diff --git a/.Rbuildignore b/.Rbuildignore
index 819a77239..bb231a66a 100644
--- a/.Rbuildignore
+++ b/.Rbuildignore
@@ -71,3 +71,5 @@ vignettes/Reference_Lists.Rmd
^[.]?air[.]toml$
^\.vscode$
environment.yml
+^\.positai$
+^\.claude$
diff --git a/.github/workflows/pkgdown.yaml b/.github/workflows/pkgdown.yaml
index b5a0a8012..129542db0 100644
--- a/.github/workflows/pkgdown.yaml
+++ b/.github/workflows/pkgdown.yaml
@@ -51,7 +51,7 @@ jobs:
any::ggplot2
any::sf
any::patchwork
- any::maps
+ any::reticulate
any::leaflet
any::readxl
any::gridExtra
diff --git a/.gitignore b/.gitignore
index 02d0a38fd..892ca673e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -17,3 +17,4 @@ vignettes/*.html
vignettes/*.R
/.quarto/
**/*.quarto_ipynb
+.positai
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index d8446a162..3dfcf3492 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -40,17 +40,14 @@ build-image:
services:
- name: ${DEVOPS_REGISTRY}usgs/docker:20-dind
alias: docker
- rules:
- - changes:
- - .gitlab-ci.yml
- - docker/Dockerfile
- - environment.yml
script:
- echo ${CI_REGISTRY_PASSWORD} | docker login -u ${CI_REGISTRY_USER} --password-stdin $CI_REGISTRY
- docker pull ${CI_REGISTRY_IMAGE}:latest || true
- docker build
-f docker/Dockerfile -t ${CI_REGISTRY_IMAGE}:latest .
- docker push --all-tags ${CI_REGISTRY_IMAGE}
+ artifacts:
+ expire_in: 5 minutes
buildcheck:
stage: check
@@ -70,7 +67,7 @@ buildcheck:
artifacts:
paths:
- "*.tar.gz"
- expire_in: 1 week
+ expire_in: 1 hour
unittests:
stage: test
@@ -91,7 +88,7 @@ unittests:
x'
artifacts:
when: always
- expire_in: 1 week
+ expire_in: 1 hour
paths:
- test-out.xml
reports:
@@ -112,6 +109,8 @@ longtest:
- if: $RUN_LONG_TESTS == "FALSE"
when: always
- when: never
+ artifacts:
+ expire_in: 5 minutes
pages:
stage: end
@@ -129,18 +128,20 @@ pages:
artifacts:
paths:
- $PAGES_OUTDIR
- expire_in: 1 week
+ expire_in: 1 hour
Validate Inventory:
- stage: end
- only:
- - main
- image: ${INTERNAL_REGISTRY}software/software-management:latest
- script:
- - software-management review
- --project "${CI_PROJECT_PATH}"
- --ref "${CI_COMMIT_BRANCH}"
- --type "provisional"
- --token "${GIT_TOKEN_CUSTOM}"
- tags:
- - chs-shared
+ stage: end
+ only:
+ - main
+ image: ${INTERNAL_REGISTRY}software/software-management:latest
+ script:
+ - software-management review
+ --project "${CI_PROJECT_PATH}"
+ --ref "${CI_COMMIT_BRANCH}"
+ --type "provisional"
+ --token "${GIT_TOKEN_CUSTOM}"
+ tags:
+ - chs-shared
+ artifacts:
+ expire_in: 5 minutes
diff --git a/DESCRIPTION b/DESCRIPTION
index 6890b9308..e7ad2af72 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -68,5 +68,5 @@ Encoding: UTF-8
BuildVignettes: true
VignetteBuilder: knitr
BugReports: https://github.com/DOI-USGS/dataRetrieval/issues
-RoxygenNote: 7.3.3
Roxygen: list(markdown = TRUE)
+Config/roxygen2/version: 8.0.0
diff --git a/NAMESPACE b/NAMESPACE
index 4817ef167..5db89fe84 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -55,6 +55,7 @@ export(read_waterdata_latest_daily)
export(read_waterdata_metadata)
export(read_waterdata_monitoring_location)
export(read_waterdata_parameter_codes)
+export(read_waterdata_peaks)
export(read_waterdata_ratings)
export(read_waterdata_samples)
export(read_waterdata_stats_daterange)
diff --git a/NEWS b/NEWS
index 2a00027a4..7daff6a98 100644
--- a/NEWS
+++ b/NEWS
@@ -2,14 +2,21 @@ dataRetrieval 2.7.25
===================
* Added read_waterdata_ratings to access USGS rating curves with
new modern endpoint.
+* Added read_waterdata_peaks to access USGS peak data with
+new modern endpoint.
* Increase flexibility of chunking by monitoring_location_id by
-including it as an argument in each relevant function.
+including it as an argument in each relevant waterdata OGC function.
* Clean up deprecated code.
* Updated retry strategy to include retry_on_failure = TRUE.
* Added countries, methods, method-categories, method-citations, and
citations to possible values in read_waterdata_metadata.
* Added field_measurements_series_id argument to read_waterdata_field_measurement
* Removed NWIS tests
+* Introduce an error if user inputs a numeric to any of the "time" arguments.
+Because it is impossible to tell if they intended Dates or POSIX, we cannot
+know for sure and therefore could add incorrect filters to the query.
+* The "id" column that comes back from read_waterdata_fiel_meta was changed to
+field_measurements_series_id to match the expectation of `read_waterdata_field_measurements`
diff --git a/R/AAA.R b/R/AAA.R
index e02bd1987..d2ed38956 100644
--- a/R/AAA.R
+++ b/R/AAA.R
@@ -24,7 +24,8 @@ pkg.env <- new.env()
"continuous",
"field-measurements-metadata",
"combined-metadata",
- "channel-measurements"
+ "channel-measurements",
+ "peaks"
)
collections <- c(
"parameter-codes",
diff --git a/R/construct_api_requests.R b/R/construct_api_requests.R
index 4fe15147c..c0469f64f 100644
--- a/R/construct_api_requests.R
+++ b/R/construct_api_requests.R
@@ -340,7 +340,7 @@ switch_arg_id <- function(ls, id_name, service) {
#' dataRetrieval:::format_api_dates(end)
#' dataRetrieval:::format_api_dates(end, TRUE)
#'
-#' end <- c(NA, as.POSIXct("2021-01-01 12:15:00"))
+#' end <- as.POSIXct(c(NA, "2021-01-01 12:15:00"))
#' dataRetrieval:::format_api_dates(end)
#'
#' start_end <- as.POSIXct(c("2021-01-01 12:15:00",
@@ -370,17 +370,24 @@ switch_arg_id <- function(ls, id_name, service) {
#' start <- "2025-10-01"
#' end <- Sys.Date()
#' dataRetrieval:::format_api_dates(c(start, end), date = TRUE)
+#'
+#' # This is a problem because the first value forces the
+#' # vector to be numeric, and then we don't really
+#' # know if the 2nd value is a Date (number of days since 1970)
+#' # or if it's a date/time (number of seconds..)
+#' half_range <- c(NA, as.Date("2025-01-01"))
+#' # Will error:
+#' #dataRetrieval:::format_api_dates(half_range, date = FALSE)
+#' # Better way to do it:
+#' better_half <- as.Date(c(NA, "2025-01-01"))
+#' dataRetrieval:::format_api_dates(better_half, date = FALSE)
format_api_dates <- function(datetime, date = FALSE) {
if (is.character(datetime)) {
datetime[datetime == ""] <- NA
datetime <- toupper(datetime)
}
- if (all(is.na(datetime))) {
- return(NA)
- }
-
- if (all(is.null(datetime))) {
+ if (all(is.na(datetime)) | all(is.null(datetime))) {
return(NA)
}
@@ -388,6 +395,18 @@ format_api_dates <- function(datetime, date = FALSE) {
stop("datetime should only include 1-2 values")
}
+ if (is.numeric(datetime)) {
+ # Until we can figure out a way to know if the
+ # original input was suppose to be Date or Posix
+ # We can't determine what the user meant.
