FUNCTIONS TRAIN TEST
Dimitrios Zacharatos
Description
This shows the output of useful functions for training and testing
from workingfunctions.
Installation instructions for workingfunctions can be found here
Plot Receiver Operating Characteristic ROC Curve
# Observed vector binary
observed<-round(abs(rnorm(100,m=0,sd=.5)))
# Predicted vector continuous
predicted<-abs(rnorm(100,m=0,sd=.5))
plot_roc(observed=observed,predicted=predicted)
# An example with a good prediction
df1<-data.frame(matrix(.999,ncol=2,nrow=2))
correlation_martix<-as.matrix(df1)
diag(correlation_martix)<-1
df1<-generate_correlation_matrix(correlation_martix,nrows=1000)
df1$X1<-ifelse(abs(df1$X1)<1,0,1)
df1$X2<-abs(df1$X2)
df1$X2<-(df1$X2-min(df1$X2))/(max(df1$X2)-min(df1$X2))
plot_roc(observed=round(abs(df1$X1),0),predicted=abs(df1$X2))
Plot Confusion Matrix
plot_confusion(observed=c(1,2,3,1,2,3),predicted=c(1,2,3,1,2,3))
observed<-c(rep("male",10),rep("female",10),"male","male")
predicted<-c(rep("male",10),rep("female",10),"female","female")
plot_confusion(observed=observed,predicted=predicted)
Plot Separability
This function generates a separability plot using ggplot2. It shows the density distribution of predicted probabilities for different observed categories. The plot helps to visualize how well the predicted probabilities separate the different observed categories.
df1<-data.frame(matrix(.999,ncol=2,nrow=2))
correlation_martix<-as.matrix(df1)
diag(correlation_martix)<-1
df1<-generate_correlation_matrix(correlation_martix,nrows=1000)
df1$X1<-ifelse(abs(df1$X1)<1,0,1)
df1$X2<-abs(df1$X2)
df1$X2<-(df1$X2-min(df1$X2))/(max(df1$X2)-min(df1$X2))
plot_separability(observed=round(abs(df1$X1),0),predicted=abs(df1$X2))
Plot Confusion Matrix Performance
This function evaluates the performance of a confusion matrix at different cut-off points. It iterates through a range of cut-off points, calculates the confusion matrix,and evaluates the proportion of correct classifications for each cut-off.
df<-data.frame(matrix(.999,ncol=2,nrow=2))
correlation_martix<-as.matrix(df)
diag(correlation_martix)<-1
df<-generate_correlation_matrix(correlation_martix,nrows=1000)
df$X1<-ifelse(abs(df$X1)<1,0,1)
df$X2<-abs(df$X2)
df$X2<-(df$X2-min(df$X2))/(max(df$X2)-min(df$X2))
result_confusion_performance(observed=round(abs(df$X1),0),
predicted=abs(df$X2),
step=.01)## $plot_performance
## ## $cut_performance ## cut_point Overall Collumn_Observed.1 Collumn_Observed.2 Row_Predicted.1 Row_Predicted.2 Mean_proportion ## 1 0.00 0.34 1.00 0.34 0.00 1.00 0.5850 ## 2 0.01 0.37 1.00 0.35 0.05 1.00 0.6000 ## 3 0.02 0.39 1.00 0.36 0.07 1.00 0.6075 ## 4 0.03 0.41 1.00 0.36 0.10 1.00 0.6150 ## 5 0.04 0.42 1.00 0.37 0.13 1.00 0.6250 ## 6 0.05 0.45 1.00 0.38 0.16 1.00 0.6350 ## 7 0.06 0.47 1.00 0.39 0.19 1.00 0.6450 ## 8 0.07 0.49 1.00 0.40 0.23 1.00 0.6575 ## 9 0.08 0.52 1.00 0.41 0.27 1.00 0.6700 ## 10 0.09 0.54 1.00 0.43 0.31 1.00 0.6850 ## 11 0.10 0.56 1.00 0.44 0.33 1.00 0.6925 ## 12 0.11 0.58 1.00 0.44 0.36 1.00 0.7000 ## 13 0.12 0.60 1.00 0.46 0.39 1.00 0.7125 ## 14 0.13 0.62 1.00 0.47 0.43 1.00 0.7250 ## 15 0.14 0.64 1.00 0.49 0.46 1.00 0.7375 ## 16 0.15 0.66 1.00 0.50 0.49 1.00 0.7475 ## 17 0.16 0.69 1.00 0.52 0.53 1.00 0.7625 ## 18 0.17 0.70 1.00 0.53 0.55 1.00 0.7700 ## 19 0.18 0.71 1.00 0.54 0.57 1.00 0.7775 ## 20 0.19 0.74 1.00 0.56 0.61 1.00 0.7925 ## 21 0.20 0.77 1.00 0.59 0.65 1.00 0.8100 ## 22 0.21 0.79 1.00 0.61 0.68 1.00 0.8225 ## 23 0.22 0.81 1.00 0.64 0.71 1.00 0.8375 ## 24 0.23 0.82 1.00 0.66 0.74 1.00 0.8500 ## 25 0.24 0.85 1.00 0.69 0.77 1.00 0.8650 ## 26 0.25 0.87 1.00 0.72 0.80 1.00 0.8800 ## 27 0.26 0.89 1.00 0.75 0.83 1.00 0.8950 ## 28 0.27 0.90 1.00 0.77 0.85 1.00 0.9050 ## 29 0.28 0.92 1.00 0.80 0.87 1.00 0.9175 ## 30 0.29 0.93 1.00 0.83 0.90 1.00 0.9325 ## 31 0.30 0.95 1.00 0.87 0.92 1.00 0.9475 ## 32 0.31 0.96 1.00 0.90 0.94 1.00 0.9600 ## 33 0.32 0.98 1.00 0.94 0.97 1.00 0.9775 ## 34 0.33 0.98 0.99 0.97 0.98 0.99 0.9825 ## 35 0.34 0.98 0.98 0.98 0.99 0.96 0.9775 ## 36 0.35 0.97 0.97 0.99 1.00 0.93 0.9725 ## 37 0.36 0.96 0.95 1.00 1.00 0.89 0.9600 ## 38 0.37 0.95 0.93 1.00 1.00 0.86 0.9475 ## 39 0.38 0.94 0.92 1.00 