notebook.community

Edit and run



In [1]:

    
import h2o



In [2]:

    
h2o.init()









    




H2O cluster uptime: 
7 minutes 34 seconds 146 milliseconds 
H2O cluster version: 
3.1.0.99999
H2O cluster name: 
spencer
H2O cluster total nodes: 
1
H2O cluster total memory: 
14.22 GB
H2O cluster total cores: 
8
H2O cluster allowed cores: 
8
H2O cluster healthy: 
True
H2O Connection ip: 
127.0.0.1
H2O Connection port: 
54321



In [3]:

    
air = h2o.upload_file(h2o.locate("smalldata/airlines/allyears2k_headers.zip"))









    



Parse Progress: [##################################################] 100%
Uploaded py2eedb6c5-0858-4b7f-833f-b24ab23140f8 into cluster with 43,978 rows and 31 cols



In [4]:

    
air.dim









    Out[4]:





[43978, 31]



In [5]:

    
numNAs = air["DepTime"].isna().sum()
print numNAs



In [6]:

    
DepTime_mean = air["DepTime"].mean(na_rm=True)
print DepTime_mean









    



1345.84666138



In [7]:

    
air.impute("DepTime", method = "median", combine_method="low")   
numNAs = air["DepTime"].isna().sum()
print numNAs

0.0



In [8]:

    
air = h2o.upload_file(h2o.locate("smalldata/airlines/allyears2k_headers.zip"))









    



Parse Progress: [##################################################] 100%
Uploaded py74d01579-0aba-47ba-91a9-c9df3c8b4649 into cluster with 43,978 rows and 31 cols



In [9]:

    
air.impute("DepTime", method = "mean", by = ["Origin", "Distance"]).show()









    



First 10 rows and first 31 columns: 






    




Year
Month
DayofMonth
DayOfWeek
DepTime
CRSDepTime
ArrTime
CRSArrTime
UniqueCarrier
FlightNum
TailNum
ActualElapsedTime
CRSElapsedTime
AirTime
ArrDelay
DepDelay
Origin
Dest
Distance
TaxiIn
TaxiOut
Cancelled
CancellationCode
Diverted
CarrierDelay
WeatherDelay
NASDelay
SecurityDelay
LateAircraftDelay
IsArrDelayed
IsDepDelayed
1987
10
14
3
741
730
912
849
PS
1451
NA
91
79

23
11
SAN
SFO
447


0
NA
0





YES
YES
1987
10
15
4
729
730
903
849
PS
1451
NA
94
79

14
-1
SAN
SFO
447


0
NA
0





YES
NO
1987
10
17
6
741
730
918
849
PS
1451
NA
97
79

29
11
SAN
SFO
447


0
NA
0





YES
YES
1987
10
18
7
729
730
847
849
PS
1451
NA
78
79

-2
-1
SAN
SFO
447


0
NA
0





NO
NO
1987
10
19
1
749
730
922
849
PS
1451
NA
93
79

33
19
SAN
SFO
447


0
NA
0





YES
YES
1987
10
21
3
728
730
848
849
PS
1451
NA
80
79

-1
-2
SAN
SFO
447


0
NA
0





NO
NO
1987
10
22
4
728
730
852
849
PS
1451
NA
84
79

3
-2
SAN
SFO
447


0
NA
0





YES
NO
1987
10
23
5
731
730
902
849
PS
1451
NA
91
79

13
1
SAN
SFO
447


0
NA
0





YES
YES
1987
10
24
6
744
730
908
849
PS
1451
NA
84
79

19
14
SAN
SFO
447


0
NA
0





YES
YES
1987
10
25
7
729
730
851
849
PS
1451
NA
82
79

2
-1
SAN
SFO
447


0
NA
0





YES
NO



In [10]:

    
air = h2o.upload_file(h2o.locate("smalldata/airlines/allyears2k_headers.zip"))









    



Parse Progress: [##################################################] 100%
Uploaded pyf6d4c8d3-78a3-4c26-9adb-a282583ae563 into cluster with 43,978 rows and 31 cols



In [11]:

    
air.impute("TailNum", method = "mode").show()









    



First 10 rows and first 31 columns: 






    




Year
Month
DayofMonth
DayOfWeek
DepTime
CRSDepTime
ArrTime
CRSArrTime
UniqueCarrier
FlightNum
TailNum
ActualElapsedTime
CRSElapsedTime
AirTime
ArrDelay
DepDelay
Origin
Dest
Distance
TaxiIn
TaxiOut
Cancelled
CancellationCode
Diverted
CarrierDelay
WeatherDelay
NASDelay
SecurityDelay
LateAircraftDelay
IsArrDelayed
IsDepDelayed
1987
10
14
3
741
730
912
849
PS
1451
NA
91
79

