features)
Input data's mask matrix indicating missing datapoints, where
`n_samples` is the number of samples and `n_features` is the
number of features.
"""
if is_scalar_nan(self.missing_values):
force_all_finite = "allow-nan"
else:
force_all_finite = True
X = self._validate_data(
X,
dtype=FLOAT_DTYPES,
order="F",
reset=in_fit,
force_all_finite=force_all_finite,
)
_check_inputs_dtype(X, self.missing_values)
X_missing_mask = _get_mask(X, self.missing_values)
mask_missing_values = X_missing_mask.copy()
if self.initial_imputer_ is None:
self.initial_imputer_ = SimpleImputer(
missing_values=self.missing_values,
strategy=self.initial_strategy,
fill_value=self.fill_value,
keep_empty_features=self.keep_empty_features,
).set_output(transform="default")
X_filled = self.initial_imputer_.fit_transform(X)
else:
X_filled = self.initial_imputer_.transform(X)
valid_mask = np.flatnonzero(
np.logical_not(np.isnan(self.initial_imputer_.statistics_))
)
if not self.keep_empty_features:
# drop empty features
Xt = X[:, valid_mask]
mask_missing_values = mask_missing_values[:, valid_mask]
else:
# mark empty features as not missing and keep the original
# imputation
mask_missing_values[:, valid_mask] = True
Xt = X
return Xt, X_filled, mask_missing_values, X_missing_mask
@staticmethod
def _validate_limit(limit, limit_type, n_features):
"""Validate the limits (min/max) of the feature values.
Converts scalar min/max limits to vectors of shape `(n_features,)`.
Parameters
----------
limit: scalar or array-like
The user-specified limit (i.e, min_value or max_value).
limit_type: {'max', 'min'}
Type of limit to validate.
n_features: int
Number of features in the dataset.
Returns
-------
limit: ndarray, shape(n_features,)
Array of limits, one for each feature.
"""
limit_bound = np.inf if limit_type == "max" else -np.inf
limit = limit_bound if limit is None else limit
if np.isscalar(limit):
limit = np.full(n_features, limit)
limit = check_array(limit, force_all_finite=False, copy=False, ensure_2d=False)
if not limit.shape[0] == n_features:
raise ValueError(
f"'{limit_type}_value' should be of "
f"shape ({n_features},) when an array-like "
f"is provided. Got {limit.shape}, instead."
)
return limit
@_fit_context(
# IterativeImputer.estimator is not validated yet
prefer_skip_nested_validation=False
)
def fit_transform(self, X, y=None, **params):
"""Fit the imputer on `X` and return the transformed `X`.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Input data, where `n_samples` is the number of samples and
`n_features` is the number of features.
y : Ignored
Not used, present for API consistency by convention.
**params : dict
Parameters routed to the `fit` method of the sub-estimator via the
metadata routing API.
.. versionadded:: 1.5
Only available if
`sklearn.set_config(enable_metadata_routing=True)` is set. See
:ref:`Metadata Routing User Guide <metadata_routing>` for more
details.
Returns
-------
Xt : array-like, shape (n_samples, n_features)
The imputed input data.
"""
_raise_for_params(params, self, "fit")
routed_params = process_routing(
self,
"fit",
**params,
)
self.random_state_ = getattr(
self, "random_state_", check_random_state(self.random_state)
)
if self.estimator is None:
from ..linear_model import BayesianRidge
self._estimator = BayesianRidge()
else:
self._estimator = clone(self.estimator)
self.imputation_sequence_ = []
self.initial_imputer_ = None
X, Xt, mask_missing_values, complete_mask = self._initial_imputation(
X, in_fit=True
)
super()._fit_indicator(complete_mask)
X_indicator = super()._transform_indicator(complete_mask)
if self.max_iter == 0 or np.all(mask_missing_values):
self.n_iter_ = 0
return super()._concatenate_indicator(Xt, X_indicator)
# Edge case: a single feature, we return the initial imputation.
if Xt.shape[1] == 1:
self.n_iter_ = 0
return super()._concatenate_indicator(Xt, X_indicator)
self._min_value = self._validate_limit(self.min_value, "min", X.shape[1])
self._max_value = self._validate_limit(self.max_value, "max", X.shape[1])
if not np.all(np.greater(self._max_value, self._min_value)):
raise ValueError("One (or more) features have min_value >= max_value.")
# order in which to impute
# note this is probably too slow for large feature data (d > 100000)
# and a better way would be good.
# see: https://goo.gl/KyCNwj and subsequent comments
ordered_idx = self._get_ordered_idx(mask_missing_values)
self.n_features_with_missing_ = len(ordered_idx)
abs_corr_mat = self._get_abs_corr_mat(Xt)
n_samples, n_features = Xt.shape
if self.verbose > 0:
print("[IterativeImputer] Completing matrix with shape %s" % (X.shape,))
start_t = time()
if not self.sample_posterior:
Xt_previous = Xt.copy()
normalized_tol = self.tol * np.max(np.abs(X[~mask_missing_values]))
for self.n_iter_ in range(1, self.max_iter + 1):
if self.imputation_order == "random":
ordered_idx = self._get_ordered_idx(mask_missing_values)
for feat_idx in ordered_idx:
neighbor_feat_idx = self._get_neighbor_feat_idx(
n_features, feat_idx, abs_corr_mat
)
Xt, estimator = self._impute_one_feature(
Xt,
mask_missing_values,
feat_idx,
neighbor_feat_idx,
estimator=None,
fit_mode=True,
params=routed_params.estimator.fit,
)
estimator_triplet = _ImputerTriplet(
feat_idx, neighbor_feat_idx, estimator
)
self.imputation_sequence_.append(estimator_triplet)
if self.verbose > 1:
print(
"[IterativeImputer] Ending imputation round "
"%d/%d, elapsed time %0.2f"
% (self.n_iter_, self.max_iter, time() - start_t)
)
if not self.sample_posterior:
inf_norm = np.linalg.norm(Xt - Xt_previous, ord=np.inf, axis=None)
if self.verbose > 0:
print(
"[IterativeImputer] Change: {}, scaled tolerance: {} ".format(
inf_norm, normalized_tol
)
)
if inf_norm < normalized_tol:
if self.verbose > 0:
print("[IterativeImputer] Early stopping criterion reached.")
break
Xt_previous = Xt.copy()
else:
if not self.sample_posterior:
warnings.warn(
"[IterativeImputer] Early stopping criterion not reached.",
ConvergenceWarning,
)
_assign_where(Xt, X, cond=~mask_missing_values)
return super()._concatenate_indicator(Xt, X_indicator)
def transform(self, X):
"""Impute all missing values in `X`.
