from util import precision_at_k
import sys
DIMENSION = 20
cs_vectors = KeyedVectors.load_word2vec_format("./bi2vec_vectors/cs_vectors_11_20.txt",binary=False)
java_vectors = KeyedVectors.load_word2vec_format("./bi2vec_vectors/java_vectors_11_20.txt",binary=False)
with open("./sentences/sentences_cs_11.txt","r") as cs_f:
cs_data = cs_f.readlines()
with open("./sentences/sentences_java_11.txt","r") as java_f:
java_data = java_f.readlines()
cs_sentences = [x for x in cs_data]
java_sentences = [x for x in java_data]
cs_word2weight = word2weight(cs_sentences)
java_word2weight = word2weight(java_sentences)
with codecs.open("./evaluation_data/keywords.csv","r") as f_csv:
reader = csv.reader(f_csv)
java_keywords = list()
cs_keywords = list()
mapping_java = {}
mapping_cs = {}
for i,row in enumerate(reader):
if i != 0:
# print "#########################"
expr_cs = row[1].strip("\"")
expr_java = row[2].strip("\"")
java_keywords.append(expr_java)
java_vectors = KeyedVectors.load_word2vec_format(
"./bi2vec_vectors/java_vectors_11_25.txt", binary=False)
# cs_vectors = KeyedVectors.load_word2vec_format("./bi2vec_vectors/cs_vectors_10_25_include_functions.txt",binary=False)
# java_vectors = KeyedVectors.load_word2vec_format("./bi2vec_vectors/java_vectors_10_25_include_functions.txt",binary=False)
smallprojects = ["factual", "mongodb", "log4j", "datastax"]
with open("./sentences/sentences_cs_11.txt", "r") as cs_f:
cs_data = cs_f.readlines()
with open("./sentences/sentences_java_11.txt", "r") as java_f:
java_data = java_f.readlines()
cs_sentences = [x for x in cs_data]
java_sentences = [x for x in java_data]
cs_word2weight = word2weight(cs_sentences)
java_word2weight = word2weight(java_sentences)
def get_random_range(project):
if project == "fpml":
return 527
if project == "antlr":
return 2019
if project == "factual":
return 95
if project == "lucene":
return 7720
if project == "mongodb":
return 65
if project == "spring":