创建DadtaFrame的问题

import pandas as pd
import csv
g_variStrFpXq= #订单编号,税号，备注
'[2724606325618536238,91530112343713723J,无],
[2692025102277631266,91330482MA2BCAQRXE,无],
[2748256921818730219,91430600MA4R1DQT25,无],
[2701373294338164869,91500105569920960F,无],
[2730012660790633301,91510100052546574C,无],
[2707600898214196225,91510700MA6249LD6C,无],'

g_variStrTemp =g_variStrFpXq

我想定义一个df,索引设置成上述 中括号第一个逗号左边的部分即，订单号

sfpxq = pd.Series(g_variStrTemp,index=[a[0] for a in g_variStrTemp])

g_variPandasDfFpx = pd.DadtaFrame(sfpxq, index=[a[0] for a in g_variStrTemp]) #索引设置成上述 中括号第一个逗号左边的部分即，订单号,是不是有问题？

g_variPandasDfFpx.to_csv(r"F:\g_variPandasDfxq.csv",encoding="GBK",header=1,index=1) #这里出来好多重复的数据，不知啥原因

下有代码，可直接复制使用。如有帮助，敬请采纳，你的采纳是我前进的动力，O(∩_∩)O谢谢！！！！！！！！


import pandas as pd
# 订单编号,税号，备注
g_variStrFpXq = [['2724606325618536238', '91530112343713723J', '无'],
                 ['2692025102277631266', '91330482MA2BCAQRXE', '无'],
                 ['2748256921818730219', '91430600MA4R1DQT25', '无'],
                 ['2701373294338164869', '91500105569920960F', '无'],
                 ['2730012660790633301', '91510100052546574C', '无'],
                 ['2730012660790633301', '91510100052546574C', '无'],
                 ['2707600898214196225', '91510700MA6249LD6C', '无']]

df_data = {}
for x in g_variStrFpXq:
    df_data[x[0]] = x
    # 不需要订单号重复时，取消下面代码注释
    # df_data[x[0]] = x[1:]
g_variPandasDfFpx = pd.DataFrame(df_data)

g_variPandasDfFpx.to_csv(r'./g_variPandasDfxq.csv', encoding='GBK')

img

  • 你的数组两端为啥还有单引号
    g_variStrFpXq=[
[2724606325618536238,91530112343713723J,无],
[2692025102277631266,91330482MA2BCAQRXE,无],
[2748256921818730219,91430600MA4R1DQT25,无],
[2701373294338164869,91500105569920960F,无],
[2730012660790633301,91510100052546574C,无],
[2730012660790633301,91510100052546574C,无],
[2707600898214196225,91510700MA6249LD6C,无]
]
  • 构造DataFrame也很奇怪，用下面即可
    g_variPandasDfFpx = pd.DataFrame({
'id': [a[0] for a in g_variStrFpXq], 
'税号':  [a[1] for a in g_variStrFpXq],
'备注': [a[2] for a in g_variStrFpXq]
}).set_index('id')