Example A.8. Linear Regression
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
#
# AdvancedMiner Example Script
# Copyright Algolytics sp. z o. o. 2004-2015
#
# Example description: Linear Regression model building, testing,
# statistics calculating and application
#
# Input data: StatLib-Datasets Archive: http://stat.cmu.edu/datasets/
# The data set came from:
# Miller, A.J., Shaw, D.E., Veitch, L.G. & Smith, E.J. (1979).
# `Analyzing the results of a cloud-seeding experiment in Tasmania',
# Communications in Statistics - Theory & Methods, vol.A8(10), 1017-1047.
#
# Data Description:
# period denotes periodical rainfalls in inches. TE and TW are the rainfalls
# for the east and
# west target areas respectively, while NC, SC and NWC are the corresponding
# rainfalls in the north, south and north-west control areas respectively.
# S = seeded, U = unseeded.
#
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
table 'cloud' :
period seeded season NC SC NWC TE
1.0 1 'AUTUMN' 1.65 1.8 3.33 1.69
2.0 0 'AUTUMN' 1.09 0.79 1.59 0.74
3.0 1 'WINTER' 2.39 0.36 2.06 0.81
4.0 0 'WINTER' 2.96 1.27 4.05 1.44
5.0 1 'WINTER' 4.16 2.16 6.0 2.48
6.0 0 'WINTER' 2.76 0.87 4.17 0.84
7.0 0 'WINTER' 1.08 0.85 3.45 0.37
8.0 1 'WINTER' 0.26 0.47 0.9 0.37
9.0 0 'SPRING' 2.53 1.08 3.65 1.33
10.0 1 'SPRING' 2.76 3.1 5.06 3.38
11.0 1 'SPRING' 1.07 0.64 1.95 0.69
12.0 0 'SPRING' 1.42 1.08 1.22 1.42
13.0 1 'SPRING' 0.24 0.44 0.94 0.44
14.0 0 'SPRING' 0.7 0.67 0.94 0.76
15.0 1 'SUMMER' 0.97 1.66 2.21 1.13
16.0 0 'SUMMER' 1.06 1.13 1.46 0.88
45.0 1 'SUMMER' 0.13 0.27 0.35 0.17
46.0 0 'SUMMER' 0.1 0.3 0.34 0.25
47.0 0 'SUMMER' 0.38 0.58 0.67 0.78
48.0 1 'SUMMER' 0.45 0.43 0.44 0.4
49.0 1 'AUTUMN' 0.42 0.47 0.53 0.52
50.0 0 'AUTUMN' 2.24 4.02 2.52 2.73
51.0 0 'AUTUMN' 0.52 1.32 2.18 0.9
52.0 1 'AUTUMN' 0.94 1.59 1.73 1.62
53.0 0 'AUTUMN' 1.19 0.85 2.31 0.93
54.0 1 'AUTUMN' 0.76 0.71 1.28 0.63
55.0 1 'WINTER' 0.13 0.59 0.91 0.42
56.0 0 'WINTER' 1.5 0.24 1.15 0.64
57.0 0 'WINTER' 1.03 0.22 1.88 0.3
58.0 1 'WINTER' 1.87 0.58 2.97 0.88
59.0 0 'WINTER' 1.85 1.36 2.17 0.76
60.0 1 'WINTER' 2.04 0.71 2.22 1.25
61.0 0 'WINTER' 1.44 1.0 1.64 1.08
62.0 1 'WINTER' 1.46 1.48 0.4 1.11
63.0 1 'SPRING' 5.08 1.77 4.2 3.43
64.0 0 'SPRING' 0.66 0.73 0.91 0.54
65.0 1 'SPRING' 0.49 0.55 0.51 0.39
66.0 0 'SPRING' 3.27 2.68 3.6 2.53
67.0 0 'SPRING' 1.33 0.43 2.18 0.81
68.0 1 'SPRING' 0.25 0.46 0.89 0.39
69.0 1 'SUMMER' 0.69 0.49 0.69 0.86
70.0 0 'SUMMER' 2.12 0.95 1.82 2.16
95.0 0 'SPRING' 1.45 1.47 2.2 1.7
96.0 1 'SPRING' 2.13 1.13 2.33 1.22
97.0 1 'SPRING' 0.02 0.08 0.24 0.07
98.0 0 'SPRING' 0.36 0.87 0.57 0.49
