import numpy as np import pickle from datetime import datetime import sys, os path = "data/X" if 0: from Xtraction3 import extractXY # extract features path2docs = "../../feats/both/" path2rlvnce = "../../gt/rGT/" # create dict word number and X X = extractXY(path2docs, path2rlvnce) with open(path, 'wb') as AutoPickleFile: pickle.dump((X), AutoPickleFile) else: with open(path, 'rb') as AutoPickleFile: X = pickle.load(AutoPickleFile) # divide set allQueries = X.keys() allQueries = sorted(allQueries) # seed rnd_seed = "stay" seed(rnd_seed) shuffle(allQueries) # for seed k = 10 testQueries = allQueries[1::k] queries = list(set(allQueries) - set(testQueries))
import numpy as np import pickle from datetime import datetime import sys, os #path = "data/X_test_all_1" path = "data/lh" if 1: from Xtraction3 import extractXY # extract features path2docs = "../../feats/both2/" # create dict word number and X X = extractXY(path2docs) with open(path, 'wb') as AutoPickleFile: pickle.dump((X), AutoPickleFile) else: with open(path, 'rb') as AutoPickleFile: X = pickle.load(AutoPickleFile) # divide set allQueries = X.keys() #allQueries = sorted(allQueries) # seed rnd_seed = "stay" seed(rnd_seed) shuffle(allQueries) # for seed #k = 10 #testQueries = allQueries[1::k] #queries = list(set(allQueries) - set(testQueries))
compute_num, compute_wd, compute_wr, doc_it import numpy as np import pickle from datetime import datetime path = "data/X" if 0: from Xtraction3 import extractXY # extract features path2docs = "../../feats/both/" path2rlvnce = "../../gt/rGT/" # create dict word number and X X = extractXY(path2docs, path2rlvnce) with open(path, 'wb') as AutoPickleFile: pickle.dump((X), AutoPickleFile) else: with open(path, 'rb') as AutoPickleFile: X = pickle.load(AutoPickleFile) # divide set allQueries = X.keys() allQueries = sorted(allQueries) # seed rnd_seed = "stay" seed(rnd_seed) shuffle(allQueries) # for seed k = 10 testQueries = allQueries[1::k]