+ stop(
+ "A time query was entered as numeric. This could lead to errors.
+Check any time queries that might have been automatically converted to numeric.
+This could happen if you use c(NA, as.Date(Sys.Date())) instead of
+as.Date(c(NA, Sys.Date()) for example."
+ )
+ }
+
if (length(datetime) == 1) {
# If the user has "P" or the "/" we assume they know what they are doing
if (
@@ -395,13 +414,13 @@ format_api_dates <- function(datetime, date = FALSE) {
grepl("/", datetime)
) {
return(datetime)
+ }
+
+ if (date) {
+ datetime <- get_Date(datetime)
} else {
- if (date) {
- datetime <- get_Date(datetime)
- } else {
- datetime1 <- get_dateTime(datetime)
- datetime <- lubridate::format_ISO8601(datetime1, usetz = "Z")
- }
+ datetime1 <- get_dateTime(datetime)
+ datetime <- lubridate::format_ISO8601(datetime1, usetz = "Z")
}
} else if (length(datetime) == 2) {
if (date) {
diff --git a/R/dataRetrieval-package.R b/R/dataRetrieval-package.R
index 9eda9c1f0..de5ae89e9 100644
--- a/R/dataRetrieval-package.R
+++ b/R/dataRetrieval-package.R
@@ -207,7 +207,7 @@ NULL
# "monitoring-locations", "latest-continuous",
# "field-measurements", "latest-daily",
# "continuous", "field-measurements-metadata",
-# "combined-metadata", "channel-measurements")
+# "combined-metadata", "channel-measurements", "peaks")
#
# property_list <- list()
# for(service in services){
diff --git a/R/readNWISunit.R b/R/readNWISunit.R
index 89399818f..fd6f5c88c 100644
--- a/R/readNWISunit.R
+++ b/R/readNWISunit.R
@@ -58,25 +58,10 @@
#' endDate <- "2014-10-10"
#' \donttest{
#'
-#' rawData <- readNWISuv(site_id, parameterCd, startDate, endDate)
+#' #rawData <- readNWISuv(site_id, parameterCd, startDate, endDate)
#'
-#' rawData_today <- readNWISuv(site_id, parameterCd, Sys.Date(), Sys.Date())
+#' #rawData_today <- readNWISuv(site_id, parameterCd, Sys.Date(), Sys.Date())
#'
-#' timeZoneChange <- readNWISuv(
-#' c("04024430", "04024000"), parameterCd,
-#' "2013-11-03", "2013-11-03"
-#' )
-#'
-#' centralTime <- readNWISuv(site_id, parameterCd,
-#' "2014-10-10T12:00", "2014-10-10T23:59",
-#' tz = "America/Chicago"
-#' )
-#'
-#' # Adding 'Z' to the time indicates to the web service to call the data with UTC time:
-#' GMTdata <- readNWISuv(
-#' site_id, parameterCd,
-#' "2014-10-10T00:00Z", "2014-10-10T23:59Z"
-#' )
#' }
readNWISuv <- function(
siteNumbers,
@@ -171,12 +156,12 @@ readNWISuv <- function(
#' @seealso [constructNWISURL()], [importRDB1()]
#' @export
#' @examplesIf is_dataRetrieval_user()
-#' site_ids <- c("01594440", "040851325")
+#' #site_ids <- c("01594440", "040851325")
#' \donttest{
-#' data <- readNWISpeak(site_ids)
-#' data2 <- readNWISpeak(site_ids, asDateTime = FALSE)
-#' stations <- c("06011000")
-#' peakdata <- readNWISpeak(stations, convertType = FALSE)
+#' #data <- readNWISpeak(site_ids)
+#' #data2 <- readNWISpeak(site_ids, asDateTime = FALSE)
+#' #stations <- c("06011000")
+#' #peakdata <- readNWISpeak(stations, convertType = FALSE)
#' }
readNWISpeak <- function(
siteNumbers,
@@ -185,8 +170,11 @@ readNWISpeak <- function(
asDateTime = TRUE,
convertType = TRUE
) {
- message(new_nwis_message())
-
+ .Deprecated(
+ new = "read_waterdata_peaks",
+ package = "dataRetrieval",
+ msg = "NWIS servers are slated for decommission. Please begin to migrate to read_waterdata_peaks."
+ )
# Doesn't seem to be a peak xml service
url <- constructNWISURL(
siteNumbers = siteNumbers,
@@ -276,8 +264,8 @@ readNWISpeak <- function(
#' @examplesIf is_dataRetrieval_user()
#' site_id <- "01594440"
#' \donttest{
-#' data <- readNWISrating(site_id, "base")
-#' attr(data, "RATING")
+#' #data <- readNWISrating(site_id, "base")
+#' #attr(data, "RATING")
#' }
readNWISrating <- function(siteNumber, type = "base", convertType = TRUE) {
.Deprecated(
@@ -354,28 +342,28 @@ readNWISrating <- function(siteNumber, type = "base", convertType = TRUE) {
#' @export
#' @examplesIf is_dataRetrieval_user()
#' \donttest{
-#' x1 <- readNWISstat(
-#' siteNumbers = c("02319394"),
-#' parameterCd = c("00060"),
-#' statReportType = "annual"
-#' )
+#' # x1 <- readNWISstat(
+#' # siteNumbers = c("02319394"),
+#' # parameterCd = c("00060"),
+#' # statReportType = "annual"
+#' # )
#'
#' # all the annual mean discharge data for two sites
-#' x2 <- readNWISstat(
-#' siteNumbers = c("02319394", "02171500"),
-#' parameterCd = c("00010", "00060"),
-#' statReportType = "annual"
-#' )
+#' #x2 <- readNWISstat(
+#' # siteNumbers = c("02319394", "02171500"),
+#' # parameterCd = c("00010", "00060"),
+#' # statReportType = "annual"
+#' # )
#'
#' # Request p25, p75, and mean values for temperature and discharge for the 2000s
#' # Note that p25 and p75 were not available for temperature, and return NAs
-#' x <- readNWISstat(
-#' siteNumbers = c("02171500"),
-#' parameterCd = c("00010", "00060"),
-#' statReportType = "daily",
-#' statType = c("mean", "median"),
-#' startDate = "2000", endDate = "2010"
-#' )
+#' #x <- readNWISstat(
+#' # siteNumbers = c("02171500"),
+#' # parameterCd = c("00010", "00060"),
+#' # statReportType = "daily",
+#' # statType = c("mean", "median"),
+#' # startDate = "2000", endDate = "2010"
+#' # )
#' }
readNWISstat <- function(
siteNumbers,
diff --git a/R/readWQPdata.R b/R/readWQPdata.R
index 92d70b67b..3f65c6263 100644
--- a/R/readWQPdata.R
+++ b/R/readWQPdata.R
@@ -86,47 +86,47 @@
#' \donttest{
#'
#' # Legacy:
-#' nameToUse <- "pH"
-#' pHData <- readWQPdata(siteid = "USGS-04024315",
-#' characteristicName = nameToUse)
-#' ncol(pHData)
-#' attr(pHData, "siteInfo")
-#' attr(pHData, "queryTime")
-#' attr(pHData, "url")
+#' #nameToUse <- "pH"
+#' #pHData <- readWQPdata(siteid = "USGS-04024315",
+#' # characteristicName = nameToUse)
+#' #ncol(pHData)
+#' #attr(pHData, "siteInfo")
+#' #attr(pHData, "queryTime")
+#' #attr(pHData, "url")
#'
#' # WQX3:
-#' pHData_wqx3 <- readWQPdata(siteid = "USGS-04024315",
-#' characteristicName = nameToUse,
-#' service = "ResultWQX3",
-#' dataProfile = "basicPhysChem")
-#' attr(pHData_wqx3, "url")
+#' #pHData_wqx3 <- readWQPdata(siteid = "USGS-04024315",
+#' # characteristicName = nameToUse,
+#' # service = "ResultWQX3",
+#' # dataProfile = "basicPhysChem")
+#' # attr(pHData_wqx3, "url")
#'
#' # More examples:
#' # querying by county
-#' DeWitt <- readWQPdata(
-#' statecode = "Illinois",
-#' countycode = "DeWitt",
-#' characteristicName = "Nitrogen"
-#' )
+#' #DeWitt <- readWQPdata(
+#' # statecode = "Illinois",
+#' # countycode = "DeWitt",
+#' # characteristicName = "Nitrogen"
+#' # )
#'
-#' attr(DeWitt, "url")
+#' #attr(DeWitt, "url")
#'
-#' DeWitt_wqx3 <- readWQPdata(
-#' statecode = "Illinois",
-#' countycode = "DeWitt",
-#' characteristicName = "Nitrogen",
-#' service = "ResultWQX3",
-#' dataProfile = "basicPhysChem",
-#' ignore_attributes = TRUE)
+#' #DeWitt_wqx3 <- readWQPdata(
+#' # statecode = "Illinois",
+#' # countycode = "DeWitt",
+#' # characteristicName = "Nitrogen",
+#' # service = "ResultWQX3",
+#' # dataProfile = "basicPhysChem",
+#' # ignore_attributes = TRUE)
#'
-#' attr(DeWitt_wqx3, "url")
+#' #attr(DeWitt_wqx3, "url")
#'
#' # Data profile: "Sampling Activity"
-#' activity <- readWQPdata(
-#' siteid = "USGS-04024315",
-#' service = "Activity"
-#' )
-#' attr(activity, "url")
+#' #activity <- readWQPdata(
+#' # siteid = "USGS-04024315",
+#' # service = "Activity"
+#' #)
+#' #attr(activity, "url")
#'
#' # activity_wqx3 <- readWQPdata(
#' # siteid = "USGS-04024315",
@@ -134,14 +134,14 @@
#' # )
#' # attr(activity_wqx3, "url")
#'
-#' Dane_activity <- readWQPdata(
-#' statecode = "Wisconsin",
-#' countycode = "Dane",
-#' startDateLo = "2023-01-01",
-#' startDateHi = "2023-12-31",
-#' service = "Activity"
-#' )
-#' attr(Dane_activity, "url")
+#' #Dane_activity <- readWQPdata(
+#' # statecode = "Wisconsin",
+#' # countycode = "Dane",
+#' # startDateLo = "2023-01-01",
+#' # startDateHi = "2023-12-31",
+#' # service = "Activity"
+#' # )
+#' #attr(Dane_activity, "url")
#'
#' # Dane_activity_wqx3 <- readWQPdata(
#' # statecode = "Wisconsin",
@@ -157,47 +157,47 @@
#'
#'
#' # Data profiles: "Organization Data"
-#' org_data <- readWQPdata(
-#' statecode = "WI",
-#' countycode = "Dane",
-#' service = "Organization"
-#' )
+#' #org_data <- readWQPdata(
+#' # statecode = "WI",
+#' # countycode = "Dane",
+#' # service = "Organization"
+#' # )
#'
#' # Data profiles: "Project Data"
-#' project_data <- readWQPdata(
-#' statecode = "WI",
-#' countycode = "Dane",
-#' service = "Project"
-#' )
+#' #project_data <- readWQPdata(
+#' # statecode = "WI",
+#' # countycode = "Dane",
+#' # service = "Project"
+#' # )
#'
#' # Data profiles: "Project Monitoring Location Weighting Data"
-#' proj_mlwd <- readWQPdata(
-#' statecode = "WI",
-#' countycode = "Dane",
-#' service = "ProjectMonitoringLocationWeighting"
-#' )
+#' #proj_mlwd <- readWQPdata(
+#' # statecode = "WI",
+#' # countycode = "Dane",
+#' # service = "ProjectMonitoringLocationWeighting"
+#' # )
#'
#' # Data profiles: "Sample Results (physical/chemical metadata)"
-#' samp_data <- readWQPdata(
-#' siteid = "USGS-04024315",
-#' dataProfile = "resultPhysChem",
-#' service = "Result"
-#' )
+#' # samp_data <- readWQPdata(
+#' # siteid = "USGS-04024315",
+#' # dataProfile = "resultPhysChem",
+#' # service = "Result"
+#' # )
#'
#' # Data profiles: "Sample Results (biological metadata)"
-#' samp_bio <- readWQPdata(
-#' siteid = "USGS-04024315",
-#' dataProfile = "biological",
-#' service = "Result"
-#' )
+#' #samp_bio <- readWQPdata(
+#' # siteid = "USGS-04024315",
+#' # dataProfile = "biological",
+#' # service = "Result"
+#' # )
#'
#'
#' # Data profiles: "Sample Results (narrow)"
-#' samp_narrow <- readWQPdata(
-#' siteid = "USGS-04024315",
-#' service = "Result",
-#' dataProfile = "narrowResult"
-#' )
+#' # samp_narrow <- readWQPdata(
+#' # siteid = "USGS-04024315",
+#' # service = "Result",
+#' # dataProfile = "narrowResult"
+#' # )
#'
#' # samp_narrow_wqx3 <- readWQPdata(
#' # siteid = "USGS-04024315",
@@ -207,38 +207,38 @@
#'
#'
#' # Data profiles: "Sampling Activity"
-#' samp_activity <- readWQPdata(
-#' siteid = "USGS-04024315",
-#' dataProfile = "activityAll",
-#' service = "Activity"
-#' )
+#' #samp_activity <- readWQPdata(
+#' # siteid = "USGS-04024315",
+#' # dataProfile = "activityAll",
+#' # service = "Activity"
+#' # )
#'
#' # Data profile: "Sampling Activity Metrics"
-#' act_metrics <- readWQPdata(
-#' statecode = "WI",
-#' countycode = "Dane",
-#' service = "ActivityMetric"
-#' )
+#' # act_metrics <- readWQPdata(
+#' # statecode = "WI",
+#' # countycode = "Dane",
+#' # service = "ActivityMetric"
+#' # )
#'
#' # Data profile: "Result Detection Quantitation Limit Data"
-#' dl_data <- readWQPdata(
-#' siteid = "USGS-04024315",
-#' service = "ResultDetectionQuantitationLimit"
-#' )
+#' # dl_data <- readWQPdata(
+#' # siteid = "USGS-04024315",
+#' # service = "ResultDetectionQuantitationLimit"
+#' # )
#'
#' # other options:
-#' Phosphorus <- readWQPdata(
-#' statecode = "WI", countycode = "Dane",
-#' characteristicName = "Phosphorus",
-#' startDateLo = "2023-01-01",
-#' ignore_attributes = TRUE,
-#' convertType = FALSE
-#' )
-#'
-#' rawPHsites_legacy <- readWQPdata(siteid = c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
-#' characteristicName = "pH",
-#' service = "Result",
-#' dataProfile = "narrowResult" )
+#' # Phosphorus <- readWQPdata(
+#' # statecode = "WI", countycode = "Dane",
+#' # characteristicName = "Phosphorus",
+#' # startDateLo = "2023-01-01",
+#' # ignore_attributes = TRUE,
+#' # convertType = FALSE
+#' # )
+#'
+#' #rawPHsites_legacy <- readWQPdata(siteid = c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
+#' # characteristicName = "pH",
