Fakenews

Introduction

This is a machine learning project that determines fake news through the url of the news.

Project Structre

This project has four major parts :

• fake_news_detection.py - This contains code fot our Machine Learning model to classify the model
• app.py - This contains Flask APIs that receives news url through GUI or API calls, extracts the article from the url, feeds it to the model and returns the prediction.
• templates - This folder contains the HTML template to allow user to enter url and displays whether the news is fake or real.
• static - This folder contains the CSS file.

Running the project on local machine

Ensure that you are in the project home directory.

Run app.py using below command to start Flask API python app.py By default, flask will run on port 5000.

Navigate to URL http://127.0.0.1:5000

Source Code: fake_news_detection.py

#Importing the libraries
import pandas as pd
import numpy as np
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfVectorizer
import pickle

#Importing the cleaned file containing the text and label
news = pd.read_csv('news.csv')
X = news['text']
y = news['label']




#Splitting the data into train
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

#Creating a pipeline that first creates bag of words(after applying stopwords) & then applies Multinomial Naive Bayes model
pipeline = Pipeline([('tfidf', TfidfVectorizer(stop_words='english')),
                    ('nbmodel', MultinomialNB())])

#Training our data
pipeline.fit(X_train, y_train)

#Predicting the label for the test data
pred = pipeline.predict(X_test)

#Checking the performance of our model
print(classification_report(y_test, pred))
print(confusion_matrix(y_test, pred))

#Serialising the file
with open('model.pickle', 'wb') as handle:
    pickle.dump(pipeline, handle, protocol=pickle.HIGHEST_PROTOCOL)