vinovator

# nltk_name_classifier.py
# Python 2.7.6

"""
Classifier to determine the gender of a name using NLTK library

Classification - task of choosing the correct class label for a given input.

Supervised classifier:
Classifier that is built on training corpora containing the correct label

vinovator

# crawler.py
# Python 2.7.6


"""
Crawl a page and extract all urls recursively within same domain
"""


from BeautifulSoup import BeautifulSoup

vinovator

# mailbot.py
# python 2.7.6

"""
Mail bot sript that sends predefined response to predefined mails
Intended for raspberry pi, which has its dedicated mail id

Algorithm
1) Check a dedicated mailbox inbox for "unread" mails
2) For each "unread" mail, fetch the sender, subject and content

vinovator

# uk_mba.py
# Python 2.7.6

"""
Extract business schools in UK with AACSB, AMBA and/or EQUIS accredition only
Scapring from http://find-mba.com/
"""

import requests
from BeautifulSoup import BeautifulSoup

vinovator

# mongo_test_restaurants.py
# Python 2.7.6

"""
Test script to connect to MongoDB collections using pymongo library
Connects to an already imported connection named "restaurants"
source - https://docs.mongodb.org/getting-started/python/
"""

from pymongo import MongoClient, ASCENDING, DESCENDING

vinovator

# world_t20_itinerary.py
# Python 2.7.6

"""
Scrap Workd T20 schedule from ICC website using BeautifulSoup & Requests
Load the schedule into an excel file using pandas
Format the excel file using openpyxl
- Apply border, wrap text and color headers
- Highlight India matches
"""

vinovator

# Python 2.7.6
# PdfAdapter.py

""" Reusable library to extract text from pdf file
Uses pdfminer library; For Python 3.x use pdfminer3k module
Below links have useful information on components of the program
https://euske.github.io/pdfminer/programming.html
http://denis.papathanasiou.org/posts/2010.08.04.post.html
"""

vinovator

# tk_PromptPassword.py
# Python 2.7.6

"""
Reusable library which pops tkinter window to prompt password
"""

import Tkinter as tk
import tkMessageBox as tkm  # To show warning/ error messages
import logging

vinovator

# imapMailboxMiner.py
# Python 2.7.6

"""
Connect to IMAP4 server and fetch mails
http://www.voidynullness.net/blog/2013/07/25/gmail-email-with-python-via-imap/
"""

import imaplib  # Library to interact with IMPAP server
import sys

vinovator

# checkDuplicates.py
# Python 2.7.6

"""
Given a folder, walk through all files within the folder and subfolders
and get list of all files that are duplicates
The md5 checcksum for each file will determine the duplicates
"""

import os