Show More
@@ -17,6 +17,11 from IPython.parallel import Client, Reference | |||
|
17 | 17 | |
|
18 | 18 | from __future__ import division |
|
19 | 19 | |
|
20 | try : #python2 | |
|
21 | from urllib import urlretrieve | |
|
22 | except : #python3 | |
|
23 | from urllib.request import urlretrieve | |
|
24 | ||
|
20 | 25 | davinci_url = "http://www.gutenberg.org/cache/epub/5000/pg5000.txt" |
|
21 | 26 | |
|
22 | 27 | def pwordfreq(view, fnames): |
@@ -47,11 +52,7 if __name__ == '__main__': | |||
|
47 | 52 | if not os.path.exists('davinci.txt'): |
|
48 | 53 | # download from project gutenberg |
|
49 | 54 | print("Downloading Da Vinci's notebooks from Project Gutenberg") |
|
50 | try : #python2 | |
|
51 | urllib.urlretrieve(davinci_url, 'davinci.txt') | |
|
52 | except : #python3 | |
|
53 | import urllib.request | |
|
54 | urllib.request.urlretrieve(davinci_url, 'davinci.txt') | |
|
55 | urlretrieve(davinci_url, 'davinci.txt') | |
|
55 | 56 | |
|
56 | 57 | # Run the serial version |
|
57 | 58 | print("Serial word frequency count:") |
@@ -60,7 +61,7 if __name__ == '__main__': | |||
|
60 | 61 | freqs = wordfreq(text) |
|
61 | 62 | toc = time.time() |
|
62 | 63 | print_wordfreq(freqs, 10) |
|
63 |
print("Took %.3f s to calc |
|
|
64 | print("Took %.3f s to calculate"%(toc-tic)) | |
|
64 | 65 | |
|
65 | 66 | |
|
66 | 67 | # The parallel version |
@@ -84,6 +85,6 if __name__ == '__main__': | |||
|
84 | 85 | pfreqs = pwordfreq(view,fnames) |
|
85 | 86 | toc = time.time() |
|
86 | 87 | print_wordfreq(freqs) |
|
87 |
print("Took %.3f s to calc |
|
|
88 | print("Took %.3f s to calculate on %i engines"%(toc-tic, len(view.targets))) | |
|
88 | 89 | # cleanup split files |
|
89 | 90 | map(os.remove, fnames) |
General Comments 0
You need to be logged in to leave comments.
Login now