1.00 0.83 0.9375 ## 40 0.39 0.94 0.91 1.00 1.00 0.81 0.9300 ## 41 0.40 0.92 0.89 1.00 1.00 0.76 0.9125 ## 42 0.41 0.91 0.88 1.00 1.00 0.73 0.9025 ## 43 0.42 0.89 0.86 1.00 1.00 0.69 0.8875 ## 44 0.43 0.88 0.85 1.00 1.00 0.66 0.8775 ## 45 0.44 0.87 0.84 1.00 1.00 0.63 0.8675 ## 46 0.45 0.86 0.83 1.00 1.00 0.60 0.8575 ## 47 0.46 0.86 0.82 1.00 1.00 0.58 0.8500 ## 48 0.47 0.85 0.82 1.00 1.00 0.56 0.8450 ## 49 0.48 0.84 0.81 1.00 1.00 0.54 0.8375 ## 50 0.49 0.83 0.80 1.00 1.00 0.50 0.8250 ## 51 0.50 0.82 0.79 1.00 1.00 0.47 0.8150 ## 52 0.51 0.81 0.78 1.00 1.00 0.44 0.8050 ## 53 0.52 0.80 0.77 1.00 1.00 0.42 0.7975 ## 54 0.53 0.80 0.77 1.00 1.00 0.40 0.7925 ## 55 0.54 0.79 0.76 1.00 1.00 0.37 0.7825 ## 56 0.55 0.78 0.75 1.00 1.00 0.35 0.7750 ## 57 0.56 0.77 0.75 1.00 1.00 0.33 0.7700 ## 58 0.57 0.77 0.74 1.00 1.00 0.32 0.7650 ## 59 0.58 0.76 0.73 1.00 1.00 0.29 0.7550 ## 60 0.59 0.76 0.73 1.00 1.00 0.28 0.7525 ## 61 0.60 0.75 0.72 1.00 1.00 0.26 0.7450 ## 62 0.61 0.74 0.72 1.00 1.00 0.23 0.7375 ## 63 0.62 0.74 0.71 1.00 1.00 0.22 0.7325 ## 64 0.63 0.73 0.71 1.00 1.00 0.20 0.7275 ## 65 0.64 0.72 0.71 1.00 1.00 0.19 0.7250 ## 66 0.65 0.72 0.70 1.00 1.00 0.18 0.7200 ## 67 0.66 0.72 0.70 1.00 1.00 0.16 0.7150 ## 68 0.67 0.71 0.70 1.00 1.00 0.15 0.7125 ## 69 0.68 0.71 0.69 1.00 1.00 0.13 0.7050 ## 70 0.69 0.70 0.69 1.00 1.00 0.12 0.7025 ## 71 0.70 0.70 0.69 1.00 1.00 0.12 0.7025 ## 72 0.71 0.70 0.69 1.00 1.00 0.11 0.7000 ## 73 0.72 0.69 0.68 1.00 1.00 0.09 0.6925 ## 74 0.73 0.69 0.68 1.00 1.00 0.09 0.6925 ## 75 0.74 0.69 0.68 1.00 1.00 0.08 0.6900 ## 76 0.75 0.69 0.68 1.00 1.00 0.08 0.6900 ## 77 0.76 0.68 0.68 1.00 1.00 0.06 0.6850 ## 78 0.77 0.68 0.68 1.00 1.00 0.06 0.6850 ## 79 0.78 0.68 0.67 1.00 1.00 0.06 0.6825 ## 80 0.79 0.68 0.67 1.00 1.00 0.05 0.6800 ## 81 0.80 0.68 0.67 1.00 1.00 0.05 0.6800 ## 82 0.81 0.68 0.67 1.00 1.00 0.05 0.6800 ## 83 0.82 0.68 0.67 1.00 1.00 0.04 0.6775 ## 84 0.83 0.67 0.67 1.00 1.00 0.04 0.6775 ## 85 0.84 0.67 0.67 1.00 1.00 0.03 0.6750 ## 86 0.85 0.67 0.67 1.00 1.00 0.03 0.6750 ## 87 0.86 0.67 0.67 1.00 1.00 0.03 0.6750 ## 88 0.87 0.67 0.67 1.00 1.00 0.02 0.6725 ## 89 0.88 0.67 0.67 1.00 1.00 0.02 0.6725 ## 90 0.89 0.67 0.67 1.00 1.00 0.02 0.6725 ## 91 0.90 0.67 0.67 1.00 1.00 0.02 0.6725 ## 92 0.91 0.67 0.66 1.00 1.00 0.02 0.6700 ## 93 0.92 0.67 0.66 1.00 1.00 0.02 0.6700 ## 94 0.93 0.67 0.66 1.00 1.00 0.02 0.6700 ## 95 0.94 0.66 0.66 1.00 1.00 0.01 0.6675 ## 96 0.95 0.66 0.66 1.00 1.00 0.01 0.6675 ## 97 0.96 0.66 0.66 1.00 1.00 0.01 0.6675 ## 98 0.97 0.66 0.66 1.00 1.00 0.01 0.6675 ## 99 0.98 0.66 0.66 1.00 1.00 0.00 0.6650 ## 100 0.99 0.66 0.66 1.00 1.00 0.00 0.6650 ## 101 1.00 0.66 0.66 0.00 1.00 0.00 0.4150 ## ## $cut ## [1] 0.33 ## ## $confusion_matrix ## 0 1 sum p ## 0 650.00 5.00 655.00 0.99 ## 1 11.00 334.00 345.00 0.97 ## sum 661.00 339.00 1000.00 1.00 ## p 0.98 0.99 1.00 0.98
result_confusion_performance(observed=c(1,2,3,1,2,3),predicted=abs(rnorm(6,0,sd=.1)))## $plot_performance
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## ## $cut_performance ## cut_point Overall Collumn_Observed.1 Collumn_Observed.2 Collumn_Observed.3 Collumn_Observed.4 Row_Predicted.1 Row_Predicted.2 Row_Predicted.3 Row_Predicted.4 Mean_proportion ## 1 0.05359314 0.33 0 0.4 0 0 0 1 0 0 0.175 ## ## $cut ## [1] 0.05359314 ## ## $confusion_matrix ## 0 1 2 3 sum p ## 0 0.00 0.00 1.00 0.00 1.00 0.00 ## 1 0.00 2.00 1.00 2.00 5.00 0.40 ## 2 0.00 0.00 0.00 0.00 0.00 0.00 ## 3 0.00 0.00 0.00 0.00 0.00 0.00 ## sum 0.00 2.00 2.00 2.00 6.00 1.00 ## p 0.00 1.00 0.00 0.00 1.00 0.33
KFOLD
Sample data for train test validation procedures
infert_formula<-as.formula(factor(case)~age+parity+education+spontaneous+induced)
result<-k_fold(infert,k=10,model_formula=infert_formula)## Fold Cases: 1 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 2 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 3 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 4 Train: 224 Test: 24 Total: 248 Unique Train: 224 Unique Test 24 ## Fold Cases: 5 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 6 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 7 Train: 224 Test: 24 Total: 248 Unique Train: 224 Unique Test 24 ## Fold Cases: 8 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 9 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25 ## Fold Cases: 10 Train: 223 Test: 25 Total: 248 Unique Train: 223 Unique Test 25
