def apply_d2v_sectionwise():
'''
Evaluate doc2vec for comparison of patent sections
'''
# define embedding size
size = 50
# load data
model = pkl.load(
open("../doc2vec/models/full_pat_corpus_dm_50_min5_iter18.model"))
corpus = np.load('../corpus/corpus_claims.npy').item()
target_ids = np.load('../corpus/target_ids.npy')
random_ids = np.load('../corpus/random_ids.npy')
dupl_ids = np.load('../corpus/dupl_ids.npy').item()
cited_ids = np.load('../corpus/cited_ids.npy').item()
id_dict = make_combis(target_ids, random_ids, cited_ids, dupl_ids)
patfeats_d2v = infer_patfeats(corpus, model)
scores = calc_simcoef_distr(patfeats_d2v, ['cited', 'duplicate', 'random'],
id_dict, 'linear')
auc = calc_auc(scores['cited'], scores['random'])[2]
'''
# guarantee that scores range between 0 and 1
for label, vals in scores.items():
scores[label] = scores[label] - np.min(scores[label])
scores[label] = scores[label]/np.max(scores[label])
'''
plot_score_distr('human_eval',
'linear', ['random', 'cited', 'duplicate'], {
'cited': scores['cited'],
'random': scores['random'],
'duplicate': scores['duplicate']
},
auc, ['cited'],
histdir='doc2vec_full%i_claims' % size,
bins=50)
def apply_kpca_rel_corpus():
# load combis for small corpus
combis = np.load('human_eval/corpus_info/combis.npy')
target_ids = list(set([comb[0] for comb in combis]))
single_pat_corpus = np.load('human_eval/corpus_info/single_pat_corpus.npy').item()
ft = FeatureTransform(renorm='max')
docfeats = ft.texts2features(single_pat_corpus)
doc_ids = docfeats.keys()
train_feats = {pid : pat for pid, pat in docfeats.items() if pid not in target_ids}
target_feats = {pid : docfeats[pid] for pid in target_ids}
# make feature matrices
X_train, featurenames = features2mat(train_feats, train_feats.keys())
X_target, _ = features2mat(target_feats, target_feats.keys(), featurenames)
# train on full patent corpus (excluding target patents)
kpca = KernelPCA(n_components=250, kernel='linear')
X_train_kpca = kpca.fit_transform(X_train)
# make feat mat for small corpus
X_target_kpca = kpca.transform(X_target)
patfeats_lsa = {pid: norm_dict(dict(zip(range(250), X_train_kpca[i,:])), 'length') for i, pid in enumerate(train_feats.keys())}
for i, pid in enumerate(target_feats.keys()):
patfeats_lsa[pid] = norm_dict(dict(zip(range(250), X_target_kpca[i,:])), 'length')
pat_ids = np.load('human_eval/corpus_info/pat_ids.npy')
binary_label_pairs = np.load('human_eval/corpus_info/binary_label_pairs.npy').item()
human_label_pairs = np.load('human_eval/corpus_info/human_label_pairs.npy').item()
binary_sim_combis, binary_diff_combis = group_combis(binary_label_pairs)
human_sim_combis, human_diff_combis = group_combis(human_label_pairs)
for simcoef in ['linear']:
binary_scores = calc_simcoef_distr(patfeats_lsa, ['random', 'cited'],
{'cited': binary_sim_combis, 'random': binary_diff_combis},
simcoef)
human_scores = calc_simcoef_distr(patfeats_lsa, ['irrelevant', 'relevant'],
{'relevant': human_sim_combis, 'irrelevant': human_diff_combis},
simcoef)
binary_auc = calc_auc(binary_scores['cited'], binary_scores['random'])[2]
human_auc = calc_auc(human_scores['relevant'], human_scores['irrelevant'])[2]
plot_score_distr('human_eval', simcoef, ['random', 'cited'],
