This report is automatically generated with the R
package knitr
(version 1.40
)
.
source("R Functions/functions_QA data.R") #lat/longs need to be rounded #lat/long of 'variable' for X2 needs to be addressed - numeric or character? #since none of these results are ND or DNQ, I am worried that some of the results are ND #but reported as half detection limit. Not sure what to do with these yet but want to be aware -JF 12/21/18 ### LOAD DATA ### App_L_THg <- readxl::read_excel('Reeval_Impl_Goals_Linkage_Analysis/Data/Aqueous/AppL.xls', sheet='Trib&Export TotHg Conc Data', guess_max = 30000) nrow(App_L_THg) #number of rows should match the Excel file (minus the header row)
## [1] 1219
### LIST COLUMNS TO BE USED, ADD USER DEFINED COLUMNS, & RENAME COLUMNS TO CEDEN STANDARDS ### #Use 1.READ ME.xlsx, 'ColumnsForR' to list & identify columns that match corresponding CEDEN Standard columns keep_cols <- c('SourceID','SourceRow', 'Project Code', 'Station Name - Grouped', 'Station Code', 'Sample Date', 'Sample Time', 'Units', 'Result', 'Reporting Limit', 'QA Code', 'Station Name', 'Result Qual') temp_cols <- c('Weather', 'Comments') #Include columns that do not match CEDEN standards but may be useful (e.g., Unit columns for MDL & RL) #temp_cols are removed before the data is merged with other datasets #str(App_L_THg) App_L_THg_new <- App_L_THg %>% select( c(keep_cols,temp_cols)) %>% #DO NOT CHANGE - selects columns specified above mutate( #Add user defined columns #COLUMNNAME = 'THE SPECIFIED VALUE' MatrixName = 'Aqueous', SampleComments = ifelse(is.na(Weather)&is.na(Comments), NA_character_, ifelse(is.na(Weather), Comments, ifelse(is.na(Comments), paste0('weather: ',Weather), paste('weather: ',Weather,'; ',Comments)))), Analyte = 'Mercury, Total', Project = NA_character_, LabBatch = NA_character_, LabSampleID = NA_character_, SampleID = NA_character_, BatchVerification = NA_character_, ComplianceCode = NA_character_, WBT = 'Not Recorded', MethodName = NA_character_, MDL = NA_character_, ResultQualCode = case_when(grepl('average', `Result Qual`, ignore.case=T) ~ 'AVG', #2019-04-02 ~ added by Robin to fix blank ResultQualCodes TRUE ~ '='), # Result Qual "n/p" meaning is unkown but assumed to be "=" for time being CoordSystem = NA_character_, BatchComments = NA_character_, SampleTypeCode = NA_character_ ) %>% rename( #Rename columns to CEDEN standards #CEDEN 'COLUMNNAME' = App_L_THg 'COLUMNNAME' #If a column doesnt match the CEDEN Standard, delete that column below, talk to Robin and discuss if we can add it using other information #If a column below doesn't exist; move COLUMNNAME to Mutate above using format; StationName = NA_character_ 'StationName' = 'Station Name - Grouped', 'StationCode' = 'Station Code', 'SampleDate' = 'Sample Date', 'SampleTime' = 'Sample Time', 'Unit' = 'Units', 'RL' = 'Reporting Limit', 'QACode' = 'QA Code', 'CollectionComments' = 'Station Name', 'ResultsComments' = 'Result Qual', 'CitationCode' = 'Project Code' ) nrow(App_L_THg_new)
## [1] 1219
#str(App_L_THg_new) #just to check data class of different columns - e.g., is Date column in POSIX format? #View(App_L_THg_new) ### FORMAT COLUMN PARAMETERS ### #matching lat longs with other tab in spreadsheet App_L_LatLong <- readxl::read_excel('Reeval_Impl_Goals_Linkage_Analysis/Data/Aqueous/AppL.xls', sheet='Lat-Long - Trib and Export', guess_max = 30000) App_L_THg_new <- App_L_THg_new %>% left_join(., App_L_LatLong, by = c('CollectionComments' = 'Station Name', 'CitationCode' = 'Project Code')) %>% rename('TargetLatitude' = 'Latitude', 'TargetLongitude' = 'Longitude') #View(App_L_THg_new) # Standardize WBT (WaterBodyType) Groups - "River/Stream", "Drain/Canal", "Wetland", "Spring", "Slough", # "Pond", "Lake/Reservoir", "Delta", "Forebay/Afterbay", "Not Recorded" # #unique(App_L_THg_new$WBT) #Identifies OLDNAMES #Look for inconsistent group pairings between MatrixName and WBT (e.g., 'Soil; Stream') #unique(paste(App_L_THg_new$MatrixName, App_L_THg_new$WBT, sep='; ')) #If an incosistent grouping