如何在json文件中使用python+numpy/pandas中的二值化创建新列

import pandas as pd
import numpy as np

# 假设我们有一个JSON文件 'data.json'，内容如下：
# [
#     {"name": "Alice", "score": 85},
#     {"name": "Bob", "score": 70},
#     {"name": "Charlie", "score": 92}
# ]

# 读取JSON文件到Pandas DataFrame
df = pd.read_json('data.json')

# 定义二值化函数
def binarize_score(score, threshold=80):
    return 1 if score >= threshold else 0

# 应用二值化函数创建新列
df['is_passing'] = df['score'].apply(binarize_score)

# 查看结果
print(df)

      name  score  is_passing
0    Alice     85           1
1      Bob     70           0
2  Charlie     92           1

# 分块读取大JSON文件
chunksize = 1000  # 根据实际情况调整
chunks = pd.read_json('large_data.json', lines=True, chunksize=chunksize)

processed_chunks = []
for chunk in chunks:
    chunk['is_passing'] = chunk['score'].apply(binarize_score)
    processed_chunks.append(chunk)

# 合并所有处理过的块
final_df = pd.concat(processed_chunks)