
import pandas as pd
from pandas import Series, DataFrame


import numpy as np
from numpy.random import randn
import os
import matplotlib.pyplot as plt
from myfunctions import *
np.random.seed(12345)
plt.rc('figure', figsize=(10, 6)) 
np.set_printoptions(precision=4)


obj = Series([100, 99, 100, 60])
obj

0    100
1     99
2    100
3     60
dtype: int64


obj.values

array([100,  99, 100,  60], dtype=int64)


obj.index

RangeIndex(start=0, stop=4, step=1)


obj2 = Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])
obj2

d    4
b    7
a   -5
c    3
dtype: int64


obj2['a']

-5


obj2['d'] = 6
obj2[['c', 'a', 'd']]

c    3
a   -5
d    6
dtype: int64


obj2[obj2 > 0]

d    6
b    7
c    3
dtype: int64


obj2

d    6
b    7
a   -5
c    3
dtype: int64


'b' in obj2.index

True


6 in obj2.values

True


sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}
obj3 = Series(sdata)
obj3

Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64


states = ['California', 'Ohio', 'Oregon', 'Texas']
obj4 = Series(sdata, index=states)
obj4

California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64


pd.isnull(obj4)

California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool


obj3

Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64


obj4

California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64


obj3 + obj4

California         NaN
Ohio           70000.0
Oregon         32000.0
Texas         142000.0
Utah               NaN
dtype: float64

obj

0    100
1     99
2    100
3     60
dtype: int64


obj.index = ['Tom', 'Steve', 'Jeff', 'Ryan']
obj

Tom      100
Steve     99
Jeff     100
Ryan      60
dtype: int64


data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002],
        'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}
frame = DataFrame(data)
frame


DataFrame(data, columns=['year', 'state', 'pop'])


frame2 = DataFrame(data, columns=['year', 'state', 'pop', 'debt'],
                   index=['one', 'two', 'three', 'four', 'five'])
frame2


frame2['state']

one        Ohio
two        Ohio
three      Ohio
four     Nevada
five     Nevada
Name: state, dtype: object


frame2.year

one      2000
two      2001
three    2002
four     2001
five     2002
Name: year, dtype: int64


frame2.ix['three']

C:\Anaconda\envs\py3\lib\site-packages\ipykernel_launcher.py:1: DeprecationWarning: 
.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/indexing.html#ix-indexer-is-deprecated
  """Entry point for launching an IPython kernel.

year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object


#frame2.loc['three']
frame2.iloc[2]

year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object


frame2['debt'] = 16.5
frame2


frame2['debt'] = np.arange(5.)
frame2


val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2['debt'] = val
frame2


frame2['eastern'] = frame2.state == 'Ohio'
frame2


del frame2['eastern']
frame2.columns

Index(['year', 'state', 'pop', 'debt'], dtype='object')


pop = {'Nevada': {2001: 2.4, 2002: 2.9},
       'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}


frame3 = DataFrame(pop)
frame3


frame3.T


frame3.values

array([[nan, 1.5],
       [2.4, 1.7],
       [2.9, 3.6]])


frame2.values

array([[2000, 'Ohio', 1.5, nan],
       [2001, 'Ohio', 1.7, -1.2],
       [2002, 'Ohio', 3.6, nan],
       [2001, 'Nevada', 2.4, -1.5],
       [2002, 'Nevada', 2.9, -1.7]], dtype=object)


frame4=DataFrame(np.array([[0, 1.5],
       [ 2.4,  1.7],
       [ 2.9,  3.6]]),index=['2001','2002','2003'],columns=['Nevada','Ohio'])
frame4


stockinfo=pd.read_excel("E:\\我的坚果云\\2017datafin\\A股基本资料.xlsx")


x=stockinfo['主营产品名称']
a=x[1]
b=stockinfo['主营产品类型']
b[2]