model_formula<-as.formula(mpg~cyl+disp+hp+drat+wt+qsec+vs+am+gear+carb)
result<-k_fold(mtcars,k=2,model_formula=model_formula)## Fold Cases: 1 Train: 16 Test: 16 Total: 32 Unique Train: 16 Unique Test 16 ## Fold Cases: 2 Train: 16 Test: 16 Total: 32 Unique Train: 16 Unique Test 16
result## $f ## $f$index ## $f$index$f1 ## [1] 1 8 9 11 13 14 15 16 17 18 22 23 24 26 29 30 ## ## $f$index$f2 ## [1] 2 3 4 5 6 7 10 12 19 20 21 25 27 28 31 32 ## ## ## $f$train ## $f$train$f1 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 ## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 ## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 ## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 ## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 ## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4 ## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3 ## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2 ## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1 ## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1 ## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2 ## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2 ## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2 ## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8 ## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2 ## ## $f$train$f2 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 ## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 ## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2 ## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4 ## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3 ## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3 ## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4 ## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4 ## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4 ## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1 ## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2 ## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2 ## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4 ## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1 ## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4 ## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6 ## ## ## $f$test ## $f$test$f1 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 ## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 ## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2 ## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4 ## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3 ## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3 ## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4 ## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4 ## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4 ## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1 ## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2 ## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2 ## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4 ## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1 ## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4 ## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6 ## ## $f$test$f2 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1 ## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1 ## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 ## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 ## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 ## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4 ## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3 ## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2 ## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1 ## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1 ## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2 ## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2 ## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2 ## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8 ## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2 ## ## ## $f$x_test ## $f$x_test$f1 ## cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 6 160.0 110 3.90 2.620 16.46 0 1 4 4 ## Merc 240D 4 146.7 62 3.69 3.190 20.00 1 0 4 2 ## Merc 230 4 140.8 95 3.92 3.150 22.90 1 0 4 2 ## Merc 280C 6 167.6 123 3.92 3.440 18.90 1 0 4 4 ## Merc 450SL 8 275.8 180 3.07 3.730 17.60 0 0 3 3 ## Merc 450SLC 8 275.8 180 3.07 3.780 18.00 0 0 3 3 ## Cadillac Fleetwood 8 472.0 205 2.93 5.250 17.98 0 0 3 4 ## Lincoln Continental 8 460.0 215 3.00 5.424 17.82 0 0 3 4 ## Chrysler Imperial 8 440.0 230 3.23 5.345 17.42 0 0 3 4 ## Fiat 128 4 78.7 66 4.08 2.200 19.47 1 1 4 1 ## Dodge Challenger 8 318.0 150 2.76 3.520 16.87 0 0 3 2 ## AMC Javelin 8 304.0 150 3.15 3.435 17.30 0 0 3 2 ## Camaro Z28 8 350.0 245 3.73 3.840 15.41 0 0 3 4 ## Fiat X1-9 4 79.0 66 4.08 1.935 18.90 1 1 4 1 ## Ford Pantera L 8 351.0 264 4.22 3.170 14.50 0 1 5 4 ## Ferrari Dino 6 145.0 175 3.62 2.770 15.50 0 1 5 6 ## ## $f$x_test$f2 ## cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 Wag 6 160.0 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 4 108.0 93 3.85 2.320 18.61 1 1 4 1 ## Hornet 4 Drive 6 258.0 110 3.08 3.215 19.44 1 0 3 1 ## Hornet Sportabout 8 360.0 175 3.15 3.440 17.02 0 0 3 2 ## Valiant 6 225.0 105 2.76 3.460 20.22 1 0 3 1 ## Duster 360 8 360.0 245 3.21 3.570 15.84 0 0 3 4 ## Merc 280 6 167.6 123 3.92 3.440 18.30 1 0 4 4 ## Merc 450SE 8 275.8 180 3.07 4.070 17.40 0 0 3 3 ## Honda Civic 4 75.7 52 4.93 1.615 18.52 1 1 4 2 ## Toyota Corolla 4 71.1 65 4.22 1.835 19.90 1 1 4 1 ## Toyota Corona 4 120.1 97 3.70 2.465 20.01 1 0 3 1 ## Pontiac Firebird 8 400.0 175 3.08 3.845 17.05 0 0 3 2 ## Porsche 914-2 4 120.3 91 4.43 2.140 16.70 0 1 5 2 ## Lotus Europa 4 95.1 113 3.77 1.513 16.90 1 1 5 2 ## Maserati Bora 8 301.0 335 3.54 3.570 14.60 0 1 5 8 ## Volvo 142E 4 121.0 109 4.11 2.780 18.60 1 1 4 2 ## ## ## $f$y_test ## $f$y_test$f1 ## [1] 21.0 24.4 22.8 17.8 17.3 15.2 10.4 10.4 14.7 32.4 15.5 15.2 13.3 27.3 15.8 19.7 ## ## $f$y_test$f2 ## [1] 21.0 22.8 21.4 18.7 18.1 14.3 19.2 16.4 30.4 33.9 21.5 19.2 26.0 30.4 15.0 21.4 ## ## ## ## $index ## [1] 1 2 2 2 2 2 2 1 1 2 1 2 1 1 1 1 1 1 2 2 2 1 1 1 2 1 2 2 1 1 2 2 ## ## $model_formula ## mpg ~ cyl + disp + hp + drat + wt + qsec + vs + am + gear + carb ## ## $variables ## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear" "carb" ## ## $predictors ## [1] "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear" "carb" ## ## $outcome ## [1] "mpg" ## ## $xgb ## $xgb$f1 ## $xgb$f1$train ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## $xgb$f1$test ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## $xgb$f1$watchlist ## $xgb$f1$watchlist$train ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## $xgb$f1$watchlist$test ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## ## $xgb$f1$ytrain ## [1] 21.0 22.8 21.4 18.7 18.1 14.3 19.2 16.4 30.4 33.9 21.5 19.2 26.0 30.4 15.0 21.4 ## ## $xgb$f1$ytest ## [1] 21.0 24.4 22.8 17.8 17.3 15.2 10.4 10.4 14.7 32.4 15.5 15.2 13.3 27.3 15.8 19.7 ## ## ## $xgb$f2 ## $xgb$f2$train ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## $xgb$f2$test ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## $xgb$f2$watchlist ## $xgb$f2$watchlist$train ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## $xgb$f2$watchlist$test ## xgb.DMatrix dim: 16 x 10 info: label colnames: yes ## ## ## $xgb$f2$ytrain ## [1] 21.0 24.4 22.8 17.8 17.3 15.2 10.4 10.4 14.7 32.4 15.5 15.2 13.3 27.3 15.8 19.7 ## ## $xgb$f2$ytest ## [1] 21.0 22.8 21.4 18.7 18.1 14.3 19.2 16.4 30.4 33.9 21.5 19.2 26.0 30.4 15.0 21.4
KSAMPLE
Sample data for train test validation procedures
infert_formula<-as.formula(factor(case)~age+parity+education+spontaneous+induced)
