通过合并添加列-熊猫

Question

我有两个数据帧。 我想用df2中的ID名称在df1中创建列，并在其中分配df2中特定列的值，但要考虑日期。

数据说明：

df1

ID  Date        X
A   07/16/2019  ..
A   07/19/2019  ..
B   07/28/2019  ..

df2

ID2 Day         Y   P
123 07/16/2019  ..  1.5
123 07/19/2019  ..  2.0
123 07/28/2019  ..  3.0
456 07/16/2019  ..  1.8
456 07/19/2019  ..  2.1
456 07/28/2019  ..  3.2
789 07/16/2019  ..  1.6
789 07/19/2019  ..  4.5

预期结果（df1）：

ID  Date        X   123_P   456_P   789_P
A   07/16/2019  ..  1.5     1.8     1.6
A   07/19/2019  ..  2.0     2.1     4.5
B   07/28/2019  ..  3.0     3.2     NaN

Answer 1

#Setup
import pandas as pd
col = ["ID2", "Day","P"]

data = [
(123, '07/16/2019', 1.5),
(123, '07/19/2019', 2.0),
(123, '07/28/2019', 3.0),
(456, '07/16/2019', 1.8),
(456, '07/19/2019', 2.1),
(456, '07/28/2019', 3.2),
(789, '07/16/2019', 1.6),
(789, '07/19/2019', 4.5),
]
df2 = pd.DataFrame(data,columns=col)

#Solution
piv_col = list(df2['ID2'].unique())
piv_col_renamed = [str(col) + '_P' for col in piv_col]
rename_dict = dict(zip(piv_col, piv_col_renamed))
df2 = df2.pivot(index='Day',values='P', columns='ID2').reset_index()
df2.rename(rename_dict,axis=1,inplace=True)

merged_df = pd.merge(df1,df2, how='left',left_on='Date',right_on='Day')

Answer 2

这是两个数据帧：

raw_data1 = {'ID':  ['A', 'B', 'C'],
             'Date':['07/16/2019', '07/19/2019', '07/28/2019'],
             'X':   ['x', 'x', 'x']}

df1 = pd.DataFrame(raw_data1)

raw_data2 = {'ID':   [123, 123, 123, 456, 456, 456, 789, 789],
             'Date': ['07/16/2019', '07/19/2019', '07/28/2019', '07/16/2019', 
                         '07/19/2019', '07/28/2019', '07/16/2019', '07/19/2019'],
             'P':    [1.5, 2.0, 3.0, 1.8, 2.1, 3.2, 1.6, 4.5]}

df2 = pd.DataFrame(raw_data2)

我执行了以下步骤：

## first make a new column that will end up being your column header
df2['colheader'] = df2['ID'].astype(str) + 'P'

# next 'pivot' over Date as index, colheader as columns and P as values
df2 = df2.pivot(index='Date',columns='colheader',values='P')

# next 'clean up' the dataset - this makes the headers easier to read
df2.columns.name = None
df2 = df2.reset_index()

# now merge with df1
df = df1.merge(df2,left_on='Date', right_on='Date')
df

结果：

Answer 3

这是使用 import React, { Component, Fragment } from "react"; import "./App.css"; export default class App extends Component { constructor(props){ super(props) this.state = { data: [ { id: 1, Firstname: "Jill", Lastname: ["john", "hobss", "smith"], Age: [1, 2, 3], company: ["facebook", "google", "netflix"], skills: ["python", "java", "scala"] }, { id: 2, Firstname: "Jill", Lastname: ["john", "hobss", "smith"], Age: [1, 2, 3], company: ["facebook", "google", "netflix"], skills: ["python", "java", "scala"] }, { id: 3, Firstname: "Jill", Lastname: ["john", "hobss", "smith"], Age: [1, 2, 3], company: ["facebook", "google", "netflix"], skills: ["python", "java", "scala"] }, { id:4, Firstname: "Jill", Lastname: ["john", "hobss", "smith"], Age: [1, 2, 3], company: ["facebook", "google", "netflix"], skills: ["python", "java", "scala"] } ] } } handleChange = (id, company, event) => { const data = this.state.data; for(let d of data){ if(d.id === id){ for(let c of d.company){ if(c === company){ c = event.target.value } } } } } render() { return ( <div> <table> <tr> <th>Firstname</th> <th>Lastname</th> <th>Age</th> <th>company</th> <th>skills</th> </tr> { this.state.data.map(td => { return ( <tr> <td>{td.Firstname}</td> <td> <table> <tr> <td>{td.Lastname[0]}</td> <td>{td.Lastname[1]}</td> <td>{td.Lastname[2]}</td> </tr> </table> </td> <td> <table> <tr> <td>{td.Age[0]}</td> <td>{td.Age[1]}</td> <td>{td.Age[2]}</td> </tr> </table> </td> <td> <table> <tr> <td> <input type="text" value={td.company[0]} onChange={(e) => this.handleChange(td.id, td.company[0], e)} /> </td> <td> <input type="text" value={td.company[1]} onChange={(e) => this.handleChange(td.id, td.company[1], e)}/> </td> <td> <input type="text" value={td.company[2]} onChange={(e) => this.handleChange(td.id, td.company[2], e)}/> </td> </tr> </table> </td> <td> <table> <tr> <td>{td.skills[0]}</td> <td>{td.skills[0]}</td> <td>{td.skills[0]}</td> </tr> </table> </td> </tr> ) }) } </table> </div> ) } } 和merge的另一种方式：

unstack()

---

m=df.merge(df2,left_on='Date',right_on='Day').query('Date==Day').drop(['Day','Y'],1)
m=m.set_index(['ID','Date','X','ID2']).unstack().sort_index(level=1,axis=1)

---

m.columns=[f'{a}_{b}' for a,b in m.columns]
m=m.reset_index()
print(m)