notebook.community

Edit and run



In [1]:

    
#----------------------------------------------------------------------
# Purpose:  Condition an Airline dataset by filtering out NAs where the
#           departure delay in the input dataset is unknown.
#
#           Then treat anything longer than minutesOfDelayWeTolerate
#           as delayed.
#----------------------------------------------------------------------



In [2]:

    
import h2o



In [3]:

    
h2o.init()









    




H2O cluster uptime: 
16 minutes 52 seconds 581 milliseconds 
H2O cluster version: 
3.5.0.99999
H2O cluster name: 
spIdea
H2O cluster total nodes: 
1
H2O cluster total memory: 
12.44 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 [4]:

    
from h2o.utils.shared_utils import _locate # private function. used to find files within h2o git project directory.

air = h2o.import_file(_locate("smalldata/airlines/allyears2k_headers.zip"))









    



Parse Progress: [##################################################] 100%



In [5]:

    
numRows, numCols = air.dim
print("Original dataset rows: {0}, columns: {1}".format(numRows, numCols))

x_cols = ["Month", "DayofMonth", "DayOfWeek", "CRSDepTime", "CRSArrTime", "UniqueCarrier", "CRSElapsedTime", "Origin", "Dest", "Distance"]
y_col = "SynthDepDelayed"

noDepDelayedNAs = air[air["DepDelay"].isna() == 0]
rows, cols = noDepDelayedNAs.dim
print("New dataset rows: {0}, columns: {1}".format(rows, cols))









    



Original dataset rows: 43978, columns: 31
New dataset rows: 42892, columns: 31



In [6]:

    
minutesOfDelayWeTolerate = 15
noDepDelayedNAs = noDepDelayedNAs.cbind(noDepDelayedNAs["DepDelay"] > minutesOfDelayWeTolerate)
noDepDelayedNAs[numCols] = noDepDelayedNAs[numCols-1].asfactor()
noDepDelayedNAs.set_name(numCols,y_col)









    





  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   SynthDepDelayed
  1987      10           14           3       741          730       912          849               5        1451      3499                  91               79       nan         23         11      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              1                 1
  1987      10           15           4       729          730       903          849               5        1451      3499                  94               79       nan         14         -1      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              0                 0
  1987      10           17           6       741          730       918          849               5        1451      3499                  97               79       nan         29         11      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              1                 1
  1987      10           18           7       729          730       847          849               5        1451      3499                  78               79       nan         -2         -1      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              0              0                 0
  1987      10           19           1       749          730       922          849               5        1451      3499                  93               79       nan         33         19      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              1                 1
  1987      10           21           3       728          730       848          849               5        1451      3499                  80               79       nan         -1         -2      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              0              0                 0
  1987      10           22           4       728          730       852          849               5        1451      3499                  84               79       nan          3         -2      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              0                 0
  1987      10           23           5       731          730       902          849               5        1451      3499                  91               79       nan         13          1      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              1                 1
  1987      10           24           6       744          730       908          849               5        1451      3499                  84               79       nan         19         14      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              1                 1
  1987      10           25           7       729          730       851          849               5        1451      3499                  82               79       nan          2         -1      106    118        447      nan       nan           0                  3          0            nan            nan        nan             nan                 nan              1              0                 0







    Out[6]:



In [7]:

    
gbm = h2o.gbm(x=noDepDelayedNAs[x_cols], y=noDepDelayedNAs[y_col], distribution="bernoulli")
gbm.show()









    



gbm Model Build Progress: [##################################################] 100%
Model Details
=============
H2OEstimator :  Gradient Boosting Machine
Model Key:  GBM_model_python_1445841486633_35

Model Summary:






    



/Library/Python/2.7/site-packages/IPython/kernel/__main__.py:1: DeprecationWarning: `h2o.gbm` is deprecated. Use the estimators sub module to build an H2OGradientBoostedEstimator.
  if __name__ == '__main__':






    





number_of_trees
model_size_in_bytes
min_depth
max_depth
mean_depth
min_leaves
max_leaves
mean_leaves

50.0
34344.0
5.0
5.0
5.0
18.0
32.0
28.62






    




ModelMetricsBinomial: gbm
** Reported on train data. **

MSE: 0.191672191035
R^2: 0.232789986813
LogLoss: 0.565710073073
AUC: 0.785428554449
Gini: 0.570857108897

Confusion Matrix (Act/Pred) for max f1 @ threshold = 0.412557029006:






    





NO
YES
Error
Rate
NO
11180.0
9707.0
0.4647
 (9707.0/20887.0)
YES
3402.0
18603.0
0.1546
 (3402.0/22005.0)
Total
14582.0
28310.0
0.3056
 (13109.0/42892.0)






    



Maximum Metrics: Maximum metrics at their respective thresholds







    




metric
threshold
value
idx
max f1
0.4
0.7
259.0
max f2
0.2
0.8
347.0
max f0point5
0.6
0.7
180.0
max accuracy
0.5
0.7
213.0
max precision
1.0
1.0
0.0
max absolute_MCC
0.5
0.4
213.0
max min_per_class_accuracy
0.5
0.7
209.0






    



Scoring History:






    





timestamp
duration
number_of_trees
training_MSE
training_logloss
training_AUC
training_classification_error