result<-k_sample(df=infert,k=10,model_formula=infert_formula)## Fold Cases: 1 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 2 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 3 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 4 Train: 12 Test: 6 Validation: 6 Total: 24 Unique Train: 12 Unique Test: 6 Unique Validation: 6 ## Fold Cases: 5 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 6 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 7 Train: 12 Test: 6 Validation: 6 Total: 24 Unique Train: 12 Unique Test: 6 Unique Validation: 6 ## Fold Cases: 8 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 9 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7 ## Fold Cases: 10 Train: 12 Test: 6 Validation: 6 Total: 25 Unique Train: 12 Unique Test: 6 Unique Validation: 7
model_formula<-as.formula(mpg~cyl+disp+hp+drat+wt+qsec+vs+am+gear+carb)
result<-k_sample(df=mtcars,k=10,model_formula=model_formula)## Fold Cases: 1 Train: 2 Test: 1 Validation: 1 Total: 4 Unique Train: 2 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 2 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 3 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 4 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 5 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 6 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 7 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 8 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 9 Train: 1 Test: 1 Validation: 1 Total: 3 Unique Train: 1 Unique Test: 1 Unique Validation: 1 ## Fold Cases: 10 Train: 2 Test: 1 Validation: 1 Total: 4 Unique Train: 2 Unique Test: 1 Unique Validation: 1
result## $f ## $f$index ## $f$index$train ## $f$index$train$fold1 ## [1] 18 10 ## ## $f$index$train$fold2 ## [1] 14 ## ## $f$index$train$fold3 ## [1] 25 ## ## $f$index$train$fold4 ## [1] 21 ## ## $f$index$train$fold5 ## [1] 26 ## ## $f$index$train$fold6 ## [1] 23 ## ## $f$index$train$fold7 ## [1] 28 ## ## $f$index$train$fold8 ## [1] 31 ## ## $f$index$train$fold9 ## [1] 5 ## ## $f$index$train$fold10 ## [1] 30 27 ## ## ## $f$index$test ## $f$index$test$fold1 ## [1] 1 ## ## $f$index$test$fold2 ## [1] 32 ## ## $f$index$test$fold3 ## [1] 16 ## ## $f$index$test$fold4 ## [1] 19 ## ## $f$index$test$fold5 ## [1] 4 ## ## $f$index$test$fold6 ## [1] 24 ## ## $f$index$test$fold7 ## [1] 17 ## ## $f$index$test$fold8 ## [1] 15 ## ## $f$index$test$fold9 ## [1] 3 ## ## $f$index$test$fold10 ## [1] 12 ## ## ## $f$index$validation ## $f$index$validation$fold1 ## [1] 9 ## ## $f$index$validation$fold2 ## [1] 6 ## ## $f$index$validation$fold3 ## [1] 11 ## ## $f$index$validation$fold4 ## [1] 7 ## ## $f$index$validation$fold5 ## [1] 2 ## ## $f$index$validation$fold6 ## [1] 20 ## ## $f$index$validation$fold7 ## [1] 22 ## ## $f$index$validation$fold8 ## [1] 29 ## ## $f$index$validation$fold9 ## [1] 13 ## ## $f$index$validation$fold10 ## [1] 8 ## ## ## ## $f$train ## $f$train$fold1 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Fiat 128 32.4 4 78.7 66 4.08 2.20 19.47 1 1 4 1 ## Merc 280 19.2 6 167.6 123 3.92 3.44 18.30 1 0 4 4 ## ## $f$train$fold2 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Merc 450SLC 15.2 8 275.8 180 3.07 3.78 18 0 0 3 3 ## ## $f$train$fold3 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Pontiac Firebird 19.2 8 400 175 3.08 3.845 17.05 0 0 3 2 ## ## $f$train$fold4 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Toyota Corona 21.5 4 120.1 97 3.7 2.465 20.01 1 0 3 1 ## ## $f$train$fold5 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Fiat X1-9 27.3 4 79 66 4.08 1.935 18.9 1 1 4 1 ## ## $f$train$fold6 ## mpg cyl disp hp drat wt qsec vs am gear carb ## AMC Javelin 15.2 8 304 150 3.15 3.435 17.3 0 0 3 2 ## ## $f$train$fold7 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.9 1 1 5 2 ## ## $f$train$fold8 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Maserati Bora 15 8 301 335 3.54 3.57 14.6 0 1 5 8 ## ## $f$train$fold9 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Hornet Sportabout 18.7 8 360 175 3.15 3.44 17.02 0 0 3 2 ## ## $f$train$fold10 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Ferrari Dino 19.7 6 145.0 175 3.62 2.77 15.5 0 1 5 6 ## Porsche 914-2 26.0 4 120.3 91 4.43 2.14 16.7 0 1 5 2 ## ## ## $f$test ## $f$test$fold1 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21 6 160 110 3.9 2.62 16.46 0 1 4 4 ## ## $f$test$fold2 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Volvo 142E 21.4 4 121 109 4.11 