li = li[:size] print "Preparing dictionaries..." if dense: vdict = util.lstmvec(dictfile) else: charset = util.make_charset(li,7) print "Preparing datasets..." dataset_train = li[:cut1] dataset_validate = li[cut1:cut2] dataset_test = li[cut2:] dataset = [] while dataset_train: x, y = util.line_toseq(dataset_train.pop(), charstop) if dense: dataset.append(util.seq_to_densevec(x, y, vdict)) else: dataset.append(util.seq_to_sparsevec(x,y,charset)) if not len(dataset_train)%1000: print "len(dataset_train)", len(dataset_train) dataset_train = dataset dataset = [] while dataset_validate: x, y = util.line_toseq(dataset_validate.pop(), charstop) if dense: dataset.append(util.seq_to_densevec(x, y, vdict)) else: dataset.append(util.seq_to_sparsevec(x,y,charset)) if not len(dataset_validate)%1000: print "len(dataset_validate)", len(dataset_validate) dataset_validate = dataset #sys.exit()
print("Preparing dictionaries...") if dense: vdict = util.lstmvec(dictfile) else: charset = util.make_charset(li, 7) print("Preparing datasets...") dataset_train = li[:cut1] dataset_validate = li[cut1:cut2] dataset_test = li[cut2:] dataset = [] print(type(dataset_train)) while dataset_train: x, y = util.line_toseq(dataset_train.pop(), charstop) if dense: dataset.append(util.seq_to_densevec(x, y, vdict)) else: dataset.append(util.seq_to_sparsevec(x, y, charset)) if not len(dataset_train) % 1000: print("len(dataset_train)", len(dataset_train)) dataset_train = dataset dataset = [] while dataset_validate: x, y = util.line_toseq(dataset_validate.pop(), charstop) if dense: dataset.append(util.seq_to_densevec(x, y, vdict)) else: dataset.append(util.seq_to_sparsevec(x, y, charset)) if not len(dataset_validate) % 1000: print("len(dataset_validate)", len(dataset_validate)) dataset_validate = dataset dataset = []