99.0 0 'SPRING' 0.72 0.99 0.98 0.71
100.0 1 'SPRING' 1.02 1.89 2.47 1.67
101.0 0 'SUMMER' 0.18 1.42 0.71 0.73
102.0 1 'SUMMER' 1.83 1.82 3.11 1.79
103.0 0 'SUMMER' 0.08 0.4 0.57 0.19
104.0 1 'SUMMER' 0.0 0.04 0.04 0.0
105.0 1 'SUMMER' 0.83 0.38 0.7 0.44
106.0 0 'SUMMER' 0.01 0.44 0.66 0.31
107.0 1 'SUMMER' 2.65 0.85 1.48 0.96
108.0 0 'SUMMER' 1.27 1.39 1.2 1.04
109.0 1 'AUTUMN' 0.01 0.23 0.1 0.05
110.0 0 'AUTUMN' 0.35 0.75 0.2 0.04
111.0 1 'AUTUMN' 1.8 1.62 3.02 1.83
112.0 0 'AUTUMN' 4.44 1.05 3.59 2.24
113.0 1 'AUTUMN' 2.84 2.44 4.48 2.5
114.0 0 'AUTUMN' 2.05 1.3 4.04 1.1
115.0 1 'AUTUMN' 3.01 1.66 4.56 1.83
116.0 0 'AUTUMN' 2.58 1.21 3.95 1.41
117.0 0 'WINTER' 2.22 0.61 2.68 0.74
118.0 1 'WINTER' 0.07 2.26 2.08 1.09
119.0 1 'WINTER' 1.62 1.16 2.87 0.79
120.0 0 'WINTER' 4.34 3.29 6.4 4.06
121.0 0 'WINTER' 1.03 0.58 1.77 0.4
122.0 1 'WINTER' 1.5 0.41 2.56 0.76
123.0 1 'SPRING' 1.52 1.62 2.86 1.53
124.0 0 'SPRING' 0.37 1.25 1.74 0.56
125.0 0 'SPRING' 2.14 1.0 4.39 1.74
126.0 1 'SPRING' 2.36 1.53 3.03 1.59
127.0 0 'SPRING' 1.71 2.03 3.24 1.91
128.0 1 'SPRING' 2.12 2.77 4.44 2.09
129.0 0 'SUMMER' 1.38 2.11 3.01 1.59
130.0 1 'SUMMER' 0.21 1.41 0.8 0.66
131.0 0 'SUMMER' 0.48 0.59 0.68 0.68
132.0 1 'SUMMER' 0.01 0.65 0.48 0.46
133.0 1 'SUMMER' 0.15 0.13 0.42 0.22
134.0 0 'SUMMER' 1.32 0.57 1.54 1.11
135.0 1 'SUMMER' 2.26 1.04 1.27 1.76
136.0 0 'SUMMER' 5.95 3.97 5.37 5.12
171.0 0 'AUTUMN' 0.19 0.28 0.7 0.12
172.0 1 'AUTUMN' 0.31 0.23 0.83 0.37
173.0 1 'AUTUMN' 1.44 3.14 0.86 4.97
174.0 0 'AUTUMN' 0.3 0.72 1.38 0.57
175.0 1 'AUTUMN' 0.11 0.14 0.58 0.13
176.0 0 'AUTUMN' 3.66 1.84 5.36 2.47
177.0 0 'AUTUMN' 1.14 0.81 2.09 1.01
178.0 1 'AUTUMN' 1.3 0.34 2.45 0.55
179.0 1 'WINTER' 0.05 0.38 0.9 0.24
180.0 0 'WINTER' 1.84 1.73 2.33 2.36
181.0 1 'WINTER' 4.24 1.67 5.48 2.35
182.0 0 'WINTER' 1.99 1.9 3.67 2.23
183.0 0 'WINTER' 2.44 1.52 4.01 1.16
184.0 1 'WINTER' 2.21 2.36 3.25 1.63
185.0 1 'WINTER' 0.8 2.25 2.79 1.08
186.0 0 'WINTER' 9.42 3.6 7.84 6.0
187.0 1 'SPRING' 2.74 3.03 6.39 2.67
188.0 0 'SPRING' 0.0 0.19 0.06 0.36
189.0 1 'SPRING' 0.96 0.64 1.24 0.58
190.0 0 'SPRING' 1.38 1.86 2.91 1.36
191.0 1 'SPRING' 1.22 2.28 1.58 1.17
192.0 0 'SPRING' 2.46 2.47 2.39 2.37
193.0 1 'SPRING' 0.05 0.02 0.09 0.02
194.0 0 'SPRING' 0.61 0.87 1.35 0.92
pd = PhysicalData('cloud')
ld = LogicalData(pd)
#------ Approximation function settings ------
fs = ApproximationFunctionSettings()
fs.logicalData = ld
fs.targetAttributeName = 'TE'
fs.attributeUsageSet.getAttribute('season').setUsage(UsageOption.inactive)
#------ Linear Regression algorithm settings ------
as = LinearRegressionSettings()
as.intercept = TRUE