2.78 18.6 1 1 4 2 ## ## $f$test$fold3 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Lincoln Continental 10.4 8 460 215 3 5.424 17.82 0 0 3 4 ## ## $f$test$fold4 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2 ## ## $f$test$fold5 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1 ## ## $f$test$fold6 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Camaro Z28 13.3 8 350 245 3.73 3.84 15.41 0 0 3 4 ## ## $f$test$fold7 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Chrysler Imperial 14.7 8 440 230 3.23 5.345 17.42 0 0 3 4 ## ## $f$test$fold8 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Cadillac Fleetwood 10.4 8 472 205 2.93 5.25 17.98 0 0 3 4 ## ## $f$test$fold9 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Datsun 710 22.8 4 108 93 3.85 2.32 18.61 1 1 4 1 ## ## $f$test$fold10 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Merc 450SE 16.4 8 275.8 180 3.07 4.07 17.4 0 0 3 3 ## ## ## $f$validation ## $f$validation$fold1 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Merc 230 22.8 4 140.8 95 3.92 3.15 22.9 1 0 4 2 ## ## $f$validation$fold2 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Valiant 18.1 6 225 105 2.76 3.46 20.22 1 0 3 1 ## ## $f$validation$fold3 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Merc 280C 17.8 6 167.6 123 3.92 3.44 18.9 1 0 4 4 ## ## $f$validation$fold4 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Duster 360 14.3 8 360 245 3.21 3.57 15.84 0 0 3 4 ## ## $f$validation$fold5 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 Wag 21 6 160 110 3.9 2.875 17.02 0 1 4 4 ## ## $f$validation$fold6 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.9 1 1 4 1 ## ## $f$validation$fold7 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Dodge Challenger 15.5 8 318 150 2.76 3.52 16.87 0 0 3 2 ## ## $f$validation$fold8 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Ford Pantera L 15.8 8 351 264 4.22 3.17 14.5 0 1 5 4 ## ## $f$validation$fold9 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Merc 450SL 17.3 8 275.8 180 3.07 3.73 17.6 0 0 3 3 ## ## $f$validation$fold10 ## mpg cyl disp hp drat wt qsec vs am gear carb ## Merc 240D 24.4 4 146.7 62 3.69 3.19 20 1 0 4 2 ## ## ## $f$x_test ## $f$x_test$fold1 ## cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 6 160 110 3.9 2.62 16.46 0 1 4 4 ## ## $f$x_test$fold2 ## cyl disp hp drat wt qsec vs am gear carb ## Volvo 142E 4 121 109 4.11 2.78 18.6 1 1 4 2 ## ## $f$x_test$fold3 ## cyl disp hp drat wt qsec vs am gear carb ## Lincoln Continental 8 460 215 3 5.424 17.82 0 0 3 4 ## ## $f$x_test$fold4 ## cyl disp hp drat wt qsec vs am gear carb ## Honda Civic 4 75.7 52 4.93 1.615 18.52 1 1 4 2 ## ## $f$x_test$fold5 ## cyl disp hp drat wt qsec vs am gear carb ## Hornet 4 Drive 6 258 110 3.08 3.215 19.44 1 0 3 1 ## ## $f$x_test$fold6 ## cyl disp hp drat wt qsec vs am gear carb ## Camaro Z28 8 350 245 3.73 3.84 15.41 0 0 3 4 ## ## $f$x_test$fold7 ## cyl disp hp drat wt qsec vs am gear carb ## Chrysler Imperial 8 440 230 3.23 5.345 17.42 0 0 3 4 ## ## $f$x_test$fold8 ## cyl disp hp drat wt qsec vs am gear carb ## Cadillac Fleetwood 8 472 205 2.93 5.25 17.98 0 0 3 4 ## ## $f$x_test$fold9 ## cyl disp hp drat wt qsec vs am gear carb ## Datsun 710 4 108 93 3.85 2.32 18.61 1 1 4 1 ## ## $f$x_test$fold10 ## cyl disp hp drat wt qsec vs am gear carb ## Merc 450SE 8 275.8 180 3.07 4.07 17.4 0 0 3 3 ## ## ## $f$y_test ## $f$y_test$fold1 ## [1] 21 ## ## $f$y_test$fold2 ## [1] 21.4 ## ## $f$y_test$fold3 ## [1] 10.4 ## ## $f$y_test$fold4 ## [1] 30.4 ## ## $f$y_test$fold5 ## [1] 21.4 ## ## $f$y_test$fold6 ## [1] 13.3 ## ## $f$y_test$fold7 ## [1] 14.7 ## ## $f$y_test$fold8 ## [1] 10.4 ## ## $f$y_test$fold9 ## [1] 22.8 ## ## $f$y_test$fold10 ## [1] 16.4 ## ## ## $f$x_validation ## $f$x_validation$fold1 ## cyl disp hp drat wt qsec vs am gear carb ## Merc 230 4 140.8 95 3.92 3.15 22.9 1 0 4 2 ## ## $f$x_validation$fold2 ## cyl disp hp drat wt qsec vs am gear carb ## Valiant 6 225 105 2.76 3.46 20.22 1 0 3 1 ## ## $f$x_validation$fold3 ## cyl disp hp drat wt qsec vs am gear carb ## Merc 280C 6 167.6 123 3.92 3.44 18.9 1 0 4 4 ## ## $f$x_validation$fold4 ## cyl disp hp