Note that this is stochastic, and that if `random_state` is not fixed,
repeated calls, or permuted input, results will differ.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The input data to complete.
Returns
-------
Xt : array-like, shape (n_samples, n_features)
The imputed input data.
"""
check_is_fitted(self)
X, Xt, mask_missing_values, complete_mask = self._initial_imputation(
X, in_fit=False
)
X_indicator = super()._transform_indicator(complete_mask)
if self.n_iter_ == 0 or np.all(mask_missing_values):
return super()._concatenate_indicator(Xt, X_indicator)
imputations_per_round = len(self.imputation_sequence_) // self.n_iter_
i_rnd = 0
if self.verbose > 0:
print("[IterativeImputer] Completing matrix with shape %s" % (X.shape,))
start_t = time()
for it, estimator_triplet in enumerate(self.imputation_sequence_):
Xt, _ = self._impute_one_feature(
Xt,
mask_missing_values,
estimator_triplet.feat_idx,
estimator_triplet.neighbor_feat_idx,
estimator=estimator_triplet.estimator,
fit_mode=False,
)
if not (it + 1) % imputations_per_round:
if self.verbose > 1:
print(
"[IterativeImputer] Ending imputation round "
"%d/%d, elapsed time %0.2f"
% (i_rnd + 1, self.n_iter_, time() - start_t)
)
i_rnd += 1
_assign_where(Xt, X, cond=~mask_missing_values)
return super()._concatenate_indicator(Xt, X_indicator)
def fit(self, X, y=None, **fit_params):
"""Fit the imputer on `X` and return self.
Parameters
----------
X : array-like, shape (n_samples, n_features)
Input data, where `n_samples` is the number of samples and
`n_features` is the number of features.
y : Ignored
Not used, present for API consistency by convention.
**fit_params : dict
Parameters routed to the `fit` method of the sub-estimator via the
metadata routing API.
.. versionadded:: 1.5
Only available if
`sklearn.set_config(enable_metadata_routing=True)` is set. See
:ref:`Metadata Routing User Guide <metadata_routing>` for more
details.
Returns
-------
self : object
Fitted estimator.
"""
self.fit_transform(X, **fit_params)
return self
def get_feature_names_out(self, input_features=None):
"""Get output feature names for transformation.
Parameters
----------
input_features : array-like of str or None, default=None
Input features.
- If `input_features` is `None`, then `feature_names_in_` is
used as feature names in. If `feature_names_in_` is not defined,
then the following input feature names are generated:
`["x0", "x1", ..., "x(n_features_in_ - 1)"]`.
- If `input_features` is an array-like, then `input_features` must
match `feature_names_in_` if `feature_names_in_` is defined.
Returns
-------
feature_names_out : ndarray of str objects
Transformed feature names.
"""
check_is_fitted(self, "n_features_in_")
input_features = _check_feature_names_in(self, input_features)
names = self.initial_imputer_.get_feature_names_out(input_features)
return self._concatenate_indicator_feature_names_out(names, input_features)
def get_metadata_routing(self):
"""Get metadata routing of this object.
Please check :ref:`User Guide <metadata_routing>` on how the routing
mechanism works.
.. versionadded:: 1.5
Returns
-------
routing : MetadataRouter
A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
routing information.
"""
router = MetadataRouter(owner=self.__class__.__name__).add(
estimator=self.estimator,
method_mapping=MethodMapping().add(callee="fit", caller="fit"),
)
return router

402
.venv/lib/python3.12/site-packages/sklearn/impute/_knn.py Normal file
View File

@@ -0,0 +1,402 @@
# Authors: Ashim Bhattarai <ashimb9@gmail.com>
# Thomas J Fan <thomasjpfan@gmail.com>
# License: BSD 3 clause
from numbers import Integral
import numpy as np
from ..base import _fit_context
from ..metrics import pairwise_distances_chunked
from ..metrics.pairwise import _NAN_METRICS
from ..neighbors._base import _get_weights
from ..utils._mask import _get_mask
from ..utils._missing import is_scalar_nan
from ..utils._param_validation import Hidden, Interval, StrOptions
from ..utils.validation import FLOAT_DTYPES, _check_feature_names_in, check_is_fitted
from ._base import _BaseImputer
class KNNImputer(_BaseImputer):
"""Imputation for completing missing values using k-Nearest Neighbors.
Each sample's missing values are imputed using the mean value from
`n_neighbors` nearest neighbors found in the training set. Two samples are
close if the features that neither is missing are close.
Read more in the :ref:`User Guide <knnimpute>`.
.. versionadded:: 0.22
Parameters
----------
missing_values : int, float, str, np.nan or None, default=np.nan
The placeholder for the missing values. All occurrences of
`missing_values` will be imputed. For pandas' dataframes with
nullable integer dtypes with missing values, `missing_values`
should be set to np.nan, since `pd.NA` will be converted to np.nan.
n_neighbors : int, default=5
Number of neighboring samples to use for imputation.
weights : {'uniform', 'distance'} or callable, default='uniform'
Weight function used in prediction. Possible values:
- 'uniform' : uniform weights. All points in each neighborhood are
weighted equally.
- 'distance' : weight points by the inverse of their distance.
in this case, closer neighbors of a query point will have a
greater influence than neighbors which are further away.
- callable : a user-defined function which accepts an
array of distances, and returns an array of the same shape
containing the weights.
metric : {'nan_euclidean'} or callable, default='nan_euclidean'
Distance metric for searching neighbors. Possible values:
- 'nan_euclidean'
- callable : a user-defined function which conforms to the definition
of ``func_metric(x, y, *, missing_values=np.nan)``. `x` and `y`
corresponds to a row (i.e. 1-D arrays) of `X` and `Y`, respectively.
The callable should returns a scalar distance value.
copy : bool, default=True
If True, a copy of X will be created. If False, imputation will
be done in-place whenever possible.
add_indicator : bool, default=False
If True, a :class:`MissingIndicator` transform will stack onto the
output of the imputer's transform. This allows a predictive estimator
to account for missingness despite imputation. If a feature has no
missing values at fit/train time, the feature won't appear on the
missing indicator even if there are missing values at transform/test
time.
keep_empty_features : bool, default=False
If True, features that consist exclusively of missing values when
`fit` is called are returned in results when `transform` is called.
The imputed value is always `0`.
