json.loads(s, *, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, **kw)

import json

# 示例 JSON 字符串
json_str = '{"name": "Alice", "age": 25, "skills": ["Python", "Machine Learning"]}'

# 使用 json.loads 將 JSON 字符串解析為 Python 字典
data = json.loads(json_str)
print(data)
# 輸出：{'name': 'Alice', 'age': 25, 'skills': ['Python', 'Machine Learning']}

# 訪問解析后的數(shù)據(jù)
print(data["name"])  # 輸出：Alice
print(data["skills"])  # 輸出：['Python', 'Machine Learning']

json.dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, default=None, sort_keys=False, **kw)

import json

# 示例 Python 對象
data = {
    "name": "Bob",
    "age": 30,
    "skills": ["JavaScript", "React", "Node.js"],
    "is_active": True
}

# 使用 json.dumps 將 Python 對象序列化為 JSON 字符串
json_str = json.dumps(data)
print(json_str)
# 輸出：{"name": "Bob", "age": 30, "skills": ["JavaScript", "React", "Node.js"], "is_active": true}

# 格式化輸出（帶縮進）
json_str_pretty = json.dumps(data, indent=4, ensure_ascii=False)
print(json_str_pretty)
# 輸出：
# {
#     "name": "Bob",
#     "age": 30,
#     "skills": [
#         "JavaScript",
#         "React",
#         "Node.js"
#     ],
#     "is_active": true
# }

import json

# 示例 JSON 字符串
json_str = '{"name": "Eve", "age": 28, "hobbies": ["Reading", "Swimming"]}'

# 將 JSON 字符串解析為 Python 字典
data = json.loads(json_str)
print("解析后的數(shù)據(jù)：", data)

# 修改數(shù)據(jù)
data["age"] = 29
data["hobbies"].append("Hiking")

# 將修改后的數(shù)據(jù)序列化為 JSON 字符串
new_json_str = json.dumps(data, indent=4, ensure_ascii=False)
print("修改后的 JSON：\n", new_json_str)

解析后的數(shù)據(jù)： {'name': 'Eve', 'age': 28, 'hobbies': ['Reading', 'Swimming']}
修改后的 JSON：
{
    "name": "Eve",
    "age": 29,
    "hobbies": [
        "Reading",
        "Swimming",
        "Hiking"
    ]
}

import json

invalid_json = "{'name': 'Alice', 'age': 25}"  # 錯誤的 JSON 格式（單引號）
try:
    data = json.loads(invalid_json)
except json.JSONDecodeError as e:
    print(f"JSONDecodeError: {e}")

import json
from datetime import datetime

data = {"name": "Alice", "timestamp": datetime.now()}

try:
    json_str = json.dumps(data)
except TypeError as e:
    print(f"TypeError: {e}")

json_str = json.dumps(data, default=str)
print(json_str)
# 輸出：{"name": "Alice", "timestamp": "2024-12-24 15:30:00.123456"}

json.loads(s, *, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, **kw)

import json

# Sample JSON string
json_str = '{"name": "Alice", "age": 25, "skills": ["Python", "Machine Learning"]}'

# Using json.loads to parse the JSON string into a Python dictionary
data = json.loads(json_str)
print(data)
# Output: {'name': 'Alice', 'age': 25, 'skills': ['Python', 'Machine Learning']}

# Accessing parsed data
print(data["name"])  # Output: Alice
print(data["skills"])  # Output: ['Python', 'Machine Learning']

json.dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, default=None, sort_keys=False, **kw)

import json

# Sample Python object
data = {
    "name": "Bob",
    "age": 30,
    "skills": ["JavaScript", "React", "Node.js"],
    "is_active": True
}

# Using json.dumps to serialize the Python object to a JSON string
json_str = json.dumps(data)
print(json_str)
# Output: {"name": "Bob", "age": 30, "skills": ["JavaScript", "React", "Node.js"], "is_active": true}

