python - 从 pandas 数据帧创建特定的 json 对象

Question

假设我有一个像这样的数据框

t = {'Tract_number': ['01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100', '01001020100'],
    'Year': [2019, 2014, 2015, 2016, 2017, 2018, 2011, 2020, 2010, 2009, 2012, 2013],
    'Median_household_income': [70625.0, 65800.0, 67356.0, 68750.0, 70486.0, 70385.0, 66953.0, 70257.0, 71278.0, 'nan', 65179.0, 65114.0], 
    'Total_Asian_Population': [2.0, 12.0, 12.0, 9.0, 22.0, 17.0, 0.0, 41.0, 0.0, 'nan', 0.0, 0.0],
    'Total_bachelors_degree': [205.0, 173.0, 166.0, 216.0, 261.0, 236.0, 139.0, 'nan', 170.0, 'nan', 156.0, 183.0], 
    'Total_graduate_or_professional_degree': [154.0, 149.0, 176.0, 191.0, 215.0, 174.0, 117.0, 'nan', 146.0, 'nan', 131.0, 127.0], 
    'Median_gross_rent': [749.0, 738.0, 719.0, 484.0, 780.0, 827.0, 398.0, 820.0, 680.0, 'nan', 502.0, 525.0]}
df_sample = pd.DataFrame(data=t)

现在假设我想制作一本看起来像这样结构的字典

A = {
    
    '01001020100': 
    {
        Median_household_income:
        {'2010': 11235, '2011': 13253 }
        Total_Asian_Population:
        {'2010': 1234, ...}
    }

}

我该怎么做？

我本来是这样的

d = {'Tract_number': df_sample['Tract_number'].iloc[0]}
e = {
    'Median_household_income': pd.Series(df_sample.Median_household_income.values,index=df_sample.Year).to_dict(),
    'Total_Asian_Population': pd.Series(df_sample.Total_Asian_Population.values,index=df_sample.Year).to_dict(),
    'Total_bachelors_degree': pd.Series(df_sample.Total_bachelors_degree.values,index=df_sample.Year).to_dict(),
    'Total_graduate_or_professional_degree': pd.Series(df_sample.Total_bachelors_degree.values,index=df_sample.Year).to_dict(),
    'Median_gross_rent': pd.Series(df_sample.Total_bachelors_degree.values,index=df_sample.Year).to_dict()
}
f = {}
f[d['Tract_number']] = e
f

然后我只需将 e 附加到 d 即可，但是有没有更 Pythonic 的方法来做到这一点？如有任何帮助，我们将不胜感激。

Answer 1

根据您提供的数据框，这是使用 Pandas groupby 执行此操作的一种方法和 MultiIndex.get_level_values ，和 median Python 标准库 statistics 中的函数模块:

import pandas as pd
from statistics import median

df = (
    pd.DataFrame(data=t)
    .sort_values(["Tract_number", "Year"])
    .groupby(["Tract_number", "Year"])
    .agg({"Median_household_income": median, "Total_Asian_Population": sum})
)

A = {
    key: {
        "Median_household_income": df.loc[(key,), "Median_household_income"].to_dict(),
        "Total_Asian_Population": df.loc[(key,), "Total_Asian_Population"].to_dict(),
    }
    for key in [idx for idx in df.index.get_level_values(0).unique()]
}

然后:

print(A)
# Output
{
    "01001020100": {
        "Median_household_income": {
            2009: "nan",
            2010: 71278.0,
            2011: 66953.0,
            2012: 65179.0,
            2013: 65114.0,
            2014: 65800.0,
            2015: 67356.0,
            2016: 68750.0,
            2017: 70486.0,
            2018: 70385.0,
            2019: 70625.0,
            2020: 70257.0,
        },
        "Total_Asian_Population": {
            2009: "nan",
            2010: 0.0,
            2011: 0.0,
            2012: 0.0,
            2013: 0.0,
            2014: 12.0,
            2015: 12.0,
            2016: 9.0,
            2017: 22.0,
            2018: 17.0,
            2019: 2.0,
            2020: 41.0,
        },
}