.. versionadded:: 1.2
Attributes
----------
indicator_ : :class:`~sklearn.impute.MissingIndicator`
Indicator used to add binary indicators for missing values.
``None`` if add_indicator is False.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
See Also
--------
SimpleImputer : Univariate imputer for completing missing values
with simple strategies.
IterativeImputer : Multivariate imputer that estimates values to impute for
each feature with missing values from all the others.
References
----------
* `Olga Troyanskaya, Michael Cantor, Gavin Sherlock, Pat Brown, Trevor
Hastie, Robert Tibshirani, David Botstein and Russ B. Altman, Missing
value estimation methods for DNA microarrays, BIOINFORMATICS Vol. 17
no. 6, 2001 Pages 520-525.
<https://academic.oup.com/bioinformatics/article/17/6/520/272365>`_
Examples
--------
>>> import numpy as np
>>> from sklearn.impute import KNNImputer
>>> X = [[1, 2, np.nan], [3, 4, 3], [np.nan, 6, 5], [8, 8, 7]]
>>> imputer = KNNImputer(n_neighbors=2)
>>> imputer.fit_transform(X)
array([[1. , 2. , 4. ],
[3. , 4. , 3. ],
[5.5, 6. , 5. ],
[8. , 8. , 7. ]])
For a more detailed example see
:ref:`sphx_glr_auto_examples_impute_plot_missing_values.py`.
"""
_parameter_constraints: dict = {
**_BaseImputer._parameter_constraints,
"n_neighbors": [Interval(Integral, 1, None, closed="left")],
"weights": [StrOptions({"uniform", "distance"}), callable, Hidden(None)],
"metric": [StrOptions(set(_NAN_METRICS)), callable],
"copy": ["boolean"],
}
def __init__(
self,
*,
missing_values=np.nan,
n_neighbors=5,
weights="uniform",
metric="nan_euclidean",
copy=True,
add_indicator=False,
keep_empty_features=False,
):
super().__init__(
missing_values=missing_values,
add_indicator=add_indicator,
keep_empty_features=keep_empty_features,
)
self.n_neighbors = n_neighbors
self.weights = weights
self.metric = metric
self.copy = copy
def _calc_impute(self, dist_pot_donors, n_neighbors, fit_X_col, mask_fit_X_col):
"""Helper function to impute a single column.
Parameters
----------
dist_pot_donors : ndarray of shape (n_receivers, n_potential_donors)
Distance matrix between the receivers and potential donors from
training set. There must be at least one non-nan distance between
a receiver and a potential donor.
n_neighbors : int
Number of neighbors to consider.
fit_X_col : ndarray of shape (n_potential_donors,)
Column of potential donors from training set.
mask_fit_X_col : ndarray of shape (n_potential_donors,)
Missing mask for fit_X_col.
Returns
-------
imputed_values: ndarray of shape (n_receivers,)
Imputed values for receiver.
"""
# Get donors
donors_idx = np.argpartition(dist_pot_donors, n_neighbors - 1, axis=1)[
:, :n_neighbors
]
# Get weight matrix from distance matrix
donors_dist = dist_pot_donors[
np.arange(donors_idx.shape[0])[:, None], donors_idx
]
weight_matrix = _get_weights(donors_dist, self.weights)
# fill nans with zeros
if weight_matrix is not None:
weight_matrix[np.isnan(weight_matrix)] = 0.0
# Retrieve donor values and calculate kNN average
donors = fit_X_col.take(donors_idx)
donors_mask = mask_fit_X_col.take(donors_idx)
donors = np.ma.array(donors, mask=donors_mask)
return np.ma.average(donors, axis=1, weights=weight_matrix).data
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y=None):
"""Fit the imputer on X.
Parameters
----------
X : array-like shape of (n_samples, n_features)
Input data, where `n_samples` is the number of samples and
`n_features` is the number of features.
y : Ignored
Not used, present here for API consistency by convention.
Returns
-------
self : object
The fitted `KNNImputer` class instance.
"""
# Check data integrity and calling arguments
if not is_scalar_nan(self.missing_values):
force_all_finite = True
else:
force_all_finite = "allow-nan"
X = self._validate_data(
X,
accept_sparse=False,
dtype=FLOAT_DTYPES,
force_all_finite=force_all_finite,
copy=self.copy,
)
self._fit_X = X
self._mask_fit_X = _get_mask(self._fit_X, self.missing_values)
self._valid_mask = ~np.all(self._mask_fit_X, axis=0)
super()._fit_indicator(self._mask_fit_X)
return self
def transform(self, X):
"""Impute all missing values in X.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The input data to complete.
Returns
-------
X : array-like of shape (n_samples, n_output_features)
The imputed dataset. `n_output_features` is the number of features
that is not always missing during `fit`.
"""
check_is_fitted(self)
if not is_scalar_nan(self.missing_values):
force_all_finite = True
else:
force_all_finite = "allow-nan"
X = self._validate_data(
X,
accept_sparse=False,
dtype=FLOAT_DTYPES,
force_writeable=True,
force_all_finite=force_all_finite,
copy=self.copy,
reset=False,
)
mask = _get_mask(X, self.missing_values)
mask_fit_X = self._mask_fit_X
valid_mask = self._valid_mask
X_indicator = super()._transform_indicator(mask)
# Removes columns where the training data is all nan
if not np.any(mask):
# No missing values in X
if self.keep_empty_features:
Xc = X
Xc[:, ~valid_mask] = 0
else:
Xc = X[:, valid_mask]
