moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

regenerating tfidf vectors

This commit is contained in:
Alejandro Moreo Fernandez 2024-03-15 14:30:51 +01:00
parent faa3af587c
commit 08c26c58f9
2 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
Ordinal/preprocess_dataset_raw2tfidf.py
View File

@ -1,5 +1,5 @@
import quapy as qp
from Ordinal.utils import load_simple_sample_raw
from Ordinal.utils import load_simple_sample_raw, load_samples_raw
from quapy.data import LabelledCollection
from sklearn.feature_extraction.text import TfidfVectorizer
from os.path import join
@ -19,6 +19,7 @@ datapath = './data'
domain = 'Books'
outname = domain + '-tfidf'
def save_preprocessing_info(transformer):
with open(join(datapath, outname, 'prep-info.txt'), 'wt') as foo:
foo.write(f'{str(transformer)}\n')
@ -30,11 +31,11 @@ os.makedirs(join(datapath, outname, 'app', 'dev_samples'), exist_ok=True)
os.makedirs(join(datapath, outname, 'app', 'test_samples'), exist_ok=True)
shutil.copyfile(join(datapath, domain, 'app', 'dev_prevalences.txt'), join(datapath, outname, 'app', 'dev_prevalences.txt'))
shutil.copyfile(join(datapath, domain, 'app', 'test_prevalences.txt'), join(datapath, outname, 'app', 'test_prevalences.txt'))
os.makedirs(join(datapath, outname, 'npp'), exist_ok=True)
os.makedirs(join(datapath, outname, 'npp', 'dev_samples'), exist_ok=True)
os.makedirs(join(datapath, outname, 'npp', 'test_samples'), exist_ok=True)
shutil.copyfile(join(datapath, domain, 'npp', 'dev_prevalences.txt'), join(datapath, outname, 'npp', 'dev_prevalences.txt'))
shutil.copyfile(join(datapath, domain, 'npp', 'test_prevalences.txt'), join(datapath, outname, 'npp', 'test_prevalences.txt'))
os.makedirs(join(datapath, outname, 'real'), exist_ok=True)
os.makedirs(join(datapath, outname, 'real', 'dev_samples'), exist_ok=True)
os.makedirs(join(datapath, outname, 'real', 'test_samples'), exist_ok=True)
shutil.copyfile(join(datapath, domain, 'real', 'dev_prevalences.txt'), join(datapath, outname, 'real', 'dev_prevalences.txt'))
shutil.copyfile(join(datapath, domain, 'real', 'test_prevalences.txt'), join(datapath, outname, 'real', 'test_prevalences.txt'))
tfidf = TfidfVectorizer(sublinear_tf=True, ngram_range=(1,2), min_df=5)
@ -45,16 +46,17 @@ save_preprocessing_info(tfidf)
pickle.dump(train, open(join(datapath, outname, 'training_data.pkl'), 'wb'), pickle.HIGHEST_PROTOCOL)
def transform_folder_samples(protocol, splitname):
for i, sample in tqdm(enumerate(load_simple_sample_raw(join(datapath, domain, protocol, splitname), classes=train.classes_))):
for i, sample in tqdm(enumerate(load_samples_raw(join(datapath, domain, protocol, splitname), classes=train.classes_))):
sample.instances = tfidf.transform(sample.instances)
pickle.dump(sample, open(join(datapath, outname, protocol, splitname, f'{i}.pkl'), 'wb'), pickle.HIGHEST_PROTOCOL)
transform_folder_samples('app', 'dev_samples')
transform_folder_samples('app', 'test_samples')
transform_folder_samples('npp', 'dev_samples')
transform_folder_samples('npp', 'test_samples')
transform_folder_samples('real', 'dev_samples')
transform_folder_samples('real', 'test_samples')

4
Ordinal/utils.py
View File

@ -48,8 +48,8 @@ def load_single_sample_pkl(parentdir, filename):
# return load_samples_folder(path_dir, filter, load_fn=load_simple_sample_npytxt)
# def load_samples_raw(path_dir, filter=None, classes=None):
# return load_samples_folder(path_dir, filter, load_fn=load_simple_sample_raw, load_fn_kwargs={'classes': classes})
def load_samples_raw(path_dir, filter=None, classes=None):
return load_samples_folder(path_dir, filter, load_fn=load_simple_sample_raw, classes=classes)
# def load_samples_as_csv(path_dir, filter=None):