Categorical Column Profile

Contains class for categorical column profiler.

class dataprofiler.profilers.categorical_column_profile.CategoricalColumn(name, options=None)

Bases: dataprofiler.profilers.base_column_profilers.BaseColumnProfiler

Categorical column profile subclass of BaseColumnProfiler.

Represents a column int the dataset which is a categorical column.

Initialize column base properties and itself.

Parameters

name (String) – Name of data

type = 'category'

diff(other_profile, options=None)

Find the differences for CategoricalColumns.

Parameters

other_profile (CategoricalColumn) – profile to find the difference with

Returns

the CategoricalColumn differences

Return type

dict

report(remove_disabled_flag=False)

Return report.

This is a private abstract method.

Parameters

remove_disabled_flag (boolean) – flag to determine if disabled options should be excluded in the report.

property profile

Return the profile of the column.

For categorical_count, it will display the top k categories most frequently occurred in descending order.

property categories

Return categories.

property categorical_counts

Return counts of each category.

property unique_ratio

Return ratio of unique categories to sample_size.

property is_match

Return true if column is categorical.

update(df_series)

Update the column profile.

Parameters

df_series (pandas.core.series.Series) – Data to profile.

Returns

None

property gini_impurity

Return Gini Impurity.

Gini Impurity is a way to calculate likelihood of an incorrect classification of a new instance of a random variable.

G = Σ(i=1; J): P(i) * (1 - P(i)), where i is the category classes. We are traversing through categories and calculating with the column

Returns

None or Gini Impurity probability

col_type = None

property unalikeability

Return Unlikeability.

Unikeability checks for “how often observations differ from one another” Reference: Perry, M. and Kader, G. Variation as Unalikeability. Teaching Statistics, Vol. 27, No. 2 (2005), pp. 58-60.

U = Σ(i=1,n)Σ(j=1,n): (Cij)/(n**2-n) Cij = 1 if i!=j, 0 if i=j

Returns

None or unlikeability probability