Issue #153: fix warnings about usage of deprecated "dplyr::arrange_()" and "dplyr::select_()" functions

dataCompareR/DESCRIPTION

@@ -39,11 +39,13 @@ Imports:
     dplyr (>= 0.5.0),
     knitr,
     stringi,
-    markdown
+    markdown,
+    tidyselect
 URL: https://github.com/capitalone/dataCompareR
 BugReports: https://github.com/capitalone/dataCompareR/issues
 License: Apache License 2.0 | file LICENSE
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.3
+Encoding: UTF-8
 Suggests:
     testthat,
     data.table,

dataCompareR/NAMESPACE

@@ -10,18 +10,19 @@ import(knitr)
 import(markdown)
 import(stringi)
 importFrom(dplyr,"%>%")
+importFrom(dplyr,across)
 importFrom(dplyr,arrange)
-importFrom(dplyr,arrange_)
 importFrom(dplyr,distinct)
 importFrom(dplyr,filter)
 importFrom(dplyr,funs)
 importFrom(dplyr,inner_join)
 importFrom(dplyr,mutate)
 importFrom(dplyr,mutate_all)
+importFrom(dplyr,rename_with)
 importFrom(dplyr,sample_n)
 importFrom(dplyr,select)
-importFrom(dplyr,select_)
 importFrom(dplyr,summarise)
+importFrom(tidyselect,all_of)
 importFrom(utils,capture.output)
 importFrom(utils,head)
 importFrom(utils,packageVersion)

dataCompareR/NEWS.md

@@ -1,3 +1,8 @@
+# dataCompareR 0.1.5
+
+Fix warnings about usage of deprecated `dplyr::arrange_()` and `dplyr::select_()`
+functions (#153).
+
 # dataCompareR 0.1.4
 
 Bug fix and minor improvement:

dataCompareR/R/cd_compareData.R

@@ -1,30 +1,30 @@
-# SPDX-Copyright: Copyright (c) Capital One Services, LLC 
-# SPDX-License-Identifier: Apache-2.0 
-# Copyright 2017 Capital One Services, LLC 
+# SPDX-Copyright: Copyright (c) Capital One Services, LLC
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2017 Capital One Services, LLC
 #
-# Licensed under the Apache License, Version 2.0 (the "License"); 
-# you may not use this file except in compliance with the License. 
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
 #
-# You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 
+# You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
 #
-# Unless required by applicable law or agreed to in writing, software distributed 
+# Unless required by applicable law or agreed to in writing, software distributed
 # under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
-# OF ANY KIND, either express or implied. 
-# 
-# See the License for the specific language governing permissions and limitations under the License. 
+# OF ANY KIND, either express or implied.
+#
+# See the License for the specific language governing permissions and limitations under the License.
 
 
 #' Compare data. Wrapper for comparison functionality.
 #'
 #' @param DFA dataframe as returned from prepareData
 #' @param DFB dataframe as returned from prepareData
 #' @param keys vector of chars - names of index variables
-#' @param maxMismatches Integer. The max number of mismatches to assess, after which dataCompareR will stop 
+#' @param maxMismatches Integer. The max number of mismatches to assess, after which dataCompareR will stop
 #' (without producing a dataCompareR object). Designed to improve performance for large datasets.
 #' @return mismatchObject containing mismatch data for each of the variables in
 #'         the dataframes
 #'
-#' @examples 
+#' @examples
 #'\dontrun{compareData(iris, iris)}
 #'
 #'\dontrun{iris2 <- iris}

dataCompareR/R/cd_createMismatchObject.R

@@ -1,16 +1,16 @@
-# SPDX-Copyright: Copyright (c) Capital One Services, LLC 
-# SPDX-License-Identifier: Apache-2.0 
-# Copyright 2017 Capital One Services, LLC 
+# SPDX-Copyright: Copyright (c) Capital One Services, LLC
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2017 Capital One Services, LLC
 #
-# Licensed under the Apache License, Version 2.0 (the "License"); 
-# you may not use this file except in compliance with the License. 
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
 #
-# You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 
+# You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
 #
-# Unless required by applicable law or agreed to in writing, software distributed 
+# Unless required by applicable law or agreed to in writing, software distributed
 # under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
-# OF ANY KIND, either express or implied. 
-# 
+# OF ANY KIND, either express or implied.
+#
 
 #' Create mismatch object
 #'
@@ -24,8 +24,8 @@
 #' @examples
 #'\dontrun{createMismatchObject(dataA, dataB, mism, idx)}
 createMismatchObject <- function(dat_a, dat_b, dat_eq, str_index) {
-  
-  
+
+
   # Initialise output object
   out <- list()
 
@@ -34,8 +34,8 @@ createMismatchObject <- function(dat_a, dat_b, dat_eq, str_index) {
   if(nrow(dat_a)==0) {
     return(out)
   }
-  
-  
+
+
   # Loop over variables to create output, ignoring index variable
   varnames <- names(dat_a)[!(names(dat_a) %in% str_index)]
   for (v in varnames) {
@@ -78,7 +78,7 @@ variableMismatches <- function(varname, vals_a, vals_b, vector_eq) {
   if ("__temprowname__" %in% names(d)) {
     d[, "__temprowname__"] <- NULL
   }
-  
+
   d[,'variable'] <- varname
   return(d)
 }
@@ -89,7 +89,7 @@ variableMismatches <- function(varname, vals_a, vals_b, vector_eq) {
 #'
 #' @return mismatch details
 variableDetails <- function(dat) {
-  
+
 
   class_a <- collapseClasses(dat[, "valueA"])
   class_b <- collapseClasses(dat[, "valueB"])
@@ -106,6 +106,6 @@ variableDetails <- function(dat) {
   } else {
     dat[, "diffAB"] <- ""
   }
-  
+
   return(dat)
 }

dataCompareR/R/cd_locateMismatches.R

@@ -1,22 +1,22 @@
-# SPDX-Copyright: Copyright (c) Capital One Services, LLC 
-# SPDX-License-Identifier: Apache-2.0 
-# Copyright 2017 Capital One Services, LLC 
+# SPDX-Copyright: Copyright (c) Capital One Services, LLC
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2017 Capital One Services, LLC
 #
-# Licensed under the Apache License, Version 2.0 (the "License"); 
-# you may not use this file except in compliance with the License. 
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
 #
-# You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 
+# You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
 #
-# Unless required by applicable law or agreed to in writing, software distributed 
+# Unless required by applicable law or agreed to in writing, software distributed
 # under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
-# OF ANY KIND, either express or implied. 
+# OF ANY KIND, either express or implied.
 
 #' collapseClasses. Collapse the classes of an object to a single string
 #'
 #' @param x any object
 #' @return a string listing the classes of x, separated by commas
 #'
-#' @examples 
+#' @examples
 #'\dontrun{collapseClasses(iris)}
 #'\dontrun{collapseClasses("hello")}
 collapseClasses <- function(x) {
@@ -41,15 +41,15 @@ mismatchHighStop <- function(trueFalseMatrix, maxMismatches) {
 }
 
