This report is automatically generated with the R package knitr (version 1.40) .

source("R Functions/functions_QA data.R")

### LOAD DATA ###
AmericanRiver <- readxl::read_excel('Reeval_Impl_Goals_Linkage_Analysis/Data/Aqueous/AmericanRiver.xlsx', sheet='Trib-Res Data112818', guess_max = 30000)
nrow(AmericanRiver) #number of rows should match the Excel file (minus the header row)
## [1] 1366
### 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', 'Project Station Code',
               'Sample Date', 'Sample Time','Comments',
               'Analyte Name','Fraction Name','Units',
               'Result [ND = MDL]','Detection Limit', 'WB Type',
               'Weather','lat', 'long', 'Project Result Qual Code',
               'Laboratory Qual Code')

temp_cols <- c('Result [ND = 1/2 MDL]') #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

rl_pattern <- ".*RL=[[:space:]]?(.*)[[:space:]]ng.*"
AmericanRiver_new <- AmericanRiver %>%
  select( c(keep_cols,temp_cols) ) %>% #DO NOT CHANGE - selects columns specified above; add temp columns if needed
  mutate(              #Add user defined columns
    CoordSystem = NA_character_,
    Project = NA_character_,
    LabBatch = NA_character_,
    LabSampleID = NA_character_,
    MatrixName = 'Aqueous',
    RL = if_else(grepl(rl_pattern, Comments), sub(rl_pattern, '\\1', Comments), NA_character_),
    MethodName =  case_when(grepl('7470A', Comments) ~ 'Method 7470A',
                            TRUE ~ NA_character_),
    `Result [ND = MDL]` = as.numeric(`Result [ND = MDL]`),
    `Result [ND = 1/2 MDL]` = as.numeric(`Result [ND = 1/2 MDL]`),
    # Assume ResultQualCode is '=' except for the following conditions
    ResultQualCode = case_when(grepl('DNQ',`Project Result Qual Code`) ~ 'DNQ',
                               grepl('EST',`Project Result Qual Code`) ~ 'E',
                               grepl('J',`Project Result Qual Code`) ~ 'DNQ',
                               `Result [ND = 1/2 MDL]` == `Result [ND = MDL]`/2 ~ 'ND',
                               TRUE ~ '='),
                               #grepl('UJ',`Project Result Qual Code`) & grepl(`U`,`Laboratory Qual Code`) ~ 'ND'), #(U code doesn't necessarily mean ND)
    SampleID = NA_character_,
    BatchVerification = NA_character_,
    ComplianceCode = NA_character_,
    BatchComments = NA_character_,
    SampleTypeCode = NA_character_
    ) %>%
rename (
    #Rename columns to CEDEN standards
    #CEDEN 'COLUMNNAME' = AmericanRiver '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_
    'CitationCode' = 'Project Code',
    'StationName' = 'Station Name - Grouped',
    'StationCode' = 'Project Station Code',
    'SampleDate' = 'Sample Date',
    'SampleTime' = 'Sample Time',
    'WBT' = 'WB Type',
    'Analyte' = 'Analyte Name',
    'Analyte_part2' = 'Fraction Name',
    'Unit' = 'Units',
    'Result' = 'Result [ND = MDL]',
    'MDL' = 'Detection Limit',
    'SampleComments' = 'Weather',
    'TargetLatitude' = 'lat',
    'TargetLongitude' = 'long',
    'QACode' = 'Project Result Qual Code',
    'CollectionComments' = 'Laboratory Qual Code',
    'ResultsComments' = 'Comments'
  )

#make ND results blank and move those values over to MDL column
###watch out for the 6 that need correcting! (noted in original spreadsheet)

AmericanRiver_new <- AmericanRiver_new %>%
  mutate( MDL= ifelse(ResultQualCode == 'ND' & is.na(MDL), Result, MDL),
          Result = ifelse(ResultQualCode == 'ND', NA_real_, Result)
  )



#no blanks in MDL column have any further detection limit information in QC notes columns (comments, Qual codes, etc.)
#flags 'U' and 'J' are not explained in associated lab code tab; assumed that U was non detect and J was do not quanitify, 
    #but looking at the data there were a few combinations of U and J. Assumed if 'Result [ND=1/2 MDL]' column value was 
     #half of the'Result [ND = MDL]' column value, then it is an ND; if there are 'Project Result Qual Code' values = DNQ, EST, J 
     #then those all equal NDQ (except when 'Project Result Qual Code' = UJ and 'Laboratory Qual Code' column is 'U' value, then it is also an ND)
    #not all data labeled as 'U' code in the original spredsheet's project result qual code were ND - only about half glancing at the data. 
    #so I only labeled NDs from if the 1/2 MDL column was half of the result = MDL column

nrow(AmericanRiver_new)
## [1] 1366
#View(AmericanRiver_new)



