Recommend_scholars

class recommend_scholars.Top_Scholar_Identifier(n_cores, id_no, top_k, generator_, agency, params)

Bases: object

This is a class to identify the top N scholars for a given proposal. The proposal dataset created using ‘main_extractor.py’ will be utilized to get details of the proposal / grant. The analytical dataset of user-publications created using ‘create_analytical_data.py’ will be utilized to get scholar profiles.

get_section_keys_for_proposal()

Function to get keywords from Description, Title adn Department sections of the proposal text

:param None :

Returns

None :rtype:

get_top_scholars(ntop_=20)

Main function to calculate the scholars suitable for the given proposal

Parameters

ntop (int) – No of scholars to be recommended

Returns

self.recommend_df :rtype: class Pandas.DataFrame

read_data()

Function which will read data from the initialized CSV files regarding proposal and scholar datails and save them as pandas dataframe

:param None :

Returns

None :rtype:

recommend_scholars.get_column_names()