In [3]:

    

"""word cloud"""

from __future__ import print_function
warned_of_error = False

def create_cloud(oname, words, maxsize=120, fontname='Lobster'):
    '''Creates a word cloud (when pytagcloud is installed)

    Parameters
    ----------
    oname : output filename
    words : list of (value,str)
    maxsize : int, optional
        Size of maximum word. The best setting for this parameter will often
        require some manual tuning for each input.
    fontname : str, optional
        Font to use.
    '''
    try:
        from pytagcloud import create_tag_image, make_tags
    except ImportError:
        if not warned_of_error:
            print("Could not import pytagcloud. Skipping cloud generation")
        return

    # gensim returns a weight between 0 and 1 for each word, while pytagcloud
    # expects an integer word count. So, we multiply by a large number and
    # round. For a visualization this is an adequate approximation.
    # We also need to flip the order as gensim returns (value, word), whilst
    # pytagcloud expects (word, value):
    words = [(w,int(v*10000)) for v,w in words]
    tags = make_tags(words, maxsize=maxsize)
    create_tag_image(tags, oname, size=(1800, 1200), fontname=fontname)


    

In [ ]:

    

"""Modeling the whole of wikipedia"""