Source code for sklearn.preprocessing.imputation

# Authors: Nicolas Tresegnie <>
# License: BSD 3 clause

import warnings

import numpy as np
import as ma
from scipy import sparse
from scipy import stats

from ..base import BaseEstimator, TransformerMixin
from ..utils import check_array
from ..utils.sparsefuncs import _get_median
from ..utils.validation import check_is_fitted
from ..utils.validation import FLOAT_DTYPES

from ..externals import six

zip =
map =

__all__ = [

def _get_mask(X, value_to_mask):
    """Compute the boolean mask X == missing_values."""
    if value_to_mask == "NaN" or np.isnan(value_to_mask):
        return np.isnan(X)
        return X == value_to_mask

def _most_frequent(array, extra_value, n_repeat):
    """Compute the most frequent value in a 1d array extended with
       [extra_value] * n_repeat, where extra_value is assumed to be not part
       of the array."""
    # Compute the most frequent value in array only
    if array.size > 0:
        mode = stats.mode(array)
        most_frequent_value = mode[0][0]
        most_frequent_count = mode[1][0]
        most_frequent_value = 0
        most_frequent_count = 0

    # Compare to array + [extra_value] * n_repeat
    if most_frequent_count == 0 and n_repeat == 0:
        return np.nan
    elif most_frequent_count < n_repeat:
        return extra_value
    elif most_frequent_count > n_repeat:
        return most_frequent_value
    elif most_frequent_count == n_repeat:
        # Ties the breaks. Copy the behaviour of scipy.stats.mode
        if most_frequent_value < extra_value:
            return most_frequent_value
            return extra_value

class Imputer(BaseEstimator, TransformerMixin):
    """Imputation transformer for completing missing values.

    Read more in the :ref:`User Guide <imputation>`.

    missing_values : integer or "NaN", optional (default="NaN")
        The placeholder for the missing values. All occurrences of
        `missing_values` will be imputed. For missing values encoded as np.nan,
        use the string value "NaN".

    strategy : string, optional (default="mean")
        The imputation strategy.

        - If "mean", then replace missing values using the mean along
          the axis.
        - If "median", then replace missing values using the median along
          the axis.
        - If "most_frequent", then replace missing using the most frequent
          value along the axis.

    axis : integer, optional (default=0)
        The axis along which to impute.

        - If `axis=0`, then impute along columns.
        - If `axis=1`, then impute along rows.

    verbose : integer, optional (default=0)
        Controls the verbosity of the imputer.

    copy : boolean, optional (default=True)
        If True, a copy of X will be created. If False, imputation will
        be done in-place whenever possible. Note that, in the following cases,
        a new copy will always be made, even if `copy=False`:

        - If X is not an array of floating values;
        - If X is sparse and `missing_values=0`;
        - If `axis=0` and X is encoded as a CSR matrix;
        - If `axis=1` and X is encoded as a CSC matrix.

    statistics_ : array of shape (n_features,)
        The imputation fill value for each feature if axis == 0.

    - When ``axis=0``, columns which only contained missing values at `fit`
      are discarded upon `transform`.
    - When ``axis=1``, an exception is raised if there are rows for which it is
      not possible to fill in the missing values (e.g., because they only
      contain missing values).
    def __init__(self, missing_values="NaN", strategy="mean",
                 axis=0, verbose=0, copy=True):
        self.missing_values = missing_values
        self.strategy = strategy
        self.axis = axis
        self.verbose = verbose
        self.copy = copy

