cba61a2909
* remove include and language option, select the corresponding dataset based on the model name in Run * change the nightly test time * change the nightly test time of harness and ppl * save the ppl result to json file * generate csv file and print table result * generate html * modify the way to get parent folder * update html in parent folder * add llm-ppl-summary and llm-ppl-summary-html * modify echo single result * remove download fp16.csv * change model name of PR * move ppl nightly related files to llm/test folder * reformat * seperate make_table from make_table_and_csv.py * separate make_csv from make_table_and_csv.py * update llm-ppl-html * remove comment * add Download fp16.results
101 lines
No EOL
3.2 KiB
Python
101 lines
No EOL
3.2 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.
|
|
#
|
|
"""
|
|
Usage:
|
|
python make_table.py <input_dir>
|
|
"""
|
|
|
|
import logging
|
|
from pytablewriter import MarkdownTableWriter, LatexTableWriter
|
|
import os
|
|
import json
|
|
import sys
|
|
import csv
|
|
import datetime
|
|
|
|
|
|
logging.basicConfig(level=logging.INFO)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def make_table(result_dict):
|
|
"""Generate table of results."""
|
|
md_writer = MarkdownTableWriter()
|
|
latex_writer = LatexTableWriter()
|
|
md_writer.headers = ["Model", "Precision", "en", "zh"]
|
|
latex_writer.headers = ["Model", "Precision", "en", "zh"]
|
|
|
|
languages = ["en", "zh"]
|
|
values = []
|
|
for model, model_results in result_dict.items():
|
|
for precision, prec_results in model_results.items():
|
|
value = [model, precision]
|
|
for language in languages:
|
|
task_results = prec_results.get(language, None)
|
|
if task_results is None:
|
|
value.append("")
|
|
else:
|
|
result = task_results["results"]
|
|
value.append("%.4f" % result)
|
|
values.append(value)
|
|
model = ""
|
|
precision = ""
|
|
|
|
md_writer.value_matrix = values
|
|
latex_writer.value_matrix = values
|
|
|
|
# todo: make latex table look good
|
|
# print(latex_writer.dumps())
|
|
|
|
return md_writer.dumps()
|
|
|
|
|
|
def merge_results(path):
|
|
# loop dirs and subdirs in results dir
|
|
# for each dir, load json files
|
|
print('Read from', path)
|
|
merged_results = dict()
|
|
for dirpath, dirnames, filenames in os.walk(path):
|
|
# skip dirs without files
|
|
if not filenames:
|
|
continue
|
|
for filename in sorted([f for f in filenames if f.endswith("result.json")]):
|
|
path = os.path.join(dirpath, filename)
|
|
model, device, precision, language = dirpath.split('/')[-4:]
|
|
with open(path, "r") as f:
|
|
result_dict = json.load(f)
|
|
if model not in merged_results:
|
|
merged_results[model] = dict()
|
|
if precision not in merged_results[model]:
|
|
merged_results[model][precision] = dict()
|
|
merged_results[model][precision][language] = result_dict
|
|
return merged_results
|
|
|
|
|
|
def main(*args):
|
|
if len(args) > 1:
|
|
input_path = args[1]
|
|
else:
|
|
raise ValueError("Input path is required")
|
|
|
|
merged_results = merge_results(input_path)
|
|
print(make_table(merged_results))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# when running from the harness, the first argument is the script name
|
|
# you must name the second argument and the third argument(optional) to be the input_dir and output_dir
|
|
main(*sys.argv) |