log-reg-iterative.ipynb

Kernel: Python 3 (ipykernel)

Logistic Regression Classifier for Text with Iterative Training

Requires fewer computate resource when used with massive datasets compared to log-reg.ipynb.

Obtaining the IMDb movie review dataset

import os
import sys
import tarfile
import time
import urllib.request

source = 'http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz'
target = 'aclImdb_v1.tar.gz'

if os.path.exists(target):
    os.remove(target)

def reporthook(count, block_size, total_size):
    global start_time
    if count == 0:
        start_time = time.time()
        return
    duration = time.time() - start_time
    progress_size = int(count * block_size)
    speed = progress_size / (1024.**2 * duration)
    percent = count * block_size * 100. / total_size

    sys.stdout.write(f'\r{int(percent)}% | {progress_size / (1024.**2):.2f} MB '
                     f'| {speed:.2f} MB/s | {duration:.2f} sec elapsed')
    sys.stdout.flush()


if not os.path.isdir('aclImdb') and not os.path.isfile('aclImdb_v1.tar.gz'):
    urllib.request.urlretrieve(source, target, reporthook)

if not os.path.isdir('aclImdb'):

    with tarfile.open(target, 'r:gz') as tar:
        tar.extractall()

Preprocessing the movie dataset into more convenient format

Install pyprind by uncommenting the next code cell.

# !pip install pyprind

import pyprind
import pandas as pd
import os
import sys
from packaging import version


# change the `basepath` to the directory of the
# unzipped movie dataset

basepath = 'aclImdb'

labels = {'pos': 1, 'neg': 0}

# if the progress bar does not show, change stream=sys.stdout to stream=2
pbar = pyprind.ProgBar(50000, stream=sys.stdout)

df = pd.DataFrame()
for s in ('test', 'train'):
    for l in ('pos', 'neg'):
        path = os.path.join(basepath, s, l)
        for file in sorted(os.listdir(path)):
            with open(os.path.join(path, file), 
                      'r', encoding='utf-8') as infile:
                txt = infile.read()
                
            if version.parse(pd.__version__) >= version.parse("1.3.2"):
                x = pd.DataFrame([[txt, labels[l]]], columns=['review', 'sentiment'])
                df = pd.concat([df, x], ignore_index=False)

            else:
                df = df.append([[txt, labels[l]]], 
                               ignore_index=True)
            pbar.update()
df.columns = ['review', 'sentiment']

0% [##############################] 100% | ETA: 00:00:00
Total time elapsed: 00:00:19

Shuffling the DataFrame:

import numpy as np


if version.parse(pd.__version__) >= version.parse("1.3.2"):
    df = df.sample(frac=1, random_state=0).reset_index(drop=True)
    
else:
    np.random.seed(0)
    df = df.reindex(np.random.permutation(df.index))

Optional: Saving the assembled data as CSV file:

df.to_csv('movie_data.csv', index=False, encoding='utf-8')

import pandas as pd

df = pd.read_csv('movie_data.csv', encoding='utf-8')

# the following is necessary on some computers:
df = df.rename(columns={"0": "review", "1": "sentiment"})

df.head(3)

df.shape

(50000, 2)

Training a logistic regression model for document classification

Working with bigger data - online algorithms and out-of-core learning

# This cell is not contained in the book but
# added for convenience so that the notebook
# can be executed starting here, without
# executing prior code in this notebook

import os
import gzip


if not os.path.isfile('movie_data.csv'):
    if not os.path.isfile('movie_data.csv.gz'):
        print('Please place a copy of the movie_data.csv.gz'
              'in this directory. You can obtain it by'
              'a) executing the code in the beginning of this'
              'notebook or b) by downloading it from GitHub:'
              'https://github.com/rasbt/machine-learning-book/'
              'blob/main/ch08/movie_data.csv.gz')
    else:
        with gzip.open('movie_data.csv.gz', 'rb') as in_f, \
                open('movie_data.csv', 'wb') as out_f:
            out_f.write(in_f.read())

import numpy as np
import re
from nltk.corpus import stopwords


# The `stop` is defined as earlier in this chapter
# Added it here for convenience, so that this section
# can be run as standalone without executing prior code
# in the directory
stop = stopwords.words('english')


def tokenizer(text):
    text = re.sub('<[^>]*>', '', text)
    emoticons = re.findall('(?::|;|=)(?:-)?(?:\)|\(|D|P)', text)
    text = re.sub('[\W]+', ' ', text.lower()) +\
        ' '.join(emoticons).replace('-', '')
    tokenized = [w for w in text.split() if w not in stop]
    return tokenized


def stream_docs(path):
    with open(path, 'r', encoding='utf-8') as csv:
        next(csv)  # skip header
        for line in csv:
            text, label = line[:-3], int(line[-2])
            yield text, label

next(stream_docs(path='movie_data.csv'))

('"In 1974, the teenager Martha Moxley (Maggie Grace) moves to the high-class area of Belle Haven, Greenwich, Connecticut. On the Mischief Night, eve of Halloween, she was murdered in the backyard of her house and her murder remained unsolved. Twenty-two years later, the writer Mark Fuhrman (Christopher Meloni), who is a former LA detective that has fallen in disgrace for perjury in O.J. Simpson trial and moved to Idaho, decides to investigate the case with his partner Stephen Weeks (Andrew Mitchell) with the purpose of writing a book. The locals squirm and do not welcome them, but with the support of the retired detective Steve Carroll (Robert Forster) that was in charge of the investigation in the 70\'s, they discover the criminal and a net of power and money to cover the murder.<br /><br />""Murder in Greenwich"" is a good TV movie, with the true story of a murder of a fifteen years old girl that was committed by a wealthy teenager whose mother was a Kennedy. The powerful and rich family used their influence to cover the murder for more than twenty years. However, a snoopy detective and convicted perjurer in disgrace was able to disclose how the hideous crime was committed. The screenplay shows the investigation of Mark and the last days of Martha in parallel, but there is a lack of the emotion in the dramatization. My vote is seven.<br /><br />Title (Brazil): Not Available"',
 1)

def get_minibatch(doc_stream, size):
    docs, y = [], []
    try:
        for _ in range(size):
            text, label = next(doc_stream)
            docs.append(text)
            y.append(label)
    except StopIteration:
        return None, None
    return docs, y

from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.linear_model import SGDClassifier


vect = HashingVectorizer(decode_error='ignore', 
                         n_features=2**21,
                         preprocessor=None, 
                         tokenizer=tokenizer)

from distutils.version import LooseVersion as Version
from sklearn import __version__ as sklearn_version

clf = SGDClassifier(loss='log_loss', random_state=1)


doc_stream = stream_docs(path='movie_data.csv')

import pyprind
pbar = pyprind.ProgBar(45)

classes = np.array([0, 1])
for _ in range(45):
    X_train, y_train = get_minibatch(doc_stream, size=1000)
    if not X_train:
        break
    X_train = vect.transform(X_train)
    clf.partial_fit(X_train, y_train, classes=classes)
    pbar.update()

0% [##############################] 100% | ETA: 00:00:00
Total time elapsed: 00:00:17

X_test, y_test = get_minibatch(doc_stream, size=5000)
X_test = vect.transform(X_test)
print(f'Accuracy: {clf.score(X_test, y_test):.3f}')

Accuracy: 0.868