stabilize code base

.Rbuildignore

@@ -17,3 +17,4 @@
 ^_kaggle_data$
 ^FUNDING\.yml$
 ^dev_notes\.R
+^dev$

DESCRIPTION

@@ -34,11 +34,12 @@ Imports:
     tibble,
     usethis
 Suggests: 
+    covr,
     knitr,
     rmarkdown
 VignetteBuilder: 
     knitr
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.3

R/api.R

@@ -46,8 +46,7 @@ kgl_api_get <- function(path, ..., body = NULL, auth = kgl_auth()) {
   r <- httr::GET(
     url = get_url,
     body = body,
-    auth,
-    httr::verbose()
+    auth
   )
 
   ## check status
@@ -100,7 +99,7 @@ kgl_request <- function(
   endpoint,
   ...,
   body = NULL
-) {
+    ) {
   resp <-
     .kaggle_base_url %>%
     httr2::request() %>%

R/auth.R

@@ -66,7 +66,6 @@ kgl_auth <- function(req = NULL, username = NULL, key = NULL, creds_file = NULL)
 
     ## alternatively, users can provide path to (or text of) creds_file
   } else if (!is.null(creds_file)) {
-
     ## read and parse kaggle.json creds file if it exists
     if (file.exists(creds_file)) {
       con <- file(creds_file)

R/competition-submissions.R

@@ -16,7 +16,7 @@ kgl_competitions_list_submissions <- function(
   id,
   page = 1,
   clean_response = TRUE
-) {
+    ) {
   encoded_params <- url_encode(id)
 
   endpoint <- glue::glue("/competitions/submissions/list/{encoded_params}")
@@ -48,7 +48,7 @@ kgl_competitions_list_submissions <- function(
 kgl_competitions_submissions_url <- function(
   id,
   file
-) {
+    ) {
   ## TODO Check if file is a dataset, if it is, prompt user to save it.
 
   content_length <- file.size(file)
@@ -85,7 +85,7 @@ kgl_competitions_submissions_url <- function(
 kgl_competitions_submissions_upload <- function(
   file,
   create_url
-) {
+    ) {
   content_length <- file.size(file)
 
   last_modified_date_utc <-
@@ -119,7 +119,7 @@ kgl_competitions_submissions_submit <- function(
   id,
   blob_file_tokens,
   submission_description
-) {
+    ) {
   encoded_params <- url_encode(id)
 
   endpoint <- glue::glue("competitions/submissions/submit/{encoded_params}")
@@ -160,7 +160,7 @@ kgl_competition_submit <- function(
   id,
   file,
   submission_description = ""
-) {
+    ) {
   url_result <- kgl_competitions_submissions_url(
     id = id,
     file = file

R/competitions-data.R

@@ -50,7 +50,7 @@ kgl_competitions_data_download <- function(
   file_name,
   output_dir = ".",
   clean_response = TRUE
-) {
+    ) {
   assertthat::assert_that(
     assertthat::is.string(id),
     assertthat::is.string(file_name),
@@ -59,6 +59,8 @@ kgl_competitions_data_download <- function(
     assertthat::is.flag(clean_response)
   )
 
+  cat("  - Downloading", file_name, "\n")
+
   if (!fs::file_exists(output_dir)) {
     stop("output_dir does not exist!")
   }
@@ -110,7 +112,7 @@ kgl_competitions_data_download_all <- function(
   id,
   output_dir = ".",
   clean_response = TRUE
-) {
+    ) {
   assertthat::assert_that(
     assertthat::is.string(id),
     assertthat::is.string(output_dir),

R/competitions-leaderboard.R

@@ -11,7 +11,7 @@ kgl_competitions_leaderboard_download <- function(
   id,
   output_dir = ".",
   clean_response = TRUE
-) {
+    ) {
   assertthat::assert_that(
     assertthat::is.string(id),
     assertthat::is.string(output_dir),
@@ -55,7 +55,7 @@ kgl_competitions_leaderboard_download <- function(
 kgl_competitions_leaderboard_view <- function(
   id,
   clean_response = TRUE
-) {
+    ) {
   assertthat::assert_that(
     assertthat::is.string(id),
     assertthat::is.flag(clean_response)