'物业出租和管理、系统集成服务、血液系统用制剂、原料药、植物类中药制剂'


stockinfo.columns

Index(['证券代码', '证券简称', '上市地点', '股票简称', '股票英文简称', '上市日期', '公司属性', '成立日期',
       '主营产品名称', '主营产品类型', '员工总数\r\n[交易日期] 2011-12-31',
       '员工总数\r\n[交易日期] 2012-12-31', '员工总数\r\n[交易日期] 2013-12-31',
       '员工总数\r\n[交易日期] 2014-12-31', '员工总数\r\n[交易日期] 2015-12-31',
       '员工总数\r\n[交易日期] 2016-12-31', '省份', '城市', '公司电话', '公司传真', '公司电子邮件地址',
       '公司网站', '公司发行证券一览', '董事长\r\n[交易日期] 最新', '公司独立董事(现任)', '公司独立董事(历任)',
       '总经理\r\n[交易日期] 最新', '资产评估机构', '法律顾问', '审计机构'],
      dtype='object')


stockinfo.tail(1)


finfutureinfo=pd.read_excel("E:\\我的坚果云\\2017datafin\\中金所品种.xlsx")


finfutureinfo.loc[20]

证券代码                  IH1710.CFE
证券简称                      IH1710
期货简称                      IH1710
期货代码                      IH1710
交易所简称                  中国金融期货交易所
涨跌幅限制                         10
交易保证金                         15
开始交易日        2017-08-21 00:00:00
最后交易日        2017-10-20 00:00:00
最后交割日        2017-10-20 00:00:00
交割月份                      201710
交易品种                    上证50股指期货
交易单位                          1张
合约乘数                         300
报价单位                           张
最小变动价位                    0.2指数点
最初交易保证金         最低交易保证金:合约价值的15%
最初交易保证金.1       最低交易保证金:合约价值的15%
Name: 20, dtype: object


commodityinfo=pd.read_excel("E:\\我的坚果云\\2017datafin\\大连商品品种.xlsx")


commodityinfo.loc[1]

证券代码                   V1711.DCE
证券简称                     PVC1711
期货简称                     PVC1711
期货代码                       V1711
交易所简称                    大连商品交易所
涨跌幅限制                          5
交易保证金                          7
开始交易日        2016-11-15 00:00:00
最后交易日        2017-11-14 00:00:00
最后交割日        2017-11-17 00:00:00
交割月份                      201711
交易品种                        聚氯乙烯
交易单位                          5吨
合约乘数                           5
报价单位                           吨
最小变动价位                   5人民币元/吨
最初交易保证金          最低交易保证金:合约价值的7%
最初交易保证金.1        最低交易保证金:合约价值的7%
Name: 1, dtype: object


commodityinfo.tail(2)


obj = Series(np.arange(5.), index=['a', 'b', 'c', 'd', 'e'])
obj.drop(['d', 'c'])

a    0.0
b    1.0
e    4.0
dtype: float64


data = DataFrame(np.arange(16).reshape((4, 4)),
                 index=['Ohio', 'Colorado', 'Utah', 'New York'],
                 columns=['one', 'two', 'three', 'four'])


data.drop(['two', 'four'], axis=1)


data


#用一个或多个关键字索引
obj = Series(np.arange(4.), index=['a', 'b', 'c', 'd'])
print(obj['b']) # index
obj[['b', 'a', 'd']]

1.0

b    1.0
a    0.0
d    3.0
dtype: float64


#通过一个整数或整数list索引
print(obj[1])
obj[[1, 3]]

1.0

b    1.0
d    3.0
dtype: float64


#用逻辑值索引
obj[obj < 2]

a    0.0
b    1.0
dtype: float64


data = DataFrame(np.arange(16).reshape((4, 4)),
                 index=['Ohio', 'Colorado', 'Utah', 'New York'],
                 columns=['one', 'two', 'three', 'four'])
data


print(data)
data[['three', 'one']]

          one  two  three  four
Ohio        0    1      2     3
Colorado    4    5      6     7
Utah        8    9     10    11
New York   12   13     14    15


print(data)
data[:2] # 切片适用

          one  two  three  four
Ohio        0    1      2     3
Colorado    4    5      6     7
Utah        8    9     10    11
New York   12   13     14    15