exists, add comment to 'CollectionComments' column using code: mutate(CollectionComments = case_when(MatrixName=='CONDITION' ~ 'COMMENT', TRUE ~ MatrixName)), #STANDARD CODE TO CHANGE GROUPING NAMES #App_L_THg_new <- App_L_THg_new %>% #mutate(WBT = recode(WBT, #"OLDNAME" = "NEWNAME" - create a new line for each OLDNAME that needs to be changed #"OLDNAME" = "River/Stream", #"OLDNAME" = "Drain/Canal", #"OLDNAME" = "Wetland", #"OLDNAME" = "Not Recorded"), #EXAMPLE FOR WHEN "OLDNAME" is 'NA' but we want a NEWNAME - if this example is deleted, also delete the comma after "Not Recorded" above #WBT = case_when(is.na(WBT) ~ "Not Recorded", #Use "Not Recorded" when WBT value is NA #TRUE ~ WBT) #Keep original WBT value in all other cases #) #unique(paste(App_L_THg_new$MatrixName, App_L_THg_new$WBT, sep='; ')) #New naming structure for Matrix Name & WBT Groupings # Standardize ResultQualCode Groups - "ND", "DNQ", NA# #unique(App_L_THg_new$ResultQualCode) #Identifies OLDNAMES #App_L_THg_new <- App_L_THg_new %>% #mutate(ResultQualCode = recode(ResultQualCode, #"" = NA_character_, #changes empty cells to NA - delete if not needed #"OLDNAME" = "ND", #"OLDNAME" = "DNQ" #) # ) #unique(App_L_THg_new$ResultQualCode) #New naming structure for ResultQualCode Groupings # Format Result Column to Numeric# # Check column for text - based on text user needs to decide what to do if(any(grepl('<|[a-df-zA-DF-Z]',App_L_THg_new$Result))){ old <-App_L_THg_new$Result new <-App_L_THg_new$Result new[grepl('<|[a-df-zA-DF-Z]', new)] <- NA #skip 'e' for exponential notation e.g., "8e-005" #Print what text was found and what is being done cat(paste0("'Result' column should be numeric but some cells contain ", grammaticList(setdiff(old, new)), ".\nACTIONS TAKEN:\n", "~explain here~.\n")) #App_L_THg_new <- App_L_THg_new %>% # mutate( #Due stuff to prep column to be converted to Numeric # Result = as.numeric(new) # ) } else { cat("'Result' column converted to numeric format\n") App_L_THg_new$Result <- as.numeric(App_L_THg_new$Result)}
## 'Result' column converted to numeric format
# Format MDL Column to Numeric# # Check column for text - based on text user needs to decide what to do if(any(grepl('[a-df-zA-DF-Z]',App_L_THg_new$MDL))){ old <-App_L_THg_new$MDL new <-App_L_THg_new$MDL new[grepl('[a-df-zA-DF-Z]', new)] <- NA #skip 'e' for exponential notation e.g., "8e-005" #Print what text was found and what is being done cat(paste0("'Result' column should be numeric but some cells contain ", grammaticList(setdiff(old, new)), ".\nACTIONS TAKEN:\n", "~explain here~.\n")) #App_L_THg_new <- App_L_THg_new %>% # mutate( #Due stuff to prep column to be converted to Numeric # MDL = as.numeric(new) # ) } else { cat("'MDL' column converted to numeric format\n") App_L_THg_new$MDL <- as.numeric(App_L_THg_new$MDL)}
## 'MDL' column converted to numeric format
# Check if Result, MDL, & RL Columns all equal <NA> or 0 - these rows have no useful information nrow(App_L_THg_new) #Number rows before
## [1] 1219
#CODE BELOW REQUIRES USER TROUBLESHOOTING DEPENDING ON AVAILABLE COLUMNS AND SPREADSHEET SPECIFIC CONDITIONS# App_L_THg_new <- App_L_THg_new %>% #Set 0 & negative values as blank mutate(Result = ifelse(Result <= 0, NA_real_, Result), MDL = ifelse(MDL <= 0, NA_real_, MDL), RL = ifelse(RL <= 0, NA_real_, RL)) na_results <- App_L_THg_new %>% #Record rows where Result, MDL, & RL all equal <NA> or 0 filter( is.na(Result) & is.na(MDL) & is.na(RL) ) #View(na_results) App_L_THg_new <- anti_join(App_L_THg_new, na_results, by='SourceRow') #returns rows from App_L_THg_new not matching values in no_result nrow(App_L_THg_new) #Number rows after - if number rows is the same as before this section can be deleted
