remaming of package and functions to inspect - more accuract that rep…

…orter

DESCRIPTION

@@ -1,5 +1,5 @@
-Package: reporter
-Title: Tools for Exploring and Comparing Data Frames
+Package: inspectdf
+Title: Inspection, Comparison and Visualisation of Data Frames
 Version: 0.0.0.9000
 Authors@R: person("Alastair", "Rushworth", email = "alastairmrushworth@gmail.com", role = c("aut", "cre"))
 Maintainer: Alastair Rushworth <alastairmrushworth@gmail.com>

NAMESPACE

@@ -1,12 +1,12 @@
 # Generated by roxygen2: do not edit by hand
 
-export(report_cat)
-export(report_cor)
-export(report_imb)
-export(report_mem)
-export(report_na)
-export(report_num)
-export(report_types)
+export(inspect_cat)
+export(inspect_cor)
+export(inspect_imb)
+export(inspect_mem)
+export(inspect_na)
+export(inspect_num)
+export(inspect_types)
 importFrom(dplyr,anti_join)
 importFrom(dplyr,arrange)
 importFrom(dplyr,bind_cols)
@@ -78,4 +78,4 @@ importFrom(tidyr,gather)
 importFrom(tidyr,replace_na)
 importFrom(utils,object.size)
 importFrom(utils,tail)
-useDynLib(reporter)
+useDynLib(inspectdf)

R/RcppExports.R

@@ -2,26 +2,26 @@
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
 count_levels_num <- function(x) {
-    .Call('_reporter_count_levels_num', PACKAGE = 'reporter', x)
+    .Call('_inspectdf_count_levels_num', PACKAGE = 'inspectdf', x)
 }
 
 count_levels_char <- function(x) {
-    .Call('_reporter_count_levels_char', PACKAGE = 'reporter', x)
+    .Call('_inspectdf_count_levels_char', PACKAGE = 'inspectdf', x)
 }
 
 na_numeric <- function(x) {
-    .Call('_reporter_na_numeric', PACKAGE = 'reporter', x)
+    .Call('_inspectdf_na_numeric', PACKAGE = 'inspectdf', x)
 }
 
 na_character <- function(x) {
-    .Call('_reporter_na_character', PACKAGE = 'reporter', x)
+    .Call('_inspectdf_na_character', PACKAGE = 'inspectdf', x)
 }
 
 na_logical <- function(x) {
-    .Call('_reporter_na_logical', PACKAGE = 'reporter', x)
+    .Call('_inspectdf_na_logical', PACKAGE = 'inspectdf', x)
 }
 
 na_integer <- function(x) {
-    .Call('_reporter_na_integer', PACKAGE = 'reporter', x)
+    .Call('_inspectdf_na_integer', PACKAGE = 'inspectdf', x)
 }
 

R/report_cat.R → R/inspect_cat.R

@@ -1,4 +1,4 @@
-#' Report and compare the levels within each categorical feature in one or two dataframes.
+#' Summarise and compare the levels within each categorical feature in one or two dataframes.
 #'
 #' @param df1 A dataframe
 #' @param df2 An optional second data frame for comparing categorical levels.  
@@ -35,11 +35,11 @@
 #' @export
 #' @examples
 #' data("starwars", package = "dplyr")
-#' report_cat(starwars)
+#' inspect_cat(starwars)
 #' # return a visualisation too
-#' report_cat(starwars, show_plot = TRUE)
+#' inspect_cat(starwars, show_plot = TRUE)
 #' # compare the levels in two data frames
-#' report_cat(starwars, starwars[1:20, ])
+#' inspect_cat(starwars, starwars[1:20, ])
 #' @importFrom tibble as_tibble
 #' @importFrom tibble tibble
 #' @importFrom dplyr arrange
@@ -56,7 +56,7 @@
 #' @importFrom dplyr ungroup
 #' @importFrom magrittr %>%
 
-report_cat <- function(df1, df2 = NULL, show_plot = FALSE){
+inspect_cat <- function(df1, df2 = NULL, show_plot = FALSE){
 