#利用逻辑值索引行

print(data)
data[(data['three'] > 5) &  (data['four']>7)]

          one  two  three  four
Ohio        0    1      2     3
Colorado    4    5      6     7
Utah        8    9     10    11
New York   12   13     14    15


data < 5


data[data < 5]


data[data < 5] = 0
data


#只指定一个整数，索引一列
data.iloc[2]

one       8
two       9
three    10
four     11
Name: Utah, dtype: int32


 
#data1=data.ix[['Colorado', 'Utah'], ['two', 'three']] 
 
data2=data.ix[['Colorado', 'Utah'], [3, 0, 1]]
 
data3=data.ix[data.three > 5, :3] 

side_by_side(data,data2,data3)


#新版本中的更新
#data.ix[['Colorado', 'Utah'], [3, 0, 1]]
data.loc[['Colorado', 'Utah'], data.columns[[3, 0, 1]]]


s1 = Series([7.3, -2.5, 3.4, 1.5], index=['a', 'c', 'd', 'e'])
s2 = Series([-2.1, 3.6, -1.5, 4, 3.1], index=['a', 'c', 'e', 'f', 'g'])
s1 + s2

a    5.2
c    1.1
d    NaN
e    0.0
f    NaN
g    NaN
dtype: float64


df1 = DataFrame(np.arange(9.).reshape((3, 3)), columns=list('bcd'),
                index=['Ohio', 'Texas', 'Colorado'])
df2 = DataFrame(np.arange(12.).reshape((4, 3)), columns=list('bde'),
                index=['Utah', 'Ohio', 'Texas', 'Oregon'])
side_by_side(df1,df2,df1 + df2)


df1 = DataFrame(np.arange(12.).reshape((3, 4)), columns=list('abcd'))
df2 = DataFrame(np.arange(20.).reshape((4, 5)), columns=list('abcde'))
#dfadd=df1+df2
dfaddfill0=df1.add(df2, fill_value=0)
side_by_side(df1,df2,dfaddfill0)


arr = np.arange(12.).reshape((3, 4))
#print(arr)
#arr - arr[0]
arr

array([[ 0.,  1.,  2.,  3.],
       [ 4.,  5.,  6.,  7.],
       [ 8.,  9., 10., 11.]])


arr - arr[0]

array([[0., 0., 0., 0.],
       [4., 4., 4., 4.],
       [8., 8., 8., 8.]])


frame = DataFrame(np.arange(12.).reshape((4, 3)), columns=list('bde'),
                  index=['Utah', 'Ohio', 'Texas', 'Oregon'])
series = frame.iloc[0]
fsubr=frame - series
side_by_side(frame,fsubr)


series2 = Series(range(3), index=['b', 'e', 'f'])
frame + series2


series3 = frame['d']
fsubc=frame.sub(series3, axis=0)

side_by_side(frame,fsubc)


frame = DataFrame(np.random.randn(4, 3), columns=list('bde'),
                  index=['Utah', 'Ohio', 'Texas', 'Oregon'])
fabs=np.abs(frame)
side_by_side(frame,fabs)


frame


f = lambda x: x.max() - x.min()

frame.apply(f)

b    1.802165
d    1.684034
e    2.689627
dtype: float64


#　将函数应用到列
frame.apply(f, axis=1)

Utah      0.998382
Ohio      2.521511
Texas     0.676115
Oregon    2.542656
dtype: float64


def f(x):
    return Series([x.min(), x.max()], index=['min', 'max'])
frame.apply(f)


format = lambda x: '%.2f' % x
frame.applymap(format)


frame['e'].map(format)

Utah      -0.52
Ohio       1.39
Texas      0.77
Oregon    -1.30
Name: e, dtype: object


#按照索引关键字进行排序，使用sort_index方法，
obj = Series(range(4), index=['d', 'a', 'b', 'c'])
obj.sort_index()

a    1
b    2
c    3
d    0
dtype: int64


#对DataFrame，默认对行排
frame = DataFrame(np.arange(8).reshape((2, 4)), index=['three', 'one'],
                  columns=['d', 'a', 'b', 'c'])
frame.sort_index()


