DataPreparation.py

"""
@author: Anshul Srivastava
"""
#import os
import pandas as pd
import csv
import numpy as np
import nltk
from nltk.stem import SnowballStemmer
from nltk.stem.porter import PorterStemmer
from nltk.tokenize import word_tokenize
import seaborn as sb

#before reading the files, setup the working directory to point to project repo
#reading data files 


test_filename = 'test.csv'
train_filename = 'train.csv'
valid_filename = 'valid.csv'

train_news = pd.read_csv(train_filename)
test_news = pd.read_csv(test_filename)
valid_news = pd.read_csv(valid_filename)



#data observation
def data_obs():
    print("training dataset size:")
    print(train_news.shape)
    print(train_news.head(10))

    #below dataset were used for testing and validation purposes
    print(test_news.shape)
    print(test_news.head(10))
    
    print(valid_news.shape)
    print(valid_news.head(10))

#check the data by calling below function
#data_obs()

#distribution of classes for prediction
def create_distribution(dataFile):
    
    return sb.countplot(x='Label', data=dataFile, palette='hls')
    

#by calling below we can see that training, test and valid data seems to be failry evenly distributed between the classes
create_distribution(train_news)
create_distribution(test_news)
create_distribution(valid_news)


#data integrity check (missing label values)
#none of the datasets contains missing values therefore no cleaning required
def data_qualityCheck():
    
    print("Checking data qualitites...")
    train_news.isnull().sum()
    train_news.info()
        
    print("check finished.")

    #below datasets were used to 
    test_news.isnull().sum()
    test_news.info()

    valid_news.isnull().sum()
    valid_news.info()

#run the below function call to see the quality check results
#data_qualityCheck()



#eng_stemmer = SnowballStemmer('english')
#stopwords = set(nltk.corpus.stopwords.words('english'))

#Stemming
def stem_tokens(tokens, stemmer):
    stemmed = []
    for token in tokens:
        stemmed.append(stemmer.stem(token))
    return stemmed

#process the data
def process_data(data,exclude_stopword=True,stem=True):
    tokens = [w.lower() for w in data]
    tokens_stemmed = tokens
    tokens_stemmed = stem_tokens(tokens, eng_stemmer)
    tokens_stemmed = [w for w in tokens_stemmed if w not in stopwords ]
    return tokens_stemmed


#creating ngrams
#unigram 
def create_unigram(words):
    assert type(words) == list
    return words

#bigram
def create_bigrams(words):
    assert type(words) == list
    skip = 0
    join_str = " "
    Len = len(words)
    if Len > 1:
        lst = []
        for i in range(Len-1):
            for k in range(1,skip+2):
                if i+k < Len:
                    lst.append(join_str.join([words[i],words[i+k]]))
    else:
        #set it as unigram
        lst = create_unigram(words)
    return lst

"""
#trigrams
def create_trigrams(words):
    assert type(words) == list
    skip == 0
    join_str = " "
    Len = len(words)
    if L > 2:
        lst = []
        for i in range(1,skip+2):
            for k1 in range(1, skip+2):
                for k2 in range(1,skip+2):
                    for i+k1 < Len and i+k1+k2 < Len:
                        lst.append(join_str.join([words[i], words[i+k1],words[i+k1+k2])])
        else:
            #set is as bigram
            lst = create_bigram(words)
    return lst
"""


porter = PorterStemmer()

def tokenizer(text):
    return text.split()


def tokenizer_porter(text):
    return [porter.stem(word) for word in text.split()]

#doc = ['runners like running and thus they run','this is a test for tokens']
#tokenizer([word for line in test_news.iloc[:,1] for word in line.lower().split()])

#show the distribution of labels in the train and test data
"""def create_datafile(filename)
    #function to slice the dataframe to keep variables necessary to be used for classification
    return "return df to be used"
"""
    
"""#converting multiclass labels present in our datasets to binary class labels
for i , row in data_TrainNews.iterrows():
    if (data_TrainNews.iloc[:,0] == "mostly-true" | data_TrainNews.iloc[:,0] == "half-true" | data_TrainNews.iloc[:,0] == "true"):
        data_TrainNews.iloc[:,0] = "true"
    else :
        data_TrainNews.iloc[:,0] = "false"
        
for i,row in data_TrainNews.iterrows():
    print(row)
"""