Return to Question

> pred <- prediction(predictions, test$cls)
> auc = as.numeric(performance(pred, "auc")@y.values)
> auc
[1] 0.8942857

Call:
glm(formula = cls ~ ., family = "binomial", data = train)

Deviance Residuals: 
   Min      1Q  Median      3Q     Max  
-1.210   0.000   0.000   0.000   1.815  

Coefficients: (1 not defined because of singularities)
             Estimate Std. Error z value Pr(>|z|)
(Intercept)   -63.029  19632.716  -0.003    0.997
x1             15.446     16.542   0.934    0.350
x2              6.708      7.812   0.859    0.390
x11            65.696   6520.412   0.010    0.992
x12            30.091     33.700   0.893    0.372
x13           -18.419   6047.451  -0.003    0.998
x14           -14.663  26855.669  -0.001    1.000
x21            37.062  19632.675   0.002    0.998
x22            16.121  19726.706   0.001    0.999
x23            -2.200  20687.068   0.000    1.000
x24                NA         NA      NA       NA
x3              7.791      7.824   0.996    0.319

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 196.078  on 999  degrees of freedom
Residual deviance:  18.571  on 989  degrees of freedom
AIC: 40.571

Number of Fisher Scoring iterations: 25

            cls           x1          x2         x11         x12          x13         x14         x21         x22         x23          x24
cls  1.00000000 -0.228158414 -0.21808962  0.62877027  0.06408317 -0.381460173 -0.06281125  0.25772091  0.06499037 -0.11428571 -0.094413507
x1  -0.22815841  1.000000000  0.05692690 -0.40907207 -0.47059084  0.339122434  0.02663309 -0.03553939 -0.06495859  0.04962622  0.008853023
x2  -0.21808962  0.056926900  1.00000000 -0.10014611 -0.04608160  0.072822544  0.66253601 -0.61372208 -0.30719548 -0.13965796  0.761337056
x11  0.62877027 -0.409072066 -0.10014611  1.00000000 -0.03614192 -0.329514671 -0.03192955  0.10787016  0.05614028 -0.04113450 -0.063671465
x12  0.06408317 -0.470590845 -0.04608160 -0.03614192  1.00000000 -0.782043609 -0.01809118  0.04226619  0.05305775 -0.07043852  0.015990310
x13 -0.38146017  0.339122434  0.07282254 -0.32951467 -0.78204361  1.000000000  0.01591565 -0.08952730 -0.06137774  0.08829694  0.002594731
x14 -0.06281125  0.026633095  0.66253601 -0.03192955 -0.01809118  0.015915651  1.00000000 -0.16082080 -0.12788433 -0.43967877  0.665278251
x21  0.25772091 -0.035539391 -0.61372208  0.10787016  0.04226619 -0.089527297 -0.16082080  1.00000000 -0.10638700 -0.36576885 -0.241734637
x22  0.06499037 -0.064958593 -0.30719548  0.05614028  0.05305775 -0.061377745 -0.12788433 -0.10638700  1.00000000 -0.29085855 -0.192226834
x23 -0.11428571  0.049626217 -0.13965796 -0.04113450 -0.07043852  0.088296938 -0.43967877 -0.36576885 -0.29085855  1.00000000 -0.660894552
x24 -0.09441351  0.008853023  0.76133706 -0.06367146  0.01599031  0.002594731  0.66527825 -0.24173464 -0.19222683 -0.66089455  1.000000000
x3   0.51362162 -0.199469306 -0.84437482  0.43450107  0.17141845 -0.389151137 -0.54093332  0.54322307  0.30336002  0.06389858 -0.627306333
             x3
cls  0.51362162
x1  -0.19946931
x2  -0.84437482
x11  0.43450107
x12  0.17141845
x13 -0.38915114
x14 -0.54093332
x21  0.54322307
x22  0.30336002
x23  0.06389858
x24 -0.62730633
x3   1.00000000

library(GGally)
library(ggplot2)
library(data.table)
library(ROSE)
library(ROCR)
data(hacide)
train <- hacide.train
test <- hacide.test
train <- train %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
test <- test %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
pilot <- glm(cls ~ ., train, family = "binomial")
predictions <- predict(pilot, test, type = "response")
tbl <- table(test$cls , predictions > 0.5)
    FALSE TRUE
  0   244    1
  1     3    2

Your advice will be appreciated.

> pred <- prediction(predictions, test$cls)
> auc = as.numeric(performance(pred, "auc")@y.values)
> auc
[1] 0.8942857

Call:
glm(formula = cls ~ ., family = "binomial", data = train)

Deviance Residuals: 
   Min      1Q  Median      3Q     Max  
-1.210   0.000   0.000   0.000   1.815  

Coefficients: (1 not defined because of singularities)
             Estimate Std. Error z value Pr(>|z|)
(Intercept)   -63.029  19632.716  -0.003    0.997
x1             15.446     16.542   0.934    0.350
x2              6.708      7.812   0.859    0.390
x11            65.696   6520.412   0.010    0.992
x12            30.091     33.700   0.893    0.372
x13           -18.419   6047.451  -0.003    0.998
x14           -14.663  26855.669  -0.001    1.000
x21            37.062  19632.675   0.002    0.998
x22            16.121  19726.706   0.001    0.999
x23            -2.200  20687.068   0.000    1.000
x24                NA         NA      NA       NA
x3              7.791      7.824   0.996    0.319

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 196.078  on 999  degrees of freedom
Residual deviance:  18.571  on 989  degrees of freedom
AIC: 40.571

