from sklearn.model_selection import train_test_splitが使用できない

Question

本を持っている方があれば嬉しいのですが、機械学習・自然学習による自然言語処理入門の本で第四章の78ページにある、train.pyを用いて日本語を抽出したいのですがそれ以前の問題でモジュールが実行できない段階となっております。
以下のURLが自分が使っている本です。

https://www.amazon.co.jp/%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%BB%E6%B7%B1%E5%B1%A4%E5%AD%A6%E7%BF%92%E3%81%AB%E3%82%88%E3%82%8B%E8%87%AA%E7%84%B6%E8%A8%80%E8%AA%9E%E5%87%A6%E7%90%86%E5%85%A5%E9%96%80-Compass-Books%E3%82%B7%E3%83%AA%E3%83%BC%E3%82%BA-%E4%B8%AD%E5%B1%B1-%E5%85%89%E6%A8%B9-ebook/dp/B084WPRT44/ref=sr_1_1?__mk_ja_JP=%E3%82%AB%E3%82%BF%E3%82%AB%E3%83%8A&crid=1O57YT9TDXZJ&dchild=1&keywords=%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92+%E6%B7%B1%E5%B1%A4%E5%AD%A6%E7%BF%92%E3%81%AB%E3%82%88%E3%82%8B%E8%87%AA%E7%84%B6%E8%A8%80%E8%AA%9E%E5%87%A6%E7%90%86%E5%85%A5%E9%96%80&qid=1601255981&s=digital-text&sprefix=%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%BB%E6%B7%B1%E5%B1%A4%E5%AD%A6%E7%BF%92%2Cdigital-text%2C267&sr=1-1

次に、レビューを抽出するデータが以下となります。これを使って実際にデータを操作していきます。
https://s3.amazonaws.com/amazon-reviews-pds/tsv/amazon_reviews_multilingual_JP_v1_00.tsv.gz

#pythonのバージョン
Python 3.8.5 (tags/v3.8.5:580fbb0, Jul 20 2020, 15:57:54) [MSC v.1924 64 bit (AMD64)] on win32
#scikit-learnのバージョン
scikit-learn 0.23.2
#_init_pyのコード

_init_pyに原因があるらしく実際に開いたところ、79行目のfrom. import__check_buildのところにエラーがあるらしいそうです。

"""
Machine learning module for Python
==================================

sklearn is a Python module integrating classical machine
learning algorithms in the tightly-knit world of scientific Python
packages (numpy, scipy, matplotlib).

It aims to provide simple and efficient solutions to learning problems
that are accessible to everybody and reusable in various contexts:
machine-learning as a versatile tool for science and engineering.

See http://scikit-learn.org for complete documentation.
"""
import sys
import logging
import os

from ._config import get_config, set_config, config_context

logger = logging.getLogger(__name__)


# PEP0440 compatible formatted version, see:
# https://www.python.org/dev/peps/pep-0440/
#
# Generic release markers:
#   X.Y
#   X.Y.Z   # For bugfix releases
#
# Admissible pre-release markers:
#   X.YaN   # Alpha release
#   X.YbN   # Beta release
#   X.YrcN  # Release Candidate
#   X.Y     # Final release
#
# Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
# 'X.Y.dev0' is the canonical version of 'X.Y.dev'
#
__version__ = '0.23.2'


# On OSX, we can get a runtime error due to multiple OpenMP libraries loaded
# simultaneously. This can happen for instance when calling BLAS inside a
# prange. Setting the following environment variable allows multiple OpenMP
# libraries to be loaded. It should not degrade performances since we manually
# take care of potential over-subcription performance issues, in sections of
# the code where nested OpenMP loops can happen, by dynamically reconfiguring
# the inner OpenMP runtime to temporarily disable it while under the scope of
# the outer OpenMP parallel section.
os.environ.setdefault("KMP_DUPLICATE_LIB_OK", "True")

# Workaround issue discovered in intel-openmp 2019.5:
# https://github.com/ContinuumIO/anaconda-issues/issues/11294
os.environ.setdefault("KMP_INIT_AT_FORK", "FALSE")

try:
    # This variable is injected in the __builtins__ by the build
    # process. It is used to enable importing subpackages of sklearn when
    # the binaries are not built
    # mypy error: Cannot determine type of '__SKLEARN_SETUP__'
    __SKLEARN_SETUP__  # type: ignore
except NameError:
    __SKLEARN_SETUP__ = False

if __SKLEARN_SETUP__:
    sys.stderr.write('Partial import of sklearn during the build process.\n')
    # We are not importing the rest of scikit-learn during the build
    # process, as it may not be compiled yet
else:
    # `_distributor_init` allows distributors to run custom init code.
    # For instance, for the Windows wheel, this is used to pre-load the
    # vcomp shared library runtime for OpenMP embedded in the sklearn/.libs
    # sub-folder.
    # It is necessary to do this prior to importing show_versions as the
    # later is linked to the OpenMP runtime to make it possible to introspect
    # it and importing it first would fail if the OpenMP dll cannot be found.
    from . import _distributor_init  # noqa: F401
    from . import __check_build  # noqa: F401
    from .base import clone
    from .utils._show_versions import show_versions

