版权声明：欢迎分享和转载，请注明出处 shuihupo：https://blog.csdn.net/shuihupo.同时,本博客部分会在云南省高校数据化运营管理工程中心博客同步。欢迎沟通交流：[email protected] https://blog.csdn.net/shuihupo/article/details/83105214
import pandas as pd
df = pd.DataFrame({"key":['green','red', 'blue'],
"data1":['a','b','c'],"sorce": [33,61,99],"sorce1": [33,61,99],"sorce2": [33,61,99]})
data1 = pd.concat([df,df],ignore_index=True)
data2=data1[-data1.sorce.isin([61])]
print("---------------")
print(data1)
print("---------------")
print(data2)
print(df["data1"])
a =pd.DataFrame(df["sorce"].append(df["sorce1"]).append(df["sorce2"]).describe(),columns=["sorce1"])
a["sorce4"]=df["sorce"].append(df["sorce1"]).append(df["sorce2"]).describe()
print(a)import pandas as pd
df = pd.DataFrame({"key":['green','red', 'blue'],
"data1":['a','b','c'],"sorce": [33,61,99]})
# # get_dummies 指定一列进行哑变量变换,在不指定新列的列名的情况下，将以原标签为列名
# print("-------df---------")
# print(df)
# df_dummies1 =pd.get_dummies(df["key"])
# print('''-------pd.get_dummies(df["key"])---------''')
# print(df_dummies1)
# #prefix参数可以给哑变量的名字加上一个前缀
# df_dummies2 =pd.get_dummies(df["key"],prefix="key")
# print('''---=pd.get_dummies(df["key"],prefix="key")---------''')
# print(df_dummies2)
# #如果不指定列的话，默认是所有的分类变量进行one_hot处理
# df_dummies3 =pd.get_dummies(df)
# print("-------pd.get_dummies(df)---------")
# print(df_dummies3)
# #prefix参数可以给哑变量的名字加上一个前缀,如果是多个则需要一个列参数
# df_dummies4 =pd.get_dummies(df,prefix=["class","like"])
# print('''-------pd.get_dummies(df,prefix=["class","like"])---------''')
# print(df_dummies4)
# print('''----------------''')
# df_new= pd.merge(df,df_dummies3)
# print(df_new)
# print(df_new.columns)
#
# df_dummies5 =pd.get_dummies(df,columns=["key","sorce"])
# print('''---=pd.get_dummies(df,columns=["key","sorce"])---------''')
# print(df_dummies5)
#
# bins=[0,61,80,100]
# cats=pd.cut(df["sorce"],bins)
# print(cats)
# group_name=["不及格","及格","优秀"]
# cats2=pd.cut(df["sorce"],bins,labels=group_name,right=False)
# print(cats2)
# df_dummies6=pd.get_dummies(cats2,prefix="sorce")
# print("----------------")# right是否是区间闭端