Number of Fisher Scoring iterations: 25

            cls           x1          x2         x11         x12          x13         x14         x21         x22         x23          x24
cls  1.00000000 -0.228158414 -0.21808962  0.62877027  0.06408317 -0.381460173 -0.06281125  0.25772091  0.06499037 -0.11428571 -0.094413507
x1  -0.22815841  1.000000000  0.05692690 -0.40907207 -0.47059084  0.339122434  0.02663309 -0.03553939 -0.06495859  0.04962622  0.008853023
x2  -0.21808962  0.056926900  1.00000000 -0.10014611 -0.04608160  0.072822544  0.66253601 -0.61372208 -0.30719548 -0.13965796  0.761337056
x11  0.62877027 -0.409072066 -0.10014611  1.00000000 -0.03614192 -0.329514671 -0.03192955  0.10787016  0.05614028 -0.04113450 -0.063671465
x12  0.06408317 -0.470590845 -0.04608160 -0.03614192  1.00000000 -0.782043609 -0.01809118  0.04226619  0.05305775 -0.07043852  0.015990310
x13 -0.38146017  0.339122434  0.07282254 -0.32951467 -0.78204361  1.000000000  0.01591565 -0.08952730 -0.06137774  0.08829694  0.002594731
x14 -0.06281125  0.026633095  0.66253601 -0.03192955 -0.01809118  0.015915651  1.00000000 -0.16082080 -0.12788433 -0.43967877  0.665278251
x21  0.25772091 -0.035539391 -0.61372208  0.10787016  0.04226619 -0.089527297 -0.16082080  1.00000000 -0.10638700 -0.36576885 -0.241734637
x22  0.06499037 -0.064958593 -0.30719548  0.05614028  0.05305775 -0.061377745 -0.12788433 -0.10638700  1.00000000 -0.29085855 -0.192226834
x23 -0.11428571  0.049626217 -0.13965796 -0.04113450 -0.07043852  0.088296938 -0.43967877 -0.36576885 -0.29085855  1.00000000 -0.660894552
x24 -0.09441351  0.008853023  0.76133706 -0.06367146  0.01599031  0.002594731  0.66527825 -0.24173464 -0.19222683 -0.66089455  1.000000000
x3   0.51362162 -0.199469306 -0.84437482  0.43450107  0.17141845 -0.389151137 -0.54093332  0.54322307  0.30336002  0.06389858 -0.627306333
             x3
cls  0.51362162
x1  -0.19946931
x2  -0.84437482
x11  0.43450107
x12  0.17141845
x13 -0.38915114
x14 -0.54093332
x21  0.54322307
x22  0.30336002
x23  0.06389858
x24 -0.62730633
x3   1.00000000

library(GGally)
library(ggplot2)
library(data.table)
library(ROSE)
library(ROCR)
data(hacide)
train <- hacide.train
test <- hacide.test
train <- train %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
test <- test %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
pilot <- glm(cls ~ ., train, family = "binomial")
predictions <- predict(pilot, test, type = "response")
tbl <- table(test$cls , predictions > 0.5)
    FALSE TRUE
  0   244    1
  1     3    2

> accuracy <- sum(diag(tbl))/sum(tbl)
> recall
[1] 0.4
> precision
[1] 0.6666667
> accuracy
[1] 0.984
> pred <- prediction(predictions, test$cls)
> auc = as.numeric(performance(pred, "auc")@y.values)
> auc
[1] 0.8942857

> pred <- prediction(predictions, test$cls)
> auc = as.numeric(performance(pred, "auc")@y.values)
> auc
[1] 0.8942857

> accuracy <- sum(diag(tbl))/sum(tbl)
> recall
[1] 0.4
> precision
[1] 0.6666667
> accuracy
[1] 0.984

library(GGally)
library(ggplot2)
library(data.table)
library(ROSE)
data(hacide)
train <- hacide.train
test <- hacide.test
train <- train %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
test <- test %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
pilot <- glm(cls ~ ., train, family = "binomial")
predictions <- predict(pilot, test, type = "response")
tbl <- table(test$cls , predictions > 0.5)
    FALSE TRUE
  0   244    1
  1     3    2

> accuracy <- sum(diag(tbl))/sum(tbl)
> recall
[1] 0.4
> precision
[1] 0.6666667
> accuracy
[1] 0.984
> pred <- prediction(predictions, test$cls)
> auc = as.numeric(performance(pred, "auc")@y.values)
> auc
[1] 0.8942857

library(GGally)
library(ggplot2)
library(data.table)
library(ROSE)
library(ROCR)
data(hacide)
train <- hacide.train
test <- hacide.test
train <- train %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
test <- test %>% mutate(
  x11 = ifelse(x1 < -1.4, 1, 0),
  x12 = ifelse(((x1 >= -1.4) & (x1 < -0.74)), 1, 0),
  x13 = ifelse(((x1 >= -0.74) & (x1 < 1)), 1, 0),
  x14 = ifelse(x2 >= 1, 1, 0),
  x21 = ifelse(x2 < -1.4, 1, 0),
  x22 = ifelse(((x2 >= -1.4) & (x2 < -1)), 1, 0),
  x23 = ifelse(((x2 >= -1) & (x2 < 0.5)), 1, 0),
  x24 = ifelse(x2 >= 0.5, 1, 0),
  x3 = x1 ^ 2 - x2
)
pilot <- glm(cls ~ ., train, family = "binomial")
predictions <- predict(pilot, test, type = "response")
tbl <- table(test$cls , predictions > 0.5)
    FALSE TRUE
  0   244    1
  1     3    2