2015-10-25 23:55:03
 0.037 sec
1.0
0.2
0.7
0.7
0.4

2015-10-25 23:55:03
 0.067 sec
2.0
0.2
0.7
0.7
0.4

2015-10-25 23:55:03
 0.093 sec
3.0
0.2
0.7
0.7
0.4

2015-10-25 23:55:03
 0.123 sec
4.0
0.2
0.7
0.7
0.4

2015-10-25 23:55:03
 0.155 sec
5.0
0.2
0.7
0.7
0.4
---
---
---
---
---
---
---
---

2015-10-25 23:55:05
 2.284 sec
46.0
0.2
0.6
0.8
0.3

2015-10-25 23:55:05
 2.341 sec
47.0
0.2
0.6
0.8
0.3

2015-10-25 23:55:06
 2.400 sec
48.0
0.2
0.6
0.8
0.3

2015-10-25 23:55:06
 2.454 sec
49.0
0.2
0.6
0.8
0.3

2015-10-25 23:55:06
 2.508 sec
50.0
0.2
0.6
0.8
0.3






    



Variable Importances:






    




variable
relative_importance
scaled_importance
percentage
Origin
6877.3
1.0
0.4
Dest
4551.0
0.7
0.3
DayofMonth
2025.6
0.3
0.1
UniqueCarrier
1279.5
0.2
0.1
CRSArrTime
724.8
0.1
0.0
CRSDepTime
636.9
0.1
0.0
DayOfWeek
408.2
0.1
0.0
CRSElapsedTime
118.8
0.0
0.0
Month
73.3
0.0
0.0
Distance
31.1
0.0
0.0

H2O cluster uptime:	16 minutes 52 seconds 581 milliseconds
H2O cluster version:	3.5.0.99999
H2O cluster name:	spIdea
H2O cluster total nodes:	1
H2O cluster total memory:	12.44 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	CancellationCode	CarrierDelay	WeatherDelay	NASDelay	SecurityDelay	LateAircraftDelay	IsArrDelayed	IsDepDelayed	SynthDepDelayed
1987	10	14	3	741	730	912	849	5	1451	3499	91	79	nan	23	11	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	1	1
1987	10	15	4	729	730	903	849	5	1451	3499	94	79	nan	14	-1	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	0	0
1987	10	17	6	741	730	918	849	5	1451	3499	97	79	nan	29	11	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	1	1
1987	10	18	7	729	730	847	849	5	1451	3499	78	79	nan	-2	-1	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	0	0	0
1987	10	19	1	749	730	922	849	5	1451	3499	93	79	nan	33	19	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	1	1
1987	10	21	3	728	730	848	849	5	1451	3499	80	79	nan	-1	-2	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	0	0	0
1987	10	22	4	728	730	852	849	5	1451	3499	84	79	nan	3	-2	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	0	0
1987	10	23	5	731	730	902	849	5	1451	3499	91	79	nan	13	1	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	1	1
1987	10	24	6	744	730	908	849	5	1451	3499	84	79	nan	19	14	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	1	1
1987	10	25	7	729	730	851	849	5	1451	3499	82	79	nan	2	-1	106	118	447	nan	nan	3	nan	nan	nan	nan	nan	1	0	0

	number_of_trees	model_size_in_bytes	min_depth	max_depth	mean_depth	min_leaves	max_leaves	mean_leaves
	50.0	34344.0	5.0	5.0	5.0	18.0	32.0	28.62

	NO	YES	Error	Rate
NO	11180.0	9707.0	0.4647	(9707.0/20887.0)
YES	3402.0	18603.0	0.1546	(3402.0/22005.0)
Total	14582.0	28310.0	0.3056	(13109.0/42892.0)

metric	threshold	value	idx
max f1	0.4	0.7	259.0
max f2	0.2	0.8	347.0
max f0point5	0.6	0.7	180.0
max accuracy	0.5	0.7	213.0
max precision	1.0	1.0	0.0
max absolute_MCC	0.5	0.4	213.0
max min_per_class_accuracy	0.5	0.7	209.0

	timestamp	duration	number_of_trees	training_MSE	training_logloss	training_AUC	training_classification_error
	2015-10-25 23:55:03	0.037 sec	1.0	0.2	0.7	0.7	0.4
	2015-10-25 23:55:03	0.067 sec	2.0	0.2	0.7	0.7	0.4
	2015-10-25 23:55:03	0.093 sec	3.0	0.2	0.7	0.7	0.4
	2015-10-25 23:55:03	0.123 sec	4.0	0.2	0.7	0.7	0.4
	2015-10-25 23:55:03	0.155 sec	5.0	0.2	0.7	0.7	0.4
---	---	---	---	---	---	---	---
	2015-10-25 23:55:05	2.284 sec	46.0	0.2	0.6	0.8	0.3
	2015-10-25 23:55:05	2.341 sec	47.0	0.2	0.6	0.8	0.3
	2015-10-25 23:55:06	2.400 sec	48.0	0.2	0.6	0.8	0.3
	2015-10-25 23:55:06	2.454 sec	49.0	0.2	0.6	0.8	0.3
	2015-10-25 23:55:06	2.508 sec	50.0	0.2	0.6	0.8	0.3

variable	relative_importance	scaled_importance	percentage
Origin	6877.3	1.0	0.4
Dest	4551.0	0.7	0.3
DayofMonth	2025.6	0.3	0.1
UniqueCarrier	1279.5	0.2	0.1
CRSArrTime	724.8	0.1	0.0
CRSDepTime	636.9	0.1	0.0
DayOfWeek	408.2	0.1	0.0
CRSElapsedTime	118.8	0.0	0.0
Month	73.3	0.0	0.0
Distance	31.1	0.0	0.0