sporada/nopaque
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git synced 2025-11-03 20:02:47 +00:00
Code Issues Projects Releases Wiki Activity

Add more visualization data

Browse Source
This commit is contained in:
Patrick Jentsch
2023-06-19 13:22:20 +02:00
parent 972f514e6b
commit f037c31b88
2 changed files with 58 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
app/corpora/cqi_over_socketio/cqi_corpora_corpus.py
View File

@@ -50,9 +50,52 @@ def cqi_corpora_corpus_update_db(cqi_client: cqi.CQiClient, corpus_name: str):
@cqi_over_socketio
def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_name: str):
corpus = cqi_client.corpora.get(corpus_name)
# s_attrs = [x for x in corpus.structural_attributes.list() if not x.has_values]
# p_attrs = corpus.positional_attributes.list()
# payload = {
# 's_attrs': {},
# 'p_attrs': {},
# 'values': {
# 's_attrs': {},
# 'p_attrs': {}
# }
# }
# for s_attr in s_attrs:
# s_attr_lbound, s_attr_rbound = s_attr.cpos_by_id(text_id)
# s_attr_cpos_range = range(s_attr_lbound, s_attr_rbound + 1)
# payload['text']['lexicon'][text_id] = {
# 's_attrs': [s_attr_lbound, s_attr_rbound],
# 'counts': {
# 'token': s_attr_rbound - s_attr_lbound + 1
# },
# 'freqs': {
# p_attr.name: dict(Counter(p_attr.ids_by_cpos(list(s_attr_cpos_range))))
# for p_attr in p_attrs
# }
# }
# for p_attr in p_attrs:
# payload['p_attrs'] = dict(
# )
# payload['values']['p_attrs'] = dict(
# zip(
# range(0, p_attr.lexicon_size),
# p_attr.values_by_ids(list(range(0, p_attr.lexicon_size)))
# )
# )
text = corpus.structural_attributes.get('text')
text_value_names = []
text_values = []
for text_sub_attr in corpus.structural_attributes.list(filters={'part_of': text}):
text_value_names.append(text_sub_attr.name[(len(text.name) + 1):])
text_values.append(text_sub_attr.values_by_ids(list(range(0, text.size))))
s = corpus.structural_attributes.get('s')
ent = corpus.structural_attributes.get('ent')
ent_value_names = []
ent_values = []
for ent_sub_attr in corpus.structural_attributes.list(filters={'part_of': ent}):
ent_value_names.append(ent_sub_attr.name[(len(ent.name) + 1):])
ent_values.append(ent_sub_attr.values_by_ids(list(range(0, ent.size))))
word = corpus.positional_attributes.get('word')
lemma = corpus.positional_attributes.get('lemma')
pos = corpus.positional_attributes.get('pos')
@@ -122,10 +165,7 @@ def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_
)
}
}
payload['text']['values'] = [
sub_attr.name[(len(text.name) + 1):]
for sub_attr in corpus.structural_attributes.list(filters={'part_of': text})
]
payload['text']['values'] = text_value_names
payload['s'] = {'lexicon': {}, 'values': None}
for s_id in range(0, s.size):
payload['s']['lexicon'][s_id] = {
@@ -140,15 +180,22 @@ def cqi_corpora_corpus_get_visualization_data(cqi_client: cqi.CQiClient, corpus_
payload['ent']['lexicon'][ent_id] = {
# 'bounds': ent.cpos_by_id(ent_id)
}
payload['ent']['values'] = [
sub_attr.name[(len(ent.name) + 1):]
for sub_attr in corpus.structural_attributes.list(filters={'part_of': ent})
]
payload['ent']['values'] = ent_value_names
payload['lookups'] = {
'corpus': {},
'text': {},
'text': {
text_id: {
text_value_name: text_values[text_value_name_idx][text_id_idx]
for text_value_name_idx, text_value_name in enumerate(text_value_names)
} for text_id_idx, text_id in enumerate(range(0, text.size))
},
's': {},
'ent': {},
'ent': {
ent_id: {
ent_value_name: ent_values[ent_value_name_idx][ent_id_idx]
for ent_value_name_idx, ent_value_name in enumerate(ent_value_names)
} for ent_id_idx, ent_id in enumerate(range(0, ent.size))
},
'word': dict(
zip(
range(0, word.lexicon_size),