library(ggplot2)
library(party)
## Loading required package: grid
## Loading required package: mvtnorm
## Loading required package: modeltools
## Loading required package: stats4
## Loading required package: strucchange
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Loading required package: sandwich
library(partykit)
##
## Attaching package: 'partykit'
## The following objects are masked from 'package:party':
##
## cforest, ctree, ctree_control, edge_simple, mob, mob_control,
## node_barplot, node_bivplot, node_boxplot, node_inner,
## node_surv, node_terminal
library(evtree)
library(randomForest)
## randomForest 4.6-12
## Type rfNews() to see new features/changes/bug fixes.
##
## Attaching package: 'randomForest'
## The following object is masked from 'package:ggplot2':
##
## margin
library(doParallel)
## Loading required package: foreach
## Loading required package: iterators
## Loading required package: parallel
library(tree)
library(caret)
## Loading required package: lattice
library(ROCR)
## Loading required package: gplots
##
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
##
## lowess
library(rpart)
library(rpart.plot)
library(RColorBrewer)
library(rattle)
## Rattle: A free graphical interface for data mining with R.
## Version 4.1.0 Copyright (c) 2006-2015 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.
data(weather)
dsname <- "weather"
target <- "RainTomorrow"
risk <- "RISK_MM"
ds <- get(dsname)
vars <- colnames(ds)
ignore <- vars[c(1, 2, if (exists("risk")) which(risk==vars))]
#names(ds)[1]==``Date''
#names(ds)[2]==``Location''
vars <- setdiff(vars, ignore)
inputs <- setdiff(vars, target)
nobs <- nrow(ds)
dim(ds[vars])
## [1] 366 21
form <- formula(paste(target, "~ ."))
set.seed(1426)
length(train <- sample(nobs, 0.7*nobs))
## [1] 256
length(test <- setdiff(seq_len(nobs), train))
## [1] 110
model <- rpart(formula=form, data=ds[train, vars])
print(model)
## n= 256
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 256 38 No (0.85156250 0.14843750)
## 2) Humidity3pm< 71 238 25 No (0.89495798 0.10504202)
## 4) Pressure3pm>=1010.25 208 13 No (0.93750000 0.06250000) *
## 5) Pressure3pm< 1010.25 30 12 No (0.60000000 0.40000000)
## 10) Sunshine>=9.95 14 1 No (0.92857143 0.07142857) *
## 11) Sunshine< 9.95 16 5 Yes (0.31250000 0.68750000) *
## 3) Humidity3pm>=71 18 5 Yes (0.27777778 0.72222222) *
summary(model)
## Call:
## rpart(formula = form, data = ds[train, vars])
## n= 256
##
## CP nsplit rel error xerror xstd
## 1 0.21052632 0 1.0000000 1.000000 0.1496982
## 2 0.07894737 1 0.7894737 1.052632 0.1528809
## 3 0.01000000 3 0.6315789 1.052632 0.1528809
##
## Variable importance
## Humidity3pm Sunshine Pressure3pm Temp9am Pressure9am Temp3pm
## 25 17 14 9 8 8
## Cloud3pm MaxTemp MinTemp
## 7 6 5
##
## Node number 1: 256 observations, complexity param=0.2105263
## predicted class=No expected loss=0.1484375 P(node) =1
## class counts: 218 38
## probabilities: 0.852 0.148
## left son=2 (238 obs) right son=3 (18 obs)
## Primary splits:
## Humidity3pm < 71 to the left, improve=12.748630, (0 missing)
## Pressure3pm < 1010.65 to the right, improve=11.244900, (0 missing)
## Cloud3pm < 6.5 to the left, improve=11.006840, (0 missing)
## Sunshine < 6.45 to the right, improve= 9.975051, (2 missing)
## Pressure9am < 1018.45 to the right, improve= 8.380711, (0 missing)
## Surrogate splits:
## Sunshine < 0.75 to the right, agree=0.949, adj=0.278, (0 split)
## Pressure3pm < 1001.55 to the right, agree=0.938, adj=0.111, (0 split)
## Temp3pm < 7.6 to the right, agree=0.938, adj=0.111, (0 split)
## Pressure9am < 1005.3 to the right, agree=0.934, adj=0.056, (0 split)
##
## Node number 2: 238 observations, complexity param=0.07894737
## predicted class=No expected loss=0.105042 P(node) =0.9296875
## class counts: 213 25
## probabilities: 0.895 0.105
## left son=4 (208 obs) right son=5 (30 obs)
## Primary splits:
## Pressure3pm < 1010.25 to the right, improve=5.972899, (0 missing)
## Cloud3pm < 6.5 to the left, improve=4.475485, (0 missing)
## Pressure9am < 1019.75 to the right, improve=4.279291, (0 missing)
## WindGustSpeed < 64 to the left, improve=3.249967, (1 missing)
## Sunshine < 6.45 to the right, improve=2.650559, (2 missing)
## Surrogate splits:
## Pressure9am < 1012.65 to the right, agree=0.950, adj=0.600, (0 split)
## Temp9am < 22.7 to the left, agree=0.887, adj=0.100, (0 split)
## Humidity3pm < 14.5 to the right, agree=0.882, adj=0.067, (0 split)
## MaxTemp < 33.5 to the left, agree=0.878, adj=0.033, (0 split)
## Rainfall < 16.8 to the left, agree=0.878, adj=0.033, (0 split)
##
## Node number 3: 18 observations
## predicted class=Yes expected loss=0.2777778 P(node) =0.0703125
## class counts: 5 13
## probabilities: 0.278 0.722
##
## Node number 4: 208 observations
## predicted class=No expected loss=0.0625 P(node) =0.8125
## class counts: 195 13
## probabilities: 0.938 0.062
##
## Node number 5: 30 observations, complexity param=0.07894737
## predicted class=No expected loss=0.4 P(node) =0.1171875
## class counts: 18 12
## probabilities: 0.600 0.400
## left son=10 (14 obs) right son=11 (16 obs)
## Primary splits:
## Sunshine < 9.95 to the right, improve=5.667857, (0 missing)
## Temp9am < 17.55 to the right, improve=4.789140, (0 missing)
## Humidity3pm < 35.5 to the left, improve=3.471429, (0 missing)
## MaxTemp < 31.25 to the right, improve=2.921739, (0 missing)
## Temp3pm < 30.25 to the right, improve=2.921739, (0 missing)
## Surrogate splits:
## Temp9am < 17.8 to the right, agree=0.867, adj=0.714, (0 split)
## Cloud3pm < 4.5 to the left, agree=0.833, adj=0.643, (0 split)
## MinTemp < 14.15 to the right, agree=0.767, adj=0.500, (0 split)
## MaxTemp < 29.15 to the right, agree=0.767, adj=0.500, (0 split)
## Temp3pm < 30.25 to the right, agree=0.767, adj=0.500, (0 split)
##
## Node number 10: 14 observations
## predicted class=No expected loss=0.07142857 P(node) =0.0546875
## class counts: 13 1
## probabilities: 0.929 0.071
##
## Node number 11: 16 observations
## predicted class=Yes expected loss=0.3125 P(node) =0.0625
## class counts: 5 11
## probabilities: 0.312 0.688
printcp(model)
##
## Classification tree:
## rpart(formula = form, data = ds[train, vars])
##
## Variables actually used in tree construction:
## [1] Humidity3pm Pressure3pm Sunshine
##
## Root node error: 38/256 = 0.14844
##
## n= 256
##
## CP nsplit rel error xerror xstd
## 1 0.210526 0 1.00000 1.0000 0.14970
## 2 0.078947 1 0.78947 1.0526 0.15288
## 3 0.010000 3 0.63158 1.0526 0.15288
plotcp(model)
plot(model)
text(model)
fancyRpartPlot(model)
prp(model)
prp(model, type=2, extra=104, nn=TRUE, fallen.leaves=TRUE,
faclen=0, varlen=0, shadow.col="grey", branch.lty=3)
pred <- predict(model, newdata=ds[test, vars], type="class")
pred.prob <- predict(model, newdata=ds[test, vars], type="prob")
table(is.na(ds))
##
## FALSE TRUE
## 8737 47
ds.complete <- ds[complete.cases(ds),]
(nobs <- nrow(ds.complete))
## [1] 328
set.seed(1426)
length(train.complete <- sample(nobs, 0.7*nobs))
## [1] 229
length(test.complete <- setdiff(seq_len(nobs), train.complete))
## [1] 99
model$cptable[which.min(model$cptable[,"xerror"]),"CP"]
## [1] 0.2105263
model <- rpart(formula=form, data=ds[train.complete, vars], cp=0)
printcp(model)
##
## Classification tree:
## rpart(formula = form, data = ds[train.complete, vars], cp = 0)
##
## Variables actually used in tree construction:
## [1] Cloud3pm Humidity9am Temp9am WindGustSpeed WindSpeed9am
##
## Root node error: 45/229 = 0.19651
##
## n= 229
##
## CP nsplit rel error xerror xstd
## 1 0.088889 0 1.00000 1.0000 0.13362
## 2 0.044444 3 0.71111 1.0889 0.13791
## 3 0.000000 5 0.62222 1.1333 0.13992
prune <- prune(model, cp=.01)
printcp(prune)
##
## Classification tree:
## rpart(formula = form, data = ds[train.complete, vars], cp = 0)
##
## Variables actually used in tree construction:
## [1] Cloud3pm Humidity9am Temp9am WindGustSpeed WindSpeed9am
##
## Root node error: 45/229 = 0.19651
##
## n= 229
##
## CP nsplit rel error xerror xstd
## 1 0.088889 0 1.00000 1.0000 0.13362
## 2 0.044444 3 0.71111 1.0889 0.13791
## 3 0.000000 5 0.62222 1.1333 0.13992
table(is.na(ds))
##
## FALSE TRUE
## 8737 47
table(is.na(ds.complete))
##
## FALSE
## 7872
subset(ds, select=-c(Humidity3pm, Humidity9am, Cloud9am, Cloud3pm))
