if __name__ =='__main__':# 全列顯示 :
pd.set_option('display.max_columns',None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
df_age = data["Age"]print(df_age)==============================================022.0138.0226.0
2 ,列操作,計算 :res = df_age * 2
目的 : 字段 * 2
代碼 :
if __name__ =='__main__':# 全列顯示 :
pd.set_option('display.max_columns',None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
df_age = data["Age"]
res = df_age *2print(df_age)print(res)==============================================022.0138.0226.0....==================044.0176.0252.0...
3 ,列操作 : 增 data[“double_age”] = res
目的 : 將 double_age 列新增到原數據中
代碼 :
if __name__ =='__main__':# 全列顯示 :
pd.set_option('display.max_columns',None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
df_age = data["Age"]
res = df_age *2
data["double_age"]= res
print(data.head(3))=========================================
Age double_age ....22.044.038.076.026.052.0....
4 ,列操作,刪除列 :data.drop([“PassengerId”],axis=1)
代碼 :
if __name__ =='__main__':# 全列顯示 :# pd.set_option('display.max_columns', None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")print(data.head(5))
res = data.drop(["PassengerId","Survived"],axis=1)print(res.head(5))==================================================
PassengerId Survived Pclass ... Fare Cabin Embarked
0103...7.2500 NaN S
1211...71.2833 C85 C
2313...7.9250 NaN S
3411...53.1000 C123 S
4503...8.0500 NaN S
[5 rows x 12 columns]
Pclass Name ... Cabin Embarked
03 Braund, Mr. Owen Harris ... NaN S
11 Cumings, Mrs. John Bradley (Florence Briggs Th...... C85 C
23 Heikkinen, Miss. Laina ... NaN S
31 Futrelle, Mrs. Jacques Heath (Lily May Peel)... C123 S
43 Allen, Mr. William Henry ... NaN S
[5 rows x 10 columns]
if __name__ =='__main__':# 全列顯示 :# pd.set_option('display.max_columns', None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")print(data.head(5))
data.rename(columns={"PassengerId":"PassengerIdOMG"},inplace=True)print(data.head(5))===========================================
PassengerId Survived Pclass ... Fare Cabin Embarked
0103...7.2500 NaN S
1211...71.2833 C85 C
2313...7.9250 NaN S
3411...53.1000 C123 S
4503...8.0500 NaN S
[5 rows x 12 columns]
PassengerIdOMG Survived Pclass ... Fare Cabin Embarked
0103...7.2500 NaN S
1211...71.2833 C85 C
2313...7.9250 NaN S
3411...53.1000 C123 S
4503...8.0500 NaN S
[5 rows x 12 columns]
6 ,行操作,查 1 行 : data.loc[0]
代碼 :
if __name__ =='__main__':# 全列顯示 :# pd.set_option('display.max_columns', None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
res = data.loc[0]print(data.head(3))print(res)========================================================================
PassengerId Survived Pclass ... Fare Cabin Embarked
0103...7.2500 NaN S
1211...71.2833 C85 C
2313...7.9250 NaN S
[3 rows x 12 columns]==========================================
PassengerId 1
Survived 0
Pclass 3
Name Braund, Mr. Owen Harris
Sex male
Age 22
SibSp 1
Parch 0
Ticket A/521171
Fare 7.25
Cabin NaN
Embarked S
Name:0, dtype:object
7 ,行操作,計算 : res01 = res * 2
代碼 : 乘 2
if __name__ =='__main__':# 全列顯示 :# pd.set_option('display.max_columns', None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
res = data.loc[0]
res01 = res *2print(res)print(res01)================================
PassengerId 1
Survived 0
Pclass 3
Name Braund, Mr. Owen Harris
Sex male
Age 22
SibSp 1
Parch 0
Ticket A/521171
Fare 7.25
Cabin NaN
Embarked S
Name:0, dtype:object==================================================================
PassengerId 2
Survived 0
Pclass 6
Name Braund, Mr. Owen HarrisBraund, Mr. Owen Harris
Sex malemale
Age 44
SibSp 2
Parch 0
Ticket A/521171A/521171
Fare 14.5
Cabin NaN
Embarked SS
Name:0, dtype:object
8 ,行操作,增 : data.append(res01, ignore_index=True)
目的 :
1 ,將最後一行 * 2
2 ,再添加回去,成爲新的最後一行
代碼 :
if __name__ =='__main__':# 全列顯示 :# pd.set_option('display.max_columns', None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
res = data.loc[890]# 將數據 * 2
res01 = res *2# 將數據加入到 data 中
data = data.append(res01, ignore_index=True)print(data.tail(3))==============================================
PassengerId Survived Pclass ... Fare Cabin Embarked
88989011...30.00 C148 C
89089103...7.75 NaN Q
891178206...15.50 NaN QQ
9 ,行操作,刪 : res02 = res01.drop(2)
目的 : 利用索引刪除指定行
代碼 :
if __name__ =='__main__':# 全列顯示 :# pd.set_option('display.max_columns', None)# 讀文件 csv
data = pd.read_csv("titanic_train.csv")
res = data.loc[890]# 將數據 * 2
res01 = res *2# 將數據加入到 data 中
data = data.append(res01, ignore_index=True)
res01 = data.tail(3)print(res01)
res01.reset_index(inplace=True,drop=True)print(res01)# 刪除第三行 ( 索引爲 2 的那行 )
res02 = res01.drop(2)print(res02)===================================================88989011...30.00 C148 C
89089103...7.75 NaN Q
891178206...15.50 NaN QQ
[3 rows x 12 columns]
PassengerId Survived Pclass ... Fare Cabin Embarked
089011...30.00 C148 C
189103...7.75 NaN Q
2178206...15.50 NaN QQ
[3 rows x 12 columns]
PassengerId Survived Pclass ... Fare Cabin Embarked
089011...30.00 C148 C
189103...7.75 NaN Q
[2 rows x 12 columns]
10 ,過濾列 : res01[res01[“Age”]%2==0]
目的 : 留下年齡爲偶數的數
思想 : True 留下,False 剔除
代碼 :
if __name__ =='__main__':# 讀文件 csv
data = pd.read_csv("titanic_train.csv")# 年齡字段 :
df_age = data["Age"].to_frame()# 清除空值
res01 = df_age.dropna()# 留下偶數
res02 = res01[res01["Age"]%2==0]print(res02)==============================
Age
022.0138.0226.0