FillMissing

class nvtabular.ops.FillMissing(fill_val=0, add_binary_cols=False)[source]

Bases: nvtabular.ops.operator.Operator

This operation replaces missing values with a constant pre-defined value

Example usage:

# Use FillMissing to define a workflow for continuous columns and specify the fill value
# Default is 0
cont_features = ['cont1', 'cont2', 'cont3'] >> ops.FillMissing() >> ...
processor = nvtabular.Workflow(cont_features)

Parameters

fill_val (float, default 0) – The constant value to replace missing values with.
add_binary_cols (boolean, default False) – When True, adds binary columns that indicate whether cells in each column were filled

transform(col_selector: nvtabular.columns.selector.ColumnSelector, df: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame[source]

Transform the dataframe by applying this operator to the set of input columns

Parameters

columns (list of str or list of list of str) – The columns to apply this operator to
df (Dataframe) – A pandas or cudf dataframe that this operator will work on

Returns

Returns a transformed dataframe for this operator

Return type

DataFrame

inference_initialize(col_selector, inference_config)[source]: load up extra configuration about this op.

compute_output_schema(input_schema: nvtabular.columns.schema.Schema, col_selector: nvtabular.columns.selector.ColumnSelector) → nvtabular.columns.schema.Schema [source]

output_column_names(col_selector: nvtabular.columns.selector.ColumnSelector) → nvtabular.columns.selector.ColumnSelector [source]