weallwegot/poets_quants_handicap

Assessing Odds of MBA Admission. Webscrape for Data Collection and some Machine Learning samples.

poets_quants_handicap's Issues

School Categorization

This code is simultaneously hilarious and terrible:

	# in progress lol, this is stupid.
	def parse_uni(self,uni_str):
		s = uni_str.upper()
		# need to rework to have this be a list that allows you to update and add more entries
		# this methodology is pretty bad. right now but ok for first pass.
		if ('IVY' in s and not 'NEAR' in s) or ('M.I.T' in s) or ('COLUMBIA' in s) or ('YALE' in s):
			return 'Tier 1'
		elif 'NEAR' in s and 'IVY' in s:
			return 'Tier 2'
		else:
			try:
				logging.warning("Not enough info to parse university: {}".format(uni_str))
			except UnicodeEncodeError:
				pass
			return 'Tier 3'

Add sleep timer for page scrapes

help to prevent ip blocking

Find out way to detect when a login is needed

Improve documentation

maybe a new repository of projects utilizing the dataset

http://scikit-learn.org/stable/modules/neighbors.html