Set of functions to download datasets from Kaggle

kaggle.R

### Set of functions to download datasets from Kaggle

# Usage:
#   
#   > train <- kaggle_get_file("train.csv",
#   +                          competition.name = "titanic-gettingStarted",
#   +                          username = "username",
#   +                          password = "password")
#
#   > head(train, n = 2)
#
#   PassengerId Survived Pclass                                                Name    Sex Age SibSp Parch
#   1           1        0      3                             Braund, Mr. Owen Harris   male  22     1     0
#   2           2        1      1 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female  38     1     0
#   Ticket    Fare Cabin Embarked
#   1 A/5 21171  7.2500              S
#   2  PC 17599 71.2833   C85        C
#
#   > cat(attr(train,"desc"))
#
#   VARIABLE DESCRIPTIONS:
#     survival        Survival
#   (0 = No; 1 = Yes)
#   pclass          Passenger Class
#   (1 = 1st; 2 = 2nd; 3 = 3rd)
#   name            Name
#   ...
#

require("rvest")
require("magrittr")
require("plyr")

BASE.URL <- "https://www.kaggle.com"

kaggle_login <- function(username, password) {
  login.url <- paste0(BASE.URL, "/account/login")
  
  session <- html_session(login.url)
  frm <- html_form(session)[[2]] %>%
    set_values(UserName = username, Password = password)
  frm$url <- paste0(BASE.URL, frm$url)
  
  submit_form(session,frm)
  
  return(session)
}

kaggle_data <- function(competition.name, username = NA, password = NA, session = NA) {
  data.url <- paste0(BASE.URL,"/c/",competition.name,"/data")
  
  if (is.na(session)) {
    session <- kaggle_login(username, password)
  }
  
  df.page <- jump_to(session, data.url)
  
  data.files <- df.page %>%
    html_nodes("#data-files") %>%
    html_nodes("a") %>%
    html_attrs()  %>%
    ldply()
  
  data.files$href <- paste0(BASE.URL,data.files$href)
  
  desc <- df.page %>%
    html_nodes(".cms-page > pre") %>%
    html_text()
  
  return(structure(data.files,
                   desc = desc,
                   session = session))
}

kaggle_get_file <- function(file.name = "train.csv",
                            competition.name = NA,
                            username = NA,
                            password = NA,
                            session = NA,
                            kaggle.data = NA) {

  if (is.na(kaggle.data)) {
    kaggle.data <- kaggle_data(competition.name, username, password, session)
  }
  session <- attr(kaggle.data,"session")
  
  train.url <- subset(kaggle.data, name == file.name)$href[1]
  
  df <- httr::content(jump_to(session, train.url)$response)
  return(structure(df,
                   session = session,
                   desc = attr(kaggle.data,"desc")))
}