pandas基础

#数组排序
fr1 = DataFrame(np.arange(8).reshape((2,4)), index=['three', 'one'], columns=['d', 'a', 'b', 'c'])
print (fr1)
print (fr1.sort_index())
print (fr1.sort_index(ascending=False))     #降序排序
print (fr1.sort_index(axis=1))
print (fr1.sort_index(axis=1, ascending=False))     #降序排序

#默认为使用索引排序

s1 = Series(range(4), index=['d','a','b','c'])

print (s1.sort_index())

s2 =Series([4, np.nan, 7, np.nan, -3, 2])
print (type(s1))
print (type(s2))
print (s2.sort_index())
print (s2.sort_values())
print (s2.sort_values(ascending=False))

 

DateFrame中，loc与iloc的区别：

loc使用的是列名称与索引名称作为位置的查找点，如下：

df1 = pd.DataFrame([[10,50],[20,60],[30,70],[40,80]], columns=['number1', 'number2'], index=['a','b','c','d'])

print (type(df1.loc['a']))
print (type(df1.loc[['a']]))
print (df1.loc[['a','d'],'number1'])        #loc，代表行和列标签，以逗号分割
print (df1.loc['a','number2'])              #二维坐标
print (df1.loc[:, 'number2'])

iloc则是相当于把表进行进行数字位置化，然后全部使用数字进行操作:

print (df1.iloc[0,0])
print (df1.iloc[[0,3], 0])
print (df1.iloc[0:4,1])