### FORMAT COLUMN PARAMETERS ###

# Standardize Analyte Groups #
unique(AmericanRiver_new$Analyte)
## [1] "Mercury, Total" "Methylmercury"
unique(AmericanRiver_new$Analyte_part2)
## [1] "Unfiltered" "Filtered"
unique(paste(AmericanRiver_new$Analyte, AmericanRiver_new$Analyte_part2, sep=', '))
## [1] "Mercury, Total, Unfiltered" "Methylmercury, Unfiltered"  "Mercury, Total, Filtered"  
## [4] "Methylmercury, Filtered"
AmericanRiver_new <- AmericanRiver_new %>%
  mutate(Analyte = case_when(Analyte == "Mercury, Total" & Analyte_part2 == "Filtered" ~ "Mercury, Dissolved",
                             Analyte == "Methylmercury" & Analyte_part2 == "Filtered" ~ "Methylmercury, Dissolved",
                             Analyte == "Methylmercury" & Analyte_part2 == "Unfiltered" ~ "Methylmercury, Total",
                             TRUE ~ Analyte)
         )%>%
  select(-Analyte_part2) #Remove 'Analyte_part2' column
unique(AmericanRiver_new$Analyte)
## [1] "Mercury, Total"           "Methylmercury, Total"     "Mercury, Dissolved"      
## [4] "Methylmercury, Dissolved"
  # Format MDL Column to Numeric#
  # Check column for text - based on text user needs to decide what to do
if(any(grepl('[a-df-zA-DF-Z]',AmericanRiver_new$MDL))){
  old <-AmericanRiver_new$MDL
  new <-AmericanRiver_new$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"))
  #AmericanRiver_new <- AmericanRiver_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")
  AmericanRiver_new$MDL <- as.numeric(AmericanRiver_new$MDL)}
## 'MDL' column converted to numeric format
# Format RL 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]',AmericanRiver_new$RL))){
  old <-AmericanRiver_new$RL
  new <-AmericanRiver_new$RL
  new[grepl('[a-df-zA-DF-Z]', new)] <- NA #skip 'e' for exponential notation e.g., "8e-005"
  #Print what text was found and what is being done
  cat(paste0("'RL' column should be numeric but some cells contain ", grammaticList(setdiff(old, new)),
             ".\nACTIONS TAKEN:\n",
             "~explain here~.\n"))
  #AmericanRiver_new <- AmericanRiver_new %>%
  #  mutate( #Due stuff to prep column to be converted to Numeric
  #    RL = as.numeric(new)
  #  )
} else {
  cat("'RL' column converted to numeric format\n")
  AmericanRiver_new$RL <- as.numeric(AmericanRiver_new$RL)}
## 'RL' column converted to numeric format
  # Check if Result, MDL, & RL Columns all equal <NA> or 0 - these rows have no useful information
nrow(AmericanRiver_new) #Number rows before
## [1] 1366
#CODE BELOW REQUIRES USER TROUBLESHOOTING DEPENDING ON AVAILABLE COLUMNS AND SPREADSHEET SPECIFIC CONDITIONS#
AmericanRiver_new <- AmericanRiver_new %>%
  #Set 0 & negative values as blank
  mutate(Result = ifelse(Result <= 0, NA_real_, Result),
         MDL = ifelse(MDL <= 0, NA_real_, MDL),
         RL = ifelse(RL <= 0, NA_real_, RL))
na_results <- AmericanRiver_new %>% #Record rows where Result, MDL, & RL all equal <NA> or 0
  filter( is.na(Result) & is.na(MDL) & is.na(RL) )
#View(na_results)
AmericanRiver_new <- anti_join(AmericanRiver_new, na_results, by='SourceRow') #returns rows from AmericanRiver_new not matching values in no_result
nrow(AmericanRiver_new) #Number rows after - if number rows is the same as before this section can be deleted
## [1] 1366
  # Format Units Column - "ng/L", "mg/Kg"
unique(AmericanRiver_new$Unit) #Identifies OLDNAMES
## [1] "ng/l" "ng/L"
# If more than 1 unit colmn exists (e.g., for RL and MDL columns) see XXX script for example on merging into 1 column

AmericanRiver_new <- AmericanRiver_new %>%
  standardizeUnits

unique(AmericanRiver_new$Unit) #New naming structure for ResultQualCode 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
AmericanRiver_new <- AmericanRiver_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 ###
AmericanRiver_new <- AmericanRiver_new %>%
  select(-one_of(temp_cols)) #Remove temp columns since they are no longer needed
#View(AmericanRiver_new)

## SAVE FORMATTED DATA AS EXCEL FILE ##
writexl::write_xlsx(AmericanRiver_new, path='Reeval_Impl_Goals_Linkage_Analysis/Data/Aqueous/AmericanRiver_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 13:12:15 PST"