'bg_bert_title', 'bg_bert_text', 'meta_media', 'bg_xlm_title',
'bg_xlm_text'
]),
('top_8', [
'bg_lsa_title', 'bg_lsa_text', 'en_elmo_title', 'en_elmo_text',
'en_use_title', 'en_use_text', 'en_bert_title', 'en_bert_text',
'bg_bert_title', 'bg_bert_text', 'meta_media', 'bg_xlm_title',
'bg_xlm_text', 'en_nela_title', 'en_nela_text'
]),
('top_9', [
'bg_lsa_title', 'bg_lsa_text', 'en_elmo_title', 'en_elmo_text',
'en_use_title', 'en_use_text', 'en_bert_title', 'en_bert_text',
'bg_bert_title', 'bg_bert_text', 'meta_media', 'bg_xlm_title',
'bg_xlm_text', 'en_nela_title', 'en_nela_text', 'bg_styl_title',
'bg_styl_textx'
]),
]
oversampler = None
models = []
for name, feature_list in features:
clf = LogisticRegression()
clf_params = {'clf__C': 1.5, 'clf__solver': 'liblinear', 'clf__tol': 0.01}
model = pipelines.make(clf, feature_list, clf_params=clf_params)
# evaluation
models.append((f'{name}', model))
compare_classifiers(models, df, df['label'], silent=False, plot=False)
multi_class="auto",
solver='liblinear',
max_iter=20000)
features = [
'bg_bert_title',
'bg_bert_text',
'bg_xlm_title',
'bg_xlm_text',
'meta_media',
'bg_styl_title',
'bg_styl_text',
'bg_lsa_title',
'bg_lsa_text',
'en_use_title',
'en_use_text',
'en_nela_title',
'en_nela_text',
'en_bert_title',
'en_bert_text',
'en_elmo_title',
'en_elmo_text',
]
all_features = [f'{x}_pred' for x in features]
# oversamplers = [None, SMOTE(), ADASYN(), RandomOverSampler(random_state=0)]
oversamplers = [None]
for oversampler in oversamplers:
model = ('pred_all', pipelines.make(clf, all_features, oversampler))
compare_classifiers([model], df, df['label'], silent=False, plot=False)
db = database.MongoDB()
clf = LogisticRegression(C=1.5,
tol=0.01,
random_state=0,
multi_class="auto",
solver='liblinear',
max_iter=20000)
df = get_df(list(db.get_articles()))
for oversampler in [
None, SMOTE(),
ADASYN(), RandomOverSampler(random_state=0)
]:
models = [
('bg_lsa',
pipelines.make(clf, ['bg_lsa_title', 'bg_lsa_text'],
oversampler=oversampler))
#('bg_bert_title_text', pipelines.make(clf, ['bg_bert_title', 'bg_bert_text'], oversampler=oversampler)),
# ('bg_xlm_title_text', pipelines.make(clf, oversampler, ['bg_xlm_title', 'bg_xlm_text', 'bg_xlm_cos'])),
# ('bg_styl_title_text', pipelines.make(clf, oversampler, ['bg_styl_title', 'bg_styl_text'])),
# ('meta_media', pipelines.make(clf, oversampler, ['meta_media'])),
# ('en_use_title_text', pipelines.make(clf, oversampler, ['en_use_title', 'en_use_text', 'en_use_cos'])),
# ('en_nela_title_text', pipelines.make(clf, oversampler, ['en_nela_title', 'en_nela_text', 'en_nela_cos'])),
# ('en_bert_title_text', pipelines.make(clf, oversampler, ['en_bert_title', 'en_bert_text', 'en_bert_cos'])),
# ('en_elmo_title_text', pipelines.make(clf, oversampler, ['en_elmo_title', 'en_elmo_text', 'en_elmo_cos'])),
]
print(f'Oversampler: { oversampler}')
compare_classifiers(models, df, df['label'], silent=False, plot=False)
all_feats = []
for feature_set in feature_sets:
all_feats.append(feature_set + '_title')
all_feats.append(feature_set + '_text')
#all_feats.append('meta_media')
param_grid = {
'clf__tol': [1e-10, 1e-8, 1e-4, 1e-2, 1e-1], # 1e-4
'clf__C': [0.05, 0.15, 0.25, 0.35, 0.50, 0.75, 1, 1.25, 1.5, 2], # 1,
'clf__solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'] # lbfgs
}
print('All features count: ', len(all_feats))
for feature_set in all_feats:
model = pipelines.make(clf, [feature_set])
gs = GridSearchCV(model,
param_grid=param_grid,
scoring='accuracy',
cv=5,
error_score=-1,
verbose=1,
n_jobs=-1,
iid=False,
return_train_score=True)
gs.fit(df, df['label'])
print(f"{feature_set} | BEST SCORE: {gs.best_score_}")
print(f"{feature_set} | BEST PARAMS: {gs.best_params_}")
# ('all_en', en_feats),
('all', all_feats)
]
oversampler = None
# evaluation
param_grid = {
# 'clf__tol': [1e-2], # [1e-10, 1e-8, 1e-4, 1e-2, 1e-1], # 1e-4
'clf__C': [0.05, 0.15, 0.25, 0.35, 0.50, 0.75, 1, 1.25, 1.5, 2], # 1,
'clf__solver':
['liblinear'] #['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga']
}
for name, feature_list in features:
model = pipelines.make(
LogisticRegression(random_state=0, multi_class="auto", max_iter=1000),
feature_list)
print(name)
gs = GridSearchCV(model,
param_grid=param_grid,
scoring='accuracy',
cv=5,
error_score=-1,
verbose=10000,
n_jobs=-1,
iid=False,
return_train_score=True)
gs.fit(df, df['label'])
]
all_feats = []
for feature_set in feature_sets:
all_feats.append(feature_set + '_title')
all_feats.append(feature_set + '_text')
if feature_set not in ['bg_styl', 'bg_lsa']:
all_feats.append(feature_set + '_cos')
all_feats.append('meta_media')
bg_feats = [x for x in all_feats if x.startswith('bg_')] + ['meta_media']
en_feats = [x for x in all_feats if x.startswith('en_')] + ['meta_media']
models = []
for feature_set in feature_sets:
title_model = (feature_set + '_title',
pipelines.make(clf, [feature_set + '_title']))
text_model = (feature_set + '_text',
pipelines.make(clf, [feature_set + '_text']))
title_text_model = (feature_set + '_title_text',
pipelines.make(
clf,
[feature_set + '_title', feature_set + '_text']))
title_text_cos_model = (feature_set + '_title_text_cos',
pipelines.make(clf, [
feature_set + '_title', feature_set + '_text',
feature_set + '_cos'
]))
models.append(title_model)
models.append(text_model)