## Date Location MinTemp MaxTemp Rainfall Evaporation Sunshine
## 1 2007-11-01 Canberra 8.0 24.3 0.0 3.4 6.3
## 2 2007-11-02 Canberra 14.0 26.9 3.6 4.4 9.7
## 3 2007-11-03 Canberra 13.7 23.4 3.6 5.8 3.3
## 4 2007-11-04 Canberra 13.3 15.5 39.8 7.2 9.1
## 5 2007-11-05 Canberra 7.6 16.1 2.8 5.6 10.6
## 6 2007-11-06 Canberra 6.2 16.9 0.0 5.8 8.2
## 7 2007-11-07 Canberra 6.1 18.2 0.2 4.2 8.4
## 8 2007-11-08 Canberra 8.3 17.0 0.0 5.6 4.6
## 9 2007-11-09 Canberra 8.8 19.5 0.0 4.0 4.1
## 10 2007-11-10 Canberra 8.4 22.8 16.2 5.4 7.7
## 11 2007-11-11 Canberra 9.1 25.2 0.0 4.2 11.9
## 12 2007-11-12 Canberra 8.5 27.3 0.2 7.2 12.5
## 13 2007-11-13 Canberra 10.1 27.9 0.0 7.2 13.0
## 14 2007-11-14 Canberra 12.1 30.9 0.0 6.2 12.4
## 15 2007-11-15 Canberra 10.1 31.2 0.0 8.8 13.1
## 16 2007-11-16 Canberra 12.4 32.1 0.0 8.4 11.1
## 17 2007-11-17 Canberra 13.8 31.2 0.0 7.2 8.4
## 18 2007-11-18 Canberra 11.7 30.0 1.2 7.2 10.1
## 19 2007-11-19 Canberra 12.4 32.3 0.6 7.4 13.0
## 20 2007-11-20 Canberra 15.6 33.4 0.0 8.0 10.4
## 21 2007-11-21 Canberra 15.3 33.4 0.0 8.8 9.5
## 22 2007-11-22 Canberra 16.4 19.4 0.4 9.2 0.0
## 23 2007-11-23 Canberra 12.8 18.5 25.8 2.8 0.6
## 24 2007-11-24 Canberra 12.0 24.3 0.4 1.2 7.5
## 25 2007-11-25 Canberra 15.4 28.4 0.0 4.4 8.1
## 26 2007-11-26 Canberra 15.6 26.9 0.0 6.8 8.9
## 27 2007-11-27 Canberra 13.3 22.2 0.2 6.6 2.3
## 28 2007-11-28 Canberra 12.9 28.0 0.0 4.4 10.7
## 29 2007-11-29 Canberra 15.1 24.3 0.0 7.0 0.4
## 30 2007-11-30 Canberra 13.6 24.1 0.4 2.6 0.5
## 31 2007-12-01 Canberra 15.1 20.4 22.6 2.4 0.2
## 32 2007-12-02 Canberra 11.6 26.3 4.2 1.6 12.0
## 33 2007-12-03 Canberra 16.6 24.2 0.2 6.6 4.7
## 34 2007-12-04 Canberra 13.3 26.5 6.6 3.8 11.8
## 35 2007-12-05 Canberra 14.5 21.8 0.0 8.4 9.8
## 36 2007-12-06 Canberra 16.3 26.8 0.0 6.0 6.3
## 37 2007-12-07 Canberra 17.2 25.8 0.0 4.2 8.8
## 38 2007-12-08 Canberra 16.5 28.2 4.0 4.2 8.8
## 39 2007-12-09 Canberra 15.0 29.4 0.0 6.6 11.1
## 40 2007-12-10 Canberra 14.9 24.8 0.0 10.4 10.0
## 41 2007-12-11 Canberra 11.8 18.5 0.6 4.8 2.3
## 42 2007-12-12 Canberra 11.7 21.5 0.0 4.2 7.3
## 43 2007-12-13 Canberra 9.6 20.3 0.0 5.0 3.6
## 44 2007-12-14 Canberra 8.9 27.1 0.0 4.4 12.7
## 45 2007-12-15 Canberra 10.1 29.9 0.0 6.8 8.8
## 46 2007-12-16 Canberra 15.5 21.1 5.4 6.4 0.9
## 47 2007-12-17 Canberra 10.8 21.7 1.4 2.8 10.6
## 48 2007-12-18 Canberra 7.5 20.9 0.0 6.6 8.7
## 49 2007-12-19 Canberra 12.8 21.0 0.0 6.4 0.8
## 50 2007-12-20 Canberra 12.6 23.1 3.4 1.6 2.3
## 51 2007-12-21 Canberra 14.8 29.5 6.4 1.8 8.1
## 52 2007-12-22 Canberra 19.9 22.0 11.0 4.4 5.9
## 53 2007-12-23 Canberra 9.2 20.4 17.4 7.8 10.2
## 54 2007-12-24 Canberra 12.4 24.4 0.0 6.2 12.1
## 55 2007-12-25 Canberra 11.3 21.7 3.4 8.2 5.6
## 56 2007-12-26 Canberra 9.8 26.3 0.0 5.2 13.0
## 57 2007-12-27 Canberra 14.3 26.7 0.0 7.2 7.1
## 58 2007-12-28 Canberra 15.1 28.3 14.4 8.8 13.2
## 59 2007-12-29 Canberra 14.4 31.6 0.0 6.6 13.6
## 60 2007-12-30 Canberra 15.4 35.0 0.0 9.6 13.0
## 61 2007-12-31 Canberra 13.8 33.5 0.0 11.4 13.6
## 62 2008-01-01 Canberra 13.6 34.2 0.0 8.8 12.8
## 63 2008-01-02 Canberra 14.3 35.0 0.0 7.6 10.5
## 64 2008-01-03 Canberra 15.9 23.4 0.0 12.6 2.2
## 65 2008-01-04 Canberra 16.7 25.3 0.0 6.2 12.5
## 66 2008-01-05 Canberra 12.1 27.5 0.0 7.4 11.7
## 67 2008-01-06 Canberra 14.3 34.1 0.0 6.6 10.5
## 68 2008-01-07 Canberra 16.5 33.9 0.0 9.0 12.6
## 69 2008-01-08 Canberra 16.5 30.3 0.0 10.0 8.1
## 70 2008-01-09 Canberra 17.5 29.9 0.0 6.6 8.8
## 71 2008-01-10 Canberra 14.7 34.2 0.0 6.6 12.8
## 72 2008-01-11 Canberra 17.5 35.8 0.0 9.4 13.3
## 73 2008-01-12 Canberra 20.9 35.7 0.0 13.8 6.9
## 74 2008-01-13 Canberra 17.0 33.8 2.0 9.0 13.5
## 75 2008-01-14 Canberra 16.0 22.8 0.0 12.4 6.0
## 76 2008-01-15 Canberra 15.4 33.8 0.0 5.2 11.1
## 77 2008-01-16 Canberra 17.9 33.2 0.0 10.4 8.4
## 78 2008-01-17 Canberra 15.2 25.1 4.8 6.4 11.6
## 79 2008-01-18 Canberra 15.1 20.4 0.0 9.6 0.1
## 80 2008-01-19 Canberra 15.3 19.6 18.8 5.0 0.0
## 81 2008-01-20 Canberra 17.2 24.7 12.2 1.4 8.1
## 82 2008-01-21 Canberra 15.9 19.9 0.8 5.6 1.6
## 83 2008-01-22 Canberra 10.0 22.5 0.0 4.4 11.6
## 84 2008-01-23 Canberra 9.9 24.4 0.0 5.8 10.8
## 85 2008-01-24 Canberra 10.3 27.8 0.0 6.4 9.9
## 86 2008-01-25 Canberra 15.4 25.7 0.0 6.8 8.2
## 87 2008-01-26 Canberra 12.7 28.8 0.0 7.4 9.0
## 88 2008-01-27 Canberra 13.2 31.3 0.0 6.6 11.6
## 89 2008-01-28 Canberra 15.3 33.2 0.0 9.4 13.2
## 90 2008-01-29 Canberra 17.9 33.9 0.0 10.4 11.8
## 91 2008-01-30 Canberra 18.0 34.9 0.0 9.2 9.9
## 92 2008-01-31 Canberra 17.6 27.8 5.2 10.2 3.6
## 93 2008-02-01 Canberra 16.0 23.8 2.2 5.4 6.2
## 94 2008-02-02 Canberra 14.9 28.8 0.0 5.8 8.1
## 95 2008-02-03 Canberra 17.1 29.6 0.0 5.8 9.2
## 96 2008-02-04 Canberra 18.2 22.6 1.8 8.0 0.0
## 97 2008-02-05 Canberra 16.8 22.8 9.0 2.8 0.3
## 98 2008-02-06 Canberra 13.6 27.4 1.0 2.8 8.0
## 99 2008-02-07 Canberra 14.5 24.2 0.0 6.8 5.9
## 100 2008-02-08 Canberra 12.4 19.9 16.2 5.4 5.6
## 101 2008-02-09 Canberra 10.4 20.9 0.0 4.0 8.9
## 102 2008-02-10 Canberra 9.1 23.1 0.0 5.8 9.6
## 103 2008-02-11 Canberra 8.9 26.0 0.0 5.0 10.7
## 104 2008-02-12 Canberra 14.5 24.2 4.4 6.6 5.9
## 105 2008-02-13 Canberra 12.6 18.2 11.0 3.2 0.4
## 106 2008-02-14 Canberra 8.6 24.2 0.2 2.8 12.7
## 107 2008-02-15 Canberra 10.8 25.2 0.0 5.6 12.6
## 108 2008-02-16 Canberra 11.2 26.1 0.0 7.2 12.6
## 109 2008-02-17 Canberra 12.1 24.1 0.0 7.4 10.2
## 110 2008-02-18 Canberra 10.8 25.8 0.0 6.8 11.7
## 111 2008-02-19 Canberra 11.4 27.1 0.0 5.6 12.1
## 112 2008-02-20 Canberra 12.0 28.9 0.0 7.2 8.2
## 113 2008-02-21 Canberra 16.3 24.8 1.8 7.8 3.8
## 114 2008-02-22 Canberra 12.7 28.6 6.6 3.2 8.6
## 115 2008-02-23 Canberra 12.7 25.1 0.0 7.8 12.4
## 116 2008-02-24 Canberra 12.0 23.8 0.0 10.4 12.4
## 117 2008-02-25 Canberra 11.5 25.9 0.0 5.2 10.2
## 118 2008-02-26 Canberra 13.0 28.2 0.0 5.0 11.6
## 119 2008-02-27 Canberra 11.7 27.6 0.0 7.8 8.1
## 120 2008-02-28 Canberra 14.8 17.3 0.0 7.6 0.8
## 121 2008-02-29 Canberra 7.7 18.4 10.4 5.2 12.0
## 122 2008-03-01 Canberra 4.4 21.8 0.0 6.2 12.1
## 123 2008-03-02 Canberra 7.4 24.4 0.0 6.2 11.6
## 124 2008-03-03 Canberra 8.3 27.3 0.0 5.6 10.1
## 125 2008-03-04 Canberra 10.1 28.2 0.0 6.0 7.3
## 126 2008-03-05 Canberra 12.0 27.6 0.0 6.0 11.0
## 127 2008-03-06 Canberra 12.9 31.8 0.0 6.0 11.3
## 128 2008-03-07 Canberra 10.8 29.2 0.0 8.4 7.5
## 129 2008-03-08 Canberra 9.5 27.4 3.0 4.8 11.5
## 130 2008-03-09 Canberra 12.1 27.8 0.0 5.0 11.5
## 131 2008-03-10 Canberra 12.5 31.7 0.0 6.6 11.2
## 132 2008-03-11 Canberra 13.9 34.7 0.0 6.4 8.5
## 133 2008-03-12 Canberra 13.3 31.7 0.2 7.8 11.0
## 134 2008-03-13 Canberra 13.2 33.1 0.0 8.6 9.7
## 135 2008-03-14 Canberra 12.3 33.8 0.0 7.2 11.3
## 136 2008-03-15 Canberra 13.8 35.2 0.0 6.4 11.2
## 137 2008-03-16 Canberra 11.3 32.3 0.0 9.4 11.4
## 138 2008-03-17 Canberra 11.7 30.2 0.0 7.8 11.2
## 139 2008-03-18 Canberra 12.5 29.9 0.0 5.8 10.7
## 140 2008-03-19 Canberra 15.1 26.2 0.0 9.0 9.8
## 141 2008-03-20 Canberra 11.5 29.3 0.0 5.2 8.0
## 142 2008-03-21 Canberra 13.0 14.8 0.0 8.2 0.0
## 143 2008-03-22 Canberra 11.6 19.6 0.0 2.8 1.6
## 144 2008-03-23 Canberra 12.8 24.9 0.0 2.4 6.2
## 145 2008-03-24 Canberra 15.5 22.4 0.6 4.8 1.9
## 146 2008-03-25 Canberra 13.1 17.4 6.4 2.8 0.0
## 147 2008-03-26 Canberra 12.6 20.2 19.8 2.6 9.1
## 148 2008-03-27 Canberra 4.4 18.3 0.0 4.6 9.6
## 149 2008-03-28 Canberra 4.4 18.2 0.0 3.6 11.0
## 150 2008-03-29 Canberra 7.1 18.5 0.0 3.4 10.0
## 151 2008-03-30 Canberra 4.2 18.9 0.0 6.4 10.8
## 152 2008-03-31 Canberra 9.6 18.8 0.0 6.4 10.0
## 153 2008-04-01 Canberra 3.5 21.8 0.0 6.0 10.3
## 154 2008-04-02 Canberra 5.3 23.3 0.0 3.6 5.6
## 155 2008-04-03 Canberra 7.0 14.3 2.6 9.6 9.7
## 156 2008-04-04 Canberra 0.4 18.9 0.0 4.8 9.6
## 157 2008-04-05 Canberra 3.2 21.4 0.0 3.2 10.6
## 158 2008-04-06 Canberra 5.9 21.8 0.0 2.8 9.3
## 159 2008-04-07 Canberra 8.1 20.5 0.0 3.8 7.8
## 160 2008-04-08 Canberra 6.9 18.9 0.0 4.2 4.1
## 161 2008-04-09 Canberra 5.6 19.5 0.0 2.8 6.8
## 162 2008-04-10 Canberra 7.2 22.9 0.0 2.2 9.5
## 163 2008-04-11 Canberra 7.1 23.4 0.0 3.4 10.2
## 164 2008-04-12 Canberra 6.1 24.1 0.0 4.6 6.1
## 165 2008-04-13 Canberra 7.1 19.8 2.0 3.2 7.7
## 166 2008-04-14 Canberra 5.6 18.0 5.2 3.8 9.3
## 167 2008-04-15 Canberra 5.4 20.7 0.0 3.2 10.8
## 168 2008-04-16 Canberra 6.3 19.3 0.0 3.4 10.6
## 169 2008-04-17 Canberra 5.3 21.0 0.0 4.6 6.3
## 170 2008-04-18 Canberra 7.9 19.7 0.0 3.2 8.3
## 171 