Scribd
Upload
44 views7 pages

FakeNewsDetection Student

This document contains code to analyze a dataset of fake and real news articles using various machine learning classifiers. It loads and preprocesses the data, explores the data distribution, and defines functions for splitting the data, fitting classifiers, and plotting confusion matrices. It then fits and evaluates the performance of a Naive Bayes classifier on the preprocessed data, storing the accuracy in a dictionary to later compare models. The document is setting up further classification experiments with logistic regression, decision trees, random forests, and SVMs.

Uploaded by

nehaila
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
44 views7 pages

FakeNewsDetection Student

This document contains code to analyze a dataset of fake and real news articles using various machine learning classifiers. It loads and preprocesses the data, explores the data distribution, and defines functions for splitting the data, fitting classifiers, and plotting confusion matrices. It then fits and evaluates the performance of a Naive Bayes classifier on the preprocessed data, storing the accuracy in a dictionary to later compare models. The document is setting up further classification experiments with logistic regression, decision trees, random forests, and SVMs.

Uploaded by

nehaila
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 7

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn.feature_extraction.text import CountVectorizer

from sklearn.feature_extraction.text import TfidfTransformer

from sklearn import feature_extraction, linear_model, model_selection,


preprocessing

from sklearn.metrics import accuracy_score

from sklearn.model_selection import train_test_split

from sklearn.pipeline import Pipeline

from sklearn.utils import shuffle

import string

# ## Read datasets

fake = pd.read_csv("data/Fake.csv")

true = pd.read_csv("data/True.csv")

fake.shape

true.shape

# Add flag to track fake and real

fake['target'] = 'fake'

true['target'] = 'true'

# Concatenate dataframes

data = pd.concat([fake, true]).reset_index(drop = True)

data.shape

# Shuffle the data


data = shuffle(data)

data = data.reset_index(drop=True)

# Check the data

data.head()

# Removing the date (we won't use it for the analysis)

data.drop(["date"],axis=1,inplace=True)

data.head()

# Removing the title (we will only use the text)

data.drop(["title"],axis=1,inplace=True)

data.head()

# Convert to lowercase

data['text'] = data['text'].apply(lambda x: x.lower())

data.head()

# Remove punctuation

#Insert code

data['text'] = data['text'].apply(punctuation_removal)

# Check

data.head()

# Removing stopwords
#Insert code

data.head()

# ## Basic data exploration

# How many articles per subject?

print(data.groupby(['subject'])['text'].count())

data.groupby(['subject'])['text'].count().plot(kind="bar")

plt.show()

# In[17]:

# How many fake and real articles?

print(data.groupby(['target'])['text'].count())

data.groupby(['target'])['text'].count().plot(kind="bar")

plt.show()

# Most frequent words counter (Code adapted from


https://www.kaggle.com/rodolfoluna/fake-news-detector)

from nltk import tokenize

token_space = tokenize.WhitespaceTokenizer()

def counter(text, column_text, quantity):

all_words = ' '.join([text for text in text[column_text]])

token_phrase = token_space.tokenize(all_words)
frequency = nltk.FreqDist(token_phrase)

df_frequency = pd.DataFrame({"Word": list(frequency.keys()),

"Frequency": list(frequency.values())})

df_frequency = df_frequency.nlargest(columns = "Frequency", n = quantity)

plt.figure(figsize=(12,8))

ax = sns.barplot(data = df_frequency, x = "Word", y = "Frequency", color =


'blue')

ax.set(ylabel = "Count")

plt.xticks(rotation='vertical')

plt.show()

# Most frequent words in fake news

counter(data[data["target"] == "fake"], "text", 20)

# Most frequent words in real news

counter(data[data["target"] == "true"], "text", 20)

# ### Peparing the data

# Split the data

#Insert code

# ## Modeling

# Function to plot the confusion matrix (code from


https://scikit-learn.org/stable/auto_examples/model_selection/plot_confusion_matrix
.html)

from sklearn import metrics

import itertools

def plot_confusion_matrix(cm, classes,


normalize=False,

title='Confusion matrix',

cmap=plt.cm.Blues):

plt.imshow(cm, interpolation='nearest', cmap=cmap)

plt.title(title)

plt.colorbar()

tick_marks = np.arange(len(classes))

plt.xticks(tick_marks, classes, rotation=45)

plt.yticks(tick_marks, classes)

if normalize:

cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]

print("Normalized confusion matrix")

else:

print('Confusion matrix, without normalization')

thresh = cm.max() / 2.

for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):

plt.text(j, i, cm[i, j],

horizontalalignment="center",

color="white" if cm[i, j] > thresh else "black")

plt.tight_layout()

plt.ylabel('True label')

plt.xlabel('Predicted label')
# # **Naive Bayes**

print("------Naive Bayes-----")

dct = dict()

from sklearn.naive_bayes import MultinomialNB

NB_classifier = MultinomialNB()

pipe = Pipeline([('vect', CountVectorizer()),

('tfidf', TfidfTransformer()),

('model', NB_classifier)])

model = pipe.fit(X_train, y_train)

prediction = model.predict(X_test)

print("accuracy: {}%".format(round(accuracy_score(y_test, prediction)*100,2)))

dct['Naive Bayes'] = round(accuracy_score(y_test, prediction)*100,2)

cm = metrics.confusion_matrix(y_test, prediction)

plot_confusion_matrix(cm, classes=['Fake', 'Real'])

# # **Logistic regression**

# # **Decision Tree**
# # **Random Forest**

# ## **SVM**

# # **Comparing** **Different Models**

import matplotlib.pyplot as plt

plt.figure(figsize=(8,7))

plt.bar(list(dct.keys()),list(dct.values()))

plt.ylim(90,100)

plt.yticks((91, 92, 93, 94, 95, 96, 97, 98, 99, 100))

plt.show()

You might also like