[docs] def fit(self, X, y=None): """Fit the imputer on X. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) Input data, where ``n_samples`` is the number of samples and ``n_features`` is the number of features. Returns ------- self : Imputer Returns self. """ # Check parameters allowed_strategies = ["mean", "median", "most_frequent"] if self.strategy not in allowed_strategies: raise ValueError("Can only use these strategies: {0} " " got strategy={1}".format(allowed_strategies, self.strategy)) if self.axis not in [0, 1]: raise ValueError("Can only impute missing values on axis 0 and 1, " " got axis={0}".format(self.axis)) # Since two different arrays can be provided in fit(X) and # transform(X), the imputation data will be computed in transform() # when the imputation is done per sample (i.e., when axis=1). if self.axis == 0: X = check_array(X, accept_sparse='csc', dtype=np.float64, force_all_finite=False) if sparse.issparse(X): self.statistics_ = self._sparse_fit(X, self.strategy, self.missing_values, self.axis) else: self.statistics_ = self._dense_fit(X, self.strategy, self.missing_values, self.axis) return self
def _sparse_fit(self, X, strategy, missing_values, axis): """Fit the transformer on sparse data.""" # Imputation is done "by column", so if we want to do it # by row we only need to convert the matrix to csr format. if axis == 1: X = X.tocsr() else: X = X.tocsc() # Count the zeros if missing_values == 0: n_zeros_axis = np.zeros(X.shape[not axis], dtype=int) else: n_zeros_axis = X.shape[axis] - np.diff(X.indptr) # Mean if strategy == "mean": if missing_values != 0: n_non_missing = n_zeros_axis # Mask the missing elements mask_missing_values = _get_mask(, missing_values) mask_valids = np.logical_not(mask_missing_values) # Sum only the valid elements new_data = new_data[mask_missing_values] = 0 X = sparse.csc_matrix((new_data, X.indices, X.indptr), copy=False) sums = X.sum(axis=0) # Count the elements != 0 mask_non_zeros = sparse.csc_matrix( (mask_valids.astype(np.float64), X.indices, X.indptr), copy=False) s = mask_non_zeros.sum(axis=0) n_non_missing = np.add(n_non_missing, s) else: sums = X.sum(axis=axis) n_non_missing = np.diff(X.indptr) # Ignore the error, columns with a np.nan statistics_ # are not an error at this point. These columns will # be removed in transform with np.errstate(all="ignore"): return np.ravel(sums) / np.ravel(n_non_missing) # Median + Most frequent else: # Remove the missing values, for each column columns_all = np.hsplit(, X.indptr[1:-1]) mask_missing_values = _get_mask(, missing_values) mask_valids = np.hsplit(np.logical_not(mask_missing_values), X.indptr[1:-1]) # astype necessary for bug in numpy.hsplit before v1.9 columns = [col[mask.astype(bool, copy=False)] for col, mask in zip(columns_all, mask_valids)] # Median if strategy == "median": median = np.empty(len(columns)) for i, column in enumerate(columns): median[i] = _get_median(column, n_zeros_axis[i]) return median # Most frequent elif strategy == "most_frequent": most_frequent = np.empty(len(columns)) for i, column in enumerate(columns): most_frequent[i] = _most_frequent(column, 0, n_zeros_axis[i]) return most_frequent def _dense_fit(self, X, strategy, missing_values, axis): """Fit the transformer on dense data.""" X = check_array(X, force_all_finite=False) mask = _get_mask(X, missing_values) masked_X = ma.masked_array(X, mask=mask) # Mean if strategy == "mean": mean_masked =, axis=axis) # Avoid the warning "Warning: converting a masked element to nan." mean = mean[] = np.nan return mean # Median elif strategy == "median": if tuple(int(v) for v in np.__version__.split('.')[:2]) < (1, 5): # In old versions of numpy, calling a median on an array # containing nans returns nan. This is different is # recent versions of numpy, which we want to mimic masked_X.mask = np.logical_or(masked_X.mask, np.isnan(X)) median_masked =, axis=axis) # Avoid the warning "Warning: converting a masked element to nan." median = median[] = np.nan return median # Most frequent elif strategy == "most_frequent": # scipy.stats.mstats.mode cannot be used because it will no work # properly if the first element is masked and if its frequency # is equal to the frequency of the most frequent valid element # See # To be able access the elements by columns if axis == 0: X = X.transpose() mask = mask.transpose() most_frequent = np.empty(X.shape[0]) for i, (row, row_mask) in enumerate(zip(X[:], mask[:])): row_mask = np.logical_not(row_mask).astype(np.bool) row = row[row_mask] most_frequent[i] = _most_frequent(row, np.nan, 0) return most_frequent
[docs] def transform(self, X): """Impute all missing values in X. Parameters ---------- X : {array-like, sparse matrix}, shape = [n_samples, n_features] The input data to complete. """ if self.axis == 0: check_is_fitted(self, 'statistics_') X = check_array(X, accept_sparse='csc', dtype=FLOAT_DTYPES, force_all_finite=False, copy=self.copy) statistics = self.statistics_ if X.shape[1] != statistics.shape[0]: raise ValueError("X has %d features per sample, expected %d" % (X.shape[1], self.statistics_.shape[0])) # Since two different arrays can be provided in fit(X) and # transform(X), the imputation data need to be recomputed # when the imputation is done per sample else: X = check_array(X, accept_sparse='csr', dtype=FLOAT_DTYPES, force_all_finite=False, copy=self.copy) if sparse.issparse(X): statistics = self._sparse_fit(X, self.strategy, self.missing_values, self.axis) else: statistics = self._dense_fit(X, self.strategy, self.missing_values, self.axis) # Delete the invalid rows/columns invalid_mask = np.isnan(statistics) valid_mask = np.logical_not(invalid_mask) valid_statistics = statistics[valid_mask] valid_statistics_indexes = np.where(valid_mask)[0] missing = np.arange(X.shape[not self.axis])[invalid_mask] if self.axis == 0 and invalid_mask.any(): if self.verbose: warnings.warn("Deleting features without " "observed values: %s" % missing) X = X[:, valid_statistics_indexes] elif self.axis == 1 and invalid_mask.any(): raise ValueError("Some rows only contain " "missing values: %s" % missing) # Do actual imputation if sparse.issparse(X) and self.missing_values != 0: mask = _get_mask(, self.missing_values) indexes = np.repeat(np.arange(len(X.indptr) - 1,, np.diff(X.indptr))[mask][mask] = valid_statistics[indexes].astype(X.dtype, copy=False) else: if sparse.issparse(X): X = X.toarray() mask = _get_mask(X, self.missing_values) n_missing = np.sum(mask, axis=self.axis) values = np.repeat(valid_statistics, n_missing) if self.axis == 0: coordinates = np.where(mask.transpose())[::-1] else: coordinates = mask X[coordinates] = values return X