{'cited': binary_scores['cited'], 'random': binary_scores['random']},
binary_auc, ['cited'], histdir='kpca_1000_rel_corp', bins=20)
plot_score_distr('human_eval', simcoef, ['irrelevant', 'relevant'],
{'relevant': human_scores['relevant'], 'irrelevant': human_scores['irrelevant']},
human_auc, ['relevant'], histdir='kpca_1000_rel_corp', bins=20)
def apply_d2v_full_corpus():
target_ids = np.load('../corpus/target_ids.npy')
random_ids = np.load('../corpus/random_ids.npy')
dupl_ids = np.load('../corpus/dupl_ids.npy').item()
cited_ids = np.load('../corpus/cited_ids.npy').item()
id_dict = make_combis(target_ids, random_ids, cited_ids, dupl_ids)
pat_corpus = np.load('../corpus/corpus.npy').item()
for size in [50]:
pat_corpus, target_pat_corpus = make_d2v_corpus(target_ids)
#train model
model = pkl.load(
open("../doc2vec/models/full_pat_corpus_dm_50_min5_iter18.model"))
#load model
#model = pkl.load(open('human_eval/patents_dm_50_min5_iter10.model'))
#patfeats_d2v = infer_patfeats(pat_corpus, model)
#patfeats_d2v = corpus_to_patfeats(model, pat_corpus, target_ids)
patfeats_d2v = make_doc2vec_corpus(model, target_pat_corpus)
#np.save('../doc2vec/patfeats_d2v%i.npy' %size, patfeats_d2v)
scores = calc_simcoef_distr(patfeats_d2v,
['cited', 'duplicate', 'random'], id_dict,
'linear')
auc = calc_auc(scores['cited'], scores['random'])[2]
'''
# guarantee that scores range between 0 and 1
for label, vals in scores.items():
scores[label] = scores[label] - np.min(scores[label])
scores[label] = scores[label]/np.max(scores[label])
'''
plot_score_distr('human_eval',
'linear', ['random', 'cited', 'duplicate'], {
'cited': scores['cited'],
'random': scores['random'],
'duplicate': scores['duplicate']
},
auc, ['cited'],
histdir='doc2vec_full%i_no_target' % size,
bins=50)
def apply_d2v_rel_corpus():
"""
Evaluate the doc2vec feature vectors on the smaller corpus for
cited/random and relevant/irrelevant labellings
"""
# load text
#pat_corpus = PatentCorpus()
#pat_corpus.mode = 'd2v'
#list(pat_corpus)
combis = np.load('human_eval/corpus_info/combis.npy')
target_ids = list(set([comb[0] for comb in combis]))
#pat_corpus = np.load('human_eval/doc2vec/corpus.npy')
#pat_corpus = [gensim.models.doc2vec.TaggedDocument(a[0], a[1]) for a in pat_corpus if a[1][0] not in target_ids]
## Plot AUC
# load model trained on entire patent corpus
model = pkl.load(
open("../doc2vec/models/full_pat_corpus_dm_50_min5_iter18.model"))
#model = pkl.load(open("../doc2vec/models/full_pat_corpus_dm_50_min5_iter18.model"))
#model = train_doc2vec(pat_corpus)
# get doc2vec feature vectors
single_pat_corpus = np.load(
'human_eval/corpus_info/single_pat_corpus.npy').item()
patfeats_d2v = infer_patfeats(single_pat_corpus, model)
#patfeats_d2v = corpus_to_patfeats(model, single_pat_corpus, [])
#patfeats_d2v = make_doc2vec_corpus(model, single_pat_corpus, target_ids)
pat_ids = np.load('human_eval/corpus_info/pat_ids.npy')
binary_label_pairs = np.load(
'human_eval/corpus_info/binary_label_pairs.npy').item()
human_label_pairs = np.load(
'human_eval/corpus_info/human_label_pairs.npy').item()
binary_sim_combis, binary_diff_combis = group_combis(binary_label_pairs)
human_sim_combis, human_diff_combis = group_combis(human_label_pairs)