# Pretty-printing the JSON with indent
json_str_pretty = json.dumps(data, indent=4, ensure_ascii=False)
print(json_str_pretty)
# Output:
# {
#     "name": "Bob",
#     "age": 30,
#     "skills": [
#         "JavaScript",
#         "React",
#         "Node.js"
#     ],
#     "is_active": true
# }

import json

# Sample JSON string
json_str = '{"name": "Eve", "age": 28, "hobbies": ["Reading", "Swimming"]}'

# Parsing the JSON string into a Python dictionary
data = json.loads(json_str)
print("Parsed data:", data)

# Modifying the data
data["age"] = 29
data["hobbies"].append("Hiking")

# Serializing the modified data back to JSON
new_json_str = json.dumps(data, indent=4, ensure_ascii=False)
print("Modified JSON:\n", new_json_str)

Parsed data: {'name': 'Eve', 'age': 28, 'hobbies': ['Reading', 'Swimming']}
Modified JSON:
{
    "name": "Eve",
    "age": 29,
    "hobbies": [
        "Reading",
        "Swimming",
        "Hiking"
    ]
}

import json

invalid_json = "{'name': 'Alice', 'age': 25}"  # Invalid JSON format (single quotes)
try:
    data = json.loads(invalid_json)
except json.JSONDecodeError as e:
    print(f"JSONDecodeError: {e}")

import json
from datetime import datetime

data = {"name": "Alice", "timestamp": datetime.now()}

try:
    json_str = json.dumps(data)
except TypeError as e:
    print(f"TypeError: {e}")

json_str = json.dumps(data, default=str)
print(json_str)
# Output: {"name": "Alice", "timestamp": "2024-12-24 15:30:00.123456"}

import json

# 指定文件路徑
file_path = "/code/peft_study/open-instruct/data/tulu-3-sft-mixture-json-sampled/train_sampled_9k.json"

# 讀取 JSON 文件并輸出前兩條數(shù)據(jù)
with open(file_path, "r") as file:
    for i, line in enumerate(file):
        if i < 2:  # 只輸出前兩條數(shù)據(jù)
            data = json.loads(line)
            print(json.dumps(data, indent=4, ensure_ascii=False))
        else:
            break

{
    "id": "personahub_xdout465m7opc85m7bjfqmdt",
    "messages": [
        {
            "content": "Write a python function to analyze a list of Bollywood movie titles and return a list of titles that are palindromes. A palindrome is a word, phrase, number, or other sequence of characters which reads the same backward as forward. For simplicity, you can ignore spaces, capitalization, and punctuation in the titles. \n\nInput:\n- A list of strings, where each string represents a Bollywood movie title.\n\nOutput:\n- A list of strings, where each string is a movie title from the input list that is a palindrome.\n\nExample:\n```python\nmovie_titles = [\"Dil Se\", \"Madam\", \"Racecar\", \"Raees\", \"Noon\"]\nprint(find_palindrome_titles(movie_titles))\n```\nExpected Output:\n```python\n[\"Madam\", \"Racecar\", \"Noon\"]\n```",
            "role": "user"
        },
        {
            "content": "def find_palindrome_titles(movie_titles):\n    palindrome_titles = []\n    for title in movie_titles:\n        cleaned_title = ''.join(char for char in title.lower() if char.isalnum())\n        if cleaned_title == cleaned_title[::-1]:\n            palindrome_titles.append(title)\n    return palindrome_titles",
            "role": "assistant"
        }
    ],
    "source": "ai2-adapt-dev/personahub_code_v2_34999"
}
{
    "id": "ai2-adapt-dev/flan_v2_converted_33757",
    "messages": [
        {
            "content": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be characterized by being or having the Tail or not. Being characterized usually describes entities' general characteristics such as rose is red, or subjective attributes such as thirst is uncomfortable. It can also map to descriptors that speak to the substance or value of items such as meat has the property of being stored in the freezer or bike is powered by a person's legs. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.\n\nLet me give you an example: Head: water<sep>Tail: effect of making things wet\nThe answer to this example can be: Yes\nHere is why: This is a good example. The water can be characterized by making things wet.\n\nOK. solve this:\nHead: PersonX always watch ___<sep>Tail: engaged\nAnswer:",
            "role": "user"
        },
        {
            "content": "No",
            "role": "assistant"
        }
    ],
    "source": "ai2-adapt-dev/flan_v2_converted"
}