def __init__(self): self.job_dictionary = self.get_all_job_info() self.job_description_list = [self.procText(self.job_dictionary[entry]['job_description']) for entry in self.job_dictionary.keys()] # self.tf_dictionary = populate_document_dictionary(self.job_description_list) # is this needed anywhere? self.df_dictionary = manual_tfidf.populate_containing_dictionary(self.job_description_list) self.doc_weights = cv_comparer.populate_doc_weights(self.job_description_list, self.df_dictionary, len(self.job_description_list)) #list of weights, same index as docList
def initCVs(self, read = None): if not read: self.cvList = [self.procText(self.bizExp[cv_index] + " " + self.edu[cv_index]) for cv_index in range(len(self.bizExp))] else: self.cvList = [self.procText(r) for r in read] self.cvDfs = manual_tfidf.populate_containing_dictionary(self.cvList) self.cvWeights = cv_comparer.populate_doc_weights(self.cvList, self.cvDfs, len(self.cvList))