for simcoef in ['linear']:
binary_scores = calc_simcoef_distr(patfeats_d2v, ['random', 'cited'], {
'cited': binary_sim_combis,
'random': binary_diff_combis
}, simcoef)
human_scores = calc_simcoef_distr(patfeats_d2v,
['irrelevant', 'relevant'], {
'relevant': human_sim_combis,
'irrelevant': human_diff_combis
}, simcoef)
binary_auc = calc_auc(binary_scores['cited'],
binary_scores['random'])[2]
human_auc = calc_auc(human_scores['relevant'],
human_scores['irrelevant'])[2]
plot_score_distr('human_eval',
simcoef, ['random', 'cited'], {
'cited': binary_scores['cited'],
'random': binary_scores['random']
},
binary_auc, ['cited'],
histdir='doc2vec_full50_rel_corp',
bins=20)
plot_score_distr('human_eval',
simcoef, ['irrelevant', 'relevant'], {
'relevant': human_scores['relevant'],
'irrelevant': human_scores['irrelevant']
},
human_auc, ['relevant'],
histdir='doc2vec_full50_rel_corp',
bins=20)
Dw_all['binary_idf_neg'] = pointwise_dict_multiply(Dw_all['idf'], Dw_all['binary_neg'])
np.save('full_patent_scores/corpus_info_for_regression/Dw_all.npy', Dw_all)
'''
for method in ['lasso']:
## use learned term weights for feature extraction
ft = FeatureTransform(identify_bigrams=False,
norm=None,
weight=True,
renorm='length')
ft.Dw = Dw_all['lasso']
patfeats = ft.texts2features(pat_corpus)
# plot the results
for simcoef in ['linear']:
binary_scores = calc_simcoef_distr(
patfeats, ['cited', 'random'], {
'cited':
[sim_combi.split('_') for sim_combi in sim_combis],
'random':
[diff_combi.split('_') for diff_combi in diff_combis]
}, simcoef)
binary_auc = calc_auc(binary_scores['cited'],
binary_scores['random'])[2]
plot_score_distr('full_patent_scores',
simcoef, ['cited', 'random'], {
'cited': binary_scores['cited'],
'random': binary_scores['random']
},
binary_auc, ['cited'],
histdir=method,
bins=50)
for n_comp in [100, 250, 500, 1000]:
print n_comp
# fit LSA
kpca = KernelPCA(n_components=n_comp, kernel='linear')
X_train_kpca = kpca.fit_transform(X_train)
#pkl.dump(kpca, open('human_eval/models/kpca_%i.model' %n_comp, 'wb'), -1)
X_target_kpca = kpca.transform(X_target)
kpca_feats = {
pid: norm_dict(dict(zip(range(n_comp), X_train_kpca[i, :])),
'length')
for i, pid in enumerate(train_feats.keys())
}
for i, pid in enumerate(target_feats.keys()):
kpca_feats[pid] = norm_dict(
dict(zip(range(n_comp), X_target_kpca[i, :])), 'length')
np.save('human_eval/corpus_info/kpca_feats.npy', kpca_feats)
scores = calc_simcoef_distr(kpca_feats,
['cited', 'duplicate', 'random'], id_dict,
'linear')
auc, aps = calc_auc(scores['cited'], scores['random'])[2::]
print(auc, aps)
plot_score_distr('human_eval',
'linear', ['random', 'cited', 'duplicate'], {
'cited': scores['cited'],
'random': scores['random'],
'duplicate': scores['duplicate']
},
auc, ['cited'],
histdir='kpca_%i' % n_comp,
bins=50)
#corpus = np.load('../corpus/corpus.npy').item()
for embed_dim in [200]:
corpus = np.load('../corpus/corpus.npy').item()
#pat_corpus = make_w2v_corpus()
#model = train_word2vec(pat_corpus, 'full_patent_corpus', seed=1, embed_dim=200)
model = pkl.load(open('human_eval/models/full_patent_corpus_sg_200_hs0_neg13_seed1.model'))
pat_ids = corpus.keys()
ft = FeatureTransform(identify_bigrams=False, norm=None, weight='tfidf', renorm='length')
