Data Transformers Registry

Data Transformers

Provides registry functionality for Transformers (feature extraction utilities). For implementation details see EligibleTransformers

normalize_numericals	Description This transformer is osbolete. For implementation details see Obsolete_NN
impute_categoricals	Description This transformer is osbolete. For implementation details see Obsolete_NN
impute_numericals	Description This transformer is osbolete. For implementation details see Obsolete_NN
encode_categoricals	Description This transformer is osbolete. For implementation details see Obsolete_NN
pca	Description Provides PCA decomposition functionality. For implementation details see PCADecompositionTransformer pca
nmf	Description Provides NMF decomposition functionality. For implementation details see NMFDecompositionTransformer nmf
binary_encoding	Description Provides binary encoding functionality. For implementation details see BinaryEncodingTransformer binary_encoding
label_encoding	Description Provides label encoding functionality. For implementation details see LabelEncodingTransformer label_encoding
one_hot	Description Provides one-hot encoding functionality. For implementation details see OneHotEncodingTransformer one_hot
multi_label_encoding	Description Provides one-hot encoding functionality for multi-label dtypes. For implementation details see MultiLabelEncodingTransformer multi_label_encoding
binarize_dna	Description Provides binarization functionality for _DNA columns. For implementation details see DNAIndicatorsBinarizationTransformer binarize_dna
map_encoding	Description Encode values according to the map provided. Sample config: .. code-block:: yaml steps: - transformer: map_encoding params: columns_to_include: - .*_DNA$ mapping: AMP: 0 DEL: 1 REARG: 2 SNP: 3 VUS: 4 WT: 5 unknown_values: -1 For implementation details see MapEncodingTransformer map_encoding
bucketize	Description Encodes values based on a list of buckets (intervals + labels). Sample config: .. code-block :: yaml steps: - transformer: bucketize params: columns_to_include: - PDL1_score suffix: _1_50_bucketized buckets: - left_bound: 0 right_bound: 1 alias: ‘<1%’ - left_bound: 1 right_bound: 50 alias: ‘>=1%-<50%’ - left_bound: 50 right_bound: 100 alias: ‘>=50%’ remove_base_columns: True For implementation details see BucketizeTransformer bucketize
encode_datetime	Description Encode datetime columns for ML. A datetime column produces three new columns: - {colname}_year_rel - relative number of years since minimal value of the column. - {colname}_year_day_sin/cos: day of the year cyclicly encoded. For implementation details see DateTimeEncodingTransformer encode_datetime
drop_columns	Description Provides columns filtering functionality. For implementation details see DropColumnsTransformer drop_columns
drop_low_var_columns	Description Provides columns filtering based on variance thresholding. NOTE: only numerical columns are considered. For implementation details see DropLowVarianceColumnsTransformer drop_low_var_columns
drop_high_mutual_info_columns	Description Provides columns filtering based on mutual information for target. NOTE: only numerical columns are considered. For implementation details see DropHighMutualInfoColumnsTransformer drop_high_mutual_info_columns
drop_nan_columns	Description Provides columns filtering based on NA fraction thresholding. For implementation details see DropNanColumnsTransformer drop_nan_columns
drop_nan_rows	Description Provides rows filtering based on NAs presence within target columns. For implementation details see DropNanRowsTransformer drop_nan_rows
drop_columns_without_mutations	Description Provides columns filtering based on mutations presence within. For implementation details see DropColumnsWithoutMutationsTransformer drop_columns_without_mutations
select_columns	Description Provides columns selection functionality. For implementation details see SelectColumnsTransformer select_columns
prevalence_filtering	Description Drops columns for which values prevalence falls lower than the threshold. Configuration class: PrevalenceFilteringTransformerParams. Filter is performed as follows: - for given column count values of params.values (if there is more than one, sum them). - divide this number by total number of values in the column (ignoring NaNs), this gives the prevalence number from 0 to 1. - if prevalence is less than params.threshold, drop the column. For implementation details see PrevalenceFilteringTransformer prevalence_filtering
dna_subset_filtering	Description For a given master set of values: 1) checks that the master set is presented within column’s values 2) removed values outof the master list For implementation details see DNASubsetFilteringTransformer dna_subset_filtering
remove_correlated_features	Description Removes correlated features based on predefined correlation groups. For implementation details see RemoveCorrelatedColumnsTransformer remove_correlated_features
impute	Description Provides imputation functionality. For implementation details see SimpleImputeTransformer impute
impute_mice	Description Provides MICE imputation functionality (Multivariate Imputation by Chained Equations). NOTE: affected columns are additionally filtered to be numerical only For implementation details see MICEImputeTransformer impute_mice
replace_value	Description Replace values according to the map provided. Not listed values are not affected. Note: yaml natively supports special values like .nan, see https://yaml.org/spec/1.2.2/ Sample config: .. code-block:: yaml steps: - transformer: replace_value params: columns_to_include: - .*_DNA$ mapping: # combine two categories into the same VUS: ‘VUS_WT’ WT: ‘VUS_WT’ For implementation details see ReplaceValueTransformer replace_value
log1p	Description Applies ‘log1p’ transformation. For implementation details see Log1pLambdaTransformer log1p
log	Description Applies ‘log’ transformation. For implementation details see LogLambdaTransformer log
binarization	Description Binarizes all target columns using a given threshold. For implementation details see BinarizationLambdaTransformer binarization
resolve_multiple_choice	Description Resolves multi-value issue for list-type columns. For implementation details see ResolveMultipleChoiceTransformer resolve_multiple_choice
convert_to_float	Description Converts column values to floats by removing and parsing special characters. In case casting is not possible for a value - replaces it with NaN. For implementation details see ConvertToFloatTransformer convert_to_float
query_to_bool	Description Transforms column to boolean using query. Puts 1 where query result is True, 0 otherwise. Sample config: .. code-block:: yaml data_preprocessing: steps: - transformer: query_to_bool params: columns_to_include: [‘single_column_here’] query: “single_column_here == ‘YES’” For implementation details see QueryBooleanTransformer query_to_bool
sanitize_columns	Description Simple metadata transformation. For implementation details see SanitizeColumnsTransformer
standard	Description Standard normalization. For implementation details see StandardNormalizationTransformer standard
maxabs	Description MaxAbs normalization. For implementation details see MaxAbsNormalizationTransformer maxabs
minmax	Description MinMax normalization. For implementation details see MinMaxNormalizationTransformer minmax
minmax_neg	Description MinMax normalization (result range is [-1; -1]). For implementation details see MinMaxNegNormalizationTransformer minmax_neg
log_standard	Description Log transformation + standard normalization. For implementation details see LogStandardNormalizationTransformer log_standard
log1p_standard	Description Log1p transformation + standard normalization. For implementation details see Log1pStandardNormalizationTransformer log1p_standard
shuffle	Description Randomly permutes a given dataset’s rows. For implementation details see ShuffleTransformer
add_random_columns	Description For a given set of target columns, creates additional ‘randomized’ columns for later significance assessment. For implementation details see AddRandomColumnsTransformer add_random_columns
upsampling	Description Implements ‘upsampling’ method for balancing classes. For implementation details see UpsamplingTransformer upsampling
downsampling	Description Implements ‘downsampling’ method for balancing classes. For implementation details see DownsamplingTransformer downsampling