preprocess_py.sh 1.7 KB
TRAIN_DIR=dataset_train
VAL_DIR=dataset_val
TEST_DIR=dataset_test
DATASET_NAME=dataset
MAX_CONTEXTS=200
WORD_VOCAB_SIZE=1301136
PATH_VOCAB_SIZE=911417
TARGET_VOCAB_SIZE=261245
NUM_THREADS=64
PYTHON=python
###########################################################

TRAIN_DATA_PATH=data/path_contexts_train.csv
VAL_DATA_PATH=data/path_contexts_val.csv
TEST_DATA_PATH=data/path_contexts_test.csv

TRAIN_DATA_FILE=${TRAIN_DATA_PATH}
VAL_DATA_FILE=${VAL_DATA_PATH}
TEST_DATA_FILE=${TEST_DATA_PATH}

mkdir -p data
mkdir -p data/${DATASET_NAME}

TARGET_HISTOGRAM_FILE=data/${DATASET_NAME}/${DATASET_NAME}.histo.tgt.c2v
ORIGIN_HISTOGRAM_FILE=data/${DATASET_NAME}/${DATASET_NAME}.histo.ori.c2v
PATH_HISTOGRAM_FILE=data/${DATASET_NAME}/${DATASET_NAME}.histo.path.c2v

cat ${TRAIN_DATA_FILE} | cut -d' ' -f1 | awk '{n[$0]++} END {for (i in n) print i,n[i]}' > ${TARGET_HISTOGRAM_FILE}
cat ${TRAIN_DATA_FILE} | cut -d' ' -f2- | tr ' ' '\n' | cut -d',' -f1,3 | tr ',' '\n' | awk '{n[$0]++} END {for (i in n) print i,n[i]}' > ${ORIGIN_HISTOGRAM_FILE}
cat ${TRAIN_DATA_FILE} | cut -d' ' -f2- | tr ' ' '\n' | cut -d',' -f2 | awk '{n[$0]++} END {for (i in n) print i,n[i]}' > ${PATH_HISTOGRAM_FILE}

DIR=`dirname "$0"`

${PYTHON} ${DIR}/preprocess.py --train_data ${TRAIN_DATA_FILE} --test_data ${TEST_DATA_FILE} --val_data ${VAL_DATA_FILE} \
  --max_contexts ${MAX_CONTEXTS} --word_vocab_size ${WORD_VOCAB_SIZE} --path_vocab_size ${PATH_VOCAB_SIZE} \
  --target_vocab_size ${TARGET_VOCAB_SIZE} --word_histogram ${ORIGIN_HISTOGRAM_FILE} \
  --path_histogram ${PATH_HISTOGRAM_FILE} --target_histogram ${TARGET_HISTOGRAM_FILE} --output_name data/${DATASET_NAME}/${DATASET_NAME}

rm ${TARGET_HISTOGRAM_FILE} ${ORIGIN_HISTOGRAM_FILE} ${PATH_HISTOGRAM_FILE}