# Even if there are no missing values in X, we still concatenate Xc
# with the missing value indicator matrix, X_indicator.
# This is to ensure that the output maintains consistency in terms
# of columns, regardless of whether missing values exist in X or not.
return super()._concatenate_indicator(Xc, X_indicator)
row_missing_idx = np.flatnonzero(mask.any(axis=1))
non_missing_fix_X = np.logical_not(mask_fit_X)
# Maps from indices from X to indices in dist matrix
dist_idx_map = np.zeros(X.shape[0], dtype=int)
dist_idx_map[row_missing_idx] = np.arange(row_missing_idx.shape[0])
def process_chunk(dist_chunk, start):
row_missing_chunk = row_missing_idx[start : start + len(dist_chunk)]
# Find and impute missing by column
for col in range(X.shape[1]):
if not valid_mask[col]:
# column was all missing during training
continue
col_mask = mask[row_missing_chunk, col]
if not np.any(col_mask):
# column has no missing values
continue
(potential_donors_idx,) = np.nonzero(non_missing_fix_X[:, col])
# receivers_idx are indices in X
receivers_idx = row_missing_chunk[np.flatnonzero(col_mask)]
# distances for samples that needed imputation for column
dist_subset = dist_chunk[dist_idx_map[receivers_idx] - start][
:, potential_donors_idx
]
# receivers with all nan distances impute with mean
all_nan_dist_mask = np.isnan(dist_subset).all(axis=1)
all_nan_receivers_idx = receivers_idx[all_nan_dist_mask]
if all_nan_receivers_idx.size:
col_mean = np.ma.array(
self._fit_X[:, col], mask=mask_fit_X[:, col]
).mean()
X[all_nan_receivers_idx, col] = col_mean
if len(all_nan_receivers_idx) == len(receivers_idx):
# all receivers imputed with mean
continue
# receivers with at least one defined distance
receivers_idx = receivers_idx[~all_nan_dist_mask]
dist_subset = dist_chunk[dist_idx_map[receivers_idx] - start][
:, potential_donors_idx
]
n_neighbors = min(self.n_neighbors, len(potential_donors_idx))
value = self._calc_impute(
dist_subset,
n_neighbors,
self._fit_X[potential_donors_idx, col],
mask_fit_X[potential_donors_idx, col],
)
X[receivers_idx, col] = value
# process in fixed-memory chunks
gen = pairwise_distances_chunked(
X[row_missing_idx, :],
self._fit_X,
metric=self.metric,
missing_values=self.missing_values,
force_all_finite=force_all_finite,
reduce_func=process_chunk,
)
for chunk in gen:
# process_chunk modifies X in place. No return value.
pass
if self.keep_empty_features:
Xc = X
Xc[:, ~valid_mask] = 0
else:
Xc = X[:, valid_mask]
return super()._concatenate_indicator(Xc, X_indicator)
def get_feature_names_out(self, input_features=None):
"""Get output feature names for transformation.
Parameters
----------
input_features : array-like of str or None, default=None
Input features.
- If `input_features` is `None`, then `feature_names_in_` is
used as feature names in. If `feature_names_in_` is not defined,
then the following input feature names are generated:
`["x0", "x1", ..., "x(n_features_in_ - 1)"]`.
- If `input_features` is an array-like, then `input_features` must
match `feature_names_in_` if `feature_names_in_` is defined.
Returns
-------
feature_names_out : ndarray of str objects
Transformed feature names.
"""
check_is_fitted(self, "n_features_in_")
input_features = _check_feature_names_in(self, input_features)
names = input_features[self._valid_mask]
return self._concatenate_indicator_feature_names_out(names, input_features)

0
.venv/lib/python3.12/site-packages/sklearn/impute/tests/__init__.py Normal file
View File

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/tests/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/tests/__pycache__/test_base.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/tests/__pycache__/test_common.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/tests/__pycache__/test_impute.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
.venv/lib/python3.12/site-packages/sklearn/impute/tests/__pycache__/test_knn.cpython-312.pyc Normal file
View File

Binary file not shown.

107
.venv/lib/python3.12/site-packages/sklearn/impute/tests/test_base.py Normal file
View File

@@ -0,0 +1,107 @@
import numpy as np
import pytest
from sklearn.impute._base import _BaseImputer
from sklearn.impute._iterative import _assign_where
from sklearn.utils._mask import _get_mask
from sklearn.utils._testing import _convert_container, assert_allclose
@pytest.fixture
def data():
X = np.random.randn(10, 2)
X[::2] = np.nan
return X
class NoFitIndicatorImputer(_BaseImputer):
def fit(self, X, y=None):
return self
def transform(self, X, y=None):
return self._concatenate_indicator(X, self._transform_indicator(X))
class NoTransformIndicatorImputer(_BaseImputer):
def fit(self, X, y=None):
mask = _get_mask(X, value_to_mask=np.nan)
super()._fit_indicator(mask)
return self
def transform(self, X, y=None):
return self._concatenate_indicator(X, None)
class NoPrecomputedMaskFit(_BaseImputer):
def fit(self, X, y=None):
self._fit_indicator(X)
return self
def transform(self, X):
return self._concatenate_indicator(X, self._transform_indicator(X))
class NoPrecomputedMaskTransform(_BaseImputer):
def fit(self, X, y=None):
mask = _get_mask(X, value_to_mask=np.nan)
self._fit_indicator(mask)
return self
def transform(self, X):
return self._concatenate_indicator(X, self._transform_indicator(X))
def test_base_imputer_not_fit(data):
imputer = NoFitIndicatorImputer(add_indicator=True)
err_msg = "Make sure to call _fit_indicator before _transform_indicator"
with pytest.raises(ValueError, match=err_msg):
imputer.fit(data).transform(data)
with pytest.raises(ValueError, match=err_msg):
imputer.fit_transform(data)
def test_base_imputer_not_transform(data):
imputer = NoTransformIndicatorImputer(add_indicator=True)
err_msg = (
"Call _fit_indicator and _transform_indicator in the imputer implementation"
)
with pytest.raises(ValueError, match=err_msg):
imputer.fit(data).transform(data)
with pytest.raises(ValueError, match=err_msg):
imputer.fit_transform(data)
def test_base_no_precomputed_mask_fit(data):
imputer = NoPrecomputedMaskFit(add_indicator=True)
err_msg = "precomputed is True but the input data is not a mask"
with pytest.raises(ValueError, match=err_msg):
imputer.fit(data)
with pytest.raises(ValueError, match=err_msg):
imputer.fit_transform(data)
def test_base_no_precomputed_mask_transform(data):
imputer = NoPrecomputedMaskTransform(add_indicator=True)
err_msg = "precomputed is True but the input data is not a mask"
imputer.fit(data)
with pytest.raises(ValueError, match=err_msg):
imputer.transform(data)
with pytest.raises(ValueError, match=err_msg):
imputer.fit_transform(data)
@pytest.mark.parametrize("X1_type", ["array", "dataframe"])
def test_assign_where(X1_type):
"""Check the behaviour of the private helpers `_assign_where`."""