R/competitions.R

@@ -15,7 +15,7 @@ kgl_competitions_list <- function(
   page = 1,
   search = NULL,
   clean_response = TRUE
-) {
+    ) {
   assertthat::assert_that(
     assertthat::is.number(page),
     is.null(search) || assertthat::is.string(search),

R/datasets.R

@@ -13,7 +13,7 @@ kgl_datasets_list <- function(
   search = NULL,
   owner_dataset = NULL,
   clean_response = TRUE
-) {
+    ) {
   assertthat::assert_that(
     assertthat::is.number(page),
     is.null(search) || assertthat::is.string(search),
@@ -130,7 +130,7 @@ kgl_datasets_download <- function(
   owner_dataset,
   fileName,
   datasetVersionNumber = NULL
-) {
+    ) {
   owner_dataset_clean <- owner_dataset_parser(owner_dataset)
   owner_slug <- owner_dataset_clean[1]
   dataset_slug <- owner_dataset_clean[2]
@@ -156,7 +156,7 @@ kgl_datasets_upload_file <- function(
   fileName,
   contentLength,
   lastModifiedDateUtc
-) {
+    ) {
   contentLength <- file.size(fileName)
   lastModifiedDateUtc <- format(
     file.info(fileName)$mtime,
@@ -183,7 +183,7 @@ kgl_datasets_upload_file <- function(
 kgl_datasets_create_version <- function(
   owner_dataset,
   datasetNewVersionRequest
-) {
+    ) {
   owner_dataset_clean <- owner_dataset_parser(owner_dataset)
   owner_slug <- owner_dataset_clean[1]
   dataset_slug <- owner_dataset_clean[2]

R/kgl_flow.R

@@ -98,12 +98,13 @@ kgl_flow <- function(id = NULL) {
 
     usethis::ui_todo(
       "These files will be downloaded:
-      {v_needs_to_download}."
+      {v_needs_to_download}
+      ------"
     )
 
     d_info <-
       v_to_download %>%
-      purrr::map_dfr(~ {
+      purrr::map(~ {
         d <- kgl_competitions_data_download(
           id = competition_id,
           file_name = .x,
@@ -143,10 +144,10 @@ kgl_flow <- function(id = NULL) {
       data_list %>%
         dplyr::mutate(name = name_old) %>%
         dplyr::select(-name_old) %>%
-        dplyr::left_join(
-          y = d_info,
-          by = "name"
-        ) %>%
+        # dplyr::left_join(
+        #   y = d_info,
+        #   by = "name"
+        # ) %>%
         saveRDS(file = path_meta)
     }
   } else {

R/kgl_flow_leaderboard.R

@@ -15,7 +15,6 @@
 #' kgl_flow_leaderboard()
 #' }
 kgl_flow_leaderboard <- function() {
-
   # usethis::ui_todo("Validating Project and Competition ID")
 
   ## Set up directories and paths

R/kgl_flow_load.R

@@ -2,6 +2,7 @@
 #'
 #' If all of the files in `_kaggle_data` are in **csv** format (excluding the meta directory) then this function will load all of the kaggle data into the current environment (or the environment of your choosing) via `readr::read_csv()`.
 #'
+#' @inheritDotParams readr::read_csv
 #' @param envir Environment to put the loaded kaggle data.
 #'
 #' @return Nothing.
@@ -14,7 +15,7 @@
 #'
 #' kgl_flow_load()
 #' }
-kgl_flow_load <- function(..., prefix = "", envir = parent.frame()) {
+kgl_flow_load <- function(..., envir = parent.frame()) {
   # d_meta <- kgl_flow_meta()
 
   dir_kgl <- usethis::proj_path(.kgl_dir)
@@ -36,9 +37,9 @@ kgl_flow_load <- function(..., prefix = "", envir = parent.frame()) {
       fs::path_file() %>%
       fs::path_ext_remove()
 
-    if (prefix != "") {
-      v_file_names <- paste0(prefix, "_", v_file_names)
-    }
+    # if (prefix != "") {
+    #   v_file_names <- paste0(prefix, "_", v_file_names)
+    # }
 
     l_d <-
       v_files_to_iterate_over %>%

R/kgl_flow_utils.R

@@ -3,7 +3,7 @@ validator_path_competition_id <- function(
   competition_id,
   dir_path,
   dir_meta
-) {
+    ) {
   if (fs::file_exists(path_competition_id)) {
     logged_competition_id <- readLines(path_competition_id)[2]
 
@@ -56,7 +56,7 @@ kgl_flow_data_download <- function(
   competition_id,
   file_name,
   dir_name
-) {
+    ) {
   get_url <- glue::glue("competitions/data/download/{competition_id}/{file_name}")
 
   get_request <- kgl_api_get(get_url)

R/utils.R

@@ -9,21 +9,24 @@
 #' @param x Output from kaggle function
 #' @return Print out of summary info and a tibble of the data.
 kgl_as_tbl <- function(x) {
-  x <-
+  d <-
     x %>%
     purrr::map_dfr(~ .x %||% NA) %>%
     tibble::as_tibble(
       .name_repair = snakecase::to_snake_case
-    ) %>%
-    readr::type_convert(col_types = readr::cols())
+    )
 
-  return(x)
+  if (nrow(d) > 0) {
+    d <- readr::type_convert(d, col_types = readr::cols())
+  }
+
+  return(d)
 }
 
 url_encode <- function(...) {
   list(...) %>%
     purrr::map_chr(as.character) %>%
-    purrr::map_chr(URLencode, reserved = TRUE) %>%
+    purrr::map_chr(utils::URLencode, reserved = TRUE) %>%
     stringr::str_c(collapse = "/")
 }
 

README.Rmd

@@ -36,7 +36,7 @@ You can install the dev version of **{kaggler}** from [CRAN](https://github.com/
 
 ```{r, eval = FALSE}
 ## install kaggler package from github
-devtools::install_packages("koderkow/kaggler")
+devtools::install_github("koderkow/kaggler")
 ```
 
 # API Authorization
@@ -54,10 +54,6 @@ Browse or search for Kaggle competitions.
 comps1 <- kgl_competitions_list()
 comps1
 
-## it's paginated, so to see page two:
-comps2 <- kgl_competitions_list(page = 2)
-comps2
-
 ## search by keyword for competitions
 imagecomps <- kgl_competitions_list(search = "image")
 imagecomps
@@ -67,12 +63,34 @@ You can look up the datalist for a given Kaggle competition using the API.
 
 ```{r}
 ## data list for a given competition
-c1_datalist <- kgl_competitions_data_list(comps1$ref[1])
+c1_datalist <- kgl_competitions_data_list("titanic")
 c1_datalist
 ```
 
 For a more in-depth walkthrough visit the [Kaggle API](https://koderkow.github.io/kaggler/articles/kaggle-api.html) page.
 
+# Kaggle Flow
+
+This is an **experimental** and **opinionated** reproducible workflow
+for working with Kaggle competitions.
+
+``` r
+library(kaggler)
+
+kgl_flow("titanic")
+
+#> • These files will be downloaded:
+#>   - 'gender_submission'
+#>   - 'test'
+#>   - 'train'.
+#> • Downloading 'gender_submission.csv'...
+#> • Downloading 'test.csv'...
+#> • Downloading 'train.csv'...
+```
+
+For a more in-depth walkthrough visit the [Kaggle
+Flow](https://koderkow.github.io/kaggler/articles/kgl-flow.html) page.
+
 ## Note(s)
 
 - The base of this package was cloned from the original at [{kaggler}](https://github.com/mkearney/kaggler). I have decided to take the developers work and continue their amazing development! Major props and recognition goes out to the original developer(s) of this package.