python读写json，json，parquet文件,各种文件格式转换代码

导入相关包

import json
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq

读json，json，parquet文件

def read_json_file(file_path):
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            data = json.load(file)
            return data
    except FileNotFoundError:
        print(f"File {file_path} not found.")
    except json.JSONDecodeError:
        print(f"File {file_path} is not a valid JSON file.")
    except Exception as e:
        print(f"An error occurred: {e}")

def read_jsonl_file(file_path):
    data = []
    with open(file_path, 'r', encoding='utf-8') as file:
        for line in file:
            try:
                data.append(json.loads(line))
            except:
                print(line)
                1/0
    return data

def read_praquet_file(file_path):
    table = pq.read_table(file_path)
    df = table.to_pandas()
    result=[row for _, row in df.iterrows()]
    return result

写json，json，parquet文件

def save_json(file_path,data):
    with open(file_path, 'w', encoding='utf-8') as file:
        json.dump(data, file, indent=4, ensure_ascii=False)
    print(f'Save {file_path} is ok!')

def save_jsonl(file_path,data):
    try:
        with open(file_path, 'w', encoding='utf-8') as file:
            for item in data:
                file.write(json.dumps(item, ensure_ascii=False) + '\n')
        print(f"Data saved to {file_path}")
    except Exception as e:
        print(f"An error occurred while saving the data: {e}")

def save_parquet(file_path, data):

    if isinstance(data, list):
        data = pd.DataFrame(data)
    if not isinstance(data, pd.DataFrame):
        raise ValueError("data must be a pandas DataFrame or a list of lists")
    pq.write_table(pa.Table.from_pandas(data), file_path)
    print(f'Save {file_path} is ok!')


# 写parquet的示例数据
data = {
        'col1': [1, 2, 3],
        'col2': ['a', 'b', 'c']
    }
df = pd.DataFrame(data)

# 保存数据到 Parquet 文件
save_parquet('output.parquet', df)

读取jsonl文件，并保存为parquet文件

def convert_lists_to_json(df):
    """Convert lists in DataFrame to JSON strings."""
    for column in df.columns:
        if df[column].apply(lambda x: isinstance(x, list)).any():
            df[column] = df[column].apply(lambda x: json.dumps(x) if isinstance(x, list) else x)
    return df

def save_parquet(file_path, data):
    if isinstance(data, list):
        data = pd.DataFrame(data)
    if not isinstance(data, pd.DataFrame):
        raise ValueError("data must be a pandas DataFrame or a list of lists")
    # Convert lists to JSON strings before saving to Parquet
    data = convert_lists_to_json(data)
    pq.write_table(pa.Table.from_pandas(data), file_path)
    print(f'Save {file_path} is ok!')


file_path='input.jsonl'
save_path='output.parquet'
data = read_jsonl_file(file_path)
df = pd.DataFrame(data)
save_parquet(save_path, df)