2008-04-19 Canberra 8.4 16.1 0.0 3.0 4.9
## 172 2008-04-20 Canberra 8.1 18.7 0.0 4.4 7.1
## 173 2008-04-21 Canberra 2.4 20.6 0.0 2.8 10.1
## 174 2008-04-22 Canberra 5.6 18.9 0.0 3.8 8.0
## 175 2008-04-23 Canberra 7.5 19.0 0.0 4.0 6.8
## 176 2008-04-24 Canberra 2.5 21.2 0.0 2.0 7.9
## 177 2008-04-25 Canberra 5.0 20.9 0.0 2.0 8.9
## 178 2008-04-26 Canberra 3.8 21.7 0.2 2.8 6.5
## 179 2008-04-27 Canberra 7.9 18.7 0.0 5.8 5.8
## 180 2008-04-28 Canberra 4.3 11.3 7.2 4.4 5.6
## 181 2008-04-29 Canberra -2.1 13.8 0.2 1.8 9.5
## 182 2008-04-30 Canberra -1.8 14.8 0.0 1.4 7.0
## 183 2008-05-01 Canberra 3.8 13.8 0.0 2.8 0.8
## 184 2008-05-02 Canberra 2.1 17.3 0.0 1.6 9.2
## 185 2008-05-03 Canberra 0.5 17.1 0.0 4.0 9.4
## 186 2008-05-04 Canberra -0.9 16.7 0.0 2.4 9.3
## 187 2008-05-05 Canberra 0.4 19.0 0.0 3.4 8.3
## 188 2008-05-06 Canberra 7.5 16.8 0.0 2.8 3.0
## 189 2008-05-07 Canberra 8.3 17.6 0.0 3.4 9.4
## 190 2008-05-08 Canberra -0.2 18.1 0.0 4.4 9.4
## 191 2008-05-09 Canberra 0.1 21.0 0.0 2.2 9.2
## 192 2008-05-10 Canberra 1.5 20.9 0.0 2.4 9.3
## 193 2008-05-11 Canberra 8.3 17.4 0.0 2.0 1.6
## 194 2008-05-12 Canberra 9.4 19.2 0.0 2.2 7.7
## 195 2008-05-13 Canberra 1.3 19.0 0.0 2.2 9.4
## 196 2008-05-14 Canberra 2.2 18.6 0.0 2.0 9.2
## 197 2008-05-15 Canberra -0.4 17.9 0.0 2.4 8.7
## 198 2008-05-16 Canberra 4.5 16.0 1.8 3.0 4.3
## 199 2008-05-17 Canberra 7.9 12.3 1.0 1.8 1.7
## 200 2008-05-18 Canberra 4.3 14.1 0.8 1.6 8.8
## 201 2008-05-19 Canberra -2.7 18.1 0.0 2.2 9.3
## 202 2008-05-20 Canberra 0.3 17.0 0.0 2.2 5.6
## 203 2008-05-21 Canberra 3.8 17.4 0.0 2.6 7.3
## 204 2008-05-22 Canberra 2.4 14.7 0.0 2.6 9.2
## 205 2008-05-23 Canberra 1.2 14.8 0.0 2.4 6.7
## 206 2008-05-24 Canberra 1.2 14.5 0.0 1.2 8.9
## 207 2008-05-25 Canberra -0.3 17.5 0.0 1.6 8.4
## 208 2008-05-26 Canberra 4.7 18.5 3.8 2.0 5.1
## 209 2008-05-27 Canberra 4.9 18.1 5.2 1.2 8.5
## 210 2008-05-28 Canberra 1.4 16.8 0.0 1.6 8.2
## 211 2008-05-29 Canberra 2.2 17.5 0.2 1.2 8.5
## 212 2008-05-30 Canberra -0.1 18.0 0.0 2.0 8.6
## 213 2008-05-31 Canberra -0.9 18.5 0.0 2.2 8.9
## 214 2008-06-01 Canberra 0.6 14.0 0.0 2.2 2.7
## 215 2008-06-02 Canberra 4.6 15.7 0.0 1.0 0.6
## 216 2008-06-03 Canberra 9.8 14.4 0.8 0.6 0.0
## 217 2008-06-04 Canberra 10.6 15.1 3.8 0.2 2.6
## 218 2008-06-05 Canberra 7.8 15.1 0.0 2.2 2.7
## 219 2008-06-06 Canberra 4.4 16.7 0.0 1.6 9.0
## 220 2008-06-07 Canberra -0.2 15.5 0.0 1.4 9.0
## 221 2008-06-08 Canberra 4.3 14.5 0.0 2.0 3.0
## 222 2008-06-09 Canberra 7.4 16.3 0.0 1.2 NA
## 223 2008-06-10 Canberra 8.6 13.7 6.2 2.2 0.0
## 224 2008-06-11 Canberra 10.2 15.0 4.8 0.2 0.5
## 225 2008-06-12 Canberra 7.3 16.4 0.2 1.2 8.5
## 226 2008-06-13 Canberra 8.7 13.0 0.6 3.2 7.1
## 227 2008-06-14 Canberra 1.0 11.8 0.0 2.2 7.2
## 228 2008-06-15 Canberra 2.1 14.7 0.0 2.6 8.2
## 229 2008-06-16 Canberra 6.4 16.9 0.0 2.6 5.9
## 230 2008-06-17 Canberra 5.4 15.5 0.0 1.6 5.8
## 231 2008-06-18 Canberra 0.4 15.5 0.0 1.0 4.7
## 232 2008-06-19 Canberra 4.0 15.9 0.0 0.6 2.0
## 233 2008-06-20 Canberra 8.4 11.7 4.8 0.6 0.0
## 234 2008-06-21 Canberra 0.4 13.9 0.6 0.8 7.7
## 235 2008-06-22 Canberra 4.2 14.0 0.0 1.4 7.6
## 236 2008-06-23 Canberra 0.9 12.9 0.0 2.0 6.8
## 237 2008-06-24 Canberra 0.8 13.0 0.0 1.4 4.1
## 238 2008-06-25 Canberra 4.3 12.6 0.0 2.0 9.0
## 239 2008-06-26 Canberra 6.3 11.8 0.0 2.6 6.5
## 240 2008-06-27 Canberra 3.5 14.3 0.0 3.4 8.9
## 241 2008-06-28 Canberra -1.5 14.8 0.0 2.2 8.0
## 242 2008-06-29 Canberra 1.2 16.0 0.0 1.4 6.1
## 243 2008-06-30 Canberra 0.5 15.4 0.0 2.4 6.4
## 244 2008-07-01 Canberra 5.3 11.7 2.0 3.6 5.6
## 245 2008-07-02 Canberra 6.6 13.1 0.2 2.8 8.2
## 246 2008-07-03 Canberra -1.6 11.5 0.0 2.8 8.9
## 247 2008-07-04 Canberra -3.1 12.0 0.0 1.8 3.9
## 248 2008-07-05 Canberra -0.1 14.2 0.0 1.4 7.0
## 249 2008-07-06 Canberra -0.6 14.0 0.0 1.2 7.1
## 250 2008-07-07 Canberra 3.0 11.1 0.8 1.4 0.2
## 251 2008-07-08 Canberra 2.9 9.5 16.8 1.4 6.5
## 252 2008-07-09 Canberra -1.3 8.8 0.0 0.8 2.8
## 253 2008-07-10 Canberra 1.8 8.7 0.0 1.8 1.2
## 254 2008-07-11 Canberra 2.9 8.4 1.6 1.4 7.7
## 255 2008-07-12 Canberra -2.6 11.1 0.2 1.4 6.5
## 256 2008-07-13 Canberra 0.5 11.0 0.0 1.0 0.9
## 257 2008-07-14 Canberra 2.7 16.5 0.0 0.6 8.9
## 258 2008-07-15 Canberra -1.7 13.6 0.0 1.8 5.2
## 259 2008-07-16 Canberra -0.9 12.8 0.2 2.0 1.9
## 260 2008-07-17 Canberra -1.8 11.5 0.0 0.6 4.7
## 261 2008-07-18 Canberra 1.3 10.6 0.0 0.8 5.6
## 262 2008-07-19 Canberra 2.4 11.6 1.2 2.2 8.1
## 263 2008-07-20 Canberra -1.1 11.0 0.2 1.8 0.0
## 264 2008-07-21 Canberra 2.3 11.6 19.2 1.8 7.5
## 265 2008-07-22 Canberra -2.2 11.6 0.0 1.4 9.2
## 266 2008-07-23 Canberra -3.5 11.2 0.0 1.6 7.7
## 267 2008-07-24 Canberra -1.0 12.2 0.0 1.6 8.4
## 268 2008-07-25 Canberra -2.1 12.9 0.0 1.2 8.1
## 269 2008-07-26 Canberra -2.0 11.3 0.2 2.2 5.9
## 270 2008-07-27 Canberra -2.3 9.7 0.0 1.4 1.9
## 271 2008-07-28 Canberra -1.6 10.7 1.4 0.8 9.1
## 272 2008-07-29 Canberra 0.8 12.2 0.0 1.8 8.6
## 273 2008-07-30 Canberra -2.8 12.2 0.0 2.6 8.7
## 274 2008-07-31 Canberra -2.8 14.1 0.0 2.2 6.8
## 275 2008-08-01 Canberra 3.0 9.7 1.0 2.6 0.7
## 276 2008-08-02 Canberra 4.4 11.5 6.6 2.2 9.3
## 277 2008-08-03 Canberra 2.3 12.8 0.0 2.2 9.6
## 278 2008-08-04 Canberra -2.0 12.3 0.0 2.4 5.8
## 279 2008-08-05 Canberra -1.9 10.9 0.0 1.8 4.2
## 280 2008-08-06 Canberra 4.8 14.1 4.0 1.6 8.3
## 281 2008-08-07 Canberra -0.6 11.1 0.0 3.0 5.0
## 282 2008-08-08 Canberra 3.1 12.5 1.2 1.4 7.2
## 283 2008-08-09 Canberra -2.9 9.6 0.0 1.8 7.3
## 284 2008-08-10 Canberra -3.5 7.6 0.4 2.4 4.7
## 285 2008-08-11 Canberra -0.3 9.3 0.4 1.4 9.9
## 286 2008-08-12 Canberra 0.1 10.4 0.0 1.8 7.9
## 287 2008-08-13 Canberra 2.3 12.2 0.0 2.8 9.8
## 288 2008-08-14 Canberra 2.1 10.7 0.0 3.4 9.4
## 289 2008-08-15 Canberra 4.6 14.7 0.0 4.4 8.4
## 290 2008-08-16 Canberra 3.7 14.2 0.0 3.0 10.0
## 291 2008-08-17 Canberra -1.3 11.6 0.0 4.0 10.4
## 292 2008-08-18 Canberra -3.4 12.5 0.0 3.0 6.8
## 293 2008-08-19 Canberra -5.3 13.1 0.0 2.2 7.9
## 294 2008-08-20 Canberra 0.0 14.0 0.0 2.4 4.7
## 295 2008-08-21 Canberra 2.4 14.1 0.0 3.0 1.8
## 296 2008-08-22 Canberra -0.6 12.2 0.0 2.6 7.0
## 297 2008-08-23 Canberra 2.3 11.6 0.0 5.4 9.5
## 298 2008-08-24 Canberra -3.7 14.4 0.0 2.6 10.4
## 299 2008-08-25 Canberra -0.9 14.2 0.0 2.6 7.8
## 300 2008-08-26 Canberra -1.5 17.3 0.0 2.8 9.0
## 301 2008-08-27 Canberra -3.3 15.1 0.0 3.0 NA
## 302 2008-08-28 Canberra -0.1 14.7 0.0 3.4 9.9
## 303 2008-08-29 Canberra -0.2 16.2 0.0 3.4 5.9
## 304 2008-08-30 Canberra 0.5 16.3 0.0 1.8 4.1
## 305 2008-08-31 Canberra 6.1 17.2 4.0 2.2 2.4
## 306 2008-09-01 Canberra 4.1 14.8 7.4 2.6 10.8
## 307 2008-09-02 Canberra 0.1 16.7 0.0 3.8 10.2
## 308 2008-09-03 Canberra 3.2 12.1 0.0 2.8 3.9
## 309 2008-09-04 Canberra 5.4 11.3 0.2 2.2 0.6
## 310 2008-09-05 Canberra 5.8 12.4 0.0 1.6 0.0
## 311 2008-09-06 Canberra 6.3 16.1 0.0 1.8 2.9
## 312 2008-09-07 Canberra -0.9 16.7 0.0 2.8 8.6
## 313 2008-09-08 Canberra 0.2 15.5 1.0 2.4 9.4
## 314 2008-09-09 Canberra -3.7 14.7 0.0 3.4 10.9
## 315 2008-09-10 Canberra -2.7 15.2 0.0 4.0 9.7
## 316 2008-09-11 Canberra -2.5 16.6 0.0 3.0 9.9
## 317 2008-09-12 Canberra -0.5 21.6 0.0 5.0 9.9
## 318 2008-09-13 Canberra 9.0 25.5 0.0 5.6 10.2
## 319 2008-09-14 Canberra 13.1 19.4 9.8 8.8 6.0
## 320 2008-09-15 Canberra 8.7 19.7 1.6 5.2 8.0
## 321 2008-09-16 Canberra 3.9 13.2 3.4 6.6 11.0
## 322 2008-09-17 Canberra 0.7 14.1 0.0 5.6 9.0
## 323 2008-09-18 Canberra 1.1 18.0 0.0 1.6 8.6
## 324 2008-09-19 Canberra 5.1 23.3 0.0 3.6 10.3
## 325 2008-09-20 Canberra 7.5 23.3 0.0 6.8 10.9
## 326 2008-09-21 Canberra 4.7 19.5 0.0 10.0 11.0
## 327 2008-09-22 Canberra 3.2 21.9 0.0 6.8 5.2
## 328 2008-09-23 Canberra 7.8 16.2 17.4 6.4 7.9
## 329 2008-09-24 Canberra 2.4 17.3 0.0 2.2 11.3
## 330 2008-09-25 Canberra 3.2 18.7 0.0 2.6 11.1
## 331 2008-09-26 Canberra 2.5 20.9 0.0 3.6 10.6
## 332 2008-09-27 Canberra 6.5 25.7 0.0 4.8 10.5
## 333 2008-09-28 Canberra 14.4 24.3 0.0 9.4 11.1
## 334 2008-09-29 Canberra 4.9 18.9 0.0 9.6 9.4
## 335 2008-09-30 Canberra 2.3 16.8 0.0 4.8 11.4
## 336 2008-10-01 Canberra 1.4 20.6 0.0 5.4 11.1
## 337 2008-10-02 Canberra 5.6 27.6 0.0 5.2 11.0
## 338 2008-10-03 Canberra 16.8 28.9 0.0 10.0 10.8
## 339 2008-10-04 Canberra 14.4 20.7 7.6 9.4 4.9
## 340 2008-10-05 Canberra 10.3 21.3 3.0 4.2 6.7
## 341 2008-10-06 Canberra 11.2 18.0 0.0 4.8 8.4
## 342 2008-10-07 Canberra 0.3 