patfeats = ft.texts2features(corpus)
featmat_w2v, featurenames = embed_features(model, patfeats, pat_ids)
patfeats_w2v = {}
for i, pid in enumerate(pat_ids):
patfeats_w2v[pid] = dict(zip(featurenames, featmat_w2v[i,:]))
#np.save('../corpus/patfeats_w2v.npy', patfeats_w2v)
#patfeats = np.load('../corpus/patfeats_w2v.npy').item()
patfeats = patfeats_w2v
target_ids = np.load('../corpus/target_ids.npy')
random_ids = np.load('../corpus/random_ids.npy')
dupl_ids = np.load('../corpus/dupl_ids.npy').item()
cited_ids = np.load('../corpus/cited_ids.npy').item()
id_dict = make_combis(target_ids, random_ids, cited_ids, dupl_ids)
scores = calc_simcoef_distr(patfeats, ['random', 'cited', 'duplicate'],
id_dict, 'linear')
auc = calc_auc(scores['cited'], scores['random'])[2]
plot_score_distr('human_eval', 'linear', ['random', 'cited'],
{'cited': scores['cited'], 'random': scores['random']},
auc, ['cited'], histdir='word2vec_full%i_nonorm_length' %embed_dim, bins=50)
ft.Dw = Dw_all['binary_idf']
patfeats_cited = ft.texts2features(single_pat_corpus)
# multiply patfeats with human idf weights
ft = FeatureTransform(identify_bigrams=False,
norm=None,
weight=True,
renorm='length')
ft.Dw = Dw_all['human_idf']
patfeats_human = ft.texts2features(single_pat_corpus)
# plot the distributions
binary_sim_combis, binary_diff_combis = group_combis(binary_label_pairs)
human_sim_combis, human_diff_combis = group_combis(human_label_pairs)
for simcoef in ['linear', 'jaccard']:
binary_scores = calc_simcoef_distr(patfeats_cited, ['cited', 'random'],
{
'cited': binary_sim_combis,
'random': binary_diff_combis
}, simcoef)
human_scores = calc_simcoef_distr(patfeats_human,
['relevant', 'not relevant'], {
'relevant': human_sim_combis,
'not relevant': human_diff_combis
}, simcoef)
binary_auc = calc_auc(binary_scores['cited'],
binary_scores['random'])[2]
human_auc = calc_auc(human_scores['relevant'],
human_scores['not relevant'])[2]
plot_score_distr('human_eval',
simcoef, ['cited', 'random'], {
'cited': binary_scores['cited'],
'random': binary_scores['random']
'human_eval/corpus_info/binary_label_pairs.npy').item()
human_label_pairs = np.load(
'human_eval/corpus_info/human_label_pairs.npy').item()
# make word2vec embedded feature matrix
featmat_w2v, featurenames = embed_features(model, patfeats, pat_ids)
#transform feature matrix into dict
patfeats_w2v = {}
for i, pid in enumerate(pat_ids):
patfeats_w2v[pid] = dict(zip(featurenames, featmat_w2v[i, :]))
## Plot AUC
binary_sim_combis, binary_diff_combis = group_combis(binary_label_pairs)
human_sim_combis, human_diff_combis = group_combis(human_label_pairs)
for simcoef in ['linear', 'jaccard']:
binary_scores = calc_simcoef_distr(patfeats_w2v, ['random', 'cited'], {
'cited': binary_sim_combis,
'random': binary_diff_combis
}, simcoef)
human_scores = calc_simcoef_distr(patfeats_w2v,
['irrelevant', 'relevant'], {
'relevant': human_sim_combis,
'irrelevant': human_diff_combis
}, simcoef)
binary_auc = calc_auc(binary_scores['cited'],
binary_scores['random'])[2]
human_auc = calc_auc(human_scores['relevant'],
human_scores['irrelevant'])[2]
plot_score_distr('human_eval',
simcoef, ['random', 'cited'], {
'cited': binary_scores['cited'],
'random': binary_scores['random']