prafulgondane

# Stemming
from nltk.stem.porter import PorterStemmer
porter_stemmer = PorterStemmer()

def stemming(text):
  stem_text = [porter_stemmer.stem(word) for word in text]
  return stem_text

prafulgondane

# Remove stopwords from tokenized text
def remove_stopwords(text):
    output= [i for i in text if i not in stopwords[0:140]]  # after 140 indext it will don't haven't kind of words
    return output

prafulgondane

# Tokenization
def tokenization(text):
    tokens = text.split()
    return tokens

prafulgondane

# Removing punctuations like . , ! $( ) * % @

def remove_punctuation(text):
    punctuationfree="".join([i for i in text if i not in string.punctuation])
    return punctuationfree

prafulgondane

aggregation_dict = {
    'NUM_INSTALMENT_VERSION': ['nunique'],
    'NUM_INSTALMENT_VERSION': ['max'],
    'DPD': ['max', 'mean', 'median', 'sum'],
    'DBD': ['max', 'mean', 'median', 'sum'],
    'PAYMENT_PERCENTAGE': ['max', 'mean', 'median', 'sum', 'var'],
    'PAYMENT_DIFFERENCE': ['max', 'mean', 'median', 'sum', 'var'],
    'AMT_INSTALMENT': ['max', 'mean', 'median', 'sum'],
    'AMT_PAYMENT': ['min', 'max', 'mean', 'median', 'sum'],
    'DAYS_ENTRY_PAYMENT': ['max', 'mean', 'median', 'sum']