In [2]:
%load_ext watermark
%watermark -d -v -m -p wordcloud,pandas,scipy,matplotlib


The watermark extension is already loaded. To reload it, use:
  %reload_ext watermark
02/12/2014 

CPython 2.7.8
IPython 2.3.0

wordcloud 1.0.0
pandas 0.13.1
scipy 0.13.3
matplotlib 1.3.1

compiler   : GCC 4.2.1 (Apple Inc. build 5577)
system     : Darwin
release    : 14.0.0
machine    : x86_64
processor  : i386
CPU cores  : 4
interpreter: 64bit

In [5]:
import pandas as pd
df = pd.read_csv('./train_lyrics_1000.csv')
lyrics = ' '.join(df['lyrics'])

In [6]:
%matplotlib inline

In [14]:
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS

from scipy.misc import imread

mask = imread('./musicnote.png', flatten=True)


wordcloud = WordCloud( 
                      font_path='/Users/sebastian/Library/Fonts/ufonts.com_flux.ttf',
                      stopwords=STOPWORDS.add('nigga'),
                      background_color='white',
                      width=2400,
                      height=1800,
                      mask=mask
                     ).generate(lyrics)

plt.imshow(wordcloud)
plt.axis('off')
plt.savefig('./lyrics_cloud.png', dpi=300)
plt.show()



In [ ]: