tengpeng

mosh --ssh="/usr/bin/ssh -i ./spot.pem" [email protected] --server="/usr/bin/mosh-server"

tengpeng

install.packages("devtools")
devtools::install_github("slowkow/ggrepel")

tengpeng

install.packages(c('shinyIncubator','markdown','whisker','Hmisc','qcc','httr','RCurl','curl','devtools'), repos='http://cran.rstudio.com/')
devtools::install_github("ropensci/ckanr")
ckanr::ckanr_setup(url="http://catalogue-beta.data.wa.gov.au/")

tengpeng

mkdir -p /var/projects/rstudio-server
docker run -d \
-p 8787:8787 \
-e USER=<username> \
-e PASSWORD=<password> \
-v /var/projects/rstudio-server/:/home/ \
rocker/ropensci

tengpeng

sudo docker run -it --device /dev/nvidiactl --device /dev/nvidia-uvm --device /dev/nvidia0 kaixhin/cuda-mxnet:7.0

tengpeng

""" Amazon Access Challenge Starter Code

These files provide some starter code using 
the scikit-learn library. It provides some examples on how
to design a simple algorithm, including pre-processing,
training a logistic regression classifier on the data,
assess its performance through cross-validation and some 
pointers on where to go next.

Paul Duan <[email protected]>

tengpeng

# Do bagging
tmpP = rep(0,nrow(test))
for (j in 1:30) {
set.seed(j+200)
print(j)
bst = xgb.train(param=param, data=xgtrain, nrounds=1200)

tmpP = tmpP + predict(bst,xgtest)
}

tengpeng

train$month <- as.integer(format(train$Original_Quote_Date, "%m"))
train$year <- as.integer(format(train$Original_Quote_Date, "%y"))
train$day <- weekdays(as.Date(train$Original_Quote_Date))

tengpeng

impute.med <- function(x) replace(x, is.na(x), median(x, na.rm = TRUE))
df_all <- sapply(df_all, function(x){
  if(is.numeric(x)){
    impute.med(x)
  } else {
    x
  }
}
)

tengpeng

# To do it for all names
col_names <- names(df_all)
# do do it for some names in a vector named 'col_names'
df_all[,col_names] <- lapply(df_all[,col_names] , factor)