+#' # service = "Result",
+#' # dataProfile = "narrowResult" )
#'
#' # rawPHsites <- readWQPdata(siteid = c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
#' # characteristicName = "pH",
@@ -416,12 +416,12 @@ create_WQP_attributes <- function(retval, ...) {
#'
#' @examplesIf is_dataRetrieval_user()
#' \donttest{
-#' rawPcode <- readWQPqw("USGS-01594440", "01075",
-#' ignore_attributes = TRUE, legacy = FALSE)
-#' headerInfo <- attr(rawPcode, "headerInfo")
-#' wqp_request_id <- headerInfo$`wqp-request-id`
-#' count_info <- wqp_check_status(wqp_request_id)
-#' count_info[["dataProviders"]]
+#' #rawPcode <- readWQPqw("USGS-01594440", "01075",
+#' # ignore_attributes = TRUE, legacy = FALSE)
+#' # headerInfo <- attr(rawPcode, "headerInfo")
+#' #wqp_request_id <- headerInfo$`wqp-request-id`
+#' #count_info <- wqp_check_status(wqp_request_id)
+#' #count_info[["dataProviders"]]
#' }
wqp_check_status <- function(wqp_request_id) {
id_url <- paste0(pkg.env[["status"]], wqp_request_id)
diff --git a/R/readWQPqw.R b/R/readWQPqw.R
index 0762b4418..92d5403b4 100644
--- a/R/readWQPqw.R
+++ b/R/readWQPqw.R
@@ -51,28 +51,28 @@
#' and [importWQP()]
#' @examplesIf is_dataRetrieval_user()
#' \donttest{
-#' rawPcode <- readWQPqw("USGS-01594440", "01075", "", "")
+#' #rawPcode <- readWQPqw("USGS-01594440", "01075", "", "")
#'
-#' attr(rawPcode, "siteInfo")
-#' attr(rawPcode, "queryTime")
-#' attr(rawPcode, "url")
+#' #attr(rawPcode, "siteInfo")
+#' #attr(rawPcode, "queryTime")
+#' #attr(rawPcode, "url")
#'
-#' rawCharacteristicName <- readWQPqw("WIDNR_WQX-10032762", "Specific conductance", "", "")
-#' pHsites_legacy <- readWQPqw(c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
-#' "pH", "", "")
-#' ncol(pHsites_legacy)
-#' attr(pHsites_legacy, "url")
+#' #rawCharacteristicName <- readWQPqw("WIDNR_WQX-10032762", "Specific conductance", "", "")
+#' #pHsites_legacy <- readWQPqw(c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
+#' # "pH", "", "")
+#' #ncol(pHsites_legacy)
+#' #attr(pHsites_legacy, "url")
#'
#' # pHsites_modern <- readWQPqw(c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
#' # "pH", "", "", legacy = FALSE)
#' # ncol(pHsites_modern)
#' # attr(pHsites_modern, "url")
#'
-#' nwisEx <- readWQPqw("USGS-04024000", c("34247", "30234", "32104", "34220"), "", "2022-12-20")
+#' # nwisEx <- readWQPqw("USGS-04024000", c("34247", "30234", "32104", "34220"), "", "2022-12-20")
#'
-#' DO <- readWQPqw(siteNumbers = "USGS-05288705",
-#' parameterCd = "00300",
-#' convertType = FALSE)
+#' # DO <- readWQPqw(siteNumbers = "USGS-05288705",
+#' # parameterCd = "00300",
+#' # convertType = FALSE)
#' }
readWQPqw <- function(
siteNumbers,
diff --git a/R/read_waterdata_field_measurements.R b/R/read_waterdata_field_measurements.R
index d0718abe6..25d822569 100644
--- a/R/read_waterdata_field_measurements.R
+++ b/R/read_waterdata_field_measurements.R
@@ -20,7 +20,12 @@
#' See also Details below for more information.
#' @param qualifier `r get_ogc_params("field-measurements")$qualifier`
#' @param field_visit_id `r get_ogc_params("field-measurements")$field_visit_id`
-#' @param field_measurements_series_id `r get_ogc_params("field-measurements")$field_measurements_series_id`
+#' @param field_measurements_series_id A unique identifier representing a single
+#' collection series. This corresponds to the `field_measurements_series_id` field in the
+#' `read_waterdata_field_meta` endpoint. Collection series are defined as the
+#' set of field measurements at a given monitoring location for a single parameter
+#' code using a single reading type.
+#'
#' @param vertical_datum `r get_ogc_params("field-measurements")$vertical_datum`
#' @param measuring_agency `r get_ogc_params("field-measurements")$measuring_agency`
#' @param control_condition `r get_ogc_params("field-measurements")$control_condition`
diff --git a/R/read_waterdata_field_meta.R b/R/read_waterdata_field_meta.R
index 4df6e2ac5..b45df0154 100644
--- a/R/read_waterdata_field_meta.R
+++ b/R/read_waterdata_field_meta.R
@@ -85,7 +85,7 @@ read_waterdata_field_meta <- function(
attach_request = getOption("dataRetrieval.attach_request")
) {
service <- "field-measurements-metadata"
- output_id <- "field_series_id"
+ output_id <- "field_measurements_series_id"
rlang::check_dots_empty()
args <- mget(names(formals()))
diff --git a/R/read_waterdata_peaks.R b/R/read_waterdata_peaks.R
new file mode 100644
index 000000000..3837a4c9a
--- /dev/null
+++ b/R/read_waterdata_peaks.R
@@ -0,0 +1,81 @@
+#' Get USGS Peak Data
+#'
+#' @description `r get_description("peaks")`
+#'
+#' @export
+#' @param monitoring_location_id `r get_ogc_params("peaks")$monitoring_location_id`
+#' Multiple monitoring_location_ids can be requested as a character vector.
+#' @param parameter_code `r get_ogc_params("peaks")$parameter_code`
+#' Multiple parameter_codes can be requested as a character vector.
+#' @param time `r get_ogc_params("peaks")$time`
+#'
+#' See also Details below for more information.
+#' @param value `r get_ogc_params("peaks")$value`
+#' @param unit_of_measure `r get_ogc_params("peaks")$unit_of_measure`
+#' @param time_series_id `r get_ogc_params("peaks")$time_series_id`
+#' @param last_modified `r get_ogc_params("peaks")$last_modified`
+#'
+#' See also Details below for more information.
+#' @param water_year `r get_ogc_params("peaks")$water_year`
+#' @param year `r get_ogc_params("peaks")$year`
+#' @param month `r get_ogc_params("peaks")$month`
+#' @param day `r get_ogc_params("peaks")$day`
+#' @param time_of_day `r get_ogc_params("peaks")$time_of_day`
+#' @param peak_since `r get_ogc_params("peaks")$peak_since`
+#' @param properties A vector of requested columns to be returned from the query.
+#' Available options are:
+#' `r dataRetrieval:::get_properties_for_docs("peaks", "peak_id")`.
