Skip to content

Instantly share code, notes, and snippets.

@rkprajapat
rkprajapat / text_processor.py
Created November 4, 2020 15:06
Text Preprocessing
import numpy as np
import multiprocessing as mp
import string
import spacy
import en_core_web_sm
from nltk.tokenize import word_tokenize
from sklearn.base import TransformerMixin, BaseEstimator
from normalise import normalise
@rkprajapat
rkprajapat / Azure_Translator_with_asyncio.py
Last active February 1, 2018 09:20
This script translates text to english using asyncio
# coding: utf-8
headers = {'Ocp-Apim-Subscription-Key': '<Your API Key>'}
import aiohttp
import asyncio
import async_timeout
from xml.etree import ElementTree
import math
import backoff
import pandas as pd
import json
def recursive(node, title=None):
leaf = {}
if type(node) == list and len(node) > 0:
# print 'Checking list', title
for item in node:
if type(item) == list or type(item) == dict:
child_leaf = recursive(item, title)
@rkprajapat
rkprajapat / contractions.txt
Last active November 22, 2016 11:12
Cleans a text corpus
{"can't" : "can not", "ren't" : " are not", "what's" : " what is|has|does", "let's" : " let us", "shan't" : " shall not", "'ll" : " will|shall", "I'm" : " I am", "won't" : " will not", "'d" : " had| would", "'re" : " are", "'ve" : " have", "n't" : " not", "'s" : " is|has"}
@rkprajapat
rkprajapat / stopwords_finder.py
Last active November 22, 2016 11:09
Stop Words finder from a text corpus. Takes dataframe series as input
# -*- coding: utf-8 -*-
"""
Created on Tue Oct 18 14:15:12 2016
@author: Roopak K Prajapat roopak.prajapat@gmail.com
"""
from __future__ import print_function
from builtins import zip
import nltk
import re
@rkprajapat
rkprajapat / jaccard_pairwise_from_gensim_corpus.py
Last active November 22, 2016 10:58
This file creates a jaccard pairwise similarity matrix from gensim corpus
# -*- coding: utf-8 -*-
"""
Created on Fri Oct 21 17:19:26 2016
@author: Roopak K Prajapat roopak.prajapat@gmail.com
"""
from __future__ import division
from __future__ import print_function
from builtins import range
from past.utils import old_div
@rkprajapat
rkprajapat / isEmpty.js
Last active November 22, 2016 10:59
This function checks whether an argument is empty or not
isEmpty = function(argument){
switch(typeof(argument)){
case "array":
if(argument.length === 0){return true;}
break;
case "object":
if(Object.keys(argument).length === 0){return true;}
break;
case "string":
if(argument.trim().length === 0){return true;}
@rkprajapat
rkprajapat / Authentication Provider for SharePoint2013
Created August 11, 2014 04:09
How to add custom authentication provider in SharePoint 2013
$root = New-Object System.Security.Cryptography.X509Certificates.X509Certificate2("path to root certificate")
New-SPTrustedRootAuthority -Name "Root" -Certificate $root
$cert = New-Object System.Security.Cryptography.X509Certificates.X509Certificate2("path to certificate provided by federation agent")
New-SPTrustedRootAuthority -Name "<authenticatino provider name>" -Certificate $cert
$upnClaimMap = New-SPClaimTypeMapping -IncomingClaimType "http://schemas.xmlsoap.org/claims/UID" -IncomingClaimTypeDisplayName "UID" -SameAsIncoming
$emailClaimMap = New-SPClaimTypeMapping -IncomingClaimType "http://schemas.xmlsoap.org/claims/EmailAddress" -IncomingClaimTypeDisplayName "EmailAddress" -SameAsIncoming
$CNClaimMap = New-SPClaimTypeMapping -IncomingClaimType "http://schemas.xmlsoap.org/claims/CommonName" -IncomingClaimTypeDisplayName "CommonName" -SameAsIncoming
$FirstNameClaimMap = New-SPClaimTypeMapping -IncomingClaimType "http://schemas.xmlsoap.org/claims/FirstName" -IncomingClaimTypeDisplayName "FirstName" -Sa