rng = np.random.RandomState(0)
n_samples, n_features = 10, 5
X1 = _convert_container(rng.randn(n_samples, n_features), constructor_name=X1_type)
X2 = rng.randn(n_samples, n_features)
mask = rng.randint(0, 2, size=(n_samples, n_features)).astype(bool)
_assign_where(X1, X2, mask)
if X1_type == "dataframe":
X1 = X1.to_numpy()
assert_allclose(X1[mask], X2[mask])

220
.venv/lib/python3.12/site-packages/sklearn/impute/tests/test_common.py Normal file
View File

@@ -0,0 +1,220 @@
import numpy as np
import pytest
from sklearn.experimental import enable_iterative_imputer # noqa
from sklearn.impute import IterativeImputer, KNNImputer, SimpleImputer
from sklearn.utils._testing import (
assert_allclose,
assert_allclose_dense_sparse,
assert_array_equal,
)
from sklearn.utils.fixes import CSR_CONTAINERS
def imputers():
return [IterativeImputer(tol=0.1), KNNImputer(), SimpleImputer()]
def sparse_imputers():
return [SimpleImputer()]
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
def test_imputation_missing_value_in_test_array(imputer):
# [Non Regression Test for issue #13968] Missing value in test set should
# not throw an error and return a finite dataset
train = [[1], [2]]
test = [[3], [np.nan]]
imputer.set_params(add_indicator=True)
imputer.fit(train).transform(test)
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("marker", [np.nan, -1, 0])
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
def test_imputers_add_indicator(marker, imputer):
X = np.array(
[
[marker, 1, 5, marker, 1],
[2, marker, 1, marker, 2],
[6, 3, marker, marker, 3],
[1, 2, 9, marker, 4],
]
)
X_true_indicator = np.array(
[
[1.0, 0.0, 0.0, 1.0],
[0.0, 1.0, 0.0, 1.0],
[0.0, 0.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0],
]
)
imputer.set_params(missing_values=marker, add_indicator=True)
X_trans = imputer.fit_transform(X)
assert_allclose(X_trans[:, -4:], X_true_indicator)
assert_array_equal(imputer.indicator_.features_, np.array([0, 1, 2, 3]))
imputer.set_params(add_indicator=False)
X_trans_no_indicator = imputer.fit_transform(X)
assert_allclose(X_trans[:, :-4], X_trans_no_indicator)
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("marker", [np.nan, -1])
@pytest.mark.parametrize(
"imputer", sparse_imputers(), ids=lambda x: x.__class__.__name__
)
@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
def test_imputers_add_indicator_sparse(imputer, marker, csr_container):
X = csr_container(
[
[marker, 1, 5, marker, 1],
[2, marker, 1, marker, 2],
[6, 3, marker, marker, 3],
[1, 2, 9, marker, 4],
]
)
X_true_indicator = csr_container(
[
[1.0, 0.0, 0.0, 1.0],
[0.0, 1.0, 0.0, 1.0],
[0.0, 0.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0],
]
)
imputer.set_params(missing_values=marker, add_indicator=True)
X_trans = imputer.fit_transform(X)
assert_allclose_dense_sparse(X_trans[:, -4:], X_true_indicator)
assert_array_equal(imputer.indicator_.features_, np.array([0, 1, 2, 3]))
imputer.set_params(add_indicator=False)
X_trans_no_indicator = imputer.fit_transform(X)
assert_allclose_dense_sparse(X_trans[:, :-4], X_trans_no_indicator)
# ConvergenceWarning will be raised by the IterativeImputer
@pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
@pytest.mark.parametrize("add_indicator", [True, False])
def test_imputers_pandas_na_integer_array_support(imputer, add_indicator):
# Test pandas IntegerArray with pd.NA
pd = pytest.importorskip("pandas")
marker = np.nan
imputer = imputer.set_params(add_indicator=add_indicator, missing_values=marker)
X = np.array(
[
[marker, 1, 5, marker, 1],
[2, marker, 1, marker, 2],
[6, 3, marker, marker, 3],
[1, 2, 9, marker, 4],
]
)
# fit on numpy array
X_trans_expected = imputer.fit_transform(X)
# Creates dataframe with IntegerArrays with pd.NA
X_df = pd.DataFrame(X, dtype="Int16", columns=["a", "b", "c", "d", "e"])
# fit on pandas dataframe with IntegerArrays
X_trans = imputer.fit_transform(X_df)
assert_allclose(X_trans_expected, X_trans)
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
@pytest.mark.parametrize("add_indicator", [True, False])
def test_imputers_feature_names_out_pandas(imputer, add_indicator):
"""Check feature names out for imputers."""
pd = pytest.importorskip("pandas")
marker = np.nan
imputer = imputer.set_params(add_indicator=add_indicator, missing_values=marker)
X = np.array(
[
[marker, 1, 5, 3, marker, 1],
[2, marker, 1, 4, marker, 2],
[6, 3, 7, marker, marker, 3],
[1, 2, 9, 8, marker, 4],
]
)
X_df = pd.DataFrame(X, columns=["a", "b", "c", "d", "e", "f"])
imputer.fit(X_df)
names = imputer.get_feature_names_out()
if add_indicator:
expected_names = [
"a",
"b",
"c",
"d",
"f",
"missingindicator_a",
"missingindicator_b",
"missingindicator_d",
"missingindicator_e",
]
assert_array_equal(expected_names, names)
else:
expected_names = ["a", "b", "c", "d", "f"]
assert_array_equal(expected_names, names)
@pytest.mark.parametrize("keep_empty_features", [True, False])
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
def test_keep_empty_features(imputer, keep_empty_features):
"""Check that the imputer keeps features with only missing values."""
X = np.array([[np.nan, 1], [np.nan, 2], [np.nan, 3]])
imputer = imputer.set_params(
add_indicator=False, keep_empty_features=keep_empty_features
)
for method in ["fit_transform", "transform"]:
X_imputed = getattr(imputer, method)(X)
if keep_empty_features:
assert X_imputed.shape == X.shape
else:
assert X_imputed.shape == (X.shape[0], X.shape[1] - 1)
@pytest.mark.parametrize("imputer", imputers(), ids=lambda x: x.__class__.__name__)
@pytest.mark.parametrize("missing_value_test", [np.nan, 1])
def test_imputation_adds_missing_indicator_if_add_indicator_is_true(
imputer, missing_value_test
):
"""Check that missing indicator always exists when add_indicator=True.
Non-regression test for gh-26590.