 #' Checks whether elements in two input data frames are equal.
-#' 
+#'
 #' @param DFA input data frame
-#' @param DFB input data frame  
-#' @param maxMismatches Integer. The max number of mismatches to assess, after which dataCompareR will stop 
+#' @param DFB input data frame
+#' @param maxMismatches Integer. The max number of mismatches to assess, after which dataCompareR will stop
 #' (without producing a dataCompareR object). Designed to improve performance for large datasets.
 #' @param keys character vector of index variables
-#' 
+#'
 #' @importFrom dplyr mutate_all
-#' 
+#'
 #' @return data frame containing keys and boolean logic of match/no match for each element
 #'         If data types are not equal returns FALSE. Treats NA and NaN as unequal.
 locateMismatches <- function(DFA, DFB, keys=NULL, maxMismatches=NA){
@@ -58,84 +58,84 @@ locateMismatches <- function(DFA, DFB, keys=NULL, maxMismatches=NA){
   if(nrow(DFA)==0) {
     return(data.frame())
   }
-  
+
     # col names
   colNames <- names(DFA)
-  
+
   # drop keys
   colCompare <- setdiff(colNames,keys)
-  
+
   #print(dim(DFA))
   #print(dim(DFB))
-  
+
   # find vars where type different excluding keys
-  colTypeDiff <- sapply(select_(DFA,.dots=colCompare), collapseClasses) == sapply(select_(DFB,.dots=colCompare), collapseClasses)
+  colTypeDiff <- sapply(select(DFA, all_of(colCompare)), collapseClasses) == sapply(select(DFB, all_of(colCompare)), collapseClasses)
   cols2Compare <- names(colTypeDiff[colTypeDiff==T])
-  
+
   # select columns to compare
   if(length(cols2Compare)>0) {
-    
+
     # First find matching cols with identical
     matchingCols <- vector(mode = 'logical', length = length(cols2Compare))
     for(i in 0:length(cols2Compare)) {
       matchingCols[i] <- identical(DFA[,cols2Compare[i]], DFB[,cols2Compare[i]])
     }
-    
+
     # Get names of full matches
     colsFullMatch <- cols2Compare[matchingCols]
-    
+
     # Create a list of cols with diffs
     cols2Diff <- setdiff(cols2Compare, colsFullMatch)
-    
+
     if(length(cols2Diff) > 0) {
-      
-      # Now handle the cases where we're not equal 
-      
+
+      # Now handle the cases where we're not equal
+
       # Get these cols once
-      subsetA <- select_(DFA,.dots = cols2Diff)
-      subsetB <- select_(DFB,.dots = cols2Diff)
-      
+      subsetA <- select(DFA, all_of(cols2Diff))
+      subsetB <- select(DFB, all_of(cols2Diff))
+
       # Look for NA's
       isNA_A <- mutate_all(subsetA, .funs = is.na)
       isNA_B <- mutate_all(subsetB, .funs = is.na)
-      
+
       # Find any cells impacted by NA's
       anyNA <- isNA_A | isNA_B
-      
+
       # and repeat the above for NAN's
       isNaN_A <- mutate_all(subsetA, .funs = is.nan)
       isNaN_B <- mutate_all(subsetB, .funs = is.nan)
       anyNaN <- isNaN_A | isNaN_B
-      
+
       # find matching NA or NaNs
       matchNA <- isNA_A == isNA_B
       matchNaN <- isNaN_A == isNaN_B
-      
+
       # Create a naive summary of matches first
       compareTF <- subsetA == subsetB
-      
+
       # Check for mismatch count, stop if exceeded
       mismatchHighStop(compareTF,maxMismatches)
-      
+
       # And then a somewhat confusing hierarchy...
       # If we get a true or a false from matchAnyway, this is correct
       # Otherwise, if they are both NA, we need to look at NA and NaN
-      
+
       # Cols that have a NaN - overwrite with NaN matching status
       compareTF[anyNA] <- matchNA[anyNA]
-      
+
       # Check for mismatch count, stop if exceeded
       mismatchHighStop(compareTF,maxMismatches)
-      
+
       # and For NA's
       compareTF[anyNaN] <- matchNaN[anyNaN]
-      
+
       # Check for mismatch count, stop if exceeded
       mismatchHighStop(compareTF,maxMismatches)
-      
+
       # Make a DF
       compareTF <- as.data.frame(compareTF)
-      
+
       # Add in cols that full match as all T
       compareTF[,colsFullMatch] <- TRUE
     }
@@ -149,21 +149,21 @@ locateMismatches <- function(DFA, DFB, keys=NULL, maxMismatches=NA){
         compareTF <- data.frame()
       }
     }
-    
-    
-    
+
+
+
   }
   else {
     compareTF <- data.frame()
   }
-  
+
   # not compared
   colsNot2Compare <- names(colTypeDiff[colTypeDiff==F])
-  
+
   # ID only
   mismatchOut <- data.frame(DFA[,keys], stringsAsFactors = FALSE)
   names(mismatchOut) <- keys
-  
+
   if(nrow(compareTF) > 0) {
     # We have some matching rows, proceed as normal
     mismatchOut <- cbind(mismatchOut,compareTF)
@@ -174,22 +174,22 @@ locateMismatches <- function(DFA, DFB, keys=NULL, maxMismatches=NA){
     for(i in colsNot2Compare) {
       mismatchOut[i] <- FALSE
     }
-    
-    
+
+
   }
-  
-  
-  
+
+
+
   # output columns in same order as input data frames
   # if statement handles cases where we have no overlap
   if(nrow(mismatchOut) == 0) {
     mismatchOut <- data.frame()
   } else {
-    mismatchOut <- mismatchOut %>% select_(.dots=colNames)
+    mismatchOut <- mismatchOut %>% select(all_of(colNames))
   }
-  
+
   return(mismatchOut)
-  
+
 }