def test_doc2weight():
from microtc.textmodel import TextModel
from microtc.weighting import TFIDF
from microtc.utils import tweet_iterator
import os
fname = join(os.path.dirname(__file__), 'text.json')
tw = list(tweet_iterator(fname))
docs = [x['text'] for x in tw]
text = TextModel(docs, token_list=[-1, 3])
# print(text['buenos dias'])
docs = [text.tokenize(d) for d in docs]
sp = TFIDF(docs)
assert len(sp.doc2weight(text.tokenize('odio odio los los'))) == 3
def test_tfidf_corpus():
from nose.tools import assert_almost_equals
from microtc.textmodel import TextModel
from microtc.weighting import TFIDF
from microtc.utils import Counter
from microtc.utils import tweet_iterator
import os
import numpy as np
fname = join(os.path.dirname(__file__), 'text.json')
tw = list(tweet_iterator(fname))
docs = [x['text'] for x in tw]
text = TextModel(token_list=[-1, 3])
docs = [text.tokenize(d) for d in docs]
counter = Counter()
[counter.update(set(x))for x in docs]
tfidf = TFIDF(docs)
tfidf2 = TFIDF.counter(counter)
assert tfidf.num_terms == tfidf2.num_terms
assert tfidf._ndocs == tfidf2._ndocs
for k in tfidf2.word2id.keys():
assert k in tfidf2.word2id
for k, v in tfidf.word2id.items():
id2 = tfidf2.word2id[k]
v = tfidf.wordWeight[v]
v2 = tfidf2.wordWeight[id2]
print(v, v2, k)
assert_almost_equals(v, v2)
def test_getitem():
from microtc.textmodel import TextModel
from microtc.weighting import TFIDF
from microtc.utils import tweet_iterator
import os
fname = join(os.path.dirname(__file__), 'text.json')
tw = list(tweet_iterator(fname))
docs = [x['text'] for x in tw]
text = TextModel(docs, token_list=[-1, 3])
# print(text['buenos dias'])
docs = [text.tokenize(d) for d in docs]
sp = TFIDF(docs)
tok = text.tokenize('buenos dias')
bow = sp.doc2weight(tok)
ids = bow[0]
assert len(ids) == len(sp[tok])
def test_lang():
from microtc.textmodel import TextModel
text = [
"Hi :) :P XD",
"excelente dia xc",
"el alma de la fiesta XD"
]
model = TextModel(text, **{
"del_dup1": True,
"emo_option": "group",
"lc": True,
"num_option": "group",
"strip_diac": False,
"token_list": [
(2, 1),
(2, 2),
-1,
# 5,
],
"url_option": "group",
"usr_option": "group",
})
text = "El alma de la fiesta :) conociendo la maquinaria @user bebiendo nunca manches que onda"
a = model.tokenize(text)
b = ['el~de', 'alma~la', 'de~fiesta', 'la~_pos', 'fiesta~conociendo', '_pos~la', 'conociendo~maquinaria', 'la~_usr', 'maquinaria~bebiendo', '_usr~nunca',
'bebiendo~manches', 'nunca~que', 'manches~onda', 'el~la', 'alma~fiesta', 'de~_pos', 'la~conociendo', 'fiesta~la', '_pos~maquinaria', 'conociendo~_usr',
'la~bebiendo', 'maquinaria~nunca', '_usr~manches', 'bebiendo~que', 'nunca~onda', 'el', 'alma', 'de', 'la', 'fiesta', '_pos',
'conociendo', 'la', 'maquinaria', '_usr', 'bebiendo', 'nunca', 'manches', 'que', 'onda']
print(text)
assert a == b, "got: {0}, expected: {1}".format(a, b)
def test_space():
from microtc.textmodel import TextModel
from microtc.weighting import TFIDF
from microtc.utils import tweet_iterator
import os
fname = os.path.dirname(__file__) + '/text.json'
tw = list(tweet_iterator(fname))
docs = [x['text'] for x in tw]
text = TextModel(docs, token_list=[-1, 3])
