def transform_thread(n_processors):
queries = {}
dictionary = load_doc_hashes("doc_mapper.txt")
with open("doc_model2.pickle") as f:
doc_model = pickle.load(f)
M = doc_model.M
b = doc_model.b
model = models.Word2Vec.load("content.word2vec")
dim = len(model[model.vocab.keys()[0]])
R = io.mmread("R_old.mtx").T
files = sorted(glob.glob(os.getcwd() + "/feature_*"))
signals = Parallel(n_jobs=n_processors)(delayed(transform_to_signal)(fname,queries,dictionary,M,b,model,dim,R) for fname in files)
return signals
__author__ = 'Martin'
from doc2vec.doc_to_vec import load_doc_hashes
from doc2vec.doc_to_vec import MySentences
class MyWords(MySentences):
def __init__(self,fname):
self.fname = fname
def __iter__(self):
with open(self.fname) as f:
for line in f:
yield line
if __name__ == "__main__":
features = MyWords("temp_features.rtData")
documents = [line for line in open("content.raw_text")]
docs = load_doc_hashes("doc_mapper.txt")
rows = []
for row in features:
parse_row = row.split("#",1)
metadata_array = parse_row[1].strip().split('\t')
qid = parse_row[0].strip().split(':', 1)[1].split(' ',1)[0]
hash = metadata_array[2]
rows.append(documents[docs[hash]])
with open("temp_all.raw_text","w") as f:
for r in rows:
f.write(r)
f.write("\n")
from doc2vec.doc_to_vec import load_doc_hashes
from doc2vec.doc_to_vec import MySentences
class MyWords(MySentences):
def __init__(self, fname):
self.fname = fname
def __iter__(self):
with open(self.fname) as f:
for line in f:
yield line
if __name__ == "__main__":
features = MyWords("temp_features.rtData")
documents = [line for line in open("content.raw_text")]
docs = load_doc_hashes("doc_mapper.txt")
rows = []
for row in features:
parse_row = row.split("#", 1)
metadata_array = parse_row[1].strip().split("\t")
qid = parse_row[0].strip().split(":", 1)[1].split(" ", 1)[0]
hash = metadata_array[2]
rows.append(documents[docs[hash]])
with open("temp_all.raw_text", "w") as f:
for r in rows:
f.write(r)
f.write("\n")