   # perform basic column check on dataframe input
   check_df_cols(df1)
@@ -79,9 +79,9 @@ report_cat <- function(df1, df2 = NULL, show_plot = FALSE){
         do.call("rbind", .) %>% 
         mutate(col_name = colnames(df_cat))
       # get the unique levels
-      levels_unique <- lapply(levels_list, nrow) %>% 
+      levels_unique <- suppressWarnings(lapply(levels_list, nrow) %>% 
         do.call("rbind", .) %>% 
-        as_tibble(rownames = "col_name")
+        as_tibble(rownames = "col_name"))
       # combine the above tables
       levels_df <- levels_unique %>% 
         left_join(levels_top, by = "col_name") %>% 
@@ -110,10 +110,10 @@ report_cat <- function(df1, df2 = NULL, show_plot = FALSE){
     }
   } else {
     # levels for df1
-    s1 <- report_cat(df1, show_plot = FALSE)  %>% 
+    s1 <- inspect_cat(df1, show_plot = FALSE)  %>% 
       select(-contains("common"), -cnt)
     # levels for df2
-    s2 <- report_cat(df2, show_plot = FALSE) %>% 
+    s2 <- inspect_cat(df2, show_plot = FALSE) %>% 
       select(-contains("common"), -cnt)
     # combine and clean up levels
     levels_df <- full_join(s1, s2, by = "col_name") %>% 

R/report_cor.R → R/inspect_cor.R

@@ -1,4 +1,4 @@
-#' Report and compare Pearson's correlation coefficients for numeric columns in one or two dataframes.
+#' Summarise and compare Pearson's correlation coefficients for numeric columns in one or two dataframes.
 #'
 #' @param df1 A data frame
 #' @param df2 An optional second data frame for comparing correlation 
@@ -36,11 +36,11 @@
 #' @examples
 #' data("starwars", package = "dplyr")
 #' # correlations in numeric columns
-#' report_cor(starwars)
+#' inspect_cor(starwars)
 #' # get visualisation with confidence bands
-#' report_cor(starwars, show_plot = TRUE)
+#' inspect_cor(starwars, show_plot = TRUE)
 #' # compare correlations with a different data frame
-#' report_cor(starwars, starwars[1:10, ], show_plot = TRUE)
+#' inspect_cor(starwars, starwars[1:10, ], show_plot = TRUE)
 #' @importFrom dplyr arrange
 #' @importFrom dplyr contains
 #' @importFrom dplyr desc
@@ -70,7 +70,7 @@
 #' @importFrom magrittr %>%
 #' @importFrom tibble tibble
 
-report_cor <- function(df1, df2 = NULL, show_plot = FALSE, alpha = 0.05, 
+inspect_cor <- function(df1, df2 = NULL, show_plot = FALSE, alpha = 0.05, 
                        absolute = TRUE){
 
   # perform basic column check on dataframe input
@@ -101,11 +101,11 @@ report_cor <- function(df1, df2 = NULL, show_plot = FALSE, alpha = 0.05,
     } 
   } else {
     # stats for df1
-    s1 <- report_cor(df1, show_plot = F) %>% 
+    s1 <- inspect_cor(df1, show_plot = F) %>% 
       select(col_1, col_2, corr) %>% 
       rename(corr_1 = corr)
     # stats for df2
-    s2 <- report_cor(df2, show_plot = F) %>% 
+    s2 <- inspect_cor(df2, show_plot = F) %>% 
       select(col_1, col_2, corr) %>% 
       rename(corr_2 = corr)
     # join the two

R/report_imb.R → R/inspect_imb.R

@@ -1,4 +1,4 @@
-#' Report and compare columnwise imbalance for non-numeric columns in one or two dataframes.
+#' Summarise and compare columnwise imbalance for non-numeric columns in one or two dataframes.
 #'
 #' @param df1 A data frame
 #' @param df2 An optional second data frame for comparing columnwise imbalance.  
@@ -37,11 +37,11 @@
 #' @examples
 #' data("starwars", package = "dplyr")
 #' # get tibble of most common levels
-#' report_imb(starwars)
+#' inspect_imb(starwars)
 #' # get most common levels and show as barplot
-#' report_imb(starwars, show_plot = TRUE)
+#' inspect_imb(starwars, show_plot = TRUE)
 #' # compare memory usage 
-#' report_imb(starwars, starwars[1:10, -3])
+#' inspect_imb(starwars, starwars[1:10, -3])
 #' @importFrom tibble tibble
 #' @importFrom dplyr arrange
 #' @importFrom dplyr contains
@@ -54,7 +54,7 @@
 #' @importFrom dplyr slice
 #' @importFrom magrittr %>%
 
-report_imb <- function(df1, df2 = NULL, show_plot = FALSE){
+inspect_imb <- function(df1, df2 = NULL, show_plot = FALSE){
 
   # perform basic column check on dataframe input
   check_df_cols(df1)
@@ -90,10 +90,10 @@ report_imb <- function(df1, df2 = NULL, show_plot = FALSE){
     }
   } else {
     # summary of df1
-    s1 <- report_imb(df1, show_plot = F) %>% 
+    s1 <- inspect_imb(df1, show_plot = F) %>% 
       rename(pcnt_1 = pcnt, cnt_1 = cnt)
     # summary of df2
-    s2 <- report_imb(df2, show_plot = F) %>% 
+    s2 <- inspect_imb(df2, show_plot = F) %>% 
       rename(pcnt_2 = pcnt, cnt_2 = cnt)
     # left join summaries together
     out <- left_join(s1, s2, by = c("col_name", "value")) %>%

