Merge pull request larymak#214 from Sneha2319/contribute

Added fake news detection project

Author: larymak

MachineLearning Projects/Fakenews/.DS_Store

@@ -0,0 +1,20 @@
+# 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

MachineLearning Projects/Fakenews/Fakenews.ipynb

@@ -0,0 +1,46 @@
+import numpy as np
+from flask import Flask, request,render_template
+from flask_cors import CORS
+import joblib
+import pickle
+import flask
+import os
+import newspaper
+from newspaper import Article
+import urllib.request
+import nltk
+nltk.download('punkt')
+
+#Loading Flask and assigning the model variable
+app = Flask(__name__)
+CORS(app)
+app=flask.Flask(__name__,template_folder='templates')
+
+with open('model.pickle', 'rb') as handle:
+	model = pickle.load(handle)
+
+@app.route('/')
+def main():
+    return render_template('index.html')
+
+#Receiving the input url from the user and using Web Scrapping to extract the news content
+@app.route('/predict',methods=['GET','POST'])
+def predict():
+    url =request.get_data(as_text=True)[5:]
+    url = urllib.parse.unquote(url)
+    article = Article(str(url))
+    article.download()
+    article.parse()
+    article.nlp()
+    news = article.summary
+    #Passing the news article to the model and returing whether it is Fake or Real
+    pred = model.predict([news])
+    return render_template('index.html', prediction_text='The news is "{}"'.format(pred[0]))
+    
+if __name__=="__main__":
+    port=int(os.environ.get('PORT',5000))
+    app.run(port=port,debug=True,use_reloader=False)
+
+
+
+

MachineLearning Projects/Fakenews/README.md

@@ -0,0 +1,40 @@
+#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)
+    
+