# print(text['buenos dias'])
docs = [text.tokenize(d) for d in docs]
sp = TFIDF(docs)
assert len(sp.wordWeight) == len(sp._w2id)
def test_tfidf_corpus2():
from nose.tools import assert_almost_equals
from microtc.textmodel import TextModel
from microtc.weighting import TFIDF
from microtc.utils import Counter
from microtc.utils import tweet_iterator
import os
import numpy as np
fname = join(os.path.dirname(__file__), 'text.json')
tw = list(tweet_iterator(fname))
docs = [x['text'] for x in tw]
tm = TextModel(token_list=[-1, 3])
docs = [tm.tokenize(d) for d in docs]
counter = Counter()
[counter.update(set(x))for x in docs]
tfidf = TFIDF(docs, token_min_filter=1)
tfidf2 = TFIDF.counter(counter, token_min_filter=1)
id2w2 = {v: k for k, v in tfidf2.word2id.items()}
for text in docs:
tokens = tm.tokenize(text)
fm = {k: v for k, v in tfidf[tokens]}
for k, v in tfidf2[tokens]:
assert_almost_equals(fm[tfidf.word2id[id2w2[k]]], v)
def test_textmodel_compute_tokens():
from microtc.textmodel import TextModel
from microtc.utils import tweet_iterator
import os
fname = os.path.dirname(__file__) + '/text.json'
tw = list(tweet_iterator(fname))
tm = TextModel(token_list=[-2, -1])
text = tm.text_transformations(tw[0]['text'])
L = tm.compute_tokens(text)
assert len(L) == 2
r = []
[r.__iadd__(x) for x in L]
for a, b in zip(tm.tokenize(tw[0]), r):
assert a == b
def test_entropy():
from microtc.textmodel import TextModel
from microtc.weighting import Entropy, TFIDF
from microtc.utils import tweet_iterator
import os
fname = join(os.path.dirname(__file__), 'text.json')
tw = list(tweet_iterator(fname))
docs = [x['text'] for x in tw]
text = TextModel(token_list=[-1, 3])
# print(text['buenos dias'])
docs = [text.tokenize(d) for d in docs]
sp = Entropy(docs, X=tw)
print(sp.wordWeight)
tfidf = TFIDF(docs)
for k in sp.wordWeight.keys():
if sp.wordWeight[k] != tfidf.wordWeight[k]:
return
# print(sp.w)
assert False
from nltk.stem.porter import PorterStemmer
from typing import Callable, Iterable
tm = TextModel(num_option=OPTION_NONE,
usr_option=OPTION_NONE,
url_option=OPTION_NONE,
emo_option=OPTION_NONE,
hashtag_option=OPTION_NONE,
ent_option=OPTION_NONE,
lc=False,
del_dup=False,
del_punc=False,
del_diac=False,
token_list=[-1])
tm.tokenize("Hello good morning")
# Count the number of words
def N_tokens_types(fname: str, counter: Counter, tm: Callable[[str],
Iterable[str]]):
txt = open(fname).read()
tokens = tm(txt)
counter.update(tokens)
N = sum([v for v in counter.values()])
return N, len(counter)
counter = Counter()
heaps = [
doc = nlp("This is a sentence. U.S. is another sentence.")
[x for x in doc.sents]
tm = TextModel(num_option=OPTION_NONE,
usr_option=OPTION_NONE,
url_option=OPTION_NONE,
emo_option=OPTION_NONE,
hashtag_option=OPTION_NONE,
ent_option=OPTION_NONE,
lc=True,
del_dup=False,
del_punc=False,
del_diac=False,
token_list=[-1])
tm.tokenize("Hello good morning")
heaps = []
counter = Counter()
for fname in glob("../books/*.txt"):
txt = open(fname).read()
tokens = tm.tokenize(txt)
counter.update(tokens)
V = len(counter)
N = sum([v for v in counter.values()])
heaps.append([N, V])
plt.plot([x for x, _ in heaps], [x for _, x in heaps])
plt.grid()
plt.xlabel("N")
plt.ylabel("|V|")