#，如果对列索引排，需要指明 axis=1,
frame.sort_index(axis=1)


frame.sort_index(axis=1, ascending=False)


#如果需要对Series的值排序，则用order方法。缺失值会放到末尾。
obj = Series([4, 7, -3, 2])
obj.sort_values()

2   -3
3    2
0    4
1    7
dtype: int64


obj = Series([4, np.nan, 7, np.nan, -3, 2])
obj.sort_values()

4   -3.0
5    2.0
0    4.0
2    7.0
1    NaN
3    NaN
dtype: float64


# 对DataFrame的值进行排序，传递给选项by列名称即可。

frame = DataFrame({'b': [4, 7, -3, 2], 'a': [0, 1, 0, 1]})
sortbyb=frame.sort_values(by='b')
sortbyab=frame.sort_values(by=['a', 'b'])
side_by_side(frame,sortbyb,sortbyab)


obj = Series([7, -5, 7, 4, 2, 0, 4])
obj.rank()

0    6.5
1    1.0
2    6.5
3    4.5
4    3.0
5    2.0
6    4.5
dtype: float64


obj.rank(ascending=False, method='max')

0    2.0
1    7.0
2    2.0
3    4.0
4    5.0
5    6.0
6    4.0
dtype: float64


frame = DataFrame({'b': [4.3, 7, -3, 2], 'a': [0, 1, 0, 1],
                   'c': [-2, 5, 8, -2.5]})
side_by_side(frame,frame.rank())


frame.rank(axis=1)


obj = Series(range(5), index=['a', 'a', 'b', 'b', 'c'])
obj

a    0
a    1
b    2
b    3
c    4
dtype: int64


obj['a']

a    0
a    1
dtype: int64


df = DataFrame(np.random.randn(4, 3), index=['a', 'a', 'b', 'b'])
df


df.loc['b']


df = DataFrame([[1.4, np.nan], [7.1, -4.5],
                [np.nan, np.nan], [0.75, -1.3]],
               index=['a', 'b', 'c', 'd'],
               columns=['one', 'two'])


df.sum()

one    9.25
two   -5.80
dtype: float64


df.sum(axis=1)
#缺失值处理方法?

a    1.40
b    2.60
c    0.00
d   -0.55
dtype: float64


df.sum(axis=1, skipna=False)

a     NaN
b    2.60
c     NaN
d   -0.55
dtype: float64


df['three']=1
df


df.idxmax()
# first occurrence

one      b
two      d
three    a
dtype: object


res1=df.cumsum(axis=1)
side_by_side(df,res1)


obj = Series(['a', 'b', 'b', 'b'] * 4)
obj.describe()

count     16
unique     2
top        b
freq      12
dtype: object


obj = Series(['c', 'a', 'd', 'a', 'a', 'b', 'b', 'c', 'c'])


uniques = obj.unique()
uniques

array(['c', 'a', 'd', 'b'], dtype=object)


#计算频数
obj.value_counts()

a    3
c    3
b    2
d    1
dtype: int64


# 判断包含关系
mask = obj.isin(['b', 'c'])
mask

0     True
1    False
2    False
3    False
4    False
5     True
6     True
7     True
8     True
dtype: bool


#利用布尔索引，取出相应数据
obj[mask]

0    c
5    b
6    b
7    c
8    c
dtype: object


data = DataFrame({'Qu1': [1, 3, 4, 3, 4],
                  'Qu2': [2, 3, 1, 2, 3],
                  'Qu3': [1, 5, 2, 4,5]})
# 计算各个数出现的频数,按列
result = data.apply(pd.value_counts,axis=1)
side_by_side(data,result)


string_data = Series(['aardvark', 'artichoke', np.nan, 'avocado'])
string_data

0     aardvark
1    artichoke
2          NaN
3      avocado
dtype: object


string_data.isnull()

0    False
1    False
2     True
3    False
dtype: bool


from numpy import nan as NA
data = Series([1, NA, 3.5, NA, 7])
data.dropna()

0    1.0
2    3.5
4    7.0
dtype: float64


data[data.notnull()]

0    1.0
2    3.5
4    7.0
dtype: float64


# DataFrame
data = DataFrame([[1., 6.5, 3.], [1., NA, NA],
                  [NA, NA, NA], [NA, 6.5, 3.]])

data


cleaned = data.dropna()
cleaned


data.dropna?