"""
X_train = np.array([[0, np.nan], [1, 2]])
# Test data where missing_value_test variable can be set to np.nan or 1.
X_test = np.array([[0, missing_value_test], [1, 2]])
imputer.set_params(add_indicator=True)
imputer.fit(X_train)
X_test_imputed_with_indicator = imputer.transform(X_test)
assert X_test_imputed_with_indicator.shape == (2, 3)
imputer.set_params(add_indicator=False)
imputer.fit(X_train)
X_test_imputed_without_indicator = imputer.transform(X_test)
assert X_test_imputed_without_indicator.shape == (2, 2)
assert_allclose(
X_test_imputed_with_indicator[:, :-1], X_test_imputed_without_indicator
)
if np.isnan(missing_value_test):
expected_missing_indicator = [1, 0]
else:
expected_missing_indicator = [0, 0]
assert_allclose(X_test_imputed_with_indicator[:, -1], expected_missing_indicator)

1788
.venv/lib/python3.12/site-packages/sklearn/impute/tests/test_impute.py Normal file
View File

File diff suppressed because it is too large Load Diff

547
.venv/lib/python3.12/site-packages/sklearn/impute/tests/test_knn.py Normal file
View File

@@ -0,0 +1,547 @@
import numpy as np
import pytest
from sklearn import config_context
from sklearn.impute import KNNImputer
from sklearn.metrics.pairwise import nan_euclidean_distances, pairwise_distances
from sklearn.neighbors import KNeighborsRegressor
from sklearn.utils._testing import assert_allclose
@pytest.mark.parametrize("weights", ["uniform", "distance"])
@pytest.mark.parametrize("n_neighbors", range(1, 6))
def test_knn_imputer_shape(weights, n_neighbors):
# Verify the shapes of the imputed matrix for different weights and
# number of neighbors.
n_rows = 10
n_cols = 2
X = np.random.rand(n_rows, n_cols)
X[0, 0] = np.nan
imputer = KNNImputer(n_neighbors=n_neighbors, weights=weights)
X_imputed = imputer.fit_transform(X)
assert X_imputed.shape == (n_rows, n_cols)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_default_with_invalid_input(na):
# Test imputation with default values and invalid input
# Test with inf present
X = np.array(
[
[np.inf, 1, 1, 2, na],
[2, 1, 2, 2, 3],
[3, 2, 3, 3, 8],
[na, 6, 0, 5, 13],
[na, 7, 0, 7, 8],
[6, 6, 2, 5, 7],
]
)
with pytest.raises(ValueError, match="Input X contains (infinity|NaN)"):
KNNImputer(missing_values=na).fit(X)
# Test with inf present in matrix passed in transform()
X = np.array(
[
[np.inf, 1, 1, 2, na],
[2, 1, 2, 2, 3],
[3, 2, 3, 3, 8],
[na, 6, 0, 5, 13],
[na, 7, 0, 7, 8],
[6, 6, 2, 5, 7],
]
)
X_fit = np.array(
[
[0, 1, 1, 2, na],
[2, 1, 2, 2, 3],
[3, 2, 3, 3, 8],
[na, 6, 0, 5, 13],
[na, 7, 0, 7, 8],
[6, 6, 2, 5, 7],
]
)
imputer = KNNImputer(missing_values=na).fit(X_fit)
with pytest.raises(ValueError, match="Input X contains (infinity|NaN)"):
imputer.transform(X)
# Test with missing_values=0 when NaN present
imputer = KNNImputer(missing_values=0, n_neighbors=2, weights="uniform")
X = np.array(
[
[np.nan, 0, 0, 0, 5],
[np.nan, 1, 0, np.nan, 3],
[np.nan, 2, 0, 0, 0],
[np.nan, 6, 0, 5, 13],
]
)
msg = "Input X contains NaN"
with pytest.raises(ValueError, match=msg):
imputer.fit(X)
X = np.array(
[
[0, 0],
[np.nan, 2],
]
)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_removes_all_na_features(na):
X = np.array(
[
[1, 1, na, 1, 1, 1.0],
[2, 3, na, 2, 2, 2],
[3, 4, na, 3, 3, na],
[6, 4, na, na, 6, 6],
]
)
knn = KNNImputer(missing_values=na, n_neighbors=2).fit(X)
X_transform = knn.transform(X)
assert not np.isnan(X_transform).any()
assert X_transform.shape == (4, 5)
X_test = np.arange(0, 12).reshape(2, 6)
X_transform = knn.transform(X_test)
assert_allclose(X_test[:, [0, 1, 3, 4, 5]], X_transform)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_zero_nan_imputes_the_same(na):
# Test with an imputable matrix and compare with different missing_values
X_zero = np.array(
[
[1, 0, 1, 1, 1.0],
[2, 2, 2, 2, 2],
[3, 3, 3, 3, 0],
[6, 6, 0, 6, 6],
]
)
X_nan = np.array(
[
[1, na, 1, 1, 1.0],
[2, 2, 2, 2, 2],
[3, 3, 3, 3, na],
[6, 6, na, 6, 6],
]
)
X_imputed = np.array(
[
[1, 2.5, 1, 1, 1.0],
[2, 2, 2, 2, 2],
[3, 3, 3, 3, 1.5],
[6, 6, 2.5, 6, 6],
]
)
imputer_zero = KNNImputer(missing_values=0, n_neighbors=2, weights="uniform")
imputer_nan = KNNImputer(missing_values=na, n_neighbors=2, weights="uniform")
assert_allclose(imputer_zero.fit_transform(X_zero), X_imputed)
assert_allclose(
imputer_zero.fit_transform(X_zero), imputer_nan.fit_transform(X_nan)
)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_verify(na):
# Test with an imputable matrix
X = np.array(
[
[1, 0, 0, 1],
[2, 1, 2, na],
[3, 2, 3, na],
[na, 4, 5, 5],
[6, na, 6, 7],
[8, 8, 8, 8],
[16, 15, 18, 19],
]
)
X_imputed = np.array(
[
[1, 0, 0, 1],
[2, 1, 2, 8],
[3, 2, 3, 8],
[4, 4, 5, 5],
[6, 3, 6, 7],
[8, 8, 8, 8],
[16, 15, 18, 19],
]
)
imputer = KNNImputer(missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed)
# Test when there is not enough neighbors
X = np.array(
[
[1, 0, 0, na],
[2, 1, 2, na],
