Nempickaxe

import re
import nltk
import emoji
from nltk.tokenize import word_tokenize

def tokenize(corpus):
    data = re.sub(r'[,!?;-]+', '.', corpus)
    data = nltk.word_tokenize(data)  # tokenize string to words
    data = [ ch.lower() for ch in data
             if ch.isalpha()

Nempickaxe

import textwrap
import PIL
from PIL import ImageFont
from PIL import Image
from PIL import ImageDraw

def text2png(text, fullpath, color = "#000", bgcolor = "#FFF", fontfullpath = None, fontsize = 13, leftpadding = 3, rightpadding = 3, width = 2000):
    REPLACEMENT_CHARACTER = '\uFFFD'
    NEWLINE_REPLACEMENT_STRING = ' ' + REPLACEMENT_CHARACTER + ' '

Nempickaxe

def get_lower_tri_heatmap(df, output="cooc_matrix.png"):
    mask = np.zeros_like(df, dtype=np.bool)
    mask[np.triu_indices_from(mask)] = True

    # Want diagonal elements as well
    mask[np.diag_indices_from(mask)] = False

    # Set up the matplotlib figure
    f, ax = plt.subplots(figsize=(11, 9))

Nempickaxe

Keybase proof

I hereby claim:

• I am nempickaxe on github.
• I am ilaichi (https://keybase.io/ilaichi) on keybase.
• I have a public key ASC0peYsZX_Z7LwCfPjY9FJz_772TLP9XsoLON6QsTED-go

To claim this, I am signing this object:

Nempickaxe

import nltk
from nltk.tokenize import WordPunctTokenizer
from nltk.collocations import BigramCollocationFinder
from nltk.metrics import BigramAssocMeasures
from nltk.corpus import stopwords
nltk.download('stopwords')
from nltk.collocations import TrigramCollocationFinder
from nltk.metrics import TrigramAssocMeasures

from collections import Counter

Nempickaxe

import dbm, os
import cPickle as pickle
from gensim.models import Word2Vec
import numpy as np

def save_model(model, directory):
    model.init_sims() # making sure syn0norm is initialised
    if not os.path.exists(directory):
        os.makedirs(directory)
    # Saving indexes as DBM'ed dictionary