+#' The default (`NA`) will return all columns of the data.
+#'
+#' @inheritParams check_arguments_api
+#' @inheritParams check_arguments_non_api
+#'
+#' @inherit read_waterdata_continuous details
+#'
+#' @examplesIf is_dataRetrieval_user()
+#'
+#' \donttest{
+#' wi_peaks <- read_waterdata_combined_meta(
+#' state_name = "Wisconsin",
+#' data_type = "Peaks",
+#' parameter_code = "00060")
+#'
+#'
+#' dv_data_sf <- read_waterdata_peaks(
+#' monitoring_location_id = wi_peaks$monitoring_location_id[1],
+#' parameter_code = "00060")
+#'
+#' }
+read_waterdata_peaks <- function(
+ monitoring_location_id = NA_character_,
+ parameter_code = NA_character_,
+ properties = NA_character_,
+ time_series_id = NA_character_,
+ unit_of_measure = NA_character_,
+ value = NA,
+ last_modified = NA_character_,
+ water_year = NA_character_,
+ year = NA_character_,
+ month = NA_character_,
+ day = NA_character_,
+ time_of_day = NA_character_,
+ peak_since = NA_character_,
+ skipGeometry = NA,
+ time = NA_character_,
+ bbox = NA,
+ ...,
+ convertType = getOption("dataRetrieval.convertType"),
+ no_paging = getOption("dataRetrieval.no_paging"),
+ chunk_size = getOption("dataRetrieval.site_chunk_size_meta"),
+ limit = getOption("dataRetrieval.limit"),
+ attach_request = getOption("dataRetrieval.attach_request")
+) {
+ service <- "peaks"
+ output_id <- "peak_id"
+ rlang::check_dots_empty()
+
+ args <- mget(names(formals()))
+ return_list <- get_ogc_data(args, output_id, service)
+
+ return(return_list)
+}
diff --git a/R/read_waterdata_samples.R b/R/read_waterdata_samples.R
index 66e005782..3ef74e805 100644
--- a/R/read_waterdata_samples.R
+++ b/R/read_waterdata_samples.R
@@ -66,7 +66,7 @@
#' @param recordIdentifierUserSupplied Record identifier, user supplied identifier. This
#' information would be needed from the data supplier.
#' @param siteTypeName Site type name query parameter. See available
-#' options by running `check_param("sitetype")$typeName`.
+#' options by running `check_waterdata_sample_params("sitetype")$typeName`.
#' @param usgsPCode USGS parameter code. See available options by running
#' `check_waterdata_sample_params("characteristics")$parameterCode`.
#' @param pointLocationLatitude Latitude for a point/radius query (decimal degrees). Must be used
diff --git a/R/whatWQPdata.R b/R/whatWQPdata.R
index 48e576030..98e1e9988 100644
--- a/R/whatWQPdata.R
+++ b/R/whatWQPdata.R
@@ -6,14 +6,14 @@
#' @examples
#' \donttest{
#'
-#' site1 <- whatWQPsamples(siteid = "USGS-01594440")
+#' #site1 <- whatWQPsamples(siteid = "USGS-01594440")
#'
-#' type <- "Stream"
+#' #type <- "Stream"
#'
-#' sites <- whatWQPsamples(countycode = "US:55:025", siteType = type)
+#' #sites <- whatWQPsamples(countycode = "US:55:025", siteType = type)
#'
-#' lakeSites_samples <- whatWQPsamples(siteType = "Lake, Reservoir, Impoundment",
-#' countycode = "US:55:025")
+#' #lakeSites_samples <- whatWQPsamples(siteType = "Lake, Reservoir, Impoundment",
+#' # countycode = "US:55:025")
#' }
whatWQPsamples <- function(..., convertType = TRUE, legacy = TRUE) {
values <- readWQPdots(..., legacy = legacy)
@@ -81,11 +81,11 @@ whatWQPsamples <- function(..., convertType = TRUE, legacy = TRUE) {
#' @examples
#' \donttest{
#'
-#' type <- "Stream"
+#' #type <- "Stream"
#'
-#' sites <- whatWQPmetrics(countycode = "US:55:025", siteType = type)
-#' lakeSites_metrics <- whatWQPmetrics(siteType = "Lake, Reservoir, Impoundment",
-#' countycode = "US:55:025")
+#' #sites <- whatWQPmetrics(countycode = "US:55:025", siteType = type)
+#' #lakeSites_metrics <- whatWQPmetrics(siteType = "Lake, Reservoir, Impoundment",
+#' # countycode = "US:55:025")
#' }
whatWQPmetrics <- function(..., convertType = TRUE) {
values <- readWQPdots(..., legacy = TRUE)
@@ -182,20 +182,20 @@ whatWQPmetrics <- function(..., convertType = TRUE) {
#' @seealso whatWQPsites readWQPsummary readWQPdata
#' @examplesIf is_dataRetrieval_user()
#' \donttest{
-#' site1 <- whatWQPdata(siteid = "USGS-01594440")
+#' #site1 <- whatWQPdata(siteid = "USGS-01594440")
#'
-#' type <- "Stream"
-#' sites <- whatWQPdata(countycode = "US:55:025", siteType = type)
+#' #type <- "Stream"
+#' #sites <- whatWQPdata(countycode = "US:55:025", siteType = type)
#'
-#' lakeSites <- whatWQPdata(siteType = "Lake, Reservoir, Impoundment",
-#' countycode = "US:55:025")
-#' lakeSites_chars <- whatWQPdata(
-#' siteType = "Lake, Reservoir, Impoundment",
-#' countycode = "US:55:025", convertType = FALSE)
+#' #lakeSites <- whatWQPdata(siteType = "Lake, Reservoir, Impoundment",
+#' # countycode = "US:55:025")
+#' #lakeSites_chars <- whatWQPdata(
+#' # siteType = "Lake, Reservoir, Impoundment",
+#' # countycode = "US:55:025", convertType = FALSE)
#'
#'
-#' bbox <- c(-86.9736, 34.4883, -86.6135, 34.6562)
-#' what_bb <- whatWQPdata(bBox = bbox)
+#' #bbox <- c(-86.9736, 34.4883, -86.6135, 34.6562)
+#' #what_bb <- whatWQPdata(bBox = bbox)
#' }
whatWQPdata <- function(..., convertType = TRUE) {
args <- convertLists(...)
