From 9262de0c7313dd313d0ef5567e197710095cb037 Mon Sep 17 00:00:00 2001
From: Mariana Kassien <kassienma@ehshpclp143.hpc.niehs.nih.gov>
Date: Mon, 18 Sep 2023 12:52:48 -0400
Subject: [PATCH] new code for data download and filtering, updated folder
 structure

---
 .Rbuildignore                                 |   4 +-
 NRTAPmodel.Rproj                              |   4 ++
 R/.DS_Store                                   | Bin 6148 -> 6148 bytes
 .../aqs_download_filter.R                     |  44 ++++++++++++++++++
 .../download_aqs_data.R                       |   0
 .../filter_minimum_poc.R                      |   0
 6 files changed, 51 insertions(+), 1 deletion(-)
 create mode 100644 R/data_download_preprocess/aqs_download_filter.R
 rename R/{data_download_functions => data_download_preprocess}/download_aqs_data.R (100%)
 rename R/{preprocessing => data_download_preprocess}/filter_minimum_poc.R (100%)

diff --git a/.Rbuildignore b/.Rbuildignore
index 13d4f111..aa62d510 100644
--- a/.Rbuildignore
+++ b/.Rbuildignore
@@ -1,2 +1,4 @@
 ^\.github$
-tools/
\ No newline at end of file
+tools/
+^.*\.Rproj$
+^\.Rproj\.user$
diff --git a/NRTAPmodel.Rproj b/NRTAPmodel.Rproj
index 8e3c2ebc..21a4da08 100755
--- a/NRTAPmodel.Rproj
+++ b/NRTAPmodel.Rproj
@@ -11,3 +11,7 @@ Encoding: UTF-8
 
 RnwWeave: Sweave
 LaTeX: pdfLaTeX
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source
diff --git a/R/.DS_Store b/R/.DS_Store
index ac2b5a6e646ef19b53c49a422ed80cfe609f9c03..92013ad87573e8b521c112cd5da096ec326698d3 100644
GIT binary patch
delta 111
zcmZoMXfc@J&&awlU^g=(>tr4lXGV$10W7kD1q?+DsSF@8pCK8@DxO@!qKH%O6w67R
SatBxwH<mqM+|17LmmdJ}yBz5N

delta 222
zcmZoMXfc@J&&aVcU^g=($7CKBXGZbK0W7kUzq86u?qd;z@c7dhN*VGPk{L=EG8yt2
z@+O~SIf+B&7;9oEFGB%C5ko4N%m?a9Whe&1OrQzro;mr+NjdpR3=9kc3=B-^Kw9rV
m7ywxe40v=-zQA%^9gloja8X`Pejdm~#)*ZCH?wp6<p%)hemVaD

diff --git a/R/data_download_preprocess/aqs_download_filter.R b/R/data_download_preprocess/aqs_download_filter.R
new file mode 100644
index 00000000..02d671d2
--- /dev/null
+++ b/R/data_download_preprocess/aqs_download_filter.R
@@ -0,0 +1,44 @@
+# Download EPA AQS data and filter to a single POC per site#
+# Author: Mariana Alifa Kassien
+# September 2023
+
+# Source functions
+source("R/data_download_preprocess/download_aqs_data.R")
+source("R/data_download_preprocess/filter_minimum_poc.R")
+
+# Define parameters of interest for download
+parameter_code = 88101
+year_start = 2018
+year_end = 2022
+resolution_temporal = "daily"
+directory_to_download = "./input/aqs/"
+directory_to_save = "./input/aqs/"
+url_aqs_download = "https://aqs.epa.gov/aqsweb/airdata/"
+
+# Run data download function
+download_aqs_data(parameter_code, year_start,year_end,resolution_temporal,
+                  directory_to_download, directory_to_save,
+                  url_aqs_download, remove_zips = FALSE)
+
+# Read in sites dataframe for filtering
+input_df= read.csv(paste(directory_to_save, resolution_temporal, "_", parameter_code, "_", year_start, "-", year_end, ".csv", sep=""), 
+                   stringsAsFactors = F)
+
+# Optional: view column names to determine right inputs for filtering
+#colnames(input_df)
+
+# Create a site ID column that does not include the POC number
+input_df = input_df |>
+  mutate(ID.Site = substr(ID.Monitor, 1, 17))
+
+site_id="ID.Site"
+poc_name="POC"
+
+# Filter sites with multiple POCs (select lowest-numbered POC per site)
+data_filtered =filter_minimum_poc(input_df, site_id, poc_name)
+
+# Save new filtered data - wasn't sure what to name it so I added "filtered_" to the beginning. We can change that too if there's a better idea.
+output_name=paste(directory_to_save, "filtered_",resolution_temporal, "_", parameter_code, "_", year_start, "-", year_end, ".csv", sep="") 
+  # output_name
+  # [1] "./input/aqs/filtered_daily_88101_2018-2022.csv"
+write.csv(data_filtered, output_name)
diff --git a/R/data_download_functions/download_aqs_data.R b/R/data_download_preprocess/download_aqs_data.R
similarity index 100%
rename from R/data_download_functions/download_aqs_data.R
rename to R/data_download_preprocess/download_aqs_data.R
diff --git a/R/preprocessing/filter_minimum_poc.R b/R/data_download_preprocess/filter_minimum_poc.R
similarity index 100%
rename from R/preprocessing/filter_minimum_poc.R
rename to R/data_download_preprocess/filter_minimum_poc.R