16.0 8.2 5.4 11.8
## 343 2008-10-08 Canberra 0.5 17.9 0.0 5.8 11.5
## 344 2008-10-09 Canberra 0.5 20.0 0.0 6.2 11.5
## 345 2008-10-10 Canberra 4.6 22.0 0.0 4.4 11.0
## 346 2008-10-11 Canberra 8.2 22.4 0.0 5.4 11.2
## 347 2008-10-12 Canberra 4.5 23.9 0.0 4.8 11.7
## 348 2008-10-13 Canberra 6.7 26.1 0.0 6.2 7.5
## 349 2008-10-14 Canberra 11.9 21.1 13.2 6.6 NA
## 350 2008-10-15 Canberra 9.2 19.6 0.6 3.4 10.4
## 351 2008-10-16 Canberra 4.4 21.0 0.0 4.2 12.2
## 352 2008-10-17 Canberra 5.0 24.1 0.0 6.2 12.0
## 353 2008-10-18 Canberra 6.7 24.7 0.0 5.4 8.6
## 354 2008-10-19 Canberra 8.3 28.5 0.0 5.8 9.8
## 355 2008-10-20 Canberra 11.3 27.4 0.2 7.6 12.1
## 356 2008-10-21 Canberra 9.0 20.6 0.0 9.0 6.2
## 357 2008-10-22 Canberra 3.4 15.0 0.8 4.8 11.7
## 358 2008-10-23 Canberra 3.2 18.0 0.0 7.4 12.2
## 359 2008-10-24 Canberra 0.9 20.7 0.0 5.4 8.4
## 360 2008-10-25 Canberra 3.3 25.5 0.0 5.2 10.8
## 361 2008-10-26 Canberra 7.9 26.1 0.0 6.8 3.5
## 362 2008-10-27 Canberra 9.0 30.7 0.0 7.6 12.1
## 363 2008-10-28 Canberra 7.1 28.4 0.0 11.6 12.7
## 364 2008-10-29 Canberra 12.5 19.9 0.0 8.4 5.3
## 365 2008-10-30 Canberra 12.5 26.9 0.0 5.0 7.1
## 366 2008-10-31 Canberra 12.3 30.2 0.0 6.0 12.6
## WindGustDir WindGustSpeed WindDir9am WindDir3pm WindSpeed9am
## 1 NW 30 SW NW 6
## 2 ENE 39 E W 4
## 3 NW 85 N NNE 6
## 4 NW 54 WNW W 30
## 5 SSE 50 SSE ESE 20
## 6 SE 44 SE E 20
## 7 SE 43 SE ESE 19
## 8 E 41 SE E 11
## 9 S 48 E ENE 19
## 10 E 31 S ESE 7
## 11 N 30 SE NW 6
## 12 E 41 E NW 2
## 13 WNW 30 S NW 6
## 14 NW 44 WNW W 7
## 15 NW 41 S W 6
## 16 E 46 SE WSW 7
## 17 ESE 44 WSW W 6
## 18 S 52 SW NE 6
## 19 E 39 NNE W 4
## 20 NE 33 NNW NNW 2
## 21 WNW 59 N NW 2
## 22 E 26 ENE E 6
## 23 ESE 28 S SE 13
## 24 NNE 26 WSW NE 6
## 25 ENE 33 SSE NE 9
## 26 E 41 E E 6
## 27 ENE 39 E E 20
## 28 S 52 S NNE 6
## 29 SE 39 SE SE 7
## 30 NNW 30 SSW S 6
## 31 SSE 41 E S 6
## 32 NNE 41 E SW 6
## 33 NW 50 WNW NW 13
## 34 NW 50 NW WNW 20
## 35 ENE 43 ESE E 11
## 36 ENE 39 ESE ESE 13
## 37 SW 41 NW N 6
## 38 NE 39 E N 7
## 39 NW 43 N W 9
## 40 NNW 35 NNE WNW 11
## 41 ENE 35 ESE E 9
## 42 ENE 41 ESE E 15
## 43 SE 39 ESE E 22
## 44 E 35 NNW N 6
## 45 E 41 SE WNW 2
## 46 S 31 SSE NE 6
## 47 ESE 48 SSE ESE 13
## 48 ENE 39 SE E 13
## 49 NE 22 NE ENE 7
## 50 NNW 30 N NW 4
## 51 N 41 NW NW 6
## 52 NNW 76 N WNW 41
## 53 ENE 39 N N 9
## 54 NW 44 NNW WNW 7
## 55 E 41 SE NE 11
## 56 NNW 41 W NNW 6
## 57 NNW 65 N NNW 7
## 58 NNW 28 NNW NW 6
## 59 NNW 30 NW N 6
## 60 E 39 SSW ESE 6
## 61 NE 31 SSE NE 7
## 62 NNE 35 ESE W 2
## 63 ESE 41 ESE WSW 2
## 64 ESE 50 ESE ESE 20
## 65 ESE 46 ESE ESE 24
## 66 NE 35 SSE E 7
## 67 ENE 39 W NNW 6
## 68 ENE 39 E NW 11
## 69 E 46 E N 7
## 70 E 43 E ENE 13
## 71 NE 33 WNW NW 6
## 72 SSE 57 NNW NW 6
## 73 SW 50 E WNW 4
## 74 WNW 52 NNW W 6
## 75 E 50 E ENE 13
## 76 W 35 E NW 7
## 77 N 59 N NNE 15
## 78 E 46 ESE ESE 20
## 79 ESE 39 ESE ESE 17
## 80 NE 33 SSE NNE 9
## 81 NW 50 NW WNW 19
## 82 E 48 SSE ESE 17
## 83 E 33 SE S 11
## 84 NE 28 SE E 7
## 85 ENE 35 SE NE 6
## 86 E 41 E NE 9
## 87 NNE 28 NW SSW 4
## 88 WSW 46 N WNW 4
## 89 NNW 44 NNE NW 4
## 90 ENE 46 S W 6
## 91 NW 69 N W 6
## 92 ESE 39 N NNW 13
## 93 SSE 30 SE ESE 11
## 94 NNE 30 SSE NNE 7
## 95 E 48 SE ESE 9
## 96 ENE 33 SSE ENE 7
## 97 ESE 30 S SSE 7
## 98 W 52 NW WNW 6
## 99 SSW 61 N NNW 11
## 100 ENE 41 ESE ESE 7
## 101 SSE 33 S S 15
## 102 ENE 41 SSE W 17
## 103 NE 31 SE NE 7
## 104 W 48 NNW WNW 9
## 105 ENE 30 SSE SSE 13
## 106 E 33 S SE 11
## 107 ENE 35 SE E 7
## 108 ENE 39 SE E 7
## 109 ENE 46 ESE NNE 9
## 110 E 31 S NNE 7
## 111 NE 33 ESE SE 6
## 112 ESE 39 SSE WNW 2
## 113 S 50 NNW N 4
## 114 W 50 <NA> W NA
## 115 NW 46 WNW WNW 20
## 116 NW 44 NW WNW 15
## 117 ENE 44 ENE WSW 9
## 118 NW 44 WSW NW 4
## 119 W 48 <NA> W NA
## 120 SSE 48 S SE 13
## 121 S 48 S S 24
## 122 S 35 SSE SSE 15
## 123 E 35 ESE WNW 7
## 124 E 35 ESE WNW 6
## 125 ESE 39 SSE WNW 6
## 126 E 46 SSE WSW 7
## 127 WSW 41 NNW NNE 6
## 128 E 50 <NA> ENE NA
## 129 NNW 24 SSE NNW 6
## 130 E 41 SE NNE 7
## 131 WNW 24 ENE W 6
## 132 SSW 46 SE ENE 11
## 133 WNW 44 ESE WSW 6
## 134 ENE 39 SE NNW 7
## 135 W 22 SE W 9
## 136 SE 48 SE ESE 7
## 137 NE 28 ENE WNW 4
## 138 NE 33 ESE NNW 9
## 139 NW 43 <NA> WNW 0
## 140 NE 31 SE NNE 4
## 141 NW 46 <NA> WSW 0
## 142 SE 30 ESE ESE 9
## 143 E 33 SE ESE 6
## 144 ENE 30 NNW SW 6
## 145 NW 28 SSE WNW 6
## 146 NNW 43 N N 11
## 147 W 46 NNW W 17
## 148 N 33 SE N 7
## 149 W 31 SE WNW 7
## 150 NW 57 N NW 9
## 151 WNW 50 WSW WNW 6
## 152 WNW 57 NW W 19
## 153 NNW 22 ESE WNW 7
## 154 NNW 83 SSW NW 2
## 155 WNW 63 NW W 26
## 156 N 22 NW WSW 6
## 157 E 26 SE NNW 7
## 158 E 35 SSW NNW 7
## 159 ENE 31 ESE ENE 11
## 160 ESE 39 SSE SE 15
## 161 SW 17 S WNW 9
## 162 E 26 NNW N 4
## 163 ESE 39 SE WSW 2
## 164 WNW 35 SSW WNW 6
## 165 W 39 SSE NW 13
## 166 S 31 SSE SSE 9
## 167 SSE 28 SSE S 7
## 168 S 31 S SE 9
## 169 WNW 26 SSW NW 7
## 170 ESE 48 SSE ENE 17
## 171 SE 35 SE ESE 13
## 172 ESE 33 SSE ESE 11
## 173 E 30 SE SSE 9
## 174 SE 33 SSE E 13
## 175 ENE 26 <NA> ESE 0
## 176 NE 28 ESE NE 7
## 177 WNW 22 <NA> NW 0
## 178 NW 44 ESE WNW 2
## 179 NW 59 NNW NW 26
## 180 W 57 WNW WNW 26
## 181 NNW 22 <NA> NNW 0
## 182 N 28 E N 2
## 183 WNW 31 W NNW 6
## 184 W 43 SSW WNW 6
## 185 NW 31 ESE W 6
## 186 NNW 30 SW NNW 2
## 187 NW 39 NE WNW 2
## 188 NW 41 W NW 7
## 189 WNW 43 NW WNW 17
## 190 NW 24 <NA> NW 0
## 191 NNW 17 WNW N 2
## 192 NW 20 NW NNW 2
## 193 E 20 WSW NE 6
## 194 <NA> 24 E NNW 4
## 195 NNW 30 SE NW 7
## 196 NNW 31 <NA> NNW NA
## 197 NW 33 NNE NW 2
## 198 NW 35 W NW 9
## 199 NW 52 NNW NW 30
## 200 NW 41 NNW WNW 13
## 201 W 52 <NA> WNW 0
## 202 WNW 31 S WNW 6
## 203 E 24 ESE W 2
## 204 ESE 20 SSE E 7
## 205 SE 17 SE SSW 11
## 206 SE 17 SE SSW 6
## 207 W 39 SE NNW 6
## 208 ESE 22 NNW W 6
## 209 NNW 22 <NA> NW 0
## 210 NW 20 <NA> NW 0
## 211 NW 20 SSE WNW 7
## 212 <NA> NA N NNW 2
## 213 E 22 <NA> N 0
## 214 NE 17 <NA> ENE NA
## 215 NNE 15 SSE NNE 6
## 216 ESE 20 S ESE 9
## 217 SSE 41 SE SE 9
## 218 S 31 SSE S 6
## 219 S 22 SE NNE 11
## 220 NE 28 N ESE 4
## 221 E 30 SSE ENE 6
## 222 NNE 30 SSE NE 6
## 223 NW 31 E <NA> 2
## 224 NW 46 NNW NW 22
## 225 NW 43 N WNW 15
## 226 WNW 54 W WNW 19
## 227 S 48 NW S 7
## 228 S 43 S SSW 24
## 229 SSW 26 SSW ESE 17
## 230 NNE 20 SSW NNE 7
## 231 N 13 N NNW 6
## 232 NNW 17 SE SSE 6
## 233 W 26 WNW WNW 6
## 234 WNW 41 E WNW 6
## 235 NW 33 NNW SE 9
## 236 NW 24 W N 7
## 237 WNW 41 S NW 2
## 238 NW 46 <NA> WNW 0
## 239 WNW 63 NNW WNW 20
## 240 NNW 35 N NNW 7
## 241 NW 15 N NW 6
## 242 NNW 31 S N 6
## 243 W 70 NW NNW 22
## 244 NW 78 NW W 33
## 245 WNW 61 NNW WNW 31
## 246 N 31 ESE NNW 7
## 247 ESE 35 SSW NE 4
## 248 W 13 <NA> WNW NA
## 249 NW 41 WNW NNW 2
## 250 W 35 <NA> N 0
## 251 NW 35 <NA> NW 0
## 252 WNW 39 NW NW 9
## 253 NW 65 NW NW 31
## 254 NW 59 NW WNW 20
## 255 N 20 E NNW 2
## 256 NNW 31 <NA> NW 0
## 257 NNW 41 SW NNW 7
## 258 NNW 28 <NA> NNW NA
## 259 N 17 SE NNW 6
## 260 NNW 41 <NA> NNW 0
## 261 NW 46 NNW WNW 24
## 262 NW 35 NNW NW 15
## 263 WNW 41 <NA> NE 0
## 264 WNW 54 WNW WNW 26
## 265 S 39 E SSW 2
## 266 ESE 26 N ESE 6
## 267 ESE 30 SE E 7
## 268 S 31 SE SE 7
## 269 WNW 33 SE WNW 2
## 270 SSE 28 SSE WSW 6
## 271 S 59 SSW S 28
## 272 <NA> NA S S 19
## 273 NNW 31 <NA> NNW 0
## 274 WNW 48 <NA> WNW 0
## 275 W 65 NW NW 19
## 276 WNW 57 NNW WNW 28
## 277 WNW 35 ENE WNW 4
## 278 W 31 ESE W 4
## 279 S 50 <NA> SSW 0
## 280 S 48 S SSE 30
## 281 NNW 41 SE N 7
## 282 N 43 WNW N 6
## 283 NW 43 N NW 6
## 284 NW 50 NW NW 30
## 285 N 39 NNW N 9
## 286 WNW 59 NW WNW 22
## 287 WNW 44 WNW NW 20
## 288 NW 59 NNW WNW 28
## 289 WNW 52 WNW NW 28
## 290 NNW 46 WNW WSW 24
## 291 N 30 ESE NNW 9
## 292 SSE 48 NNW WNW 7
## 293 NW 33 N NNW 4
## 294 WNW 39 NNW WNW 13
## 295 NW 46 NNW NW 15
## 296 S 59 S S 15
## 297 S 54 SSW ESE 30
## 298 NNW 22 N NNW 2
## 299 WNW 31 SSW N 7
## 300 NW 48 <NA> WNW 0
## 301 SSW 30 SSE SE 9
## 302 ENE 30 SE NE 6
## 303 E 28 <NA> ENE 0
## 304 NNW 39 SSW WSW 4
## 305 NW 59 NW WNW 24
## 306 NW 46 NW W 20
## 307 WNW 28 ESE NNE 2
## 308 ESE 41 SE SE 17
## 309 ENE 35 SE ESE 11
## 310 SE 26 SSE ESE 13
## 311 S 35 S S 19
## 312 NW 35 WNW NW 7
## 313 SE 31 <NA> WNW 0
## 314 SSE 43 SE N 9
## 315 N 30 SW WNW 6
## 316 NW 31 NE N 4
## 317 NW 48 NNE NW 9
## 318 NW 50 N NW 20
## 319 NNW 67 N NW 39
## 320 NW 98 NW NNW 31
## 321 WNW 65 WNW WNW 26
## 322 ENE 20 SSW NNW 6
## 323 NNW 39 NNW