kubapok/biological-lms
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

minor fix

Browse Source
This commit is contained in:
kubapok 2024-08-04 14:23:12 +02:00
parent dd80f72b31
commit 77a1e13c8f
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
1.py
View File

@ -8,22 +8,25 @@ import pandas as pd
# example usage one arg python 1.py model_cv_1_0_preds.csv # example usage one arg python 1.py model_cv_1_0_preds.csv
# example usage mulitple args python 1.py model_cv_1_0_preds.csv model_cv_1_1_preds.csv model_cv_1_2_preds.csv # example usage mulitple args python 1.py model_cv_1_0_preds.csv model_cv_1_1_preds.csv model_cv_1_2_preds.csv
PREDICTED_COLUMN_NAME = 'query_annot' # PREDICTED_COLUMN_NAME = 'query_annot'
LABEL_COLUMN_NAME = 'target_annot' # LABEL_COLUMN_NAME = 'target_annot'
# COLUMN_SEPARATOR = '\t'
PREDICTED_COLUMN_NAME = 'plm_names' PREDICTED_COLUMN_NAME = 'plm_names'
LABEL_COLUMN_NAME = 'targets' LABEL_COLUMN_NAME = 'targets'
COLUMN_SEPARATOR = ',' COLUMN_SEPARATOR = ','
predicted_all_splits = list() predicted_all_splits = list()
label_all_splits = list() label_all_splits = list()
bleu = BLEU(effective_order=True) bleu = BLEU()
bleu_one_sentence = BLEU(effective_order=True)
chrf = CHRF() chrf = CHRF()
def get_statistics(r): def get_statistics(r):
metrics = dict() metrics = dict()
r['score_bleu'] = r.apply( r['score_bleu'] = r.apply(
lambda row: round(bleu.sentence_score(row[PREDICTED_COLUMN_NAME], [row[LABEL_COLUMN_NAME]]).score, 2), axis=1) lambda row: round(bleu_one_sentence.sentence_score(row[PREDICTED_COLUMN_NAME], [row[LABEL_COLUMN_NAME]]).score, 2), axis=1)
r['score_chrf'] = r.apply( r['score_chrf'] = r.apply(
lambda row: round(chrf.sentence_score(row[PREDICTED_COLUMN_NAME], [row[LABEL_COLUMN_NAME]]).score, 2), axis=1) lambda row: round(chrf.sentence_score(row[PREDICTED_COLUMN_NAME], [row[LABEL_COLUMN_NAME]]).score, 2), axis=1)
r['score_exact_match'] = r.apply(lambda row: 1 if row[PREDICTED_COLUMN_NAME] == row[LABEL_COLUMN_NAME] else 0, r['score_exact_match'] = r.apply(lambda row: 1 if row[PREDICTED_COLUMN_NAME] == row[LABEL_COLUMN_NAME] else 0,