mirror of https://github.com/hpcaitech/ColossalAI
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
63 lines
1.6 KiB
63 lines
1.6 KiB
import io
|
|
import json
|
|
import os
|
|
|
|
|
|
def _make_w_io_base(f, mode: str):
|
|
if not isinstance(f, io.IOBase):
|
|
f_dirname = os.path.dirname(f)
|
|
if f_dirname != "":
|
|
os.makedirs(f_dirname, exist_ok=True)
|
|
f = open(f, mode=mode)
|
|
return f
|
|
|
|
|
|
def _make_r_io_base(f, mode: str):
|
|
if not isinstance(f, io.IOBase):
|
|
f = open(f, mode=mode)
|
|
return f
|
|
|
|
|
|
def jdump(obj, f, mode="w", indent=4, default=str):
|
|
"""Dump a str or dictionary to a file in json format.
|
|
Args:
|
|
obj: An object to be written.
|
|
f: A string path to the location on disk.
|
|
mode: Mode for opening the file.
|
|
indent: Indent for storing json dictionaries.
|
|
default: A function to handle non-serializable entries; defaults to `str`.
|
|
"""
|
|
f = _make_w_io_base(f, mode)
|
|
if isinstance(obj, (dict, list)):
|
|
json.dump(obj, f, indent=indent, default=default)
|
|
elif isinstance(obj, str):
|
|
f.write(obj)
|
|
else:
|
|
raise ValueError(f"Unexpected type: {type(obj)}")
|
|
f.close()
|
|
|
|
|
|
def jload(f, mode="r"):
|
|
"""Load a .json file into a dictionary."""
|
|
f = _make_r_io_base(f, mode)
|
|
jdict = json.load(f)
|
|
f.close()
|
|
return jdict
|
|
|
|
|
|
def get_json_list(file_path):
|
|
with open(file_path, 'r') as f:
|
|
json_list = []
|
|
for line in f:
|
|
json_list.append(json.loads(line))
|
|
return json_list
|
|
|
|
|
|
def get_data_per_category(data, categories):
|
|
data_per_category = {category: [] for category in categories}
|
|
for item in data:
|
|
category = item["category"]
|
|
data_per_category[category].append(item)
|
|
|
|
return data_per_category
|