import numpy as np #machine learning tool used for efficient array processing

import pandas as pd #machine learning tool used for data sets and data frames

from sklearn.model$\_$selection import train$\_$test$\_$split #traditional machine learning

from sklearn.feature$\_$extraction.text import TfidfVectorizer#text is converted into vectrorizeor $($numbers$)$ to feed into computer

#tf$-$how much times a term is repeated,idf$-$inverse documentry frequency$-$no of documents$/$no of documents has the term

from sklearn.linear$\_$model import PassiveAggressiveClassifier # this is for text classification

from sklearn.metrics import accuracy$\_$score, confusion$\_$matrix #for result

# Read the data

df $=$ pd$.$read$\_$csv$(\text{'}/$content$/$fake$\_$or$\_$real$\_$news.csv$\text{'})$ #reading the data and lebelling them,for accuracy

# Get shape and head

print$($df$.$shape$)$#This line prints the shape of the DataFrame df$,$ which represents the number of rows and columns in the DataFrame.

print$($df$.$head$())$# This line prints the first few rows of the DataFrame df$.$ By default, it prints the first $5$ rows

#DataFlair $-$ Get the labels

labels$=$df$.$label

labels.head$()$

class TextClassification:

def $\_\_$init$\_\_($self$,$ df$,$ labels$)$:#here we split the data into train and test so that we can see the accurcy

self.df $=$ df #df $($pandas$.$DataFrame$)$:The DataFrame containing the text data and labels.

self.labels $=$ labels #The Series containing the labels $($target variable$)$

self.x$\_$train, self.x$\_$test, self.y$\_$train, self.y$\_$test $=$ train$\_$test$\_$split$($df$[\text{'}$text$\text{'}],$ labels, test$\_$size$=0\mathrm{.}2,$ random$\_$state$=7)$# Split data into training and testing sets $(80\%$ train, $20\%$ test$)$

self.tfidf$\_$vectorizer $=$ TfidfVectorizer$($stop$\_$words$=$'english', max$\_$df$=0\mathrm{.}7)$# Create a TF$-$IDF vectorizer with English stop words removed and a maximum document frequency threshold of $0\mathrm{.}7$

self.tfidf$\_$train $=$ None

self.tfidf$\_$test $=$ None

self.pac $=$ PassiveAggressiveClassifier$($max$\_$iter$=50)$# Instantiate a PassiveAggressiveClassifier with a maximum number of iterations of $50$

def preprocess$\_$data$($self$)$:#Preprocesses the text data using TF$-$IDF vectorization.

self.tfidf$\_$train $=$ self.tfidf$\_$vectorizer.fit$\_$transform$($self$.$x$\_$train$)$

self.tfidf$\_$test $=$ self.tfidf$\_$vectorizer.transform$($self$.$x$\_$test$)$

def train$\_$model$($self$)$:#Trains the text classification model using the PassiveAggressiveClassifier.

self.pac.fit$($self$.$tfidf$\_$train, self.y$\_$train$)$

def evaluate$\_$model$($self$)$:#Evaluates the trained model's performance using accuracy and confusion matrix.

y$\_$pred $=$ self.pac.predict$($self$.$tfidf$\_$test$)$

score $=$ accuracy$\_$score$($self$.$y$\_$test, y$\_$pred$)$

print$($f$\text{'}$Accuracy: $\{$round$($score$*100,2)\}\%\text{'})$

confusion$\_$mat $=$ confusion$\_$matrix$($self$.$y$\_$test, y$\_$pred, labels$=[\text{'}$FAKE$\text{'},$ 'REAL'$])$

print$("$Confusion Matrix:"$)$

print$($confusion$\_$mat$)$

if $\_\_$name$\_\_=="\_\_$main$\_\_"$:

# Sample usage

df $=$ pd$.$read$\_$csv$(\text{'}/$content$/$fake$\_$or$\_$real$\_$news.csv$\text{'})$

labels $=$ df$[\text{'}$label$\text{'}]$

# Create an instance of TextClassification

classifier $=$ TextClassification$($df$,$ labels$)$

# Preprocess the data

classifier.preprocess$\_$data$()$

# Train the model

classifier.train$\_$model$()$

# Evaluate the model

classifier.evaluate$\_$model$()..$this is code and output screenshot for fake news detection using python pls do provide with detailed ellaborate content for Abstract

Introduction

Methodology

Results $($Results Screenshot$)$

Conclusion for this project