# 其它参数选项
res1=data.dropna(axis=0,how='all')
side_by_side(data,res1)


df.fillna(0)


res2=df.fillna({"one": 0.5, "two": -1},axis=0)
side_by_side(df,res2)


data = Series(np.random.randn(10),
              index=[['a', 'a', 'a', 'b', 'b', 'b', 'c', 'c', 'd', 'd'],
                     [1, 2, 3, 1, 2, 3, 1, 2, 2, 3]])
data

a  1   -0.577087
   2    0.124121
   3    0.302614
b  1    0.523772
   2    0.000940
   3    1.343810
c  1   -0.713544
   2   -0.831154
d  2   -2.370232
   3   -1.860761
dtype: float64


data.index

MultiIndex(levels=[['a', 'b', 'c', 'd'], [1, 2, 3]],
           labels=[[0, 0, 0, 1, 1, 1, 2, 2, 3, 3], [0, 1, 2, 0, 1, 2, 0, 1, 1, 2]])


data['b']

1    0.523772
2    0.000940
3    1.343810
dtype: float64


data['b':'c']

b  1    0.523772
   2    0.000940
   3    1.343810
c  1   -0.713544
   2   -0.831154
dtype: float64


data.loc[['b', 'd']]

b  1    0.523772
   2    0.000940
   3    1.343810
d  2   -2.370232
   3   -1.860761
dtype: float64


data[:, 2]

a    0.124121
b    0.000940
c   -0.831154
d   -2.370232
dtype: float64


frame = DataFrame({'a': range(7), 'b': range(7, 0, -1),
                   'c': ['one', 'one', 'one', 'two', 'two', 'two', 'two'],
                   'd': [0, 1, 2, 0, 1, 2, 3],
                "e":["四川"]*5+["北京"]*2})
frame


frame2 = frame.set_index(['c', 'd'])
frame2


frame.set_index(['c', 'd'], drop=False)


df1 = DataFrame({'key': ['b', 'b', 'a', 'c', 'a', 'a', 'b'],
                 'data1': range(7)})
df2 = DataFrame({'key': ['a', 'b', 'b'],
                 'data2': range(3)})
side_by_side(df1,df2)


pd.merge(df1, df2) # 共同的关键字，inner

	a	b	c	d	e
0	0.0	1.0	2.0	3.0	4.0
1	5.0	6.0	7.0	8.0	9.0
2	10.0	11.0	12.0	13.0	14.0
3	15.0	16.0	17.0	18.0	19.0

	a	b	c	d	e
0	0.0	2.0	4.0	6.0	4.0
1	9.0	11.0	13.0	15.0	9.0
2	18.0	20.0	22.0	24.0	14.0
3	15.0	16.0	17.0	18.0	19.0

	b	d	e
Utah	-0.204708	0.478943	-0.519439
Ohio	-0.555730	1.965781	1.393406
Texas	0.092908	0.281746	0.769023
Oregon	1.246435	1.007189	-1.296221

	b	d	e
Utah	0.204708	0.478943	0.519439
Ohio	0.555730	1.965781	1.393406
Texas	0.092908	0.281746	0.769023
Oregon	1.246435	1.007189	1.296221

	b	d	e
Utah	-0.204708	0.478943	-0.519439
Ohio	-0.555730	1.965781	1.393406
Texas	0.092908	0.281746	0.769023
Oregon	1.246435	1.007189	-1.296221

