initial commit

.Rbuildignore

@@ -0,0 +1 @@
+^\.github$

.gitignore

@@ -0,0 +1,42 @@
+# History files
+.Rhistory
+.Rapp.history
+
+# Session Data files
+.RData
+
+# User-specific files
+.Ruserdata
+
+# Example code in package build process
+*-Ex.R
+
+# Output files from R CMD build
+/*.tar.gz
+
+# Output files from R CMD check
+/*.Rcheck/
+
+# RStudio files
+.Rproj.user/
+
+# produced vignettes
+vignettes/*.html
+vignettes/*.pdf
+
+# OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
+.httr-oauth
+
+# knitr and R markdown default cache directories
+*_cache/
+/cache/
+
+# Temporary files created by R markdown
+*.utf8.md
+*.knit.md
+
+# R Environment Variables
+.Renviron
+
+
+data/current_well.csv

R/archive_new_wells.R

@@ -0,0 +1,79 @@
+library(dplyr)
+library(readr)
+library(janitor)
+library(DBI)
+library(RPostgres)
+source("R/col_types_wells.R")
+con1 <- DBI::dbConnect(
+  #RPostgreSQL::PostgreSQL(),
+  RPostgres::Postgres(),
+  dbname = Sys.getenv("BCGOV_DB"),
+  host = Sys.getenv("BCGOV_HOST"),
+  user = Sys.getenv("BCGOV_USR"),
+  password=Sys.getenv("BCGOV_PWD")
+)
+
+#library(reticulate)
+#use_condaenv(condaenv = "gwells_locationqa", required= TRUE)
+
+# this script has the type of all columns in the wells.csv
+source("R/col_types_wells.R")
+
+# lubridate can return time given a specific time zone. here are vancouver time and date
+#lubridate::with_tz(Sys.time(), "America/Vancouver")
+#as.Date(Sys.time() , tz = "America/Vancouver")
+
+# read the  frehsly downloaded data/wells.csv downloaded by the python script.
+#newest_wells_file <- read_csv("data/wells.csv" , col_types = col_types_wells) # coltypes from R/coltypes_we
+
+# actually we arent going to use the python script here because we need to read the other csvs in the zip file.
+url <- "https://s3.ca-central-1.amazonaws.com/gwells-export/export/v2/gwells.zip"
+temp_zip <- tempfile()
+download.file(url, destfile = temp_zip)
+temp_dir <- tempdir()
+utils::unzip(temp_zip,exdir = temp_dir) #  files =  "well.csv", 
+
+newest_wells_file <- read_csv(
+  paste0(temp_dir, "/well.csv"), col_types = col_types_wells # from R/coltypes_we
+) 
+
+
+wells_in_db <- dbGetQuery(con1, "select well_tag_number from wells") 
+
+#test <-  dbGetQuery(con1, "select * from wells limit 100") 
+#------------------------------------------------------------
+# Update historical caracteristics of wells on the day they were added
+#------------------------------------------------------------
+
+new_wells <- newest_wells_file %>%
+  anti_join(wells_in_db) %>%
+  mutate(date_added = as.Date(Sys.time() , tz = "America/Vancouver")) %>%
+  janitor::clean_names()
+
+if(nrow(new_wells)> 0){
+  message("Appending new wells:", nrow(new_wells), " rows.", paste(new_wells$well_tag_number, collapse = " "))
+  dbAppendTable(con1, "wells", new_wells)
+
+} else{message("No new wells to append.")}
+
+
+############## do same thing for drilling method file 
+
+newest_drilling_method <-  read_csv(
+  paste0(temp_dir, "/drilling_method.csv")  ,
+  col_types = cols(well_tag_number = col_double(), drilling_method_code = col_character())
+) 
+
+wells_in_drilling_method_db <- dbGetQuery(con1, "select well_tag_number from drilling_method") 
+
+new_drilling_method <- newest_drilling_method %>%
+  anti_join(wells_in_drilling_method_db) %>% 
+  mutate(date_added = as.Date(Sys.time() , tz = "America/Vancouver")) %>%
+  janitor::clean_names()
+
+
+if(nrow(new_drilling_method)> 0){
+  message("Appending  new_drilling_method:", nrow(new_drilling_method), " rows.", paste(new_drilling_method$well_tag_number, collapse = " "))
+  dbAppendTable(con1, "drilling_method", new_drilling_method)
+
+} else{message("No new drilling method to append.")}

R/clean_after_geocode.R

@@ -0,0 +1,26 @@
+library(dplyr)
+library(readr)
+library(janitor)
+source("R/col_types_wells.R")
+
+library(RPostgres)
+con1 <- DBI::dbConnect(
+  RPostgres::Postgres(),
+  dbname = Sys.getenv("BCGOV_DB"),
+  host = Sys.getenv("BCGOV_HOST"),
+  user = Sys.getenv("BCGOV_USR"),
+  password=Sys.getenv("BCGOV_PWD")
+)
+
+# this is the list of well we geocoded today
+newly_geocoded <- read_csv("data/wells_geocoded.csv", col_types = col_types_geocoded) %>% 
+  mutate(date_geocoded = as.Date(Sys.time() , tz = "America/Vancouver")) %>%
+  janitor::clean_names()
+
+if(nrow(newly_geocoded)> 0){
+  message("printing newly geocoded")
+  glimpse(newly_geocoded)
+  message("Appending newly geocoded  wells:", nrow(newly_geocoded), " rows. well_tag_number=", paste(newly_geocoded$well_tag_number, collase = " "))
+  dbAppendTable(con1, "wells_geocoded", newly_geocoded)
+
+} else{message("No new geocodedwells to append.")}

R/clean_after_qa.R

@@ -0,0 +1,37 @@
+library(dplyr)
+library(readr)
+library(janitor)
+
+source("R/col_types_wells.R")
+source("R/col_types_wells.R")
+
+library(RPostgres)
+con1 <- DBI::dbConnect(
+  RPostgres::Postgres(),
+  dbname = Sys.getenv("BCGOV_DB"),
+  host = Sys.getenv("BCGOV_HOST"),
+  user = Sys.getenv("BCGOV_USR"),
+  password=Sys.getenv("BCGOV_PWD")
+)
+
+old_qa <- dbGetQuery(con1, "select * from wells_qa limit 10")
+message("printing out QA")
+glimpse(old_qa)
+
+
+newly_qa <- read_csv("gwells_locationqa.csv", col_types = col_types_qa) %>%
+  select(-one_of(c("Unnamed: 0", "date_added"))) %>% 
+  mutate(date_qa = as.Date(Sys.time() , tz = "America/Vancouver")) %>%
+  janitor::clean_names() 
+
+
+if(nrow(newly_qa)> 0){
+
+  message("printing new qa")
+  glimpse(newly_qa)
+  message("Appending newly qa  wells:", nrow(newly_qa), " rows. well_tag_number=", paste(newly_qa$well_tag_number, collase = " "))
+  dbAppendTable(con1, "wells_qa", newly_qa)
+  message("done")
+
+} else{message("No new qa wells to append.")}
+