pandas将list数据拆分成行或列的实现

脚本专栏 2024/12/23 佚名

3 2 1

数据

import numpy as np
import pandas as pd

data = [{'Name': '小明', 'Chinese': [70, 80], 'Math': [90, 80]},
    {'Name': '小红', 'Chinese': [70, 80, 90], 'Math': [90, 80, 70]}]
data = pd.DataFrame(data)
data

拆分成行

def split_row(data, column):
  '''拆分成行

  :param data: 原始数据
  :param column: 拆分的列名
  :type data: pandas.core.frame.DataFrame
  :type column: str
  '''
  row_len = list(map(len, data[column].values))
  rows = []
  for i in data.columns:
    if i == column:
      row = np.concatenate(data[i].values)
    else:
      row = np.repeat(data[i].values, row_len)
    rows.append(row)
  return pd.DataFrame(np.dstack(tuple(rows))[0], columns=data.columns)


split_row(data, column='Chinese')

拆分成列

from copy import deepcopy


def split_col(data, column):
  '''拆分成列

  :param data: 原始数据
  :param column: 拆分的列名
  :type data: pandas.core.frame.DataFrame
  :type column: str
  '''
  data = deepcopy(data)
  max_len = max(list(map(len, data[column].values))) # 最大长度
  new_col = data[column].apply(lambda x: x + [None]*(max_len - len(x))) # 补空值，None可换成np.nan
  new_col = np.array(new_col.tolist()).T # 转置
  for i, j in enumerate(new_col):
    data[column + str(i)] = j
  return data


split_col(data, column='Chinese')

其他情况

1. 批量处理+不要原列

def split_col(data, columns):
  '''拆分成列

  :param data: 原始数据
  :param columns: 拆分的列名
  :type data: pandas.core.frame.DataFrame
  :type columns: list
  '''
  for c in columns:
    new_col = data.pop(c)
    max_len = max(list(map(len, new_col.values))) # 最大长度
    new_col = new_col.apply(lambda x: x + [None]*(max_len - len(x))) # 补空值，None可换成np.nan
    new_col = np.array(new_col.tolist()).T # 转置
    for i, j in enumerate(new_col):
      data[c + str(i)] = j


split_col(data, columns=['Chinese','Math'])
data

2. 带int和list数据

转成这样：

import numpy as np
import pandas as pd

data = [{'Name': '小爱', 'Chinese': 70, 'Math': 90},
    {'Name': '小明', 'Chinese': [70, 80], 'Math': [90, 80]},
    {'Name': '小红', 'Chinese': [70, 80, 90], 'Math': [90, 80, 70]}]
data = pd.DataFrame(data)

def split_col(data, columns):
  '''拆分成列

  :param data: 原始数据
  :param columns: 拆分的列名
  :type data: pandas.core.frame.DataFrame
  :type columns: list
  '''
  for c in columns:
    new_col = data.pop(c)
    max_len = max(list(map(lambda x:len(x) if isinstance(x, list) else 1, new_col.values))) # 最大长度
    new_col = new_col.apply(lambda x: x+[None]*(max_len - len(x)) if isinstance(x, list) else [x]+[None]*(max_len - 1)) # 补空值，None可换成np.nan
    new_col = np.array(new_col.tolist()).T # 转置
    for i, j in enumerate(new_col):
      data[c + str(i)] = j


split_col(data, columns=['Chinese','Math'])
data