## [1] 1219
# Format Units Column - "ng/L", "mg/Kg" unique(App_L_THg_new$Unit) #Identifies OLDNAMES
## [1] "ng/L"
# If more than 1 unit colmn exists (e.g., for RL and MDL columns) see WQP script for example on merging into 1 column App_L_THg_new <- App_L_THg_new %>% standardizeUnits unique(App_L_THg_new$Unit) #New naming structure for Unit Groupings
## [1] "ng/L"
# Format Date and Time Column # # NEED TO TALK ABOUT HOW WE WANT TO DO THIS - To graph in R we need Date and Time in same column # THE EXAMPLE CODE BELOW ASSUMES DATE AND TIME ARE IN SEPERATE COLUMNS #If R is having trouble accessing the time from excel, create a new column in excel and input this code into it #{=TEXT(F8, "hh:mm")&":00"}, where F8 is the excel cell that contained the original time. #Label this new column as the 'SampleTime' column for R and run it. Basically, R needs time to have hh:mm:ss #and excel wasn't uniformly formatting the time correctly, so this is the work around App_L_THg_new <- App_L_THg_new %>% #rowise() %>% # rowise is very slow - so used sapply to make this a rowise operation mutate( #If SampleDate & CollectioTIme are not in Character format by defualt, turn it into a character class so it exports better SampleDate = ifelse(sapply(SampleDate, is.character), SampleDate, as.character(as.Date(SampleDate))), SampleTime = ifelse(sapply(SampleTime, is.character), SampleTime, format(lubridate::ymd_hms(SampleTime), "%H:%M:%S")), #COMBINE DATE AND TIME INTO SampleDateTime COLUMN SampleDateTime = ifelse(!is.na(SampleTime), paste(SampleDate, SampleTime), paste(SampleDate, '00:00:00')), #FORMAT SampleDateTime COLUMN TO DATE FORMAT SampleDateTime = lubridate::ymd_hms(SampleDateTime) ) ### REMOVE TEMPORARY COLUMNS ### App_L_THg_new <- App_L_THg_new %>% select(-one_of(temp_cols)) #Remove temp columns since they are no longer needed #View(App_L_THg_new) ## SAVE FORMATTED DATA AS EXCEL FILE ## writexl::write_xlsx(App_L_THg_new, path='Reeval_Impl_Goals_Linkage_Analysis/Data/Aqueous/App_L_THg_ceden_format.xlsx') # In excel, to convert SampleDate column to Date format # 1 - Select the date column. # 2 - Go to the Data-tab and choose "Text to Columns". # 3 - On the first screen, leave radio button on "delimited" and click Next. # 4 - Unselect any delimiter boxes (everything blank) and click Next. # 5 - Under column data format choose Date, select YMD # 6 - Click Finish.
The R session information (including the OS info, R version and all packages used):
sessionInfo()
## R version 4.2.2 (2022-10-31 ucrt) ## Platform: x86_64-w64-mingw32/x64 (64-bit) ## Running under: Windows 10 x64 (build 22621) ## ## Matrix products: default ## ## locale: ## [1] LC_COLLATE=English_United States.utf8 LC_CTYPE=C ## [3] LC_MONETARY=English_United States.utf8 LC_NUMERIC=C ## [5] LC_TIME=English_United States.utf8 ## system code page: 65001 ## ## attached base packages: ## [1] grid stats graphics grDevices utils datasets methods base ## ## other attached packages: ## [1] mgcv_1.8-41 nlme_3.1-160 lubridate_1.8.0 plotly_4.10.0 ## [5] readxl_1.4.1 actuar_3.3-0 NADA_1.6-1.1 forcats_0.5.2 ## [9] stringr_1.4.1 dplyr_1.0.9 purrr_0.3.4 readr_2.1.2 ## [13] tidyr_1.2.0 tibble_3.1.8 ggplot2_3.3.6 tidyverse_1.3.2 ## [17] fitdistrplus_1.1-8 survival_3.4-0 MASS_7.3-58.1 ## ## loaded via a namespace (and not attached): ## [1] httr_1.4.4 jsonlite_1.8.0 viridisLite_0.4.1 splines_4.2.2 ## [5] modelr_0.1.9 assertthat_0.2.1 highr_0.9 googlesheets4_1.0.1 ## [9] cellranger_1.1.0 yaml_2.3.5 pillar_1.8.1 backports_1.4.1 ## [13] lattice_0.20-45 glue_1.6.2 digest_0.6.29 rvest_1.0.3 ## [17] colorspace_2.0-3 htmltools_0.5.3 Matrix_1.5-1 pkgconfig_2.0.3 ## [21] broom_1.0.1 haven_2.5.1 webshot_0.5.3 scales_1.2.1 ## [25] tzdb_0.3.0 googledrive_2.0.0 generics_0.1.3 ellipsis_0.3.2 ## [29] withr_2.5.0 lazyeval_0.2.2 cli_3.3.0 magrittr_2.0.3 ## [33] crayon_1.5.1 evaluate_0.16 fs_1.5.2 fansi_1.0.3 ## [37] xml2_1.3.3 tools_4.2.2 data.table_1.14.2 hms_1.1.2 ## [41] expint_0.1-7 gargle_1.2.0 lifecycle_1.0.1 munsell_0.5.0 ## [45] reprex_2.0.2 writexl_1.4.0 compiler_4.2.2 rlang_1.0.5 ## [49] rstudioapi_0.14 htmlwidgets_1.5.4 crosstalk_1.2.0 rmarkdown_2.16 ## [53] gtable_0.3.1 DBI_1.1.3 R6_2.5.1 knitr_1.40 ## [57] fastmap_1.1.0 utf8_1.2.2 stringi_1.7.8 vctrs_0.4.1 ## [61] dbplyr_2.2.1 tidyselect_1.1.2 xfun_0.32
Sys.time()
## [1] "2023-12-29 13:34:46 PST"