diff --git a/R/whatWQPsites.R b/R/whatWQPsites.R
index f18677309..08a2fde40 100644
--- a/R/whatWQPsites.R
+++ b/R/whatWQPsites.R
@@ -36,14 +36,14 @@
#' @examplesIf is_dataRetrieval_user()
#' \donttest{
#'
-#' site1 <- whatWQPsites(siteid = "USGS-01594440")
+#' #site1 <- whatWQPsites(siteid = "USGS-01594440")
#'
-#' type <- "Stream"
-#' sites <- whatWQPsites(
-#' countycode = "US:55:025",
-#' characteristicName = "Phosphorus",
-#' siteType = type
-#' )
+#' #type <- "Stream"
+#' #sites <- whatWQPsites(
+#' # countycode = "US:55:025",
+#' # characteristicName = "Phosphorus",
+#' # siteType = type
+#' #)
#' }
whatWQPsites <- function(..., legacy = TRUE, convertType = TRUE) {
values <- readWQPdots(..., legacy = legacy)
@@ -118,36 +118,36 @@ whatWQPsites <- function(..., legacy = TRUE, convertType = TRUE) {
#' @examplesIf is_dataRetrieval_user()
#' \donttest{
#' # Summary of a single site for the last 5 years:
-#' site_5 <- readWQPsummary(
-#' siteid = "USGS-07144100",
-#' summaryYears = 5
-#' )
+#' #site_5 <- readWQPsummary(
+#' # siteid = "USGS-07144100",
+#' # summaryYears = 5
+#'# )
#'
#' # Summary of a single site for the full period of record:
-#' site_all <- readWQPsummary(
-#' siteid = "USGS-07144100",
-#' summaryYears = "all"
-#' )
+#' #site_all <- readWQPsummary(
+#' # siteid = "USGS-07144100",
+#' # summaryYears = "all"
+#' # )
#'
#' # Summary of the data available from streams in a single county:
-#' dane_county_data <- readWQPsummary(
-#' countycode = "US:55:025",
-#' summaryYears = 5,
-#' siteType = "Stream"
-#' )
+#' # dane_county_data <- readWQPsummary(
+#' # countycode = "US:55:025",
+#' # summaryYears = 5,
+#' # siteType = "Stream"
+#' # )
#'
#' # Summary of the data all available from lakes in a single county:
-#' lake_sites <- readWQPsummary(
-#' siteType = "Lake, Reservoir, Impoundment",
-#' countycode = "US:55:025"
-#' )
+#' # lake_sites <- readWQPsummary(
+#' # siteType = "Lake, Reservoir, Impoundment",
+#' # countycode = "US:55:025"
+#' # )
#'
#' # Summary of the data available for the last 5 years in New Jersey:
-#' state1 <- readWQPsummary(
-#' statecode = "NJ",
-#' summaryYears = 5,
-#' siteType = "Stream"
-#' )
+#' #state1 <- readWQPsummary(
+#' # statecode = "NJ",
+#' # summaryYears = 5,
+#' # siteType = "Stream"
+#' # )
#' }
readWQPsummary <- function(...) {
wqp_message()
diff --git a/_pkgdown.yml b/_pkgdown.yml
index df8a331bf..6dc8a7711 100644
--- a/_pkgdown.yml
+++ b/_pkgdown.yml
@@ -90,6 +90,7 @@ reference:
- read_waterdata_field_meta
- read_waterdata_combined_meta
- read_waterdata_ratings
+ - read_waterdata_peaks
- title: National Water Information System (NWIS)
desc: Functions to retrieve (USGS) NWIS data. These will be slowly phased out and replaced with the read_waterdata family of functions.
contents:
diff --git a/environment.yml b/environment.yml
index 823381120..2244b414b 100644
--- a/environment.yml
+++ b/environment.yml
@@ -24,7 +24,7 @@ dependencies:
- pip=25.2=pyh8b19718_0
- python=3.11.8=hab00c5b_0_cpython
- readline=8.2=h8c095d6_2
- - scipy
+ - matplotlib
- setuptools=80.9.0=pyhff2d567_0
- tk=8.6.13=noxft_hd72426e_102
- tzdata=2025b=h78e105d_0
diff --git a/man/construct_waterdata_sample_request.Rd b/man/construct_waterdata_sample_request.Rd
index e6489e925..0ab3f968b 100644
--- a/man/construct_waterdata_sample_request.Rd
+++ b/man/construct_waterdata_sample_request.Rd
@@ -100,7 +100,7 @@ would be needed from prior project information.}
information would be needed from the data supplier.}
\item{siteTypeName}{Site type name query parameter. See available
-options by running \code{check_param("sitetype")$typeName}.}
+options by running \code{check_waterdata_sample_params("sitetype")$typeName}.}
\item{usgsPCode}{USGS parameter code. See available options by running
\code{check_waterdata_sample_params("characteristics")$parameterCode}.}
diff --git a/man/readNWISpeak.Rd b/man/readNWISpeak.Rd
index f36a4007b..c07c8a96a 100644
--- a/man/readNWISpeak.Rd
+++ b/man/readNWISpeak.Rd
@@ -77,12 +77,12 @@ R Date objects.
}
\examples{
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
-site_ids <- c("01594440", "040851325")
+#site_ids <- c("01594440", "040851325")
\donttest{
-data <- readNWISpeak(site_ids)
-data2 <- readNWISpeak(site_ids, asDateTime = FALSE)
-stations <- c("06011000")
-peakdata <- readNWISpeak(stations, convertType = FALSE)
+#data <- readNWISpeak(site_ids)
+#data2 <- readNWISpeak(site_ids, asDateTime = FALSE)
+#stations <- c("06011000")
+#peakdata <- readNWISpeak(stations, convertType = FALSE)
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/readNWISrating.Rd b/man/readNWISrating.Rd
index 0aaafcb90..cf520780a 100644
--- a/man/readNWISrating.Rd
+++ b/man/readNWISrating.Rd
@@ -48,8 +48,8 @@ relate flow to stage.
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
site_id <- "01594440"
\donttest{
-data <- readNWISrating(site_id, "base")
-attr(data, "RATING")
+#data <- readNWISrating(site_id, "base")
+#attr(data, "RATING")
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/readNWISstat.Rd b/man/readNWISstat.Rd
index e2d9907cf..ab394f0a0 100644
--- a/man/readNWISstat.Rd
+++ b/man/readNWISstat.Rd
@@ -62,28 +62,28 @@ Retrieves site statistics from the USGS Statistics Web Service beta.
\examples{
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
\donttest{
-x1 <- readNWISstat(
- siteNumbers = c("02319394"),
- parameterCd = c("00060"),
- statReportType = "annual"
-)
+# x1 <- readNWISstat(
+# siteNumbers = c("02319394"),
+# parameterCd = c("00060"),
+# statReportType = "annual"
+# )
# all the annual mean discharge data for two sites
-x2 <- readNWISstat(
- siteNumbers = c("02319394", "02171500"),
- parameterCd = c("00010", "00060"),
- statReportType = "annual"
-)
+#x2 <- readNWISstat(
+# siteNumbers = c("02319394", "02171500"),
+# parameterCd = c("00010", "00060"),
+# statReportType = "annual"
+# )
# Request p25, p75, and mean values for temperature and discharge for the 2000s
# Note that p25 and p75 were not available for temperature, and return NAs
-x <- readNWISstat(
- siteNumbers = c("02171500"),
- parameterCd = c("00010", "00060"),
- statReportType = "daily",
- statType = c("mean", "median"),
- startDate = "2000", endDate = "2010"
-)
+#x <- readNWISstat(
+# siteNumbers = c("02171500"),
+# parameterCd = c("00010", "00060"),
+# statReportType = "daily",
+# statType = c("mean", "median"),
+# startDate = "2000", endDate = "2010"
+# )
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/readNWISuv.Rd b/man/readNWISuv.Rd
index f2bf779c7..2878063f3 100644
--- a/man/readNWISuv.Rd
+++ b/man/readNWISuv.Rd
@@ -69,25 +69,10 @@ startDate <- "2014-10-10"
endDate <- "2014-10-10"
\donttest{
-rawData <- readNWISuv(site_id, parameterCd, startDate, endDate)
+#rawData <- readNWISuv(site_id, parameterCd, startDate, endDate)
-rawData_today <- readNWISuv(site_id, parameterCd, Sys.Date(), Sys.Date())