vss = VariableSelectionSettings()
vss.variableSelectionMethod = VariableSelectionMethod.forward
vss.modelEntryLevel = 0.15
as.variableSelectionSettings = vss
fs.algorithmSettings = as
save('cloud_pd', pd)
save('cloud_ld', ld)
save('reg_settings', fs)
#------ model building ------
bt = MiningBuildTask('cloud_pd', 'reg_settings', 'reg_model')
save('cloud_build', bt)
execute('cloud_build')
print "Build task for linear regression example was successfully executed"
#------ model testing ------
tt = ApproximationTestTask('cloud_pd', 'reg_model', 'cloud_out')
tt.testDataTargetAttributeName = 'TE'
save('cloud_test', tt)
execute('cloud_test')
print "Test task for linear regression example was successfully executed"
#----- model application ------
pdout = PhysicalData('cloud_apply')
save('cloud_pd_apply', pdout)
at = MiningApplyTask()
at.modelName = 'reg_model'
at.sourceDataName = 'cloud_pd'
at.targetDataName = 'cloud_pd_apply'
at.replaceExistingData = TRUE
directMapping = java.util.ArrayList()
asi = ApplySourceItem()
asi.sourceName = 'TE'
asi.destinationName = 'actual_target'
directMapping.add(asi)
at.setDirectMapping(directMapping)
ao = ApproximationApplyOutput()
aai = ApproximationOutputItem()
aai.setDestinationName('predicted_target')
aai.setOutputType(ApproximationOutputType.predictedValue)
ao.item.add(aai)
at.applyOutput = ao
save('cloud_apply', at)
execute('cloud_apply')
print "Apply task for linear regression example was successfully executed"
print
# print model fit
statModel = load('reg_model').getModelStatistics()
statNames = statModel.getModelStatNames()
print "Model statistics \t value"
for row in range(len(statNames)):
print statNames[row], " \t ", statModel.getModelStatValue(row)
print
statModel = load('reg_model')
varStats =statModel.getModelStatistics().getVariableStatistics()
print "Variable \t Coeff \t VIF"
for v in varStats.getNames():
print v, "\t", varStats.getVarStatValue(v,"Coeff"), "\t", varStats.getVarStatValue(v,"VIF")
Output
Build task for linear regression example was successfully executed Test task for linear regression example was successfully executed Apply task for linear regression example was successfully executed Model statistics value dfR 3.0 SSR 109.91431878975642 MSR 36.63810626325214 dfE 104.0 SSE 14.2393552843176 MSE 0.13691687773382308 dfT 107.0 SST 124.15367407407402 F-test 267.59379025922163 Pr>F 0.0 s 0.37002280704548884 Rsq 0.8853086274690353 ADJRsq 0.8820002224921806 Variable Coeff VIF Intercept -0.04717301845975744 NaN NC 0.47842241886110154 3.7075209337995614 SC 0.7328626001274345 1.9650100440149518 NWC -0.14680322892118228 4.256510917786886