infineac.compare_results

Compare the results of the different models created by the infineac.pipeline or the infineac.topic_extractor modules.

Functions

aggregate_results(df[, category_names])	Aggregates the results of the given DataFrame df and returns a DataFrame with the count of the combinations of categories and strategies.
calculate_similarity(df)	Calculates the intersection and union of all the given categories and topics and, based on this, the similarity within the categories and topics.
create_compare_df(dfs, suffixes)	Joins the given DataFrames(dfs) on the company name and year columns.
create_empty_count_df([column_names])	Creates an empty DataFrame from the cartesian product of the categories and the strategies with the columns category, strategy as well as the given column_names.
get_strategy_list(dictionary)	Returns a list of lists with the strategies for each row of the given dict.
update_count(count, categories, strategies, ...)	Updates the given count DataFrame for the combination of the given categories and strategies in the given column.