import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report, confusion_matrix
df = pd.read_csv('spam.csv', encoding='latin-1')[['v1', 'v2']]
df.columns = ['label', 'text']
df['label'] = df['label'].map({'ham': 0, 'spam': 1})
X_train, X_test …

from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.svm import LinearSVC
from sklearn.metrics import classification_report, confusion_matrix
categories = ['rec.sport.baseball', 'sci.space', 'comp.graphics', 'talk.politics.mideast']  
newsgroups = fetch_20newsgroups(subset='all', categories=categories, remove=('headers', 'footers', 'quotes'))
X_train, X_test …

import pandas as pd
import csv
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, confusion_matrix

df = pd.read_csv('IMDB Dataset.csv',
    quoting=csv.QUOTE_MINIMAL,
    on_bad_lines='skip',
    encoding='utf-8')
df.head()

import pandas as pd
import numpy as np
import requests
from io import BytesIO
import re
from bs4 import BeautifulSoup
import nltk
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.metrics import accuracy_score, classification_report …