23
11
SAN
SFO
447


0
NA
0





YES
YES
1987
10
15
4
729
730
903
849
PS
1451
NA
94
79

14
-1
SAN
SFO
447


0
NA
0





YES
NO
1987
10
17
6
741
730
918
849
PS
1451
NA
97
79

29
11
SAN
SFO
447


0
NA
0





YES
YES
1987
10
18
7
729
730
847
849
PS
1451
NA
78
79

-2
-1
SAN
SFO
447


0
NA
0





NO
NO
1987
10
19
1
749
730
922
849
PS
1451
NA
93
79

33
19
SAN
SFO
447


0
NA
0





YES
YES
1987
10
21
3
728
730
848
849
PS
1451
NA
80
79

-1
-2
SAN
SFO
447


0
NA
0





NO
NO
1987
10
22
4
728
730
852
849
PS
1451
NA
84
79

3
-2
SAN
SFO
447


0
NA
0





YES
NO
1987
10
23
5
731
730
902
849
PS
1451
NA
91
79

13
1
SAN
SFO
447


0
NA
0





YES
YES
1987
10
24
6
744
730
908
849
PS
1451
NA
84
79

19
14
SAN
SFO
447


0
NA
0





YES
YES
1987
10
25
7
729
730
851
849
PS
1451
NA
82
79

2
-1
SAN
SFO
447


0
NA
0





YES
NO



In [12]:

    
air = h2o.upload_file(h2o.locate("smalldata/airlines/allyears2k_headers.zip"))









    



Parse Progress: [##################################################] 100%
Uploaded py77ce3a79-0fa0-4116-91d4-c928a7084e68 into cluster with 43,978 rows and 31 cols



In [13]:

    
air.impute("TailNum", method = "mode", by=["Month", "Year"]).show()









    



First 10 rows and first 31 columns: 






    




Year
Month
DayofMonth
DayOfWeek
DepTime
CRSDepTime
ArrTime
CRSArrTime
UniqueCarrier
FlightNum
TailNum
ActualElapsedTime
CRSElapsedTime
AirTime
ArrDelay
DepDelay
Origin
Dest
Distance
TaxiIn
TaxiOut
Cancelled
CancellationCode
Diverted
CarrierDelay
WeatherDelay
NASDelay
SecurityDelay
LateAircraftDelay
IsArrDelayed
IsDepDelayed
1987
10
14
3
741
730
912
849
PS
1451
NA
91
79

23
11
SAN
SFO
447


0
NA
0





YES
YES
1987
10
15
4
729
730
903
849
PS
1451
NA
94
79

14
-1
SAN
SFO
447


0
NA
0





YES
NO
1987
10
17
6
741
730
918
849
PS
1451
NA
97
79

29
11
SAN
SFO
447


0
NA
0





YES
YES
1987
10
18
7
729
730
847
849
PS
1451
NA
78
79

-2
-1
SAN
SFO
447


0
NA
0





NO
NO
1987
10
19
1
749
730
922
849
PS
1451
NA
93
79

33
19
SAN
SFO
447


0
NA
0





YES
YES
1987
10
21
3
728
730
848
849
PS
1451
NA
80
79

-1
-2
SAN
SFO
447


0
NA
0





NO
NO
1987
10
22
4
728
730
852
849
PS
1451
NA
84
79

3
-2
SAN
SFO
447


0
NA
0





YES
NO
1987
10
23
5
731
730
902
849
PS
1451
NA
91
79

13
1
SAN
SFO
447


0
NA
0





YES
YES
1987
10
24
6
744
730
908
849
PS
1451
NA
84
79

19
14
SAN
SFO
447


0
NA
0





YES
YES
1987
10
25
7
729
730
851
849
PS
1451
NA
82
79

2
-1
SAN
SFO
447


0
NA
0





YES
NO

H2O cluster uptime:	7 minutes 34 seconds 146 milliseconds
H2O cluster version:	3.1.0.99999
H2O cluster name:	spencer
H2O cluster total nodes:	1
H2O cluster total memory:	14.22 GB
H2O cluster total cores:	8
H2O cluster allowed cores:	8
H2O cluster healthy:	True
H2O Connection ip:	127.0.0.1
H2O Connection port:	54321

Year	Month	DayofMonth	DayOfWeek	DepTime	CRSDepTime	ArrTime	CRSArrTime	UniqueCarrier	FlightNum	TailNum	ActualElapsedTime	CRSElapsedTime	AirTime	ArrDelay	DepDelay	Origin	Dest	Distance	TaxiIn	TaxiOut	Cancelled	CancellationCode	Diverted	CarrierDelay	WeatherDelay	NASDelay	SecurityDelay	LateAircraftDelay	IsArrDelayed	IsDepDelayed
1987	10	14	3	741	730	912	849	PS	1451	NA	91	79		23	11	SAN	SFO	447			0	NA	0						YES	YES
1987	10	15	4	729	730	903	849	PS	1451	NA	94	79		14	-1	SAN	SFO	447			0	NA	0						YES	NO
1987	10	17	6	741	730	918	849	PS	1451	NA	97	79		29	11	SAN	SFO	447			0	NA	0						YES	YES
1987	10	18	7	729	730	847	849	PS	1451	NA	78	79		-2	-1	SAN	SFO	447			0	NA	0						NO	NO
1987	10	19	1	749	730	922	849	PS	1451	NA	93	79		33	19	SAN	SFO	447			0	NA	0						YES	YES
1987	10	21	3	728	730	848	849	PS	1451	NA	80	79		-1	-2	SAN	SFO	447			0	NA	0						NO	NO
1987	10	22	4	728	730	852	849	PS	1451	NA	84	79		3	-2	SAN	SFO	447			0	NA	0						YES	NO
1987	10	23	5	731	730	902	849	PS	1451	NA	91	79		13	1	SAN	SFO	447			0	NA	0						YES	YES
1987	10	24	6	744	730	908	849	PS	1451	NA	84	79		19	14	SAN	SFO	447			0	NA	0						YES	YES
1987	10	25	7	729	730	851	849	PS	1451	NA	82	79		2	-1	SAN	SFO	447			0	NA	0						YES	NO