【数据分析可视化】谈一谈NaN

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

# 创建NaN
n = np.nan

# 类型
type(n)

float

# 任何数字和nan做计算永远是nan
m = 1
m + n

nan

# 创建含nan情况
s1 = Series([1,2,np.nan,3,4],index=['A','B','C','D','E'])
s1

A    1.0
B    2.0
C    NaN
D    3.0
E    4.0
dtype: float64

# 判断是否nan
s1.isnull()

A    False
B    False
C     True
D    False
E    False
dtype: bool

s1.notnull()

A     True
B     True
C    False
D     True
E     True
dtype: bool

# nan删除掉nan
s1.dropna()

A    1.0
B    2.0
D    3.0
E    4.0
dtype: float64

# 创建含有nan情况
df1 = DataFrame(np.random.rand(25).reshape(5,5))
df1.ix[2,4] = np.nan
df1.ix[1,3] = np.nan
df1

/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:3: FutureWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated
  This is separate from the ipykernel package so we can avoid doing imports until
/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:4: FutureWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated
  after removing the cwd from sys.path.

# 判断nan
df1.isnull()

df1.notnull()

# 删除的使用（df二维的，因此略有不同）
# axis=0所有带nan的行全部删除
df2 = df1.dropna(axis=0)
df2

# axis=1所有带nan的列全部删除
df2 = df1.dropna(axis=1)
df2

# 如何删除now，参数now
# any 只要有一个为nan就删掉 当前行或列
df2 = df1.dropna(axis=0,how='any')
df2

# 如何删除now，参数now
# all 只有全部为nan就删掉 当前行或列
df2 = df1.dropna(axis=0,how='all')
df2

# 为测试thresh参数新建数据
df2 = DataFrame(np.random.rand(25).reshape(5,5))
df2.ix[2,:] = np.nan
df2.ix[1,3] = np.nan
df2.ix[3,3] = np.nan
df2.ix[3,4] = np.nan
df2

/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:3: FutureWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated
  This is separate from the ipykernel package so we can avoid doing imports until
/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:4: FutureWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated
  after removing the cwd from sys.path.
/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:5: FutureWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated
  """
/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:6: FutureWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated

# thresh参数是一个删除界限（当前行或列的nan>2，则删除）
df3 = df2.dropna(thresh=2)
df3

# nan填充值（可以具体指定行列nan填充值）
df2.fillna(value=1)

# 可以具体指定行列nan填充值）
df2.fillna(value={0:0,1:1,2:2,3:3,4:4})