[3, 2, 3, na],
[4, 4, 5, na],
[6, 7, 6, na],
[8, 8, 8, na],
[20, 20, 20, 20],
[22, 22, 22, 22],
]
)
# Not enough neighbors, use column mean from training
X_impute_value = (20 + 22) / 2
X_imputed = np.array(
[
[1, 0, 0, X_impute_value],
[2, 1, 2, X_impute_value],
[3, 2, 3, X_impute_value],
[4, 4, 5, X_impute_value],
[6, 7, 6, X_impute_value],
[8, 8, 8, X_impute_value],
[20, 20, 20, 20],
[22, 22, 22, 22],
]
)
imputer = KNNImputer(missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed)
# Test when data in fit() and transform() are different
X = np.array([[0, 0], [na, 2], [4, 3], [5, 6], [7, 7], [9, 8], [11, 16]])
X1 = np.array([[1, 0], [3, 2], [4, na]])
X_2_1 = (0 + 3 + 6 + 7 + 8) / 5
X1_imputed = np.array([[1, 0], [3, 2], [4, X_2_1]])
imputer = KNNImputer(missing_values=na)
assert_allclose(imputer.fit(X).transform(X1), X1_imputed)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_one_n_neighbors(na):
X = np.array([[0, 0], [na, 2], [4, 3], [5, na], [7, 7], [na, 8], [14, 13]])
X_imputed = np.array([[0, 0], [4, 2], [4, 3], [5, 3], [7, 7], [7, 8], [14, 13]])
imputer = KNNImputer(n_neighbors=1, missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_all_samples_are_neighbors(na):
X = np.array([[0, 0], [na, 2], [4, 3], [5, na], [7, 7], [na, 8], [14, 13]])
X_imputed = np.array([[0, 0], [6, 2], [4, 3], [5, 5.5], [7, 7], [6, 8], [14, 13]])
n_neighbors = X.shape[0] - 1
imputer = KNNImputer(n_neighbors=n_neighbors, missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed)
n_neighbors = X.shape[0]
imputer_plus1 = KNNImputer(n_neighbors=n_neighbors, missing_values=na)
assert_allclose(imputer_plus1.fit_transform(X), X_imputed)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_weight_uniform(na):
X = np.array([[0, 0], [na, 2], [4, 3], [5, 6], [7, 7], [9, 8], [11, 10]])
# Test with "uniform" weight (or unweighted)
X_imputed_uniform = np.array(
[[0, 0], [5, 2], [4, 3], [5, 6], [7, 7], [9, 8], [11, 10]]
)
imputer = KNNImputer(weights="uniform", missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed_uniform)
# Test with "callable" weight
def no_weight(dist):
return None
imputer = KNNImputer(weights=no_weight, missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed_uniform)
# Test with "callable" uniform weight
def uniform_weight(dist):
return np.ones_like(dist)
imputer = KNNImputer(weights=uniform_weight, missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed_uniform)
@pytest.mark.parametrize("na", [np.nan, -1])
def test_knn_imputer_weight_distance(na):
X = np.array([[0, 0], [na, 2], [4, 3], [5, 6], [7, 7], [9, 8], [11, 10]])
# Test with "distance" weight
nn = KNeighborsRegressor(metric="euclidean", weights="distance")
X_rows_idx = [0, 2, 3, 4, 5, 6]
nn.fit(X[X_rows_idx, 1:], X[X_rows_idx, 0])
knn_imputed_value = nn.predict(X[1:2, 1:])[0]
# Manual calculation
X_neighbors_idx = [0, 2, 3, 4, 5]
dist = nan_euclidean_distances(X[1:2, :], X, missing_values=na)
weights = 1 / dist[:, X_neighbors_idx].ravel()
manual_imputed_value = np.average(X[X_neighbors_idx, 0], weights=weights)
X_imputed_distance1 = np.array(
[[0, 0], [manual_imputed_value, 2], [4, 3], [5, 6], [7, 7], [9, 8], [11, 10]]
)
# NearestNeighbor calculation
X_imputed_distance2 = np.array(
[[0, 0], [knn_imputed_value, 2], [4, 3], [5, 6], [7, 7], [9, 8], [11, 10]]
)
imputer = KNNImputer(weights="distance", missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed_distance1)
assert_allclose(imputer.fit_transform(X), X_imputed_distance2)
# Test with weights = "distance" and n_neighbors=2
X = np.array(
[
[na, 0, 0],
[2, 1, 2],
[3, 2, 3],
[4, 5, 5],
]
)
# neighbors are rows 1, 2, the nan_euclidean_distances are:
dist_0_1 = np.sqrt((3 / 2) * ((1 - 0) ** 2 + (2 - 0) ** 2))
dist_0_2 = np.sqrt((3 / 2) * ((2 - 0) ** 2 + (3 - 0) ** 2))
imputed_value = np.average([2, 3], weights=[1 / dist_0_1, 1 / dist_0_2])
X_imputed = np.array(
[
[imputed_value, 0, 0],
[2, 1, 2],
[3, 2, 3],
[4, 5, 5],
]
)
imputer = KNNImputer(n_neighbors=2, weights="distance", missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed)
# Test with varying missingness patterns
X = np.array(
[
[1, 0, 0, 1],
[0, na, 1, na],
[1, 1, 1, na],
[0, 1, 0, 0],
[0, 0, 0, 0],
[1, 0, 1, 1],
[10, 10, 10, 10],
]
)
# Get weights of donor neighbors
dist = nan_euclidean_distances(X, missing_values=na)
r1c1_nbor_dists = dist[1, [0, 2, 3, 4, 5]]
r1c3_nbor_dists = dist[1, [0, 3, 4, 5, 6]]
r1c1_nbor_wt = 1 / r1c1_nbor_dists
r1c3_nbor_wt = 1 / r1c3_nbor_dists
r2c3_nbor_dists = dist[2, [0, 3, 4, 5, 6]]
r2c3_nbor_wt = 1 / r2c3_nbor_dists
# Collect donor values
col1_donor_values = np.ma.masked_invalid(X[[0, 2, 3, 4, 5], 1]).copy()
col3_donor_values = np.ma.masked_invalid(X[[0, 3, 4, 5, 6], 3]).copy()
# Final imputed values
r1c1_imp = np.ma.average(col1_donor_values, weights=r1c1_nbor_wt)
r1c3_imp = np.ma.average(col3_donor_values, weights=r1c3_nbor_wt)
