70b17c87be
* add merge steps * move to pr mode * remove build + add merge.py * add tohtml and change cp * change test_batch folder path * change merge_temp path * change to html folder * revert * change place * revert 437 * revert space --------- Co-authored-by: Yishuo Wang <yishuo.wang@intel.com>
45 lines
1.7 KiB
Python
45 lines
1.7 KiB
Python
#
|
|
# Copyright 2016 The BigDL Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
# Python program to concat CSVs
|
|
|
|
import os
|
|
import sys
|
|
import argparse
|
|
import pandas as pd
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description="concat .csv files")
|
|
parser.add_argument("-f", "--folder_path", type=str, dest="folder_path",
|
|
help="The directory which stores the .csv files", default="./")
|
|
args = parser.parse_args()
|
|
|
|
csv_files = []
|
|
for file_name in os.listdir(args.folder_path):
|
|
file_path = os.path.join(args.folder_path, file_name)
|
|
if os.path.isfile(file_path) and file_name.endswith(".csv"):
|
|
csv_files.append(file_path)
|
|
csv_files.sort()
|
|
|
|
merged_df = pd.concat([pd.read_csv(file, index_col=0) for file in csv_files], ignore_index=True)
|
|
merged_df["input_len"] = merged_df["input/output tokens"].apply(lambda x: int(x.split("-")[0]))
|
|
merged_df = merged_df.sort_values(by=["model", "input_len", "batch_size"])
|
|
merged_df.reset_index(drop=True, inplace=True)
|
|
merged_csv = csv_files[0].replace("_batch1", "").replace("_batch2", "").replace("_batch4", "")
|
|
merged_df.drop("input_len", axis=1).to_csv(merged_csv)
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|