+#rawData_today <- readNWISuv(site_id, parameterCd, Sys.Date(), Sys.Date())
-timeZoneChange <- readNWISuv(
- c("04024430", "04024000"), parameterCd,
- "2013-11-03", "2013-11-03"
-)
-
-centralTime <- readNWISuv(site_id, parameterCd,
- "2014-10-10T12:00", "2014-10-10T23:59",
- tz = "America/Chicago"
-)
-
-# Adding 'Z' to the time indicates to the web service to call the data with UTC time:
-GMTdata <- readNWISuv(
- site_id, parameterCd,
- "2014-10-10T00:00Z", "2014-10-10T23:59Z"
-)
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/readWQPdata.Rd b/man/readWQPdata.Rd
index 68680d59c..a2a915b44 100644
--- a/man/readWQPdata.Rd
+++ b/man/readWQPdata.Rd
@@ -105,47 +105,47 @@ Sampling Activity \tab ActivityWQX3 \tab /wqx3/Activity/search \cr
\donttest{
# Legacy:
-nameToUse <- "pH"
-pHData <- readWQPdata(siteid = "USGS-04024315",
- characteristicName = nameToUse)
-ncol(pHData)
-attr(pHData, "siteInfo")
-attr(pHData, "queryTime")
-attr(pHData, "url")
+#nameToUse <- "pH"
+#pHData <- readWQPdata(siteid = "USGS-04024315",
+# characteristicName = nameToUse)
+#ncol(pHData)
+#attr(pHData, "siteInfo")
+#attr(pHData, "queryTime")
+#attr(pHData, "url")
# WQX3:
-pHData_wqx3 <- readWQPdata(siteid = "USGS-04024315",
- characteristicName = nameToUse,
- service = "ResultWQX3",
- dataProfile = "basicPhysChem")
-attr(pHData_wqx3, "url")
+#pHData_wqx3 <- readWQPdata(siteid = "USGS-04024315",
+# characteristicName = nameToUse,
+# service = "ResultWQX3",
+# dataProfile = "basicPhysChem")
+# attr(pHData_wqx3, "url")
# More examples:
# querying by county
-DeWitt <- readWQPdata(
- statecode = "Illinois",
- countycode = "DeWitt",
- characteristicName = "Nitrogen"
-)
+#DeWitt <- readWQPdata(
+# statecode = "Illinois",
+# countycode = "DeWitt",
+# characteristicName = "Nitrogen"
+# )
-attr(DeWitt, "url")
+#attr(DeWitt, "url")
-DeWitt_wqx3 <- readWQPdata(
- statecode = "Illinois",
- countycode = "DeWitt",
- characteristicName = "Nitrogen",
- service = "ResultWQX3",
- dataProfile = "basicPhysChem",
- ignore_attributes = TRUE)
+#DeWitt_wqx3 <- readWQPdata(
+# statecode = "Illinois",
+# countycode = "DeWitt",
+# characteristicName = "Nitrogen",
+# service = "ResultWQX3",
+# dataProfile = "basicPhysChem",
+# ignore_attributes = TRUE)
-attr(DeWitt_wqx3, "url")
+#attr(DeWitt_wqx3, "url")
# Data profile: "Sampling Activity"
-activity <- readWQPdata(
- siteid = "USGS-04024315",
- service = "Activity"
-)
-attr(activity, "url")
+#activity <- readWQPdata(
+# siteid = "USGS-04024315",
+# service = "Activity"
+#)
+#attr(activity, "url")
# activity_wqx3 <- readWQPdata(
# siteid = "USGS-04024315",
@@ -153,14 +153,14 @@ attr(activity, "url")
# )
# attr(activity_wqx3, "url")
-Dane_activity <- readWQPdata(
- statecode = "Wisconsin",
- countycode = "Dane",
- startDateLo = "2023-01-01",
- startDateHi = "2023-12-31",
- service = "Activity"
-)
-attr(Dane_activity, "url")
+#Dane_activity <- readWQPdata(
+# statecode = "Wisconsin",
+# countycode = "Dane",
+# startDateLo = "2023-01-01",
+# startDateHi = "2023-12-31",
+# service = "Activity"
+# )
+#attr(Dane_activity, "url")
# Dane_activity_wqx3 <- readWQPdata(
# statecode = "Wisconsin",
@@ -176,47 +176,47 @@ attr(Dane_activity, "url")
# Data profiles: "Organization Data"
-org_data <- readWQPdata(
- statecode = "WI",
- countycode = "Dane",
- service = "Organization"
-)
+#org_data <- readWQPdata(
+# statecode = "WI",
+# countycode = "Dane",
+# service = "Organization"
+# )
# Data profiles: "Project Data"
-project_data <- readWQPdata(
- statecode = "WI",
- countycode = "Dane",
- service = "Project"
-)
+#project_data <- readWQPdata(
+# statecode = "WI",
+# countycode = "Dane",
+# service = "Project"
+# )
# Data profiles: "Project Monitoring Location Weighting Data"
-proj_mlwd <- readWQPdata(
- statecode = "WI",
- countycode = "Dane",
- service = "ProjectMonitoringLocationWeighting"
-)
+#proj_mlwd <- readWQPdata(
+# statecode = "WI",
+# countycode = "Dane",
+# service = "ProjectMonitoringLocationWeighting"
+# )
# Data profiles: "Sample Results (physical/chemical metadata)"
-samp_data <- readWQPdata(
- siteid = "USGS-04024315",
- dataProfile = "resultPhysChem",
- service = "Result"
-)
+# samp_data <- readWQPdata(
+# siteid = "USGS-04024315",
+# dataProfile = "resultPhysChem",
+# service = "Result"
+# )
# Data profiles: "Sample Results (biological metadata)"
-samp_bio <- readWQPdata(
- siteid = "USGS-04024315",
- dataProfile = "biological",
- service = "Result"
-)
+#samp_bio <- readWQPdata(
+# siteid = "USGS-04024315",
+# dataProfile = "biological",
+# service = "Result"
+# )
# Data profiles: "Sample Results (narrow)"
-samp_narrow <- readWQPdata(
- siteid = "USGS-04024315",
- service = "Result",
- dataProfile = "narrowResult"
-)
+# samp_narrow <- readWQPdata(
+# siteid = "USGS-04024315",
+# service = "Result",
+# dataProfile = "narrowResult"
+# )
# samp_narrow_wqx3 <- readWQPdata(
# siteid = "USGS-04024315",
@@ -226,38 +226,38 @@ samp_narrow <- readWQPdata(
# Data profiles: "Sampling Activity"
-samp_activity <- readWQPdata(
- siteid = "USGS-04024315",
- dataProfile = "activityAll",
- service = "Activity"
-)
+#samp_activity <- readWQPdata(
+# siteid = "USGS-04024315",
+# dataProfile = "activityAll",
+# service = "Activity"
+# )
# Data profile: "Sampling Activity Metrics"
-act_metrics <- readWQPdata(
- statecode = "WI",
- countycode = "Dane",
- service = "ActivityMetric"
-)
+# act_metrics <- readWQPdata(
+# statecode = "WI",
+# countycode = "Dane",
+# service = "ActivityMetric"
+# )
# Data profile: "Result Detection Quantitation Limit Data"
-dl_data <- readWQPdata(
- siteid = "USGS-04024315",
- service = "ResultDetectionQuantitationLimit"
-)
+# dl_data <- readWQPdata(
+# siteid = "USGS-04024315",
+# service = "ResultDetectionQuantitationLimit"
+# )
# other options:
-Phosphorus <- readWQPdata(
- statecode = "WI", countycode = "Dane",
- characteristicName = "Phosphorus",
- startDateLo = "2023-01-01",
- ignore_attributes = TRUE,
- convertType = FALSE
-)
+# Phosphorus <- readWQPdata(
+# statecode = "WI", countycode = "Dane",
+# characteristicName = "Phosphorus",
+# startDateLo = "2023-01-01",
+# ignore_attributes = TRUE,
+# convertType = FALSE
+# )
-rawPHsites_legacy <- readWQPdata(siteid = c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
- characteristicName = "pH",
- service = "Result",
- dataProfile = "narrowResult" )
+#rawPHsites_legacy <- readWQPdata(siteid = c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
+# characteristicName = "pH",
+# service = "Result",
+# dataProfile = "narrowResult" )
# rawPHsites <- readWQPdata(siteid = c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
# characteristicName = "pH",
diff --git a/man/readWQPqw.Rd b/man/readWQPqw.Rd
index 5049d688e..e0fbd54d4 100644
--- a/man/readWQPqw.Rd
+++ b/man/readWQPqw.Rd
@@ -77,28 +77,28 @@ site name, such as 'USGS-01234567'.
