pacnpal/twitter_ebooks
1
0
Fork 0
mirror of https://github.com/thewesker/twitter_ebooks.git synced 2025-12-22 21:31:06 -05:00
Code Issues Packages Projects Releases Wiki Activity

consume multiple corpuses

Browse Source
This commit is contained in:
Geoffroy Couprie
2014-10-29 18:56:37 +01:00
parent 9731575a3d
commit 2698963fb1
2 changed files with 66 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
bin/ebooks
View File

@@ -62,6 +62,32 @@ STR
end
end
def self.consume_all(name, paths)
usage = <<STR
Usage: ebooks consume-all <name> <corpus_path> [corpus_path2] [...]
Processes some number of text files or json tweet corpuses
into one usable model. It will be output at model/<name>.model
STR
if paths.empty?
log usage
exit
end
outpath = File.join(APP_PATH, 'model', "#{name}.model")
#pathes.each do |path|
# filename = File.basename(path)
# shortname = filename.split('.')[0..-2].join('.')
#
# outpath = File.join(APP_PATH, 'model', "#{shortname}.model")
# Model.consume(path).save(outpath)
# log "Corpus consumed to #{outpath}"
#end
Model.consume_all(paths).save(outpath)
log "Corpuses consumed to #{outpath}"
end
def self.gen(model_path, input)
usage = <<STR
Usage: ebooks gen <model_path> [input]
@@ -187,6 +213,7 @@ STR
Usage:
ebooks new <reponame>
ebooks consume <corpus_path> [corpus_path2] [...]
ebooks consume-all <corpus_path> [corpus_path2] [...]
ebooks gen <model_path> [input]
ebooks score <model_path> <input>
ebooks archive <@user> <outpath>
@@ -202,6 +229,7 @@ STR
case args[0]
when "new" then new(args[1])
when "consume" then consume(args[1..-1])
when "consume-all" then consume_all(args[1], args[2..-1])
when "gen" then gen(args[1], args[2..-1].join(' '))
when "score" then score(args[1], args[2..-1].join(' '))
when "archive" then archive(args[1], args[2])