r2c3_imp = np.ma.average(col3_donor_values, weights=r2c3_nbor_wt)
X_imputed = np.array(
[
[1, 0, 0, 1],
[0, r1c1_imp, 1, r1c3_imp],
[1, 1, 1, r2c3_imp],
[0, 1, 0, 0],
[0, 0, 0, 0],
[1, 0, 1, 1],
[10, 10, 10, 10],
]
)
imputer = KNNImputer(weights="distance", missing_values=na)
assert_allclose(imputer.fit_transform(X), X_imputed)
X = np.array(
[
[0, 0, 0, na],
[1, 1, 1, na],
[2, 2, na, 2],
[3, 3, 3, 3],
[4, 4, 4, 4],
[5, 5, 5, 5],
[6, 6, 6, 6],
[na, 7, 7, 7],
]
)
dist = pairwise_distances(
X, metric="nan_euclidean", squared=False, missing_values=na
)
# Calculate weights
r0c3_w = 1.0 / dist[0, 2:-1]
r1c3_w = 1.0 / dist[1, 2:-1]
r2c2_w = 1.0 / dist[2, (0, 1, 3, 4, 5)]
r7c0_w = 1.0 / dist[7, 2:7]
# Calculate weighted averages
r0c3 = np.average(X[2:-1, -1], weights=r0c3_w)
r1c3 = np.average(X[2:-1, -1], weights=r1c3_w)
r2c2 = np.average(X[(0, 1, 3, 4, 5), 2], weights=r2c2_w)
r7c0 = np.average(X[2:7, 0], weights=r7c0_w)
X_imputed = np.array(
[
[0, 0, 0, r0c3],
[1, 1, 1, r1c3],
[2, 2, r2c2, 2],
[3, 3, 3, 3],
[4, 4, 4, 4],
[5, 5, 5, 5],
[6, 6, 6, 6],
[r7c0, 7, 7, 7],
]
)
imputer_comp_wt = KNNImputer(missing_values=na, weights="distance")
assert_allclose(imputer_comp_wt.fit_transform(X), X_imputed)
def test_knn_imputer_callable_metric():
# Define callable metric that returns the l1 norm:
def custom_callable(x, y, missing_values=np.nan, squared=False):
x = np.ma.array(x, mask=np.isnan(x))
y = np.ma.array(y, mask=np.isnan(y))
dist = np.nansum(np.abs(x - y))
return dist
X = np.array([[4, 3, 3, np.nan], [6, 9, 6, 9], [4, 8, 6, 9], [np.nan, 9, 11, 10.0]])
X_0_3 = (9 + 9) / 2
X_3_0 = (6 + 4) / 2
X_imputed = np.array(
[[4, 3, 3, X_0_3], [6, 9, 6, 9], [4, 8, 6, 9], [X_3_0, 9, 11, 10.0]]
)
imputer = KNNImputer(n_neighbors=2, metric=custom_callable)
assert_allclose(imputer.fit_transform(X), X_imputed)
@pytest.mark.parametrize("working_memory", [None, 0])
@pytest.mark.parametrize("na", [-1, np.nan])
# Note that we use working_memory=0 to ensure that chunking is tested, even
# for a small dataset. However, it should raise a UserWarning that we ignore.
@pytest.mark.filterwarnings("ignore:adhere to working_memory")
def test_knn_imputer_with_simple_example(na, working_memory):
X = np.array(
[
[0, na, 0, na],
[1, 1, 1, na],
[2, 2, na, 2],
[3, 3, 3, 3],
[4, 4, 4, 4],
[5, 5, 5, 5],
[6, 6, 6, 6],
[na, 7, 7, 7],
]
)
r0c1 = np.mean(X[1:6, 1])
r0c3 = np.mean(X[2:-1, -1])
r1c3 = np.mean(X[2:-1, -1])
r2c2 = np.mean(X[[0, 1, 3, 4, 5], 2])
r7c0 = np.mean(X[2:-1, 0])
X_imputed = np.array(
[
[0, r0c1, 0, r0c3],
[1, 1, 1, r1c3],
[2, 2, r2c2, 2],
[3, 3, 3, 3],
[4, 4, 4, 4],
[5, 5, 5, 5],
[6, 6, 6, 6],
[r7c0, 7, 7, 7],
]
)
with config_context(working_memory=working_memory):
imputer_comp = KNNImputer(missing_values=na)
assert_allclose(imputer_comp.fit_transform(X), X_imputed)
@pytest.mark.parametrize("na", [-1, np.nan])
@pytest.mark.parametrize("weights", ["uniform", "distance"])
def test_knn_imputer_not_enough_valid_distances(na, weights):
# Samples with needed feature has nan distance
X1 = np.array([[na, 11], [na, 1], [3, na]])
X1_imputed = np.array([[3, 11], [3, 1], [3, 6]])
knn = KNNImputer(missing_values=na, n_neighbors=1, weights=weights)
assert_allclose(knn.fit_transform(X1), X1_imputed)
X2 = np.array([[4, na]])
X2_imputed = np.array([[4, 6]])
assert_allclose(knn.transform(X2), X2_imputed)
@pytest.mark.parametrize("na", [-1, np.nan])
def test_knn_imputer_drops_all_nan_features(na):
X1 = np.array([[na, 1], [na, 2]])
knn = KNNImputer(missing_values=na, n_neighbors=1)
X1_expected = np.array([[1], [2]])
assert_allclose(knn.fit_transform(X1), X1_expected)
X2 = np.array([[1, 2], [3, na]])
X2_expected = np.array([[2], [1.5]])
assert_allclose(knn.transform(X2), X2_expected)
@pytest.mark.parametrize("working_memory", [None, 0])
@pytest.mark.parametrize("na", [-1, np.nan])
def test_knn_imputer_distance_weighted_not_enough_neighbors(na, working_memory):
X = np.array([[3, na], [2, na], [na, 4], [5, 6], [6, 8], [na, 5]])
dist = pairwise_distances(
X, metric="nan_euclidean", squared=False, missing_values=na
)
X_01 = np.average(X[3:5, 1], weights=1 / dist[0, 3:5])
X_11 = np.average(X[3:5, 1], weights=1 / dist[1, 3:5])
X_20 = np.average(X[3:5, 0], weights=1 / dist[2, 3:5])
X_50 = np.average(X[3:5, 0], weights=1 / dist[5, 3:5])
X_expected = np.array([[3, X_01], [2, X_11], [X_20, 4], [5, 6], [6, 8], [X_50, 5]])
with config_context(working_memory=working_memory):
knn_3 = KNNImputer(missing_values=na, n_neighbors=3, weights="distance")
assert_allclose(knn_3.fit_transform(X), X_expected)
knn_4 = KNNImputer(missing_values=na, n_neighbors=4, weights="distance")
assert_allclose(knn_4.fit_transform(X), X_expected)
@pytest.mark.parametrize("na, allow_nan", [(-1, False), (np.nan, True)])
def test_knn_tags(na, allow_nan):
knn = KNNImputer(missing_values=na)
assert knn._get_tags()["allow_nan"] == allow_nan