NNW 2
## 324 NW 44 N NW 9
## 325 WNW 65 N NW 15
## 326 NNW 46 NNE NNW 13
## 327 NW 80 SSE NW 2
## 328 NW 50 NW N 15
## 329 E 31 SSE SW 4
## 330 N 31 E NNW 4
## 331 NNW 44 NW WNW 20
## 332 NNW 50 NNW NW 2
## 333 WNW 52 NW NW 31
## 334 NW 44 S NW 6
## 335 N 41 NNW NNW 6
## 336 N 46 SW N 6
## 337 NW 46 NNW NW 15
## 338 NNW 70 NW NW 31
## 339 NNW 33 NNW NNW 20
## 340 NNW 43 ENE N 7
## 341 W 65 N W 24
## 342 NW 57 NNW N 11
## 343 N 44 NNE NNW 2
## 344 NNW 31 S N 2
## 345 N 41 NNW N 6
## 346 NW 31 SSW NW 2
## 347 NW 30 ENE NNW 4
## 348 SSW 70 NE NNW 6
## 349 NW 41 NNE N 7
## 350 ENE 31 SSE NNW 4
## 351 NW 28 SW NW 2
## 352 NNW 52 <NA> NNW 0
## 353 NW 43 N NW 4
## 354 NW 46 W NW 2
## 355 NW 52 SE NW 6
## 356 ENE 39 S SW 11
## 357 S 70 S S 35
## 358 SSE 48 SSE S 26
## 359 NNW 39 SSE N 2
## 360 N 43 N NNW 4
## 361 NNW 43 <NA> WNW 0
## 362 NNW 76 SSE NW 7
## 363 N 48 NNW NNW 2
## 364 ESE 43 ENE ENE 11
## 365 NW 46 SSW WNW 6
## 366 NW 78 NW WNW 31
## WindSpeed3pm Pressure9am Pressure3pm Temp9am Temp3pm RainToday RISK_MM
## 1 20 1019.7 1015.0 14.4 23.6 No 3.6
## 2 17 1012.4 1008.4 17.5 25.7 Yes 3.6
## 3 6 1009.5 1007.2 15.4 20.2 Yes 39.8
## 4 24 1005.5 1007.0 13.5 14.1 Yes 2.8
## 5 28 1018.3 1018.5 11.1 15.4 Yes 0.0
## 6 24 1023.8 1021.7 10.9 14.8 No 0.2
## 7 26 1024.6 1022.2 12.4 17.3 No 0.0
## 8 24 1026.2 1024.2 12.1 15.5 No 0.0
## 9 17 1026.1 1022.7 14.1 18.9 No 16.2
## 10 6 1024.1 1020.7 13.3 21.7 Yes 0.0
## 11 9 1024.4 1021.1 14.6 24.0 No 0.2
## 12 15 1023.8 1019.9 16.8 26.0 No 0.0
## 13 7 1022.0 1017.1 17.0 27.1 No 0.0
## 14 20 1017.3 1013.1 19.7 30.7 No 0.0
## 15 20 1018.2 1013.7 18.7 30.4 No 0.0
## 16 9 1017.9 1012.8 19.1 30.7 No 0.0
## 17 19 1014.4 1009.8 20.2 29.8 No 1.2
## 18 11 1016.4 1013.0 20.1 28.6 Yes 0.6
## 19 17 1017.1 1013.3 20.2 31.2 No 0.0
## 20 13 1018.5 1013.7 22.8 32.0 No 0.0
## 21 31 1012.4 1006.5 22.2 32.8 No 0.4
## 22 11 1010.7 1008.9 16.5 18.3 No 25.8
## 23 13 1014.0 1014.9 14.0 16.8 Yes 0.4
## 24 9 1020.7 1019.2 17.8 22.8 No 0.0
## 25 15 1022.4 1018.6 16.8 27.3 No 0.0
## 26 22 1019.7 1016.5 19.8 25.1 No 0.2
## 27 17 1021.0 1018.6 16.5 21.2 No 0.0
## 28 11 1019.2 1014.8 18.8 26.7 No 0.0
## 29 17 1019.0 1017.1 18.9 19.7 No 0.4
## 30 6 1017.2 1013.3 17.3 23.2 No 22.6
## 31 20 1015.0 1014.1 17.0 16.3 Yes 4.2
## 32 9 1013.9 1009.5 16.7 25.2 Yes 0.2
## 33 35 1007.9 1004.6 20.5 19.9 No 6.6
## 34 26 1007.3 1006.3 18.8 25.1 Yes 0.0
## 35 30 1015.0 1015.3 18.6 20.5 No 0.0
## 36 9 1018.8 1016.1 18.6 24.5 No 0.0
## 37 6 1014.5 1011.5 21.5 22.6 No 4.0
## 38 13 1014.8 1011.4 18.0 26.3 Yes 0.0
## 39 24 1010.8 1008.5 20.6 28.6 No 0.0
## 40 6 1011.7 1010.4 19.3 22.9 No 0.6
## 41 15 1018.0 1017.4 13.8 16.4 No 0.0
## 42 24 1021.1 1019.6 15.7 19.4 No 0.0
## 43 20 1021.9 1019.3 15.8 19.2 No 0.0
## 44 11 1018.1 1012.5 15.8 25.0 No 0.0
## 45 13 1012.6 1010.2 17.4 29.1 No 5.4
## 46 7 1010.1 1008.6 16.6 20.0 Yes 1.4
## 47 20 1017.6 1016.8 15.3 20.8 Yes 0.0
## 48 20 1020.6 1018.3 15.3 19.8 No 0.0
## 49 6 1018.0 1015.6 16.1 20.0 No 3.4
## 50 13 1015.8 1014.1 15.3 20.4 Yes 6.4
## 51 22 1012.9 1008.3 21.0 28.2 Yes 11.0
## 52 30 996.5 996.8 20.6 19.6 Yes 17.4
## 53 20 1009.5 1009.1 14.9 18.8 Yes 0.0
## 54 13 1012.8 1009.7 15.0 22.5 No 3.4
## 55 11 1020.4 1019.1 12.4 21.0 Yes 0.0
## 56 19 1023.2 1018.0 15.3 23.9 No 0.0
## 57 48 1017.3 1014.3 19.8 19.0 No 14.4
## 58 13 1016.8 1013.4 18.3 27.4 Yes 0.0
## 59 7 1017.1 1014.2 21.5 30.3 No 0.0
## 60 22 1017.4 1015.0 23.4 34.3 No 0.0
## 61 9 1019.2 1015.6 21.9 32.2 No 0.0
## 62 11 1015.8 1011.6 21.9 31.8 No 0.0
## 63 9 1012.6 1008.7 23.0 33.6 No 0.0
## 64 24 1016.8 1016.3 19.2 22.3 No 0.0
## 65 26 1016.2 1013.0 20.3 23.9 No 0.0
## 66 15 1011.8 1007.4 18.6 26.8 No 0.0
## 67 19 1006.6 1003.3 18.9 31.9 No 0.0
## 68 11 1012.3 1009.5 20.8 31.3 No 0.0
## 69 9 1015.7 1013.4 18.1 28.0 No 0.0
## 70 11 1018.5 1015.9 19.3 27.9 No 0.0
## 71 11 1017.8 1013.3 21.3 32.2 No 0.0
## 72 19 1011.8 1006.5 24.7 34.5 No 0.0
## 73 17 1007.6 1003.0 23.6 34.0 No 2.0
## 74 24 1004.0 1001.8 23.0 31.8 Yes 0.0
## 75 19 1012.3 1012.3 17.0 21.6 No 0.0
## 76 15 1014.2 1009.0 18.0 31.7 No 0.0
## 77 20 1008.5 1006.1 24.5 23.5 No 4.8
## 78 28 1016.8 1015.0 17.1 23.9 Yes 0.0
## 79 19 1017.5 1015.8 17.8 19.4 No 18.8
## 80 13 1008.7 1006.0 18.0 18.6 Yes 12.2
## 81 28 1004.9 1004.0 19.4 21.9 Yes 0.8
## 82 22 1011.4 1012.1 17.4 18.6 No 0.0
## 83 7 1018.7 1016.8 14.7 22.2 No 0.0
## 84 7 1021.6 1019.2 16.2 22.7 No 0.0
## 85 11 1021.3 1018.1 17.0 26.3 No 0.0
## 86 17 1020.1 1016.9 17.6 24.6 No 0.0
## 87 7 1016.5 1012.4 18.3 28.3 No 0.0
## 88 26 1013.1 1009.5 19.7 30.7 No 0.0
## 89 24 1013.9 1012.0 22.4 32.1 No 0.0
## 90 11 1017.4 1014.6 19.8 32.3 No 0.0
## 91 13 1018.0 1013.7 22.2 33.1 No 5.2
## 92 13 1014.6 1012.8 21.4 26.3 Yes 2.2
## 93 11 1018.9 1017.1 16.5 22.9 Yes 0.0
## 94 11 1018.2 1014.5 19.1 27.0 No 0.0
## 95 17 1016.7 1012.8 21.7 29.1 No 1.8
## 96 13 1014.4 1011.5 18.5 22.1 Yes 9.0
## 97 11 1010.0 1007.8 18.4 21.5 Yes 1.0
## 98 24 1002.1 997.5 18.7 26.5 No 0.0
## 99 20 999.4 998.9 17.9 20.3 No 16.2
## 100 20 1007.6 1005.0 13.6 18.7 Yes 0.0
## 101 17 1007.7 1006.8 13.8 18.7 No 0.0
## 102 13 1013.6 1011.4 14.0 21.4 No 0.0
## 103 13 1016.1 1011.7 14.6 24.2 No 4.4
## 104 17 1010.8 1006.8 15.8 22.6 Yes 11.0
## 105 15 1010.0 1011.0 16.3 16.8 Yes 0.2
## 106 9 1017.5 1015.1 13.7 22.0 No 0.0
## 107 7 1020.2 1016.7 15.0 24.3 No 0.0
## 108 19 1022.9 1020.0 15.3 24.7 No 0.0
## 109 13 1025.2 1021.4 15.4 22.5 No 0.0
## 110 11 1021.3 1017.4 17.2 24.1 No 0.0
## 111 15 1017.6 1012.8 16.9 26.1 No 0.0
## 112 9 1012.2 1009.1 17.4 28.6 No 1.8
## 113 7 1011.8 1008.4 17.5 24.0 Yes 6.6
## 114 28 1008.3 1002.3 16.5 27.4 Yes 0.0
## 115 26 1007.4 1005.4 15.7 24.5 No 0.0
## 116 30 1007.9 1007.2 15.1 22.9 No 0.0
## 117 7 1016.4 1014.3 15.8 24.3 No 0.0
## 118 17 1017.6 1014.4 17.4 27.0 No 0.0
## 119 30 1013.6 1009.1 17.6 26.8 No 0.0
## 120 13 1010.0 1009.9 15.7 15.3 No 10.4
## 121 17 1015.5 1014.5 10.6 16.8 Yes 0.0
## 122 15 1020.8 1019.3 11.7 20.0 No 0.0
## 123 11 1026.3 1023.2 12.2 22.1 No 0.0
## 124 9 1025.4 1020.4 13.8 25.5 No 0.0
## 125 7 1021.1 1018.2 15.6 27.0 No 0.0
## 126 6 1025.5 1022.2 15.7 26.2 No 0.0
## 127 9 1023.9 1019.3 17.4 30.0 No 0.0
## 128 9 1021.6 1017.7 17.5 27.7 No 3.0
## 129 9 1024.7 1020.7 14.0 24.9 Yes 0.0
## 130 11 1024.8 1023.1 17.8 27.0 No 0.0
## 131 9 1024.9 1020.4 17.2 30.1 No 0.0
## 132 7 1022.8 1019.3 20.2 32.7 No 0.2
## 133 28 1021.6 1017.6 17.5 30.7 No 0.0
## 134 7 1020.9 1017.7 16.1 31.7 No 0.0
## 135 13 1022.6 1019.1 17.9 32.7 No 0.0
## 136 4 1022.5 1019.3 21.4 34.1 No 0.0
## 137 6 1024.3 1020.7 18.2 30.5 No 0.0
## 138 13 1024.3 1020.6 17.7 28.8 No 0.0
## 139 19 1022.7 1018.8 16.8 29.2 No 0.0
## 140 15 1022.1 1018.7 19.7 24.5 No 0.0
## 141 26 1013.8 1009.4 17.1 27.6 No 0.0
## 142 17 1017.4 1019.3 13.3 13.9 No 0.0
## 143 17 1023.6 1021.8 14.0 17.9 No 0.0
## 144 7 1023.2 1019.3 15.5 24.2 No 0.6
## 145 19 1018.7 1015.4 17.1 21.1 No 6.4
## 146 20 1010.2 1006.5 16.4 16.6 Yes 19.8
## 147 20 1007.9 1008.4 15.1 17.4 Yes 0.0
## 148 17 1014.8 1012.6 8.4 17.4 No 0.0
## 149 19 1017.4 1015.0 9.2 17.2 No 0.0
## 150 22 1015.1 1011.3 8.8 18.2 No 0.0
## 151 31 1011.2 1009.3 11.2 18.1 No 0.0
## 152 26 1012.7 1013.0 13.1 16.5 No 0.0
## 153 11 1023.9 1021.2 8.7 21.2 No 0.0
## 154 37 1018.0 1010.5 9.5 22.5 No 2.6
## 155 33 1010.3 1012.7 9.1 13.7 Yes 0.0
## 156 7 1021.2 1019.1 5.2 17.6 No 0.0
## 157 7 1025.2 1022.3 8.2 20.5 No 0.0
## 158 11 1028.0 1024.1 12.9 20.8 No 0.0
## 159 11 1027.8 1024.0 14.9 19.5 No 0.0
## 160 9 1028.2 1025.4 13.8 17.8 No 0.0
## 161 6 1025.7 1021.8 14.3 18.6 No 0.0
## 162 6 1023.1 1019.2 14.0 22.2 No 0.0
## 163 7 1021.0 1016.9 12.7 22.4 No 0.0
## 164 11 1019.2 1015.8 11.5 23.7 No 2.0
## 165 15 1018.4 1013.8 10.7 19.1 Yes 5.2
## 166 20 1020.8 1019.6 12.4 17.9 Yes 0.0
## 167 9 1027.2 1023.9 12.3 20.4 No 0.0
## 168 13 1027.9 1024.4 12.6 18.8 No 0.0
## 169 7 1027.2 1023.3 12.0 20.4 No 0.0
## 170 11 1027.3 1024.1 14.0 19.1 No 0.0
## 171 22 1029.5 1027.4 13.6 15.2 No 0.0
## 172 30 1028.2 1024.2 13.5 15.6 No 0.0
## 173 7 1024.8 1021.0 10.6 19.8 No 0.0
## 174 22 1025.8 1023.5 12.5 17.7 No 0.0
## 175 7 1025.5 1022.2 12.6 18.1 No 0.0
## 176 9 1023.7 1019.8 9.2 17.6 No 0.0
## 177 7 1019.9 1014.3 10.1 20.6 No 0.2
## 178 20 1011.9 1006.7 7.9 20.2 No 0.0
## 179 31 1003.2 997.7 14.4 16.6 No 7.2
## 180 22 1006.3 1008.1 7.1 8.8 Yes 0.2
## 181 9 1020.6 1019.6 