In [2]:
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
有两种丢失数据:
- None
- np.nan(NaN)
In [3]:
type(None)
Out[3]:
NoneType
In [4]:
type(np.nan)
Out[4]:
float
In [5]:
type(1000)
Out[5]:
int
In [6]:
type("hello")
Out[6]:
str
In [7]:
np.nan + 100
Out[7]:
nan
In [8]:
100 + "dsaf"
--------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-8-fb724d538b75> in <module>() ----> 1 100 + "dsaf" TypeError: unsupported operand type(s) for +: 'int' and 'str'
In [ ]:
None + 100
object类型的运算要比int类型的运算慢得多
计算不同数据类型求和时间
%timeit np.arange(1e5,dtype=xxx).sum()
In [ ]:
1e5
In [ ]:
%timeit np.arange(1e6,dtype="int").sum()