def test_db():
gl_vlist = VocabList()
log('searching directory: %s' % FEED_DIR)
for dir in os.listdir(FEED_DIR):
if '.mk4' in dir[-4:]:
log('found database: %s' % dir)
# open database
db = metakit.storage(os.path.join(FEED_DIR, dir), 0)
data = read_database(db)
if len(data) > 0:
# feed content in database
log('create library')
lib = Library()
for feed in data:
lib.add_document(read_data(feed))
vlist = lib.gen_vocablist()
vlist.clean(5)
gl_vlist.merge(vlist)
db = None # close database
print gl_vlist
def print80(text):
tmp = ''
for c in text:
tmp+=c
if len(tmp) > 80:
print(tmp)
tmp = ''
print(tmp)
def printlist(list):
for item in list:
print(item)
if __name__ == '__main__':
from nbot.document import Document, Library
q = ['file:///home/stes/dislike.html']
lib = Library()
url = q.pop(0)
page = fetch_content(url)
hrefs = get_hyperlinks(page)
q.extend(hrefs)
while q:
print 'currently %d elements in the queue' % len(q)
url = q.pop(0)
print 'getting %s' % url
page = fetch_content(url)
doc = Document(page)
lib.add_document(doc)
lib.save('res/dislike')
def train_recsys():
from nbot.document import Document, Library, VocabList, load_document
doc0 = load_document('res/sample/blubb.html')
doc1 = load_document('res/sample/page.html')
doc2 = load_document('res/sample/dislikepage.html')
lib_like = Library()
lib_like.load('res/like', False)
lib_dislike = Library()
lib_dislike.load('res/dislike', False)
like_cv = []
keys = lib_like.get_keys()
shuffle(keys)
for key in keys[:5]:
like_cv.append(lib_like.rmv_document(key))
dislike_cv = []
keys = lib_dislike.get_keys()
shuffle(keys)
for key in keys[:5]:
dislike_cv.append(lib_dislike.rmv_document(key))
vlist_like = lib_like.gen_vocablist()
vlist_dislike = lib_dislike.gen_vocablist()
vlist_like.clean(10)
vlist_dislike.clean(10)
like_mask = vlist_like.gen_mask()
dislike_mask = vlist_dislike.gen_mask()
mask = []
mask.extend(like_mask)
mask.extend(dislike_mask)
rsys = RecommenderSystem(mask, len(mask))
for key in lib_like.get_keys():
doc = lib_like.get_document(key)
rsys.set_rate(doc.content(), 1.)
for key in lib_dislike.get_keys():
doc = lib_dislike.get_document(key)
rsys.set_rate(doc.content(), 0.)
rsys.train(10000000, 0.1)
likes = lib_like.get_keys()
shuffle(likes)
for key in likes[:5]:
doc = lib_like.get_document(key)
print rsys.rate(doc.content())
dislikes = lib_dislike.get_keys()
shuffle(dislikes)
for key in dislikes[:5]:
doc = lib_dislike.get_document(key)
print rsys.rate(doc.content())
print '---------------------------------------'
print rsys.rate(doc0.content())
print rsys.rate(doc1.content())
print rsys.rate(doc2.content())
print '---------------------------------------'
print 'CV data'
print '(1) LIKE'
for doc in like_cv:
print rsys.rate(doc.content())
print '(2) DISLIKE'
for doc in dislike_cv:
print rsys.rate(doc.content())
# This seems to work, however, more training/cv data will be necessary!
print '---------------------------------------'
return rsys
[X, Y] = self.__gen_matrix()
self.__lreg.train(iterations, learnrate, X, Y)
def __gen_matrix(self):
return [ array(self.__training_set), array(self.__ratings) ]
if __name__ == '__main__':
# some tests
from nbot.document import Document, Library, VocabList
doc0 = load_document('res/sample/blubb.html')
doc1 = load_document('res/sample/page.html')
doc2 = load_document('res/sample/dislikepage.html')
lib_like = Library()
lib_like.load('res/like', False)
lib_dislike = Library()
lib_dislike.load('res/dislike', False)
like_cv = []
keys = lib_like.get_keys()
shuffle(keys)
for key in keys[:5]:
like_cv.append(lib_like.rmv_document(key))
dislike_cv = []
keys = lib_dislike.get_keys()
shuffle(keys)
for key in keys[:5]:
dislike_cv.append(lib_dislike.rmv_document(key))