R/report_mem.R → R/inspect_mem.R

@@ -1,4 +1,4 @@
-#' Report and compare the memory usage in one or two dataframes.
+#' Summarise and compare the memory usage in one or two dataframes.
 #'
 #' @param df1 A data frame.
 #' @param df2 An optional second data frame for comparing column sizes.  
@@ -28,11 +28,11 @@
 #' @examples
 #' data("starwars", package = "dplyr")
 #' # get tibble of column memory usage for the starwars data
-#' report_mem(starwars)
+#' inspect_mem(starwars)
 #' # get column memory usage and show as barplot
-#' report_mem(starwars, show_plot = TRUE)
+#' inspect_mem(starwars, show_plot = TRUE)
 #' # compare memory usage 
-#' report_mem(starwars, starwars[1:10, -3])
+#' inspect_mem(starwars, starwars[1:10, -3])
 #' @importFrom dplyr arrange
 #' @importFrom dplyr contains
 #' @importFrom dplyr desc
@@ -55,7 +55,7 @@
 #' @importFrom tibble tibble
 #' @export
 
-report_mem <- function(df1, df2 = NULL, show_plot = FALSE){
+inspect_mem <- function(df1, df2 = NULL, show_plot = FALSE){
 
   # perform basic column check on dataframe input
   check_df_cols(df1)
@@ -93,8 +93,8 @@ report_mem <- function(df1, df2 = NULL, show_plot = FALSE){
     return(out)
   } else {
     # get the space report for both input dfs
-    df1 <- report_mem(df1, show_plot = F)
-    df2 <- report_mem(df2, show_plot = F)
+    df1 <- inspect_mem(df1, show_plot = F)
+    df2 <- inspect_mem(df2, show_plot = F)
     sjoin <- full_join(df1, df2, by = "col_name") %>%
       select(col_name, contains("size"), contains("pcnt"))
     colnames(sjoin)[2:3] <- paste0("size_",  1:2)

R/report_na.R → R/inspect_na.R

@@ -1,4 +1,4 @@
-#' Report and compare the rate of missingness in one or two dataframes.
+#' Summarise and compare the rate of missingness in one or two dataframes.
 #'
 #' @param df1 A data frame
 #' @param df2 An optional second data frame for making columnwise comparison of missingness.  
@@ -35,12 +35,12 @@
 #' 
 #' @examples
 #' data("starwars", package = "dplyr")
-#' # report missingness in starwars data
-#' report_na(starwars)
+#' # inspect missingness in starwars data
+#' inspect_na(starwars)
 #' # show the result as a barplot
-#' report_na(starwars, show_plot = TRUE)
+#' inspect_na(starwars, show_plot = TRUE)
 #' # compare two dataframes
-#' report_na(starwars, starwars[1:30, ])
+#' inspect_na(starwars, starwars[1:30, ])
 #' @importFrom dplyr arrange
 #' @importFrom dplyr desc
 #' @importFrom dplyr full_join
@@ -53,12 +53,12 @@
 #' @importFrom tibble tibble
 #' @export
 
-report_na <- function(df1, df2 = NULL, show_plot = FALSE, alpha = 0.05){
+inspect_na <- function(df1, df2 = NULL, show_plot = FALSE, alpha = 0.05){
   # perform basic column check on dataframe input
   check_df_cols(df1)
   # capture the data frame names
   df_names <- get_df_names()
-  # if ony one df input then report na content
+  # if ony one df input then inspect na content
   if(is.null(df2)){
     # find the  10 with most missingness
     out <- vec_to_tibble(sapply(df1, sumna)) %>%
@@ -77,8 +77,8 @@ report_na <- function(df1, df2 = NULL, show_plot = FALSE, alpha = 0.05){
     }
     if(type == "console") invisible(df1)
   } else {
-    s1 <- report_na(df1, show_plot = F) 
-    s2 <- report_na(df2, show_plot = F)
+    s1 <- inspect_na(df1, show_plot = F) 
+    s2 <- inspect_na(df2, show_plot = F)
     na_tab <- full_join(s1, s2, by = "col_name")
     na_tab$p_value <- prop_test(na_1 = na_tab$cnt.x, 
                                 na_2 = na_tab$cnt.y, 