drat wt qsec vs am gear carb ## Duster 360 8 360 245 3.21 3.57 15.84 0 0 3 4 ## ## $f$x_validation$fold5 ## cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 Wag 6 160 110 3.9 2.875 17.02 0 1 4 4 ## ## $f$x_validation$fold6 ## cyl disp hp drat wt qsec vs am gear carb ## Toyota Corolla 4 71.1 65 4.22 1.835 19.9 1 1 4 1 ## ## $f$x_validation$fold7 ## cyl disp hp drat wt qsec vs am gear carb ## Dodge Challenger 8 318 150 2.76 3.52 16.87 0 0 3 2 ## ## $f$x_validation$fold8 ## cyl disp hp drat wt qsec vs am gear carb ## Ford Pantera L 8 351 264 4.22 3.17 14.5 0 1 5 4 ## ## $f$x_validation$fold9 ## cyl disp hp drat wt qsec vs am gear carb ## Merc 450SL 8 275.8 180 3.07 3.73 17.6 0 0 3 3 ## ## $f$x_validation$fold10 ## cyl disp hp drat wt qsec vs am gear carb ## Merc 240D 4 146.7 62 3.69 3.19 20 1 0 4 2 ## ## ## $f$y_validation ## $f$y_validation$fold1 ## [1] 22.8 ## ## $f$y_validation$fold2 ## [1] 18.1 ## ## $f$y_validation$fold3 ## [1] 17.8 ## ## $f$y_validation$fold4 ## [1] 14.3 ## ## $f$y_validation$fold5 ## [1] 21 ## ## $f$y_validation$fold6 ## [1] 33.9 ## ## $f$y_validation$fold7 ## [1] 15.5 ## ## $f$y_validation$fold8 ## [1] 15.8 ## ## $f$y_validation$fold9 ## [1] 17.3 ## ## $f$y_validation$fold10 ## [1] 24.4 ## ## ## ## $index ## [1] 1 5 9 5 9 2 4 10 1 1 3 10 9 2 8 3 7 1 4 6 4 7 6 6 3 5 10 7 8 10 8 2 ## ## $model_formula ## mpg ~ cyl + disp + hp + drat + wt + qsec + vs + am + gear + carb ## ## $variables ## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear" "carb" ## ## $predictors ## [1] "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear" "carb" ## ## $outcome ## [1] "mpg" ## ## $xgb ## $xgb$fold1 ## $xgb$fold1$train ## xgb.DMatrix dim: 2 x 10 info: label colnames: yes ## ## $xgb$fold1$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold1$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold1$watchlist ## $xgb$fold1$watchlist$train ## xgb.DMatrix dim: 2 x 10 info: label colnames: yes ## ## $xgb$fold1$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold1$ytrain ## [1] 32.4 19.2 ## ## $xgb$fold1$ytest ## [1] 21 ## ## $xgb$fold1$yvalidation ## [1] 21 ## ## ## $xgb$fold2 ## $xgb$fold2$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold2$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold2$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold2$watchlist ## $xgb$fold2$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold2$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold2$ytrain ## [1] 15.2 ## ## $xgb$fold2$ytest ## [1] 21.4 ## ## $xgb$fold2$yvalidation ## [1] 21.4 ## ## ## $xgb$fold3 ## $xgb$fold3$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold3$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold3$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold3$watchlist ## $xgb$fold3$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold3$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold3$ytrain ## [1] 19.2 ## ## $xgb$fold3$ytest ## [1] 10.4 ## ## $xgb$fold3$yvalidation ## [1] 10.4 ## ## ## $xgb$fold4 ## $xgb$fold4$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold4$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold4$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold4$watchlist ## $xgb$fold4$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold4$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold4$ytrain ## [1] 21.5 ## ## $xgb$fold4$ytest ## [1] 30.4 ## ## $xgb$fold4$yvalidation ## [1] 30.4 ## ## ## $xgb$fold5 ## $xgb$fold5$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold5$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold5$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold5$watchlist ## $xgb$fold5$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold5$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold5$ytrain ## [1] 27.3 ## ## $xgb$fold5$ytest ## [1] 21.4 ## ## $xgb$fold5$yvalidation ## [1] 21.4 ## ## ## $xgb$fold6 ## $xgb$fold6$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold6$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold6$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold6$watchlist ## $xgb$fold6$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold6$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold6$ytrain ## [1] 15.2 ## ## $xgb$fold6$ytest ## [1] 13.3 ## ## $xgb$fold6$yvalidation ## [1] 13.3 ## ## ## $xgb$fold7 ## $xgb$fold7$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold7$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold7$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold7$watchlist ## $xgb$fold7$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold7$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold7$ytrain ## [1] 30.4 ## ## $xgb$fold7$ytest ## [1] 14.7 ## ## $xgb$fold7$yvalidation ## [1] 14.7 ## ## ## $xgb$fold8 ## $xgb$fold8$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold8$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold8$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold8$watchlist ## $xgb$fold8$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold8$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold8$ytrain ## [1] 15 ## ## $xgb$fold8$ytest ## [1] 10.4 ## ## $xgb$fold8$yvalidation ## [1] 10.4 ## ## ## $xgb$fold9 ## $xgb$fold9$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold9$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold9$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold9$watchlist ## $xgb$fold9$watchlist$train ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold9$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold9$ytrain ## [1] 18.7 ## ## $xgb$fold9$ytest ## [1] 22.8 ## ## $xgb$fold9$yvalidation ## [1] 22.8 ## ## ## $xgb$fold10 ## $xgb$fold10$train ## xgb.DMatrix dim: 2 x 10 info: label colnames: yes ## ## $xgb$fold10$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold10$validation ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## $xgb$fold10$watchlist ## $xgb$fold10$watchlist$train ## xgb.DMatrix dim: 2 x 10 info: label colnames: yes ## ## $xgb$fold10$watchlist$test ## xgb.DMatrix dim: 1 x 10 info: label colnames: yes ## ## ## $xgb$fold10$ytrain ## [1] 19.7 26.0 ## ## $xgb$fold10$ytest ## [1] 16.4 ## ## $xgb$fold10$yvalidation ## [1] 16.4
Scaling
Scale all data between 0 and 1
result<-recode_scale_dummy(infert)
head(result)## X6.11yrs X12..yrs X0.5yrs age parity induced case spontaneous stratum pooled.stratum ## 1 0 0 1 0.2173913 1.0 0.5 1 1.0 0.00000000 0.03225806 ## 2 0 0 1 0.9130435 0.0 0.5 1 0.0 0.01219512 0.00000000 ## 3 0 0 1 0.7826087 1.0 1.0 1 0.0 0.02439024 0.04838710 ## 4 0 0 1 0.5652174 0.6 1.0 1 0.0 0.03658537 0.01612903 ## 5 1 0 0 0.6086957 0.4 0.5 1 0.5 0.04878049 0.50000000 ## 6 1 0 0 0.6521739 0.6 1.0 1 0.5 0.06097561 0.56451613
Confusion Matrix for Classification
confusion(observed=c(1,2,3,4,5,10),predicted=c(1,2,3,4,5,11))## observed ## predicted 1 2 3 4 5 10 11 ## 1 1 0 0 0 0 0 0 ## 2 0 1 0 0 0 0 0 ## 3 0 0 1 0 0 0 0 ## 4 0 0 0 1 0 0 0 ## 5 0 0 0 0 1 0 0 ## 10 0 0 0 0 0 0 0 ## 11 0 0 0 0 0 1 0
confusion(observed=c(1,2,2,2,2),predicted=c(1,1,2,2,2))## observed ## predicted 1 2 ## 1 1 1 ## 2 0 3
Proportion Accutate
proportion_accurate(observed=c(1,2,3,4,5,10),predicted=c(1,2,3,4,5,11))## cm_diagonal cm_off_diagonal kappa_unweighted kappa_linear kappa_squared ## 1 0.8333333 1 0.8064516 0.9285714 0.9801325
Confusion Matrix Percent
observed<-factor(round(rnorm(10000,m=10,sd=1)))
predicted<-factor(round(rnorm(10000,m=10,sd=1)))
confusion_matrix_percent(observed,predicted)## 6 7 8 9 10 11 12 13 14 sum p ## 6 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 1.00 0.00 ## 7 0.00 0.00 3.00 10.00 26.00 12.00 5.00 0.00 0.00 56.00 0.00 ## 8 0.00 4.00 33.00 143.00 252.00 154.00 35.00 3.00 0.00 624.00 0.05 ## 9 0.00 11.00 135.00 594.00 872.00 572.00 114.00 8.00 1.00 2307.00 0.26 ## 10 0.00 20.00 237.00 965.00 1508.00 929.00 224.00 20.00 0.00 3903.00 0.39 ## 11 3.00 15.00 134.00 549.00 876.00 609.00 169.00 16.00 1.00 2372.00 0.26 ## 12 0.00 7.00 38.00 164.00 263.00 147.00 42.00 6.00 0.00 667.00 0.06 ## 13 0.00 1.00 8.00 17.00 24.00 15.00 3.00 1.00 0.00 69.00 0.01 ## 14 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 1.00 0.00 ## sum 3.00 58.00 588.00 2442.00 3822.00 2439.00 592.00 54.00 2.00 10000.00 1.00 ## p 0.00 0.00 0.06 0.24 0.39 0.25 0.07 0.02 0.00 1.00 0.28