    __all__ = ['calibration', 'cluster', 'covariance', 'cross_decomposition',
               'datasets', 'decomposition', 'dummy', 'ensemble', 'exceptions',
               'experimental', 'externals', 'feature_extraction',
               'feature_selection', 'gaussian_process', 'inspection',
               'isotonic', 'kernel_approximation', 'kernel_ridge',
               'linear_model', 'manifold', 'metrics', 'mixture',
               'model_selection', 'multiclass', 'multioutput',
               'naive_bayes', 'neighbors', 'neural_network', 'pipeline',
               'preprocessing', 'random_projection', 'semi_supervised',
               'svm', 'tree', 'discriminant_analysis', 'impute', 'compose',
               # Non-modules:
               'clone', 'get_config', 'set_config', 'config_context',
               'show_versions']


def setup_module(module):
    """Fixture for the tests to assure globally controllable seeding of RNGs"""
    import os
    import numpy as np
    import random

    # Check if a random seed exists in the environment, if not create one.
    _random_seed = os.environ.get('SKLEARN_SEED', None)
    if _random_seed is None:
        _random_seed = np.random.uniform() * np.iinfo(np.int32).max
    _random_seed = int(_random_seed)
    print("I: Seeding RNGs with %r" % _random_seed)
    np.random.seed(_random_seed)
    random.seed(_random_seed)

このコードを用いて、train.pyを用いたところエラー?が出ました。train.pyを実行するためのコードです。
#preprocessing.py

"""
Preprocessings.
"""
import re

from bs4 import BeautifulSoup
from janome.tokenizer import Tokenizer
t = Tokenizer()


def clean_html(html, strip=False):
    soup = BeautifulSoup(html, 'html.parser')
    text = soup.get_text(strip=strip)
    return text


def tokenize(text):
    return t.tokenize(text, wakati=True)


def tokenize_base_form(text):
    tokens = [token.base_form for token in t.tokenize(text)]
    return tokens


def normalize_number(text, reduce=False):
    if reduce:
        normalized_text = re.sub(r'\d+', '0', text)
    else:
        normalized_text = re.sub(r'\d', '0', text)
    return normalized_text


def truncate(sequence, maxlen):
    return sequence[:maxlen]


def remove_url(html):
    soup = BeautifulSoup(html, 'html.parser')
    for a in soup.findAll('a'):
        a.replaceWithChildren()
    return str(soup)

#utilis.py

import string
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score


def filter_by_ascii_rate(text, threshold=0.9):
    ascii_letters = set(string.printable)
    rate = sum(c in ascii_letters for c in text) / len(text)
    return rate <= threshold


def load_dataset(filename, n=5000, state=6):
    df = pd.read_csv(filename, sep='\t')

    # extracts Japanese texts.
    is_jp = df.review_body.apply(filter_by_ascii_rate)
    df = df[is_jp]

    # sampling.
    df = df.sample(frac=1, random_state=state)  # shuffle
    grouped = df.groupby('star_rating')
    df = grouped.head(n=n)
    return df.review_body.values, df.star_rating.values


def train_and_eval(x_train, y_train, x_test, y_test,
                   lowercase=False, tokenize=None, preprocessor=None):
    vectorizer = CountVectorizer(lowercase=lowercase,
                                 tokenizer=tokenize,
                                 preprocessor=preprocessor)
    x_train_vec = vectorizer.fit_transform(x_train)
    x_test_vec = vectorizer.transform(x_test)
    clf = LogisticRegression(solver='liblinear')
    clf.fit(x_train_vec, y_train)
    y_pred = clf.predict(x_test_vec)
    score = accuracy_score(y_test, y_pred)
    print('{:.4f}'.format(score))

#train.py

from sklearn.model_selection import train_test_split

from preprocessing import clean_html, normalize_number, tokenize, tokenize_base_form
from utils import load_dataset, train_and_eval


def main():
    x, y = load_dataset('data/amazon_reviews_multilingual_JP_v1_00.tsv', n=1000)

    x_train, x_test, y_train, y_test = train_test_split(x, y,
                                                        test_size=0.2,
                                                        random_state=42)

    print('Tokenization only.')
    train_and_eval(x_train, y_train, x_test, y_test, tokenize=tokenize)

    print('Clean html.')
    train_and_eval(x_train, y_train, x_test, y_test, tokenize=tokenize, preprocessor=clean_html)

    print('Normalize number.')
    train_and_eval(x_train, y_train, x_test, y_test, tokenize=tokenize, preprocessor=normalize_number)

    print('Base form.')
    train_and_eval(x_train, y_train, x_test, y_test, tokenize=tokenize_base_form)

    print('Lower text.')
    train_and_eval(x_train, y_train, x_test, y_test, tokenize=tokenize, lowercase=True)


if __name__ == '__main__':
    main()

#エラー？らしきもの
python train.pyを実行してみたところ、このようなエラーが出てしまいました。

Answer 1

普通にただ、文字がミスしていただけでした。ここで数時間も時間食らって悔しいです