pandas df の基本操作

サンプルデータの作成

import pandas as pd

data = {
    "Name": ["user1", "user2", "user3", "user1", "user2", "user1"],
    "Reserve_Data": ["1/1/2024", "2/1/2024", "3/1/2024", "4/1/2024", "5/1/2024", "6/1/2024"],
    "Money": ["1000", "12000", "36000","400", "26","403330"],
}

df = pd.DataFrame(data, columns=["Name", "Reserve_Data", "Money"])
df
    Name Reserve_Data   Money
0  user1     1/1/2024    1000
1  user2     2/1/2024   12000
2  user3     3/1/2024   36000
3  user1     4/1/2024     400
4  user2     5/1/2024      26
5  user1     6/1/2024  403330

dfの単独列をリストで取得する

name_list = df["Name"].tolist()
print(name_list)
['user1', 'user2', 'user3', 'user1', 'user2', 'user1']

dfから特定の値を持つ行を抽出する

#１つの値との一致
print(df[df['Name'] == 'user1'])
    Name Reserve_Data   Money
0  user1     1/1/2024    1000
3  user1     4/1/2024     400
5  user1     6/1/2024  403330

#複数の値との一致 参考：https://hk29.hatenablog.jp/entry/2021/07/16/235822
target_list = ["user1","user3"]
df2 = df.query('Name in @target_list')
print(df2)
    Name Reserve_Data   Money
0  user1     1/1/2024    1000
2  user3     3/1/2024   36000
3  user1     4/1/2024     400
5  user1     6/1/2024  403330

行の並び替え

print(df.sort_values('Name'))
    Name Reserve_Data   Money
0  user1     1/1/2024    1000
3  user1     4/1/2024     400
5  user1     6/1/2024  403330
1  user2     2/1/2024   12000
4  user2     5/1/2024      26
2  user3     3/1/2024   36000

print(df2.sort_values('Name'))
    Name Reserve_Data   Money
0  user1     1/1/2024    1000
3  user1     4/1/2024     400
5  user1     6/1/2024  403330
2  user3     3/1/2024   36000