I trained a logistic regression model with tensorflow but the accuracy of the model was so poor (accuracy = 0.68). The model was trained using simulated dataset and the result should be very good. is there something wrong with the code ?
#simulated dataSet
sim_data <- function(n=2000){
library(dummies)
age <- round(abs(rnorm(n,mean = 60, sd = 20)))
lac <- round(abs(rnorm(n,3,1)),1)
wbc <- round(abs(rnorm(n,10,3)),1)
sex <- factor(rbinom(n,size = 1,prob = 0.6),
labels = c("Female","Male"));
type <- as.factor(sample(c("Med","Emerg","Surg"),
size = n,replace = T,
prob = c(0.4,0.4,0.2)))
linPred <- cbind(1,age,lac,wbc,dummy(sex)[,-1],
dummy(type)[,-1]) %*%
c(-30,0.2,4,1,-2,3,-3)
pi <- 1/(1+exp(-linPred))
mort <- factor(rbinom(n,size = 1, prob = pi),
labels = c("Alive","Died"))
dat <- data.frame(age=age,lac=lac,wbc=wbc,
sex=sex,type=type,
mort = mort)
return(dat)
}
set.seed(123)
dat <- sim_data()
dat_test <- sim_data(n=1000)
#logistic regression in conventional method
mod <- glm(mort~.,data = dat,family = "binomial")
library(tableone)
ShowRegTable(mod)
#diagnotic accuracy
pred <- predict.glm(mod,newdata = dat_test,
type = "response")
library(pROC)
roc(response = dat_test$mort,predictor = pred,ci=T)
predBi <- pred >= 0.5
crossTab <- table(predBi,dat_test$mort)
(crossTab[1]+crossTab[4])/sum(crossTab)
#choose different cutoff for the accuracy
DTaccuracy <- data.frame()
for (cutoff in seq(0,1,by = 0.01)) {
predBi <- pred >= cutoff;
crossTab <- table(predBi,dat_test$mort)
accuracy = (crossTab[1]+crossTab[4])/sum(crossTab)
DTaccuracy <- rbind(DTaccuracy,c(accuracy,cutoff))
}
names(DTaccuracy) <- c('Accuracy','Cutoff')
qplot(x=Cutoff, y = Accuracy, data = DTaccuracy)
#tensorflow method
library(caret)
y = with(dat, model.matrix(~ mort + 0))
x = model.matrix(~.,dat[,!names(dat)%in%"mort"])
trainIndex = createDataPartition(1:nrow(x),
p=0.7, list=FALSE,times=1)
x_train = x[trainIndex,]
x_test = x[-trainIndex,]
y_train = y[trainIndex,]
y_test = y[-trainIndex,]
# Hyper-parameters
epochs = 30 # Total number of training epochs
batch_size = 30 # Training batch size
display_freq = 10 # Frequency of displaying the training results
learning_rate = 0.1 # The optimization initial learning rate
#Then we will define the placeholders for features and labels:
library(tensorflow)
X <- tf$placeholder(tf$float32, shape(NULL, ncol(x)),
name = "X")
Y = tf$placeholder(tf$float32, shape(NULL, 2L), name = "Y")
#we will define the parameters. We will randomly initialize the weights with mean “0” and a standard deviation of “1.” We will initialize bias to “0.”
W = tf$Variable(tf$random_normal(shape(ncol(x),2L),
stddev = 1.0),
name = "weghts")
b = tf$Variable(tf$zeros(shape(2L)), name = "bias")
#Then we will compute the logit.
logits = tf$add(tf$matmul(X, W), b)
pred = tf$nn$sigmoid(logits)
#The next step is to define the loss function. We will use sigmoid cross entropy with logits as a loss function.
entropy = tf$nn$sigmoid_cross_entropy_with_logits(labels = Y,
logits = logits)
loss = tf$reduce_mean(entropy,name = "loss")
#The last step of the model composition is to define the training op. We will use a gradient descent with a learning rate 0.1 to minimize cost.
optimizer = tf$train$GradientDescentOptimizer(learning_rate = learning_rate)$minimize(loss)
init_op = tf$global_variables_initializer()
#Now that we have trained the model, let’s evaluate it:
correct_prediction <- tf$equal(tf$argmax(logits, 1L), tf$argmax(Y, 1L),
name = "correct_pred")
accuracy <- tf$reduce_mean(tf$cast(correct_prediction, tf$float32),
name = "accuracy")
#Having structured the graph, let’s execute it:
with(tf$Session() %as% sess, {
sess$run(init_op)
for (i in 1:5000) {
sess$run(optimizer,
feed_dict = dict(X=x_train, Y=y_train))
}
sess$run(accuracy,
feed_dict=dict(X = x_test, Y = y_test))
})
The accuracy obtained by glm() method is quite good (accuracy=0.95), which is as expected; however, the accuracy was only 0.68 with TensorFlow method. How can I solve the problem?