R/report_num.R → R/inspect_num.R

@@ -1,4 +1,4 @@
-#' Report and compare the numeric variables within one or two dataframes
+#' Summarise and compare the numeric variables within one or two dataframes
 #'
 #' @param df1 A data frame
 #' @param df2 An optional second data frame for comparing categorical levels.  
@@ -16,7 +16,7 @@
 #' @return A \code{tibble} containing statistical summaries of the numeric 
 #' columns of \code{df1}, or comparing the histograms of \code{df1} and \code{df2}.
 #' @details 
-#' If only \code{df1} is specified, \code{report_num} returns a tibble with columns
+#' If only \code{df1} is specified, \code{inspect_num} returns a tibble with columns
 #' \itemize{
 #'   \item \code{col_name} character vector containing the column names in \code{df1}
 #'   and \code{df2}
@@ -46,11 +46,11 @@
 #' @examples
 #' data("starwars", package = "dplyr")
 #' # show summary statistics for starwars
-#' report_num(starwars)
+#' inspect_num(starwars)
 #' # with a visualisation too - try to limit number of bins
-#' report_num(starwars, breaks = 10)
+#' inspect_num(starwars, breaks = 10)
 #' # compare two data frames
-#' report_num(starwars, starwars[-c(1:10), ], breaks = 10, show_plot = TRUE)
+#' inspect_num(starwars, starwars[-c(1:10), ], breaks = 10, show_plot = TRUE)
 #' @importFrom dplyr arrange
 #' @importFrom dplyr contains
 #' @importFrom dplyr desc
@@ -81,7 +81,7 @@
 #' @importFrom tidyr gather
 #' @importFrom utils tail
 
-report_num <- function(df1, df2 = NULL, show_plot = F, 
+inspect_num <- function(df1, df2 = NULL, show_plot = F, 
                        breaks = 20, plot_layout = NULL, breakseq = NULL){
 
   # perform basic column check on dataframe input
@@ -145,13 +145,13 @@ report_num <- function(df1, df2 = NULL, show_plot = F,
     }
   } else {
     # get histogram and summaries for first df
-    s1 <- report_num(df1, show_plot = F, breaks = breaks) %>% 
+    s1 <- inspect_num(df1, show_plot = F, breaks = breaks) %>% 
       select(col_name, mean, sd, hist)
     # extract breaks from the above
     breaks_table <- tibble(col_name = s1$col_name, 
                            breaks = lapply(s1$hist, get_break))
     # get new histoggrams and summary stats using breaks from s1
-    s2 <- report_num(df2, breakseq = breaks_table, show_plot = F) %>% 
+    s2 <- inspect_num(df2, breakseq = breaks_table, show_plot = F) %>% 
       select(col_name, mean, sd, hist)
     s12 <- full_join(s1, s2, by = "col_name")
     # calculate psi and fisher p-value

R/report_types.R → R/inspect_types.R

@@ -1,4 +1,4 @@
-#' Report and compare column types in one or two dataframes.
+#' Summarise and compare column types in one or two dataframes.
 #'
 #' @param df1 A data frame.
 #' @param df2 An optional second data frame for comparison.  
@@ -27,11 +27,11 @@
 #' @examples
 #' data("starwars", package = "dplyr")
 #' # get tibble of column types for the starwars data
-#' report_types(starwars)
+#' inspect_types(starwars)
 #' # get column types and show as barplot
-#' report_types(starwars, show_plot = TRUE)
+#' inspect_types(starwars, show_plot = TRUE)
 #' # compare two data frames
-#' report_types(starwars, starwars[, -1], show_plot = TRUE)
+#' inspect_types(starwars, starwars[, -1], show_plot = TRUE)
 #' @export
 #' @importFrom dplyr arrange
 #' @importFrom dplyr case_when
@@ -50,9 +50,9 @@
 #' @importFrom tibble tibble
 #' @importFrom tidyr gather
 #' @importFrom tidyr replace_na
-#' @useDynLib reporter
+#' @useDynLib inspectdf
 
-report_types <- function(df1, df2 = NULL, show_plot = FALSE){
+inspect_types <- function(df1, df2 = NULL, show_plot = FALSE){
 
   # perform basic column check on dataframe input
   check_df_cols(df1)
@@ -87,9 +87,9 @@ report_types <- function(df1, df2 = NULL, show_plot = FALSE){
     # return dataframe
     return(out)
   } else {
-    s1 <- report_types(df1, show_plot = F) %>% select(-col_name)
+    s1 <- inspect_types(df1, show_plot = F) %>% select(-col_name)
     colnames(s1)[2:3] <- paste0(c("cnt_", "pcnt_"), 1)
-    s2 <- report_types(df2, show_plot = F) %>% select(-col_name)
+    s2 <- inspect_types(df2, show_plot = F) %>% select(-col_name)
     colnames(s2)[2:3] <- paste0(c("cnt_", "pcnt_"), 2)
     out <- full_join(s1, s2, by = "type") %>% 
       replace(is.na(.), 0)