Question about aravec HOT 3 CLOSED

Hi. You can simply write all the embeddings into a txt file to use anywhere. I do not know if this could help you or not ?

import gensim
import json

model = gensim.models.Word2Vec.load('model/tweets_sg_100')

# ----- Write to txt File

all_tokens_vecs = {}
for i in range(0,len(model.wv.index2word)):
    all_tokens_vecs[ model.wv.index2word[i] ] = model.wv[model.wv.index2word[i]]

res = open("model.txt", 'w', encoding='utf8')
res.write(json.dumps(all_tokens_vecs))
res.close()

# ---- Read
with open('model.txt', 'r', encoding='utf8') as content_file:
    all_tokens_vecs = json.loads(content_file.read())

print(all_tokens_vecs['محمد'])

from aravec.

thank you for your effort
I prefer to convert it to .bin extension
however,
I try to do same code for both "full_grams_sg_300_twitter.mdl" and "full_grams_cbow_300_twitter.mdl"
and I had this error

TypeError Traceback (most recent call last)
in ()
12
13 res = open("model.txt", 'w', encoding='utf8')
---> 14 res.write(json.dumps(all_tokens_vecs))
15 res.close()
16

/anaconda3/lib/python3.7/json/init.py in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)
229 cls is None and indent is None and separators is None and
230 default is None and not sort_keys and not kw):
--> 231 return _default_encoder.encode(obj)
232 if cls is None:
233 cls = JSONEncoder

/anaconda3/lib/python3.7/json/encoder.py in encode(self, o)
197 # exceptions aren't as detailed. The list call should be roughly
198 # equivalent to the PySequence_Fast that ''.join() would do.
--> 199 chunks = self.iterencode(o, _one_shot=True)
200 if not isinstance(chunks, (list, tuple)):
201 chunks = list(chunks)

/anaconda3/lib/python3.7/json/encoder.py in iterencode(self, o, _one_shot)
255 self.key_separator, self.item_separator, self.sort_keys,
256 self.skipkeys, _one_shot)
--> 257 return _iterencode(o, 0)
258
259 def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,

/anaconda3/lib/python3.7/json/encoder.py in default(self, o)
177
178 """
--> 179 raise TypeError(f'Object of type {o.class.name} '
180 f'is not JSON serializable')
181

TypeError: Object of type ndarray is not JSON serializable

any help to convert that .mdl file to .bin, please?
I would be very thankful?

from aravec.

thank you for your effort
I prefer to convert it to .bin extension
however,
I try to do same code for both "full_grams_sg_300_twitter.mdl" and "full_grams_cbow_300_twitter.mdl"
and I had this error

TypeError Traceback (most recent call last)
in ()
12
13 res = open("model.txt", 'w', encoding='utf8')
---> 14 res.write(json.dumps(all_tokens_vecs))
15 res.close()
16

/anaconda3/lib/python3.7/json/init.py in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)
229 cls is None and indent is None and separators is None and
230 default is None and not sort_keys and not kw):
--> 231 return _default_encoder.encode(obj)
232 if cls is None:
233 cls = JSONEncoder

/anaconda3/lib/python3.7/json/encoder.py in encode(self, o)
197 # exceptions aren't as detailed. The list call should be roughly
198 # equivalent to the PySequence_Fast that ''.join() would do.
--> 199 chunks = self.iterencode(o, _one_shot=True)
200 if not isinstance(chunks, (list, tuple)):
201 chunks = list(chunks)

/anaconda3/lib/python3.7/json/encoder.py in iterencode(self, o, _one_shot)
255 self.key_separator, self.item_separator, self.sort_keys,
256 self.skipkeys, _one_shot)
--> 257 return _iterencode(o, 0)
258
259 def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,

/anaconda3/lib/python3.7/json/encoder.py in default(self, o)
177
178 """
--> 179 raise TypeError(f'Object of type {o.class.name} '
180 f'is not JSON serializable')
181

TypeError: Object of type ndarray is not JSON serializable

any help to convert that .mdl file to .bin, please?
I would be very thankful?

thank you for your effort
I prefer to convert it to .bin extension
however,
I try to do same code for both "full_grams_sg_300_twitter.mdl" and "full_grams_cbow_300_twitter.mdl"
and I had this error

TypeError Traceback (most recent call last)
in ()
12
13 res = open("model.txt", 'w', encoding='utf8')
---> 14 res.write(json.dumps(all_tokens_vecs))
15 res.close()
16

/anaconda3/lib/python3.7/json/init.py in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)
229 cls is None and indent is None and separators is None and
230 default is None and not sort_keys and not kw):
--> 231 return _default_encoder.encode(obj)
232 if cls is None:
233 cls = JSONEncoder

/anaconda3/lib/python3.7/json/encoder.py in encode(self, o)
197 # exceptions aren't as detailed. The list call should be roughly
198 # equivalent to the PySequence_Fast that ''.join() would do.
--> 199 chunks = self.iterencode(o, _one_shot=True)
200 if not isinstance(chunks, (list, tuple)):
201 chunks = list(chunks)

/anaconda3/lib/python3.7/json/encoder.py in iterencode(self, o, _one_shot)
255 self.key_separator, self.item_separator, self.sort_keys,
256 self.skipkeys, _one_shot)
--> 257 return _iterencode(o, 0)
258
259 def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,

/anaconda3/lib/python3.7/json/encoder.py in default(self, o)
177
178 """
--> 179 raise TypeError(f'Object of type {o.class.name} '
180 f'is not JSON serializable')
181

TypeError: Object of type ndarray is not JSON serializable

any help to convert that .mdl file to .bin, please?
I would be very thankful?

@waadth Hi did you find a fix for the below error appreciated

TypeError: Object of type ndarray is not JSON serializable

from aravec.