def vectorize_init(labels, titles):
encoder = LabelEncoder()
encoder.fit(labels)
labels_ = encoder.transform(labels)
dump(encoder.classes_, "chap06-encoder-classes") # <class 'numpy.ndarray'>
vectorizer = TfidfVectorizer()
vectorizer.fit(titles)
features_ = vectorizer.transform(titles)
dump(vectorizer.vocabulary_, "chap06-vectorizer-vocabs") # <class 'dict'>
dump(vectorizer.get_feature_names(), "chap06-vectorizer-names") # [+] saved : chap06-model
return features_, labels_
wiki = load("UK")
infobox = re.search(
r"""
^{{基礎情報\s国
(?P<Infobox_body>.+?)
^}}$
""",
wiki,
flags=re.VERBOSE | re.DOTALL | re.MULTILINE,
).group("Infobox_body")
reg = re.compile(r"(.+?)\s*=\s*(.+)", re.DOTALL)
od = OrderedDict(
reg.search(line.strip()).groups() for line in infobox.split("\n|")
if line)
dump(od, "infobox")
with Renderer("knock25") as out:
for k, v in od.items():
out.result(k, green(v))
assert od == OrderedDict(
reg.search(line.strip()).groups()
for line in extract_infobox(wiki).lstrip("基礎情報 国").split("\n|")
if line)
assert od == OrderedDict(
re.findall(
r"""
\| # |
(?P<Key>.+?) # 略名
from kiyuna.utils.message import Renderer # noqa: E402 isort:skip
from kiyuna.utils.pickle import dump, load # noqa: E402 isort:skip
def vectorize_init(labels, titles):
encoder = LabelEncoder()
encoder.fit(labels)
labels_ = encoder.transform(labels)
dump(encoder.classes_, "chap06-encoder-classes") # <class 'numpy.ndarray'>
vectorizer = TfidfVectorizer()
vectorizer.fit(titles)
features_ = vectorizer.transform(titles)
dump(vectorizer.vocabulary_, "chap06-vectorizer-vocabs") # <class 'dict'>
dump(vectorizer.get_feature_names(), "chap06-vectorizer-names") # [+] saved : chap06-model
return features_, labels_
def load_dataset(path):
labels, titles = zip(*(line.strip().split("\t") for line in open(path)))
return vectorize_init(labels, titles)
if __name__ == "__main__":
features, labels = load_dataset("./train.feature.txt")
classifier = LogisticRegression(multi_class="multinomial", solver="lbfgs", random_state=123)
classifier.fit(features, labels)
dump(classifier, "chap06-classifier")
def country_embeddings():
wv = load("chap07-embeddings")
country_names = np.array(list_country_names(), dtype=object)
embeddings = [wv[country_name] for country_name in country_names]
dump([embeddings, country_names], "chap07-embeddings-country")
return embeddings, country_names
country_names |= {country1, country2}
return list(country_names)
def country_embeddings():
wv = load("chap07-embeddings")
country_names = np.array(list_country_names(), dtype=object)
embeddings = [wv[country_name] for country_name in country_names]
dump([embeddings, country_names], "chap07-embeddings-country")
return embeddings, country_names
if __name__ == "__main__":
embeddings, country_names = country_embeddings()
kmeans = KMeans(n_clusters=5).fit(embeddings)
dump(kmeans, "chap07-kmeans")
with Renderer("knock67", start=0) as out:
for i in range(5):
out.result(f"Class {i}", country_names[kmeans.labels_ == i])
"""result
[*] 0. Class 0
['Bhutan' 'Bahrain' 'Japan' 'Morocco' 'Indonesia' 'Pakistan' 'Thailand'
'Tunisia' 'Oman' 'Egypt' 'Turkey' 'Qatar' 'Iraq' 'Laos' 'Libya' 'Lebanon'
'Jordan' 'Afghanistan' 'Bangladesh' 'Syria' 'Nepal' 'China' 'Vietnam'
'Iran']
[*] 1. Class 1
['Samoa' 'Chile' 'Dominica' 'Australia' 'Ecuador' 'Fiji' 'Bahamas'
'Canada' 'Jamaica' 'Nicaragua' 'Cuba' 'Peru' 'Venezuela' 'Uruguay'
'Guyana' 'Honduras' 'Belize' 'Greenland' 'Philippines' 'Taiwan' 'Tuvalu'
'Suriname']
[*] 2. Class 2
if path == "MEMO":
with Renderer("個人メモ") as out:
out.result(
"type hints",
(
typing.get_type_hints(list_word_freq),
build_word_frequency_cnter.__annotations__,
),
)
out.header("with 内で return しても大丈夫なはず")
dis.dis(build_word_frequency_cnter, file=sys.stderr)
out.header("doctest")
doctest.testmod(verbose=True)
out.header("check serialize")
cnter = list_word_freq("../../test/00-input.txt")
dump(cnter, "cnter")
cnter = load("cnter")
exit(0)
with Renderer("単語の異なり数") as out:
out.result("map", len(list_word_freq(path)))
out.result("set", len(get_vocab(path)))
num = 10
with Renderer(f"数単語の頻度（上位 {num} 単語のみ）") as out:
out.result(
"大文字と小文字の区別をする",
build_word_frequency_cnter(path, str).most_common(num),
)
trans = lambda w: w.lower() # noqa: E731
out.result(
[MEMO]
2015 年版の knock86 に対応
"""
import os
import sys
from gensim.models import KeyedVectors
sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
from kiyuna.utils.pickle import dump, load # noqa: E402 isort:skip
if __name__ == "__main__":
if not os.path.exists("../pickles/chap07-embeddings.pkl"):
path = "./GoogleNews-vectors-negative300.bin.gz"
embeddings = KeyedVectors.load_word2vec_format(path, binary=True)
dump(embeddings, "chap07-embeddings")
wv = load("chap07-embeddings")
print(wv["United_States"])
"""result
[-3.61328125e-02 -4.83398438e-02 2.35351562e-01 1.74804688e-01
-1.46484375e-01 -7.42187500e-02 -1.01562500e-01 -7.71484375e-02
1.09375000e-01 -5.71289062e-02 -1.48437500e-01 -6.00585938e-02
1.74804688e-01 -7.71484375e-02 2.58789062e-02 -7.66601562e-02
-3.80859375e-02 1.35742188e-01 3.75976562e-02 -4.19921875e-02
-3.56445312e-02 5.34667969e-02 3.68118286e-04 -1.66992188e-01
-1.17187500e-01 1.41601562e-01 -1.69921875e-01 -6.49414062e-02
-1.66992188e-01 1.00585938e-01 1.15722656e-01 -2.18750000e-01
-9.86328125e-02 -2.56347656e-02 1.23046875e-01 -3.54003906e-02
-1.58203125e-01 -1.60156250e-01 2.94189453e-02 8.15429688e-02
6.88476562e-02 1.87500000e-01 6.49414062e-02 1.15234375e-01
"""
import gzip
import json
import os
import pprint
import sys
sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
from kiyuna.utils.message import Renderer, message # noqa: E402 isort:skip
from kiyuna.utils.pickle import dump # noqa: E402 isort:skip
def extract_wiki(path: str, title: str) -> dict:
with gzip.open(path, "rt") as f:
for line in f:
d = json.loads(line)
if d["title"] == title:
return d
if __name__ == "__main__":
input_path, title, out_fname, *_ = sys.argv[1:]
article = extract_wiki(input_path, title)
dump(article["text"], out_fname)
with Renderer("MEMO") as out:
out.result("article.keys()", article.keys())
# pprint.pprint(article)