6.3 13.2 No 0.0
## 182 19 1024.2 1020.5 5.3 13.9 No 0.0
## 183 26 1020.6 1018.5 10.5 12.4 No 0.0
## 184 28 1020.0 1017.3 8.7 15.9 No 0.0
## 185 13 1020.8 1017.4 7.4 16.2 No 0.0
## 186 15 1022.7 1018.5 6.2 15.4 No 0.0
## 187 19 1019.8 1015.8 7.7 18.5 No 0.0
## 188 26 1018.0 1013.8 12.5 15.4 No 0.0
## 189 30 1015.8 1013.5 12.4 16.5 No 0.0
## 190 9 1021.4 1018.9 6.7 16.9 No 0.0
## 191 9 1023.2 1020.3 7.6 20.7 No 0.0
## 192 9 1023.2 1020.0 8.4 20.9 No 0.0
## 193 11 1024.4 1021.5 13.5 17.2 No 0.0
## 194 15 1024.2 1020.3 12.1 18.8 No 0.0
## 195 15 1024.7 1021.4 7.9 18.6 No 0.0
## 196 20 1024.4 1021.0 8.5 17.8 No 0.0
## 197 20 1023.5 1018.7 6.8 17.7 No 1.8
## 198 15 1017.7 1013.7 10.0 15.2 Yes 1.0
## 199 24 1006.3 1005.9 11.3 7.3 No 0.8
## 200 26 1008.4 1008.3 7.9 13.3 No 0.0
## 201 24 1017.8 1014.3 3.5 16.7 No 0.0
## 202 24 1021.9 1018.6 3.8 16.2 No 0.0
## 203 7 1024.5 1022.9 8.0 16.6 No 0.0
## 204 6 1030.4 1026.0 5.9 13.8 No 0.0
## 205 6 1028.5 1024.8 5.3 14.5 No 0.0
## 206 6 1026.7 1023.5 6.5 13.9 No 0.0
## 207 15 1025.5 1021.8 6.2 17.2 No 3.8
## 208 6 1026.6 1023.1 7.0 17.9 Yes 5.2
## 209 13 1025.7 1022.3 8.9 17.7 Yes 0.0
## 210 6 1027.2 1024.7 6.2 16.3 No 0.2
## 211 7 1032.1 1029.6 5.5 17.3 No 0.0
## 212 15 1033.2 1028.7 5.6 17.4 No 0.0
## 213 7 1030.2 1027.4 4.7 18.2 No 0.0
## 214 7 1032.3 1028.9 4.6 13.9 No 0.0
## 215 6 1030.3 1027.1 9.9 15.5 No 0.8
## 216 11 1028.5 1027.2 12.1 13.6 No 3.8
## 217 20 1028.2 1025.7 11.5 13.3 Yes 0.0
## 218 20 1025.9 1023.4 10.3 14.8 No 0.0
## 219 4 1025.2 1022.1 9.6 16.2 No 0.0
## 220 11 1027.6 1027.0 4.9 14.5 No 0.0
## 221 13 1034.3 1031.7 7.9 13.0 No 0.0
## 222 19 1031.4 1027.9 12.1 14.5 No 6.2
## 223 0 1027.8 1024.3 10.3 11.6 Yes 4.8
## 224 17 1022.9 1022.1 12.9 13.7 Yes 0.2
## 225 24 1023.7 1019.7 11.2 14.7 No 0.6
## 226 28 1013.7 1014.1 8.8 11.1 No 0.0
## 227 24 1025.7 1025.6 6.5 11.0 No 0.0
## 228 26 1029.0 1026.3 9.0 13.8 No 0.0
## 229 9 1027.8 1024.8 9.5 16.0 No 0.0
## 230 7 1028.6 1025.5 9.4 14.9 No 0.0
## 231 9 1026.7 1023.5 4.0 15.0 No 0.0
## 232 7 1022.5 1019.7 8.4 14.8 No 4.8
## 233 7 1021.2 1019.2 9.7 11.3 Yes 0.6
## 234 19 1023.0 1021.0 4.2 12.1 No 0.0
## 235 9 1026.4 1025.7 8.8 12.5 No 0.0
## 236 15 1025.1 1022.1 5.5 12.3 No 0.0
## 237 28 1028.2 1024.2 4.3 11.7 No 0.0
## 238 28 1026.3 1021.9 7.8 11.3 No 0.0
## 239 28 1018.7 1020.4 7.0 11.5 No 0.0
## 240 24 1027.8 1025.0 6.7 12.7 No 0.0
## 241 9 1029.1 1026.0 2.1 14.5 No 0.0
## 242 22 1024.6 1020.9 6.5 14.6 No 0.0
## 243 28 1017.2 1010.2 9.7 12.9 No 2.0
## 244 33 1012.1 1012.3 6.9 11.1 Yes 0.2
## 245 30 1013.5 1014.0 10.6 12.3 No 0.0
## 246 20 1024.3 1021.9 3.0 11.1 No 0.0
## 247 13 1030.5 1030.0 5.9 10.2 No 0.0
## 248 2 1032.9 1028.9 4.7 12.6 No 0.0
## 249 22 1030.0 1026.3 3.7 13.6 No 0.8
## 250 13 1024.4 1021.1 6.3 8.6 No 16.8
## 251 15 1021.6 1019.6 5.5 7.4 Yes 0.0
## 252 15 1020.0 1016.8 1.8 8.0 No 0.0
## 253 35 1014.6 1010.5 6.0 6.9 No 1.6
## 254 31 1016.7 1018.2 5.5 7.1 Yes 0.2
## 255 7 1027.1 1022.7 0.8 9.9 No 0.0
## 256 15 1024.4 1021.9 2.8 10.7 No 0.0
## 257 22 1021.8 1019.0 6.7 15.9 No 0.0
## 258 17 1023.0 1020.1 3.9 13.3 No 0.2
## 259 9 1024.1 1020.8 2.7 12.1 No 0.0
## 260 24 1019.7 1013.9 1.3 11.0 No 0.0
## 261 33 1010.8 1009.4 7.7 8.2 No 1.2
## 262 22 1016.7 1014.9 6.0 10.7 Yes 0.2
## 263 6 1014.4 1009.0 2.4 8.7 No 19.2
## 264 31 1006.9 1010.3 7.6 11.2 Yes 0.0
## 265 28 1025.7 1025.8 3.4 11.0 No 0.0
## 266 11 1033.5 1031.1 3.6 10.1 No 0.0
## 267 13 1032.2 1027.4 3.7 10.8 No 0.0
## 268 13 1025.7 1020.9 1.4 12.3 No 0.2
## 269 19 1020.0 1015.3 1.2 10.9 No 0.0
## 270 13 1013.8 1010.0 1.0 7.8 No 1.4
## 271 37 1014.1 1014.9 5.6 9.6 Yes 0.0
## 272 22 1020.9 1016.8 6.5 11.2 No 0.0
## 273 15 1018.3 1014.6 2.7 11.5 No 0.0
## 274 26 1017.3 1012.9 3.0 12.8 No 1.0
## 275 28 1005.1 1001.3 9.6 8.6 No 6.6
## 276 31 1013.9 1014.9 6.9 10.5 Yes 0.0
## 277 24 1021.2 1018.1 7.8 11.6 No 0.0
## 278 19 1020.9 1018.3 2.6 9.1 No 0.0
## 279 26 1020.8 1019.2 5.5 7.2 No 4.0
## 280 22 1018.2 1017.6 8.9 13.6 Yes 0.0
## 281 26 1018.4 1015.9 3.8 5.7 No 1.2
## 282 30 1019.8 1019.1 7.6 11.3 Yes 0.0
## 283 24 1022.4 1019.0 5.6 8.1 No 0.4
## 284 24 1014.8 1012.6 3.3 5.1 No 0.4
## 285 30 1017.4 1016.6 4.7 8.3 No 0.0
## 286 24 1021.3 1020.1 7.0 8.6 No 0.0
## 287 30 1024.2 1022.4 6.5 10.4 No 0.0
## 288 39 1022.2 1018.2 6.2 9.5 No 0.0
## 289 33 1014.7 1012.4 9.2 12.0 No 0.0
## 290 28 1012.7 1011.8 8.7 13.5 No 0.0
## 291 17 1023.3 1022.0 4.5 10.8 No 0.0
## 292 30 1025.2 1021.8 1.4 11.2 No 0.0
## 293 20 1029.6 1025.6 0.1 12.2 No 0.0
## 294 24 1027.3 1024.4 7.9 12.4 No 0.0
## 295 30 1021.4 1017.8 8.6 13.2 No 0.0
## 296 26 1018.5 1016.8 6.9 10.7 No 0.0
## 297 17 1025.9 1025.5 6.7 11.1 No 0.0
## 298 11 1031.0 1028.0 5.2 14.0 No 0.0
## 299 19 1030.2 1024.4 5.3 12.8 No 0.0
## 300 26 1023.9 1020.3 4.8 15.8 No 0.0
## 301 13 1027.7 1025.5 7.9 14.4 No 0.0
## 302 15 1029.9 1025.9 7.2 12.3 No 0.0
## 303 20 1027.6 1022.9 7.3 14.6 No 0.0
## 304 6 1023.7 1017.5 6.2 15.4 No 4.0
## 305 15 1011.2 1010.4 13.5 12.6 Yes 7.4
## 306 28 1023.2 1021.7 8.8 14.3 Yes 0.0
## 307 13 1027.0 1024.8 9.0 14.9 No 0.0
## 308 20 1033.6 1033.2 9.3 11.1 No 0.2
## 309 17 1035.7 1031.9 8.3 10.2 No 0.0
## 310 13 1027.3 1023.5 8.7 10.8 No 0.0
## 311 24 1019.7 1016.2 10.0 15.7 No 0.0
## 312 22 1018.1 1013.9 6.4 15.5 No 1.0
## 313 11 1020.6 1018.2 7.2 15.3 No 0.0
## 314 22 1025.8 1020.9 5.5 13.4 No 0.0
## 315 20 1022.8 1017.9 6.3 14.9 No 0.0
## 316 20 1018.8 1013.9 6.0 16.3 No 0.0
## 317 26 1014.6 1010.9 11.9 21.5 No 0.0
## 318 26 1015.3 1011.4 17.5 25.1 No 9.8
## 319 30 1007.3 1006.0 16.7 18.2 Yes 1.6
## 320 52 1009.1 1001.5 15.6 18.5 Yes 3.4
## 321 31 1017.0 1017.6 7.1 12.2 Yes 0.0
## 322 7 1026.7 1022.1 7.4 13.7 No 0.0
## 323 28 1021.0 1015.6 7.0 17.8 No 0.0
## 324 28 1016.4 1011.7 16.4 22.4 No 0.0
## 325 41 1012.5 1010.9 18.3 21.3 No 0.0
## 326 33 1018.7 1015.1 14.5 18.3 No 0.0
## 327 20 1012.1 1006.5 15.9 21.0 No 17.4
## 328 22 1016.7 1017.8 8.0 14.3 Yes 0.0
## 329 6 1030.5 1027.7 10.7 16.5 No 0.0
## 330 13 1032.2 1026.9 11.0 18.1 No 0.0
## 331 26 1025.4 1020.6 15.4 20.0 No 0.0
## 332 24 1022.8 1016.4 15.9 24.7 No 0.0
## 333 30 1010.5 1009.9 20.4 23.0 No 0.0
## 334 22 1015.2 1013.9 14.9 16.0 No 0.0
## 335 28 1019.8 1017.0 9.8 16.3 No 0.0
## 336 30 1020.8 1015.4 11.3 19.5 No 0.0
## 337 28 1017.7 1014.1 19.0 26.7 No 0.0
## 338 41 1016.3 1011.8 22.5 28.4 No 7.6
## 339 19 1015.5 1013.2 14.5 19.3 Yes 3.0
## 340 19 1018.1 1013.6 11.7 19.8 Yes 0.0
## 341 33 1009.5 1005.3 12.8 16.2 No 8.2
## 342 28 1016.8 1013.3 6.9 14.6 Yes 0.0
## 343 26 1019.1 1017.5 7.2 16.6 No 0.0
## 344 9 1026.2 1024.2 8.1 18.8 No 0.0
## 345 19 1028.8 1024.9 10.0 21.4 No 0.0
## 346 17 1027.8 1023.8 13.6 20.6 No 0.0
## 347 11 1025.8 1021.5 12.6 22.3 No 0.0
## 348 33 1020.9 1016.0 16.3 23.2 No 13.2
## 349 24 1019.2 1016.7 14.5 19.4 Yes 0.6
## 350 7 1022.3 1019.7 11.6 18.4 No 0.0
## 351 9 1025.7 1022.3 9.6 19.2 No 0.0
## 352 26 1024.5 1020.7 11.6 21.9 No 0.0
## 353 20 1025.7 1022.2 12.7 23.7 No 0.0
## 354 26 1024.1 1019.8 16.8 27.4 No 0.2
## 355 31 1021.4 1017.5 16.4 26.3 No 0.0
## 356 11 1022.3 1018.6 11.4 18.5 No 0.8
## 357 37 1023.4 1023.1 8.3 14.3 No 0.0
## 358 15 1026.6 1022.8 9.1 16.3 No 0.0
## 359 17 1023.2 1018.4 9.4 19.1 No 0.0
## 360 19 1018.8 1014.6 12.0 24.8 No 0.0
## 361 19 1017.6 1014.2 16.3 25.9 No 0.0
## 362 50 1016.1 1010.8 20.4 30.0 No 0.0
## 363 19 1020.0 1016.9 17.2 28.2 No 0.0
## 364 9 1024.0 1022.8 14.5 18.3 No 0.0
## 365 28 1021.0 1016.2 15.8 25.9 No 0.0
## 366 35 1009.6 1009.2 23.8 28.6 No 0.0
## RainTomorrow
## 1 Yes
## 2 Yes
## 3 Yes
## 4 Yes
## 5 No
## 6 No
## 7 No
## 8 No
## 9 Yes
## 10 No
## 11 No
## 12 No
## 13 No
## 14 No
## 15 No
## 16 No
## 17 Yes
## 18 No
## 19 No
## 20 No
## 21 No
## 22 Yes
## 23 No
## 24 No
## 25 No
## 26 No
## 27 No
## 28 No
## 29 No
## 30 Yes
## 31 Yes
## 32 No
## 33 Yes
## 34 No
## 35 No
## 36 No
## 37 Yes
## 38 No
## 39 No
## 40 No
## 41 No
## 42 No
## 43 No
## 44 No
## 45 Yes
## 46 Yes
## 47 No
## 48 No
## 49 Yes
## 50 Yes
## 51 Yes
## 52 Yes
## 53 No
## 54 Yes
## 55 No
## 56 No
## 57 Yes
## 58 No
## 59 No
## 60 No
## 61 No
## 62 No
## 63 No
## 64 No
## 65 No
## 66 No
## 67 No
## 68 No
## 69 No
## 70 No
## 71 No
## 72 No
## 73 Yes
## 74 No
## 75 No
## 76 No
## 77 Yes
## 78 No
## 79 Yes
## 80 Yes
## 81 No
## 82 No
## 83 No
## 84 No
## 85 No
## 86 No
## 87 No
## 88 No
## 89 No
## 90 No
## 91 Yes
## 