
import pandas as pd
import numpy as np
import nltk
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score


# Load the BBC News dataset
df = pd.read_csv(r"C:\Users\ahlad\Downloads\bbc-text.csv.zip")
df


# Preprocess the text data
nltk.download('stopwords')
stop_words = set(stopwords.words('english'))
ps = PorterStemmer()
df['text'] = df['text'].apply(lambda x: ' '.join([ps.stem(word) for word in x.split() if word.lower() not in stop_words]))

[nltk_data] Downloading package stopwords to
[nltk_data]     C:\Users\ahlad\AppData\Roaming\nltk_data...
[nltk_data]   Package stopwords is already up-to-date!


# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(df['text'], df['category'], test_size=0.2, random_state=42)


# Convert the text data into numerical form using TF-IDF vectorization
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(X_train)
X_test = vectorizer.transform(X_test)


# Train a Naive Bayes classifier on the training data
clf = MultinomialNB()
clf.fit(X_train, y_train)

MultinomialNB()


# Evaluate the performance of the classifier on the testing data
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')


print("Accuracy:", accuracy)
print("Precision:", precision)
print("Recall:", recall)
print("F1 Score:", f1)

Accuracy: 0.9573033707865168
Precision: 0.9588842437695448
Recall: 0.9573033707865168
F1 Score: 0.9571039269250978

	category	text
0	tech	tv future in the hands of viewers with home th...
1	business	worldcom boss left books alone former worldc...
2	sport	tigers wary of farrell gamble leicester say ...
3	sport	yeading face newcastle in fa cup premiership s...
4	entertainment	ocean s twelve raids box office ocean s twelve...
...	...	...
2220	business	cars pull down us retail figures us retail sal...
2221	politics	kilroy unveils immigration policy ex-chatshow ...
2222	entertainment	rem announce new glasgow concert us band rem h...
2223	politics	how political squabbles snowball it s become c...
2224	sport	souness delight at euro progress boss graeme s...

ASSIGNMENT - 12¶

1. Text Classification of News Articles using NLP.¶