def ilp_wordification(input_dict):
target_table = input_dict.get('target_table',None)
other_tables = input_dict.get('other_tables', None)
context = input_dict.get('context', None)
word_att_length = int(input_dict.get('f_ngram_size', 1))
for _ in range(1):
wordification = Wordification(target_table,other_tables,context,word_att_length)
wordification.run(1)
wordification.calculate_tf_idfs(False)
#wordification.prune(50)
#wordification.to_arff()
#from wordification import Wordification_features_test
#wft=Wordification_features_test(target_table,other_tables,context)
#wft.print_results()
return {'arff' : wordification.to_arff(),'corpus': wordification.wordify()}
def ilp_wordification(input_dict):
target_table = input_dict.get('target_table',None)
other_tables = input_dict.get('other_tables', None)
weighting_measure = input_dict.get('weighting_measure', 'tfidf')
context = input_dict.get('context', None)
word_att_length = int(input_dict.get('f_ngram_size', 1))
idf=input_dict.get('idf', None)
for _ in range(1):
wordification = Wordification(target_table,other_tables,context,word_att_length,idf)
wordification.run(1)
wordification.calculate_tf_idfs(weighting_measure)
#wordification.prune(50)
#wordification.to_arff()
if 1==0:
from wordification import Wordification_features_test
wft=Wordification_features_test(target_table,other_tables,context)
wft.print_results()
return {'arff' : wordification.to_arff(),'corpus': wordification.wordify(),'idf':wordification.idf}
def __init__(self,target_table,other_tables,context):
self.max_witem_length=6
self.results=[]
self.feature_counts=[]
self.accuracies=[]
for prunning_percentage in [None,20,40]:
rez_a=[]
rez_c=[]
for word_att_length in range(1,self.max_witem_length):
print "percentage:",prunning_percentage,"witem:",word_att_length
pruned=Wordification(target_table,other_tables,context,word_att_length)
pruned.run()
pruned.calculate_tf_idfs("tfidf")
if prunning_percentage:
pruned.prune(prunning_percentage)
wordification_string=pruned.wordify()
rez_c.append(len(split_string_to_words(wordification_string)))
a= pruned.to_arff()
rez_a.append(get_cross_validation_accuracy(a))
self.feature_counts.append([prunning_percentage,rez_c])
self.accuracies.append([prunning_percentage,rez_a])