92 Yes
## 93 No
## 94 No
## 95 Yes
## 96 Yes
## 97 No
## 98 No
## 99 Yes
## 100 No
## 101 No
## 102 No
## 103 Yes
## 104 Yes
## 105 No
## 106 No
## 107 No
## 108 No
## 109 No
## 110 No
## 111 No
## 112 Yes
## 113 Yes
## 114 No
## 115 No
## 116 No
## 117 No
## 118 No
## 119 No
## 120 Yes
## 121 No
## 122 No
## 123 No
## 124 No
## 125 No
## 126 No
## 127 No
## 128 Yes
## 129 No
## 130 No
## 131 No
## 132 No
## 133 No
## 134 No
## 135 No
## 136 No
## 137 No
## 138 No
## 139 No
## 140 No
## 141 No
## 142 No
## 143 No
## 144 No
## 145 Yes
## 146 Yes
## 147 No
## 148 No
## 149 No
## 150 No
## 151 No
## 152 No
## 153 No
## 154 Yes
## 155 No
## 156 No
## 157 No
## 158 No
## 159 No
## 160 No
## 161 No
## 162 No
## 163 No
## 164 Yes
## 165 Yes
## 166 No
## 167 No
## 168 No
## 169 No
## 170 No
## 171 No
## 172 No
## 173 No
## 174 No
## 175 No
## 176 No
## 177 No
## 178 No
## 179 Yes
## 180 No
## 181 No
## 182 No
## 183 No
## 184 No
## 185 No
## 186 No
## 187 No
## 188 No
## 189 No
## 190 No
## 191 No
## 192 No
## 193 No
## 194 No
## 195 No
## 196 No
## 197 Yes
## 198 No
## 199 No
## 200 No
## 201 No
## 202 No
## 203 No
## 204 No
## 205 No
## 206 No
## 207 Yes
## 208 Yes
## 209 No
## 210 No
## 211 No
## 212 No
## 213 No
## 214 No
## 215 No
## 216 Yes
## 217 No
## 218 No
## 219 No
## 220 No
## 221 No
## 222 Yes
## 223 Yes
## 224 No
## 225 No
## 226 No
## 227 No
## 228 No
## 229 No
## 230 No
## 231 No
## 232 Yes
## 233 No
## 234 No
## 235 No
## 236 No
## 237 No
## 238 No
## 239 No
## 240 No
## 241 No
## 242 No
## 243 Yes
## 244 No
## 245 No
## 246 No
## 247 No
## 248 No
## 249 No
## 250 Yes
## 251 No
## 252 No
## 253 Yes
## 254 No
## 255 No
## 256 No
## 257 No
## 258 No
## 259 No
## 260 No
## 261 Yes
## 262 No
## 263 Yes
## 264 No
## 265 No
## 266 No
## 267 No
## 268 No
## 269 No
## 270 Yes
## 271 No
## 272 No
## 273 No
## 274 No
## 275 Yes
## 276 No
## 277 No
## 278 No
## 279 Yes
## 280 No
## 281 Yes
## 282 No
## 283 No
## 284 No
## 285 No
## 286 No
## 287 No
## 288 No
## 289 No
## 290 No
## 291 No
## 292 No
## 293 No
## 294 No
## 295 No
## 296 No
## 297 No
## 298 No
## 299 No
## 300 No
## 301 No
## 302 No
## 303 No
## 304 Yes
## 305 Yes
## 306 No
## 307 No
## 308 No
## 309 No
## 310 No
## 311 No
## 312 No
## 313 No
## 314 No
## 315 No
## 316 No
## 317 No
## 318 Yes
## 319 Yes
## 320 Yes
## 321 No
## 322 No
## 323 No
## 324 No
## 325 No
## 326 No
## 327 Yes
## 328 No
## 329 No
## 330 No
## 331 No
## 332 No
## 333 No
## 334 No
## 335 No
## 336 No
## 337 No
## 338 Yes
## 339 Yes
## 340 No
## 341 Yes
## 342 No
## 343 No
## 344 No
## 345 No
## 346 No
## 347 No
## 348 Yes
## 349 No
## 350 No
## 351 No
## 352 No
## 353 No
## 354 No
## 355 No
## 356 No
## 357 No
## 358 No
## 359 No
## 360 No
## 361 No
## 362 No
## 363 No
## 364 No
## 365 No
## 366 No
setnum <- colnames(ds.complete)[16:19]
ds.complete[,setnum] <- lapply(ds.complete[,setnum],
function(x) as.numeric(x))
ds.complete$Humidity3pm <- as.numeric(ds.complete$Humidity3pm)
ds.complete$Humidity9am <- as.numeric(ds.complete$Humidity9am)
table(is.na(ds.complete))
##
## FALSE
## 7872
begTime <- Sys.time()
set.seed(1426)
model <- randomForest(formula=form,data=ds.complete[train.complete,vars],importance=TRUE)
runTime <- Sys.time()-begTime
runTime
## Time difference of 0.309031 secs
#Time difference of 0.3833725 secs
begTime <- Sys.time()
set.seed(1426)
model <- randomForest(formula=form, data=ds.complete[train, vars],
ntree=500, replace = FALSE, sampsize = .632*.7*nrow(ds),
na.action=na.omit,importance=TRUE)
runTime <- Sys.time()-begTime
runTime
## Time difference of 0.164017 secs
#Time difference of 0.2392061 secs
plot(density(ds.complete$Sunshine))
print(model)
##
## Call:
## randomForest(formula = form, data = ds.complete[train, vars], ntree = 500, replace = FALSE, sampsize = 0.632 * 0.7 * nrow(ds), importance = TRUE, na.action = na.omit)
## Type of random forest: classification
## Number of trees: 500
## No. of variables tried at each split: 4
##
## OOB estimate of error rate: 13.1%
## Confusion matrix:
## No Yes class.error
## No 184 6 0.03157895
## Yes 24 15 0.61538462
summary(model)
## Length Class Mode
## call 8 -none- call
## type 1 -none- character
## predicted 229 factor numeric
## err.rate 1500 -none- numeric
## confusion 6 -none- numeric
## votes 458 matrix numeric
## oob.times 229 -none- numeric
## classes 2 -none- character
## importance 80 -none- numeric
## importanceSD 60 -none- numeric
## localImportance 0 -none- NULL
## proximity 0 -none- NULL
## ntree 1 -none- numeric
## mtry 1 -none- numeric
## forest 14 -none- list
## y 229 factor numeric
## test 0 -none- NULL
## inbag 0 -none- NULL
## terms 3 terms call
## na.action 27 omit numeric
str(model)
## List of 20
## $ call : language randomForest(formula = form, data = ds.complete[train, vars], ntree = 500, replace = FALSE, sampsize = 0.632 * 0.7 * nrow(ds), importance = TRUE, ...
## $ type : chr "classification"
## $ predicted : Factor w/ 2 levels "No","Yes": 1 2 1 1 1 1 1 1 1 1 ...
## ..- attr(*, "names")= chr [1:229] "1" "305" "299" "161" ...
## ..- attr(*, "na.action")=Class 'omit' Named int [1:27] 7 11 40 46 52 57 59 62 80 98 ...
## .. .. ..- attr(*, "names")= chr [1:27] "NA" "NA.1" "NA.2" "NA.3" ...
## $ err.rate : num [1:500, 1:3] 0.25 0.235 0.215 0.224 0.176 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : NULL
## .. ..$ : chr [1:3] "OOB" "No" "Yes"
## $ confusion : num [1:2, 1:3] 184 24 6 15 0.0316 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:2] "No" "Yes"
## .. ..$ : chr [1:3] "No" "Yes" "class.error"
## $ votes : matrix [1:229, 1:2] 0.761 0.358 0.954 0.952 0.718 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:229] "1" "305" "299" "161" ...
## .. ..$ : chr [1:2] "No" "Yes"
## ..- attr(*, "class")= chr [1:2] "matrix" "votes"
## $ oob.times : num [1:229] 134 151 152 147 156 140 160 145 143 148 ...
## $ classes : chr [1:2] "No" "Yes"
## $ importance : num [1:20, 1:4] 0.007429 0.01583 0.000221 -0.000354 0.021888 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:20] "MinTemp" "MaxTemp" "Rainfall" "Evaporation" ...
## .. ..$ : chr [1:4] "No" "Yes" "MeanDecreaseAccuracy" "MeanDecreaseGini"
## $ importanceSD : num [1:20, 1:3] 0.001299 0.001632 0.000471 0.001011 0.001654 ...
## ..- attr(*, "dimnames")=List of 2
## .. ..$ : chr [1:20] "MinTemp" "MaxTemp" "Rainfall" "Evaporation" ...
## .. ..$ : chr [1:3] "No" "Yes" "MeanDecreaseAccuracy"
## $ localImportance: NULL
## $ proximity : NULL
## $ ntree : num 500
## $ mtry : num 4
## $ forest :List of 14
## ..$ ndbigtree : int [1:500] 55 47 51 49 57 45 47 45 37 41 ...
## ..$ nodestatus: int [1:69, 1:500] 1 1 1 1 1 1 1 1 1 -1 ...
## ..$ bestvar : int [1:69, 1:500] 12 15 11 16 6 3 7 10 17 0 ...
## ..$ treemap : int [1:69, 1:2, 1:500] 2 4 6 8 10 12 14 16 18 0 ...
## ..$ nodepred : int [1:69, 1:500] 0 0 0 0 0 0 0 0 0 1 ...
## ..$ xbestsplit: num [1:69, 1:500] 87.5 1016 14 1.5 14.5 ...
## ..$ pid : num [1:2] 1 1
## ..$ cutoff : num [1:2] 0.5 0.5
## ..$ ncat : Named int [1:20] 1 1 1 1 1 1 1 1 1 1 ...
## .. ..- attr(*, "names")= chr [1:20] "MinTemp" "MaxTemp" "Rainfall" "Evaporation" ...
## ..$ maxcat : int 2
## ..$ nrnodes : int 69
## ..$ ntree : num 500
## ..$ nclass : int 2
## ..$ xlevels :List of 20
## .. ..$ MinTemp : num 0
## .. ..$ MaxTemp : num 0
## .. ..$ Rainfall : num 0
## .. ..$ Evaporation : num 0
## .. ..$ Sunshine : num 0
## .. ..$ WindGustDir : num 0
## .. ..$ WindGustSpeed: num 0
## .. ..$ WindDir9am : num 0
## .. ..$ WindDir3pm : num 0
## .. ..$ WindSpeed9am : num 0
## .. ..$ WindSpeed3pm : num 0
## .. ..$ Humidity9am : num 0
## .. ..$ Humidity3pm : num 0
## .. ..$ Pressure9am : num 0
## .. ..$ Pressure3pm : num 0
## .. ..$ Cloud9am : num 0
## .. ..$ Cloud3pm : num 0
## .. ..$ Temp9am : num 0
## .. ..$ Temp3pm : num 0
## .. ..$ RainToday : chr [1:2] "No" "Yes"
## $ y : Factor w/ 2 levels "No","Yes": 2 2 1 1 1 1 2 1 1 1 ...
## ..- attr(*, "names")= chr [1:229] "1" "305" "299" "161" ...
## ..- attr(*, "na.action")=Class 'omit' Named int [1:27] 7 11 40 46 52 57 59 62 80 98 ...
## .. .. ..- attr(*, "names")= chr [1:27] "NA" "NA.1" "NA.2" "NA.3" ...
## $ test : NULL
## $ inbag : NULL
## $ terms :Classes 'terms', 'formula' language RainTomorrow ~ MinTemp + MaxTemp + Rainfall + Evaporation + Sunshine + WindGustDir + WindGustSpeed + WindDir9am + WindDir3pm + WindSpeed9am + ...