Pandas [CHI]

pandas¶

内容¶

介绍Pandas数据结构¶

Series¶

DataFrame¶

基本功能¶

舍弃某些数据¶

索引、选取和过滤（ Indexing, selection, and filtering）¶

算术运算和数据对齐¶

处理运算中的缺失值¶

DataFrame 和 Series 之间的运算¶

函数应用和映射¶

序¶

有重复的索引¶

汇总和描述性统计量的计算¶

唯一集合，频数等¶

处理缺失值¶

数据选择，滤掉一些缺失值¶

填补缺失值¶

分层索引¶

使用 DataFrame的列作为索引使用¶

数据合并¶

	pop	state	year
0	1.5	Ohio	2000
1	1.7	Ohio	2001
2	3.6	Ohio	2002
3	2.4	Nevada	2001
4	2.9	Nevada	2002

	year	state	pop	debt
one	2000	Ohio	1.5	16.5
two	2001	Ohio	1.7	16.5
three	2002	Ohio	3.6	16.5
four	2001	Nevada	2.4	16.5
five	2002	Nevada	2.9	16.5

	year	state	pop	debt	eastern
one	2000	Ohio	1.5	NaN	True
two	2001	Ohio	1.7	-1.2	True
three	2002	Ohio	3.6	NaN	True
four	2001	Nevada	2.4	-1.5	False
five	2002	Nevada	2.9	-1.7	False

	证券代码	证券简称	期货简称	期货代码	交易所简称	涨跌幅限制	交易保证金	开始交易日	最后交易日	最后交割日	交割月份	交易品种	交易单位	合约乘数	报价单位	最小变动价位	最初交易保证金	最初交易保证金.1
165	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaT	NaT	NaT	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
166	数据来源：Wind资讯	NaN	NaN	NaN	NaN	NaN	NaN	NaT	NaT	NaT	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	one	two	three	four
Ohio	0.0	1.0	2.0	3.0
Colorado	4.0	NaN	NaN	NaN
Utah	NaN	NaN	NaN	NaN
New York	NaN	NaN	NaN	NaN

	b	d	e
Utah	-0.20	0.48	-0.52
Ohio	-0.56	1.97	1.39
Texas	0.09	0.28	0.77
Oregon	1.25	1.01	-1.30

	0	1	2
a	0.274992	0.228913	1.352917
a	0.886429	-2.001637	-0.371843
b	1.669025	-0.438570	-0.539741
b	0.476985	3.248944	-1.021228

	1	2	3	4	5
0	2.0	1.0	NaN	NaN	NaN
1	NaN	NaN	2.0	NaN	1.0
2	1.0	1.0	NaN	1.0	NaN
3	NaN	1.0	1.0	1.0	NaN
4	NaN	NaN	1.0	1.0	1.0

	a	b	c	d	e
0	0	7	one	0	四川
1	1	6	one	1	四川
2	2	5	one	2	四川
3	3	4	two	0	四川
4	4	3	two	1	四川
5	5	2	two	2	北京
6	6	1	two	3	北京

	1	2	3	4	5
0	2.0	1.0	NaN	NaN	NaN
1	NaN	NaN	2.0	NaN	1.0
2	1.0	1.0	NaN	1.0	NaN
3	NaN	1.0	1.0	1.0	NaN
4	NaN	NaN	1.0	1.0	1.0

Pandas [CHI]

pandas¶

内容¶

介绍Pandas数据结构¶

Series¶

DataFrame¶

基本功能¶

舍弃某些数据¶

索引、选取和过滤 （ Indexing, selection, and filtering）¶

算术运算和数据对齐¶

处理运算中的缺失值¶

DataFrame 和 Series 之间的运算¶

函数应用和映射¶

序¶

有重复的索引¶

汇总和描述性统计量的计算¶

唯一集合，频数等¶

处理缺失值¶

数据选择，滤掉一些缺失值¶

填补缺失值¶

分层索引¶

使用 DataFrame的列作为索引使用¶

数据合并¶

索引、选取和过滤（ Indexing, selection, and filtering）¶

	1	2	3	4	5
0	2.0	1.0	NaN	NaN	NaN
1	NaN	NaN	2.0	NaN	1.0
2	1.0	1.0	NaN	1.0	NaN
3	NaN	1.0	1.0	1.0	NaN
4	NaN	NaN	1.0	1.0	1.0