溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
小編給大家分享一下Pandas中merge如何合并DataFrame，相信大部分人都還不怎么了解，因此分享這篇文章給大家參考一下，希望大家閱讀完這篇文章后大有收獲，下面讓我們一起去了解一下吧！
import pandas as pd
left=pd.DataFrame({
'key':['k0','k1','k2','k3','k4','k5'],
'A':['A0','A1','A2','A3','A4','A5'],
'B':['B0','B1','B2','B3','B4','B5']
})
right=pd.DataFrame({
'key':['k0','k1','k2','k3','k4','k5'],
'C':['C0','C1','C2','C3','C4','C5'],
'D':['D0','D1','D2','D3','D4','D5']
})
print(left)
print('-'*20)
print(right)key A B 0 k0 A0 B0 1 k1 A1 B1 2 k2 A2 B2 3 k3 A3 B3 4 k4 A4 B4 5 k5 A5 B5 -------------------- key C D 0 k0 C0 D0 1 k1 C1 D1 2 k2 C2 D2 3 k3 C3 D3 4 k4 C4 D4 5 k5 C5 D5
# 合并
res=pd.merge(left,right)
print(res)
print('-'*20)
# 指定合并的key
res=pd.merge(left,right,on='key')
print(res)key A B C D 0 k0 A0 B0 C0 D0 1 k1 A1 B1 C1 D1 2 k2 A2 B2 C2 D2 3 k3 A3 B3 C3 D3 4 k4 A4 B4 C4 D4 5 k5 A5 B5 C5 D5 -------------------- key A B C D 0 k0 A0 B0 C0 D0 1 k1 A1 B1 C1 D1 2 k2 A2 B2 C2 D2 3 k3 A3 B3 C3 D3 4 k4 A4 B4 C4 D4 5 k5 A5 B5 C5 D5
left = pd.DataFrame({'key1': ['K0', 'K1', 'K2', 'K3'],
'key2': ['K0', 'K1', 'K2', 'K3'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key1': ['K0', 'K1', 'K2', 'K3'],
'key2': ['K0', 'K1', 'K2', 'K4'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
print(left)
print('-'*20)
print(right)key1 key2 A B 0 K0 K0 A0 B0 1 K1 K1 A1 B1 2 K2 K2 A2 B2 3 K3 K3 A3 B3 -------------------- key1 key2 C D 0 K0 K0 C0 D0 1 K1 K1 C1 D1 2 K2 K2 C2 D2 3 K3 K4 C3 D3
# 默認取交集 how='inner' res=pd.merge(left,right,on=['key1','key2']) print(res)
key1 key2 A B C D 0 K0 K0 A0 B0 C0 D0 1 K1 K1 A1 B1 C1 D1 2 K2 K2 A2 B2 C2 D2
# how='outer' 取并集 res=pd.merge(left,right,on=['key1','key2'],how='outer') print(res)
key1 key2 A B C D 0 K0 K0 A0 B0 C0 D0 1 K1 K1 A1 B1 C1 D1 2 K2 K2 A2 B2 C2 D2 3 K3 K3 A3 B3 NaN NaN 4 K3 K4 NaN NaN C3 D3
# 顯示合并數據中數據來自哪個表 res=pd.merge(left,right,on=['key1','key2'],how='outer',indicator=True) print(res)
key1 key2 A B C D _merge 0 K0 K0 A0 B0 C0 D0 both 1 K1 K1 A1 B1 C1 D1 both 2 K2 K2 A2 B2 C2 D2 both 3 K3 K3 A3 B3 NaN NaN left_only 4 K3 K4 NaN NaN C3 D3 right_only
# 左鏈接
res=pd.merge(left,right,on=['key1','key2'],how='left')
print(res)
print('-'*30)
# 右鏈接
res=pd.merge(left,right,on=['key1','key2'],how='right')
print(res)key1 key2 A B C D 0 K0 K0 A0 B0 C0 D0 1 K1 K1 A1 B1 C1 D1 2 K2 K2 A2 B2 C2 D2 3 K3 K3 A3 B3 NaN NaN ------------------------------ key1 key2 A B C D 0 K0 K0 A0 B0 C0 D0 1 K1 K1 A1 B1 C1 D1 2 K2 K2 A2 B2 C2 D2 3 K3 K4 NaN NaN C3 D3
left = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3'],
'key': ['K0', 'K1', 'K0', 'K1']})
right = pd.DataFrame({'C': ['C0', 'C1'],
'D': ['D0', 'D1']},
index=['K0', 'K1'])
print(left)
print('-'*15)
print(right)A B key 0 A0 B0 K0 1 A1 B1 K1 2 A2 B2 K0 3 A3 B3 K1 --------------- C D K0 C0 D0 K1 C1 D1