## .. ..- attr(*, "variables")= language list(RainTomorrow, MinTemp, MaxTemp, Rainfall, Evaporation, Sunshine, WindGustDir, WindGustSpeed, WindDir9am, WindDir3pm, WindSpeed9am, ...
## .. ..- attr(*, "factors")= int [1:21, 1:20] 0 1 0 0 0 0 0 0 0 0 ...
## .. .. ..- attr(*, "dimnames")=List of 2
## .. .. .. ..$ : chr [1:21] "RainTomorrow" "MinTemp" "MaxTemp" "Rainfall" ...
## .. .. .. ..$ : chr [1:20] "MinTemp" "MaxTemp" "Rainfall" "Evaporation" ...
## .. ..- attr(*, "term.labels")= chr [1:20] "MinTemp" "MaxTemp" "Rainfall" "Evaporation" ...
## .. ..- attr(*, "order")= int [1:20] 1 1 1 1 1 1 1 1 1 1 ...
## .. ..- attr(*, "intercept")= num 0
## .. ..- attr(*, "response")= int 1
## .. ..- attr(*, ".Environment")=<environment: R_GlobalEnv>
## .. ..- attr(*, "predvars")= language list(RainTomorrow, MinTemp, MaxTemp, Rainfall, Evaporation, Sunshine, WindGustDir, WindGustSpeed, WindDir9am, WindDir3pm, WindSpeed9am, ...
## .. ..- attr(*, "dataClasses")= Named chr [1:21] "factor" "numeric" "numeric" "numeric" ...
## .. .. ..- attr(*, "names")= chr [1:21] "RainTomorrow" "MinTemp" "MaxTemp" "Rainfall" ...
## $ na.action :Class 'omit' Named int [1:27] 7 11 40 46 52 57 59 62 80 98 ...
## .. ..- attr(*, "names")= chr [1:27] "NA" "NA.1" "NA.2" "NA.3" ...
## - attr(*, "class")= chr [1:2] "randomForest.formula" "randomForest"
#importance(model)
#pred <- predict(model, newdata=ds.complete[test.complete, vars])
library(doParallel)
ntree = 500; numCore = 4
rep <- 125 # tree / numCore
registerDoParallel(cores=numCore)
begTime <- Sys.time()
set.seed(1426)
#rf <- foreach(ntree=rep(rep, numCore), .combine=combine,
# .packages='randomForest') %dopar%
#randomForest(formula=form, data=ds.complete[train.complete, vars],
# ntree=ntree,
# mtry=6,
# importance=TRUE,
# na.action=na.roughfix, #can also use na.action = na.omit
# replace=FALSE)
runTime <- Sys.time()-begTime
runTime
## Time difference of 0.001999855 secs
#Time difference of 0.1990662 secs
#pred <- predict(rf, newdata=ds.complete[test.complete, vars])
#confusionMatrix(pred, ds.complete[test.complete, target])
#id <- which(!(ds$var.name %in% levels(ds$var.name)))
#ds$var.name[id] <- NA
model <- ctree(formula=form, data=ds[train, vars])
#ctree: plot(model)
print(model)
##
## Model formula:
## RainTomorrow ~ MinTemp + MaxTemp + Rainfall + Evaporation + Sunshine +
## WindGustDir + WindGustSpeed + WindDir9am + WindDir3pm + WindSpeed9am +
## WindSpeed3pm + Humidity9am + Humidity3pm + Pressure9am +
## Pressure3pm + Cloud9am + Cloud3pm + Temp9am + Temp3pm + RainToday
##
## Fitted party:
## [1] root
## | [2] Sunshine <= 6.4
## | | [3] Pressure3pm <= 1015.9: Yes (n = 29, err = 24.1%)
## | | [4] Pressure3pm > 1015.9: No (n = 36, err = 8.3%)
## | [5] Sunshine > 6.4
## | | [6] Cloud3pm <= 6
## | | | [7] Pressure3pm <= 1009.8: No (n = 18, err = 22.2%)
## | | | [8] Pressure3pm > 1009.8: No (n = 147, err = 1.4%)
## | | [9] Cloud3pm > 6: No (n = 26, err = 26.9%)
##
## Number of inner nodes: 4
## Number of terminal nodes: 5
library(caret)
#pred <- predict(model, newdata=ds[test, vars])
confusionMatrix(pred, ds[test, target])
## $positive
## [1] "No"
##
## $table
## Reference
## Prediction No Yes
## No 72 12
## Yes 10 16
##
## $overall
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.8000000 0.4603033 0.7130049 0.8702115 0.7454545
## AccuracyPValue McnemarPValue
## 0.1124876 0.8311704
##
## $byClass
## Sensitivity Specificity Pos Pred Value
## 0.8780488 0.5714286 0.8571429
## Neg Pred Value Precision Recall
## 0.6153846 0.8571429 0.8780488
## F1 Prevalence Detection Rate
## 0.8674699 0.7454545 0.6545455
## Detection Prevalence Balanced Accuracy
## 0.7636364 0.7247387
##
## $mode
## [1] "sens_spec"
##
## $dots
## list()
##
## attr(,"class")
## [1] "confusionMatrix"
mc <- table(pred, ds[test, target])
err <- 1.0 - (mc[1,1] + mc[2,2]) / sum(mc) #resubstitution error rate
library(ROCR)
ctree
## function (formula, data, weights, subset, na.action = na.pass,
## control = ctree_control(...), ytrafo = NULL, scores = NULL,
## ...)
## {
## if (missing(data))
## data <- environment(formula)
## mf <- match.call(expand.dots = FALSE)
## m <- match(c("formula", "data", "subset", "weights", "na.action"),
## names(mf), 0)
## mf <- mf[c(1, m)]
## formula <- Formula::Formula(formula)
## mf$formula <- formula
## mf$drop.unused.levels <- FALSE
## mf$na.action <- na.action
## mf[[1]] <- quote(stats::model.frame)
## mf <- eval(mf, parent.frame())
## response <- names(Formula::model.part(formula, mf, lhs = 1))
## weights <- model.weights(mf)
## dat <- mf[, colnames(mf) != "(weights)"]
## if (!is.null(scores)) {
## for (n in names(scores)) {
## sc <- scores[[n]]
## if (is.ordered(dat[[n]]) && nlevels(dat[[n]]) ==
## length(sc)) {
## attr(dat[[n]], "scores") <- as.numeric(sc)
## }
## else {
## warning("scores for variable ", sQuote(n), " ignored")
## }
## }
## }
## if (is.null(weights))
## weights <- rep(1, nrow(mf))
## storage.mode(weights) <- "integer"
## nvar <- sum(!(colnames(dat) %in% response))
## control$cfun <- function(...) {
## if (control$teststat == "quad")
## p <- .pX2(..., pval = (control$testtype != "Teststatistic"))
## if (control$teststat == "max")
## p <- .pmaxT(..., pval = (control$testtype != "Teststatistic"))
## names(p) <- c("statistic", "p.value")
## if (control$testtype == "Bonferroni")
## p["p.value"] <- p["p.value"] * min(nvar, control$mtry)
## crit <- p["statistic"]
## if (control$testtype != "Teststatistic")
## crit <- p["p.value"]
## c(crit, p)
## }
## tree <- .ctree_fit(dat, response, weights = weights, ctrl = control,
## ytrafo = ytrafo)
## fitted <- data.frame(`(fitted)` = fitted_node(tree, dat),
## `(weights)` = weights, check.names = FALSE)
## fitted[[3]] <- dat[, response, drop = length(response) ==
## 1]
## names(fitted)[3] <- "(response)"
## ret <- party(tree, data = dat, fitted = fitted, info = list(call = match.call(),
## control = control))
## class(ret) <- c("constparty", class(ret))
## ret$terms <- terms(mf)
## return(ret)
## }
## <environment: namespace:partykit>
#pred.prob <- predict(model, newdata=ds[test, vars], type="prob")
summary(pred)
## No Yes
## 84 26
summary(pred.prob)
## No Yes
## Min. :0.2778 Min. :0.06250
## 1st Qu.:0.9286 1st Qu.:0.06250
## Median :0.9375 Median :0.06250
## Mean :0.7860 Mean :0.21402
## 3rd Qu.:0.9375 3rd Qu.:0.07143
## Max. :0.9375 Max. :0.72222
err
## [1] 0.2
pred <- do.call(rbind, as.list(pred))
summary(pred)
## 3
## Min. :1.000
## 1st Qu.:1.000
## Median :1.000
## Mean :1.236
## 3rd Qu.:1.000
## Max. :2.000
roc <- prediction(pred[,1], ds[test, target])
plot(performance(roc, measure="tpr", x.measure="fpr"), colorize=TRUE)
plot(performance(roc, measure="lift", x.measure="rpp"), colorize=TRUE)
plot(performance(roc, measure="sens", x.measure="spec"), colorize=TRUE)
plot(performance(roc, measure="prec", x.measure="rec"), colorize=TRUE)
model <- train(ds[, vars], ds[,target], method='rpart', tuneLength=10)
n <- nrow(ds)
K <- 10
taille <- n%/%K
set.seed(5)
alea <- runif(n)
rang <- rank(alea)
bloc <- (rang-1)%/%taille +1
bloc <- as.factor(bloc)
print(summary(bloc))
## 1 2 3 4 5 6 7 8 9 10 11
## 36 36 36 36 36 36 36 36 36 36 6
all.err <- numeric(0)
#for(k in 1:K){
# model <- rpart(formula=form, data = ds[train,vars], method="class")
#pred <- predict(model, newdata=ds[test,vars], type="class")
#mc <- table(ds[test,target],pred)
#err <- 1.0 - (mc[1,1] +mc[2,2]) / sum(mc)
#all.err <- rbind(all.err,err)
#}
print(all.err)
## numeric(0)
(err.cv <- mean(all.err))
## [1] NaN
model <- cforest(formula=form, data=ds.complete[train.complete, vars])
print(cforest)
## function (formula, data, weights, subset, na.action = na.pass,
## control = ctree_control(teststat = "quad", testtype = "Univ",
## mincriterion = 0, ...), ytrafo = NULL, scores = NULL,
## ntree = 500L, perturb = list(replace = FALSE, fraction = 0.632),
## mtry = ceiling(sqrt(nvar)), applyfun = NULL, cores = NULL,
## trace = FALSE, ...)
## {
## if (missing(data))
## data <- environment(formula)
## mf <- match.call(expand.dots = FALSE)
## m <- match(c("formula", "data", "subset", "weights", "na.action"),
## names(mf), 0)
## mf <- mf[c(1, m)]
## formula <- Formula::Formula(formula)
## mf$formula <- formula
## mf$drop.unused.levels <- FALSE
## mf$na.action <- na.action
## mf[[1]] <- quote(stats::model.frame)
## mf <- eval(mf, parent.frame())
## response <- names(Formula::model.part(formula, mf, lhs = 1))
## weights <- model.weights(mf)
## dat <- mf[, colnames(mf) != "(weights)"]
## if (!is.null(scores)) {
## for (n in names(scores)) {
## sc <- scores[[n]]
## if (is.ordered(dat[[n]]) && nlevels(dat[[n]]) ==
## length(sc)) {
## attr(dat[[n]], "scores") <- as.numeric(sc)
## }
## else {
## warning("scores for variable ", sQuote(n), " ignored")
## }
## }
## }
## if (is.null(weights))
## weights <- rep(1, nrow(mf))
## nvar <- sum(!(colnames(dat) %in% response))
## control$mtry <- mtry
## control$cfun <- function(...) {
## if (control$teststat == "quad")
## p <- .pX2(..., pval = (control$testtype != "Teststatistic"))
## if (control$teststat == "max")
## p <- .pmaxT(..., pval = (control$testtype != "Teststatistic"))
## names(p) <- c("statistic", "p.value")
## if (control$testtype == "Bonferroni")
## p["p.value"] <- p["p.value"] * min(nvar, control$mtry)
## crit <- p["statistic"]
## if (control$testtype != "Teststatistic")
## crit <- p["p.value"]
## c(crit, p)
## }
## perturb <- do.call(".perturb", perturb)
## if (!is.matrix(weights)) {
## probw <- weights/sum(weights)
## rw <- replicate(ntree, perturb(probw), simplify = FALSE)
## }
## else {
## stopifnot(nrow(weights) == nrow(dat) && ncol(weights) ==
## ntree)
## rw <- as.data.frame(weights)
## class(rw) <- "list"
## }
## if (is.null(applyfun)) {
## applyfun <- if (is.null(cores)) {
## lapply
## }
## else {
## function(X, FUN, ...) parallel::mclapply(X, FUN,
## ..., mc.cores = cores)
## }
## }
## control$applyfun <- lapply
## if (trace)
## pb <- txtProgressBar(style = 3)
## forest <- applyfun(1:ntree, function(b) {
## if (trace)
## setTxtProgressBar(pb, b/ntree)
## .ctree_fit(dat, response, weights = rw[[b]], ctrl = control,
## ytrafo = ytrafo)
## })
## if (trace)
## close(pb)
## fitted <- data.frame(idx = 1:nrow(dat))
## fitted[[2]] <- dat[, response, drop = length(response) ==
## 1]
## names(fitted)[2] <- "(response)"
## fitted <- fitted[2]
## ret <- constparties(nodes = forest, data = dat, weights = rw,
## fitted = fitted, terms = terms(mf), info = list(call = match.call(),
## control = control))
## class(ret) <- c("cforest", class(ret))
## return(ret)
## }
## <environment: namespace:partykit>
plot(density(ds$Cloud9am))
plot(density(ds$Cloud3pm))
plot(density(ds$Temp9am))
plot(density(ds$Temp3pm))
