Merge pull request #30 from tidymodels/no-right-join

topepo · web-flow · commit 9a14b1d0660e · 2020-06-27T15:33:00.000-04:00
Remove right join from k-means
diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
@@ -1,4 +1,10 @@
-on: [push, pull_request]
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
 
 name: R-CMD-check
 
@@ -13,13 +19,13 @@ jobs:
       matrix:
         config:
           - {os: macOS-latest,   r: 'devel'}
-          - {os: macOS-latest,   r: '4.0'}
-          - {os: windows-latest, r: '4.0'}
-          - {os: ubuntu-16.04,   r: '4.0', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
-          - {os: ubuntu-16.04,   r: '3.6', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
-          - {os: ubuntu-16.04,   r: '3.5', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
-          - {os: ubuntu-16.04,   r: '3.4', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
-          - {os: ubuntu-16.04,   r: '3.3', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: macOS-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+          - {os: ubuntu-16.04,   r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-16.04,   r: 'oldrel',  rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-16.04,   r: '3.5',     rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-16.04,   r: '3.4',     rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-16.04,   r: '3.3',     rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
 
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
@@ -39,15 +45,16 @@ jobs:
         run: |
           install.packages('remotes')
           saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
+          writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
         shell: Rscript {0}
 
       - name: Cache R packages
         if: runner.os != 'Windows'
         uses: actions/cache@v1
         with:
           path: ${{ env.R_LIBS_USER }}
-          key: ${{ runner.os }}-r-${{ matrix.config.r }}-1-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-1-
+          key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-
 
       - name: Install system dependencies
         if: runner.os == 'Linux'
diff --git a/.github/workflows/pkgdown.yaml b/.github/workflows/pkgdown.yaml
@@ -20,14 +20,15 @@ jobs:
         run: |
           install.packages('remotes')
           saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
+          writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
         shell: Rscript {0}
 
       - name: Cache R packages
         uses: actions/cache@v1
         with:
           path: ${{ env.R_LIBS_USER }}
-          key: macOS-r-4.0-1-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: macOS-r-4.0-1-
+          key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-
 
       - name: Install dependencies
         run: |
diff --git a/.github/workflows/test-coverage.yaml b/.github/workflows/test-coverage.yaml
@@ -24,14 +24,15 @@ jobs:
         run: |
           install.packages('remotes')
           saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
+          writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
         shell: Rscript {0}
 
       - name: Cache R packages
         uses: actions/cache@v1
         with:
           path: ${{ env.R_LIBS_USER }}
-          key: macOS-r-4.0-1-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: macOS-r-4.0-1-
+          key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-
 
       - name: Install dependencies
         run: |
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -27,6 +27,6 @@ Suggests:
 License: GPL-3
 URL: https://modeldb.tidymodels.org, https://github.com/tidymodels/modeldb
 BugReports: https://github.com/tidymodels/modeldb/issues
-RoxygenNote: 7.0.2
+RoxygenNote: 7.1.0.9000
 Encoding: UTF-8
 VignetteBuilder: knitr
diff --git a/NAMESPACE b/NAMESPACE
@@ -17,18 +17,19 @@ importFrom(dplyr,bind_cols)
 importFrom(dplyr,case_when)
 importFrom(dplyr,collect)
 importFrom(dplyr,contains)
+importFrom(dplyr,everything)
 importFrom(dplyr,filter)
 importFrom(dplyr,filter_all)
 importFrom(dplyr,funs)
 importFrom(dplyr,group_by)
 importFrom(dplyr,group_vars)
 importFrom(dplyr,lag)
+importFrom(dplyr,left_join)
 importFrom(dplyr,mutate)
 importFrom(dplyr,n)
 importFrom(dplyr,pull)
 importFrom(dplyr,rename)
 importFrom(dplyr,rename_all)
-importFrom(dplyr,right_join)
 importFrom(dplyr,select)
 importFrom(dplyr,summarise)
 importFrom(dplyr,summarise_all)
diff --git a/R/kmeans.R b/R/kmeans.R
@@ -87,11 +87,12 @@ simple_kmeans_db <- function(df,
     if (all(prev_centroids == centroids)) break()
   }
   centroids_db <- rename_all(centroids_db, ~paste0("k_", .))
-  right_join(
+  joined <- left_join(
+    rename(new_centroids, k_center = center), 
     centroids_db,
-    new_centroids, 
-    by = c("k_center" = "center")
+    by = "k_center"
     )
+  select(joined, contains("k_"), everything())
 }
 
 calculate_centers <- function(df, center_df, centers, vars) {
diff --git a/R/modeldb.R b/R/modeldb.R
@@ -1,15 +1,15 @@
 #' @import rlang
 #' @import ggplot2
 #' @import tibble
-#' @importFrom dplyr mutate summarise right_join
+#' @importFrom dplyr mutate summarise left_join
 #' @importFrom dplyr summarise_all filter_all
 #' @importFrom dplyr pull collect arrange 
 #' @importFrom dplyr contains tally ungroup
 #' @importFrom dplyr group_vars lag bind_cols
 #' @importFrom dplyr all_vars group_by funs
 #' @importFrom dplyr n as_tibble filter select
 #' @importFrom dplyr case_when rename rename_all 
-#' @importFrom dplyr tbl_vars
+#' @importFrom dplyr tbl_vars everything
 #' @importFrom purrr map map2 map_df transpose
 #' @importFrom purrr reduce imap pluck
 #' @importFrom tidypredict as_parsed_model
diff --git a/man/modeldb-package.Rd b/man/modeldb-package.Rd

Original file line number	Diff line number	Diff line change
`@@ -87,11 +87,12 @@ simple_kmeans_db <- function(df,`
`87`	`87`	`if (all(prev_centroids == centroids)) break()`
`88`	`88`	`}`
`89`	`89`	`centroids_db <- rename_all(centroids_db, ~paste0("k_", .))`
`90`		`- right_join(`
	`90`	`+ joined <- left_join(`
	`91`	`+ rename(new_centroids, k_center = center),`
`91`	`92`	`centroids_db,`
`92`		`- new_centroids,`
`93`		`- by = c("k_center" = "center")`
	`93`	`+ by = "k_center"`
`94`	`94`	`)`
	`95`	`+ select(joined, contains("k_"), everything())`
`95`	`96`	`}`
`96`	`97`
`97`	`98`	`calculate_centers <- function(df, center_df, centers, vars) {`