Text Vectorizer

xxxxxxxxxx

 

1

from sklearn.feature_extraction.text import CountVectorizer

2

corpus=['Have you already set your goals for the New Year?', 

3

        'Do you want to lose ten kilos, '+\

4

        'run a marathon or speak fluent English?', 

5

        'Some experts believe that you need systems, not goals.', 

6

        'A system is something you do on a regular basis. ',

7

        'This means focusing on what you can control '+\

8

        '(your actions) rather than what you can’t.',

9

        'For example, do not focus on losing ten kilos.',

10

        'Focus on shopping for healthy food and '+\

11

        'cooking something light every day.',

12

        'Do not focus on the marathon.',

13

        'Focus on the training schedule.',

14

        'Invent a system to improve your English, '+\

15

        'one step at a time.',

16

        'Good luck!']

17

c_vectorizer=CountVectorizer(min_df=1)

18

corpus_features=c_vectorizer.fit_transform(corpus)

19

corpus_array=corpus_features.toarray().astype('int16')

20

c_analyzer=c_vectorizer.build_analyzer()

21

import pylab as pl; pl.figure(figsize=(6,5))

22

pl.title('Word Occurrences in Sentences',fontsize=12)

23

for i in range(len(corpus_array)):

24

    pl.scatter(range(len(corpus_array[i])),

25

               (corpus_array[i]*.5+i),marker='*')

26

pl.tight_layout(); pl.grid(); pl.show()

Language: Sage Gap GP HTML Macaulay2 Maxima Octave Python R Singular

---

Messages