This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import unicodedata | |
""" Normalise (normalize) unicode data in Python to remove umlauts, accents etc. """ | |
data = u'naïve café' | |
normal = unicodedata.normalize('NFKD', data).encode('ASCII', 'ignore') | |
print normal | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import unittest, os, os.path, sys, urllib | |
import tornado.database | |
import tornado.options | |
from tornado.options import options | |
from tornado.testing import AsyncHTTPTestCase | |
# add application root to sys.path | |
APP_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), '..')) | |
sys.path.append(os.path.join(APP_ROOT, '..')) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Path to your oh-my-zsh configuration. | |
export ZSH=$HOME/.oh-my-zsh | |
# Set name of the theme to load. | |
# Look in ~/.oh-my-zsh/themes/ | |
# Optionally, if you set this to "random", it'll load a random theme each | |
# time that oh-my-zsh is loaded. | |
#export ZSH_THEME="robbyrussell" | |
export ZSH_THEME="zanshin" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import numpy | |
from nltk.cluster import KMeansClusterer, GAAClusterer, euclidean_distance | |
import nltk.corpus | |
from nltk import decorators | |
import nltk.stem | |
stemmer_func = nltk.stem.EnglishStemmer().stem | |
stopwords = set(nltk.corpus.stopwords.words('english')) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def map_feature(x1, x2): | |
''' | |
Maps the two input features to quadratic features. | |
Returns a new feature array with more features, comprising of | |
X1, X2, X1 ** 2, X2 ** 2, X1*X2, X1*X2 ** 2, etc... | |
Inputs X1, X2 must be the same size | |
''' | |
x1.shape = (x1.size, 1) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from numpy import loadtxt, where, zeros, e, array, log, ones, append, linspace | |
from pylab import scatter, show, legend, xlabel, ylabel, contour, title | |
from scipy.optimize import fmin_bfgs | |
def sigmoid(X): | |
'''Compute the sigmoid function ''' | |
#d = zeros(shape=(X.shape)) | |
den = 1.0 + e ** (-1.0 * X) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import getopt | |
import sys | |
from sqlalchemy import create_engine, MetaData, Table | |
from sqlalchemy.dialects.mysql.base import TINYINT | |
from sqlalchemy.orm import sessionmaker | |
from sqlalchemy.ext.declarative import declarative_base | |
from sqlalchemy.exc import ProgrammingError |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
auth = OAuthHandler(CLIENT_ID, CLIENT_SECRET, CALLBACK) | |
auth.set_access_token(ACCESS_TOKEN) | |
api = API(auth) | |
venue = api.venues(id='4bd47eeb5631c9b69672a230') | |
stopwords = nltk.corpus.stopwords.words('portuguese') | |
tokenizer = RegexpTokenizer("[\w’]+", flags=re.UNICODE) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#-*- coding: utf-8 -*- | |
import re | |
import nltk | |
from nltk.tokenize import RegexpTokenizer | |
from nltk import bigrams, trigrams | |
import math | |
stopwords = nltk.corpus.stopwords.words('portuguese') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#-*- coding: utf-8 -*- | |
import re | |
import nltk | |
from nltk.tokenize import RegexpTokenizer | |
from nltk import bigrams, trigrams | |
import math | |
stopwords = nltk.corpus.stopwords.words('portuguese') |
OlderNewer