res=left.join(right,on='key') print(res)
A B key C D 0 A0 B0 K0 C0 D0 1 A1 B1 K1 C1 D1 2 A2 B2 K0 C0 D0 3 A3 B3 K1 C1 D1
df = pd.DataFrame({'Month': ["January", "January", "January", "January",
"February", "February", "February", "February",
"March", "March", "March", "March"],
'Category': ["Transportation", "Grocery", "Household", "Entertainment",
"Transportation", "Grocery", "Household", "Entertainment",
"Transportation", "Grocery", "Household", "Entertainment"],
'Amount': [74., 235., 175., 100., 115., 240., 225., 125., 90., 260., 200., 120.]})
print(df)Month Category Amount 0 January Transportation 74.0 1 January Grocery 235.0 2 January Household 175.0 3 January Entertainment 100.0 4 February Transportation 115.0 5 February Grocery 240.0 6 February Household 225.0 7 February Entertainment 125.0 8 March Transportation 90.0 9 March Grocery 260.0 10 March Household 200.0 11 March Entertainment 120.0
# 構造一個索引為Category 列為Month 值為Amount的表 res=df.pivot(index='Category',columns='Month',values='Amount') print(res)
Month February January March Category Entertainment 125.0 100.0 120.0 Grocery 240.0 235.0 260.0 Household 225.0 175.0 200.0 Transportation 115.0 74.0 90.0
# 按列求和 res.sum(axis=0)
Month February 705.0 January 584.0 March 670.0 dtype: float64
# 按行求和 res.sum(axis=1)
Category Entertainment 345.0 Grocery 735.0 Household 600.0 Transportation 279.0 dtype: float64
df=pd.read_csv('./pandas/data/titanic.csv')
df.columnsIndex(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'], dtype='object')
#默認求平均值 res=df.pivot_table(index='Sex',columns='Pclass',values='Fare') print(res)
Pclass 1 2 3 Sex female 106.125798 21.970121 16.118810 male 67.226127 19.741782 12.661633
# 求最大值 res=df.pivot_table(index='Sex',columns='Pclass',values='Fare',aggfunc='max') print(res)
Pclass 1 2 3 Sex female 512.3292 65.0 69.55 male 512.3292 73.5 69.55
# 統計個數
res=df.pivot_table(index='Sex',columns='Pclass',values='Fare',aggfunc='count')
print(res)
print('-'*20)
# crosstab 統計個數
res=pd.crosstab(index=df['Sex'],columns=df['Pclass'])
print(res)Pclass 1 2 3 Sex female 94 76 144 male 122 108 347 -------------------- Pclass 1 2 3 Sex female 94 76 144 male 122 108 347
# 求平均值 res=df.pivot_table(index='Sex',columns='Pclass',values='Fare',aggfunc='mean') print(res)
Pclass 1 2 3 Sex female 106.125798 21.970121 16.118810 male 67.226127 19.741782 12.661633
# 計算未成年男女存活率 df['minor']=df['Age']<=18 res=df.pivot_table(index='minor',columns='Sex',values='Survived',aggfunc='mean') print(res)
Sex female male minor False 0.760163 0.167984 True 0.676471 0.338028
以上是“Pandas中merge如何合并DataFrame”這篇文章的所有內容，感謝各位的閱讀！相信大家都有了一定的了解，希望分享的內容對大家有所幫助，如果還想學習更多知識，歡迎關注億速云行業資訊頻道！
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