\examples{
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
\donttest{
-rawPcode <- readWQPqw("USGS-01594440", "01075", "", "")
+#rawPcode <- readWQPqw("USGS-01594440", "01075", "", "")
-attr(rawPcode, "siteInfo")
-attr(rawPcode, "queryTime")
-attr(rawPcode, "url")
+#attr(rawPcode, "siteInfo")
+#attr(rawPcode, "queryTime")
+#attr(rawPcode, "url")
-rawCharacteristicName <- readWQPqw("WIDNR_WQX-10032762", "Specific conductance", "", "")
-pHsites_legacy <- readWQPqw(c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
- "pH", "", "")
-ncol(pHsites_legacy)
-attr(pHsites_legacy, "url")
+#rawCharacteristicName <- readWQPqw("WIDNR_WQX-10032762", "Specific conductance", "", "")
+#pHsites_legacy <- readWQPqw(c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
+# "pH", "", "")
+#ncol(pHsites_legacy)
+#attr(pHsites_legacy, "url")
# pHsites_modern <- readWQPqw(c("USGS-05406450", "USGS-05427949", "WIDNR_WQX-133040"),
# "pH", "", "", legacy = FALSE)
# ncol(pHsites_modern)
# attr(pHsites_modern, "url")
-nwisEx <- readWQPqw("USGS-04024000", c("34247", "30234", "32104", "34220"), "", "2022-12-20")
+# nwisEx <- readWQPqw("USGS-04024000", c("34247", "30234", "32104", "34220"), "", "2022-12-20")
-DO <- readWQPqw(siteNumbers = "USGS-05288705",
- parameterCd = "00300",
- convertType = FALSE)
+# DO <- readWQPqw(siteNumbers = "USGS-05288705",
+# parameterCd = "00300",
+# convertType = FALSE)
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/readWQPsummary.Rd b/man/readWQPsummary.Rd
index 9dfd922d0..a939331ee 100644
--- a/man/readWQPsummary.Rd
+++ b/man/readWQPsummary.Rd
@@ -36,36 +36,36 @@ available data at the WQP sites, and some metadata on the sites themselves.
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
\donttest{
# Summary of a single site for the last 5 years:
-site_5 <- readWQPsummary(
- siteid = "USGS-07144100",
- summaryYears = 5
-)
+#site_5 <- readWQPsummary(
+# siteid = "USGS-07144100",
+# summaryYears = 5
+# )
# Summary of a single site for the full period of record:
-site_all <- readWQPsummary(
- siteid = "USGS-07144100",
- summaryYears = "all"
-)
+#site_all <- readWQPsummary(
+# siteid = "USGS-07144100",
+# summaryYears = "all"
+# )
# Summary of the data available from streams in a single county:
-dane_county_data <- readWQPsummary(
- countycode = "US:55:025",
- summaryYears = 5,
- siteType = "Stream"
-)
+# dane_county_data <- readWQPsummary(
+# countycode = "US:55:025",
+# summaryYears = 5,
+# siteType = "Stream"
+# )
# Summary of the data all available from lakes in a single county:
-lake_sites <- readWQPsummary(
- siteType = "Lake, Reservoir, Impoundment",
- countycode = "US:55:025"
-)
+# lake_sites <- readWQPsummary(
+# siteType = "Lake, Reservoir, Impoundment",
+# countycode = "US:55:025"
+# )
# Summary of the data available for the last 5 years in New Jersey:
-state1 <- readWQPsummary(
- statecode = "NJ",
- summaryYears = 5,
- siteType = "Stream"
-)
+#state1 <- readWQPsummary(
+# statecode = "NJ",
+# summaryYears = 5,
+# siteType = "Stream"
+# )
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/read_waterdata_channel.Rd b/man/read_waterdata_channel.Rd
index 024cd908d..e9bee3b98 100644
--- a/man/read_waterdata_channel.Rd
+++ b/man/read_waterdata_channel.Rd
@@ -111,8 +111,7 @@ Examples:
Only features that have a \code{last_modified} that intersects the value of datetime are selected.
-\if{html}{\out{}}\preformatted{ field_visit_id = NA_character_,
-}\if{html}{\out{
}}}
+field_visit_id = NA_character_,}
\item{channel_measurement_type}{The channel measurement type.}
diff --git a/man/read_waterdata_combined_meta.Rd b/man/read_waterdata_combined_meta.Rd
index f7d22c0d1..efab47c84 100644
--- a/man/read_waterdata_combined_meta.Rd
+++ b/man/read_waterdata_combined_meta.Rd
@@ -237,7 +237,7 @@ See also Details below for more information.}
\item{properties}{A vector of requested columns to be returned from the query.
Available options are:
-geometry, monitoring_location_id, agency_code, agency_name, monitoring_location_number, monitoring_location_name, district_code, country_code, country_name, state_code, state_name, county_code, county_name, minor_civil_division_code, site_type_code, site_type, hydrologic_unit_code, basin_code, altitude, altitude_accuracy, altitude_method_code, altitude_method_name, vertical_datum, vertical_datum_name, horizontal_positional_accuracy_code, horizontal_positional_accuracy, horizontal_position_method_code, horizontal_position_method_name, original_horizontal_datum, original_horizontal_datum_name, drainage_area, contributing_drainage_area, time_zone_abbreviation, uses_daylight_savings, construction_date, aquifer_code, national_aquifer_code, aquifer_type_code, well_constructed_depth, hole_constructed_depth, depth_source_code, field_measurement_id, unit_of_measure, parameter_name, parameter_code, statistic_id, last_modified, begin, end, data_type, computation_identifier, thresholds, sublocatio
+geometry, monitoring_location_id, agency_code, agency_name, monitoring_location_number, monitoring_location_name, district_code, country_code, country_name, state_code, state_name, county_code, county_name, minor_civil_division_code, site_type_code, site_type, hydrologic_unit_code, basin_code, altitude, altitude_accuracy, altitude_method_code, altitude_method_name, vertical_datum, vertical_datum_name, horizontal_positional_accuracy_code, horizontal_positional_accuracy, horizontal_position_method_code, horizontal_position_method_name, original_horizontal_datum, original_horizontal_datum_name, drainage_area, contributing_drainage_area, time_zone_abbreviation, uses_daylight_savings, construction_date, aquifer_code, national_aquifer_code, aquifer_type_code, well_constructed_depth, hole_constructed_depth, depth_source_code, field_measurement_id, unit_of_measure, parameter_name, parameter_code, statistic_id, last_modified, begin, end, data_type, computation_identifier, thresholds, sublocation_identifier, primary, web_description, parameter_description, parent_time_series_id.
The default (\code{NA}) will return all columns of the data.}
\item{skipGeometry}{This parameter can be used to skip response geometries for
diff --git a/man/read_waterdata_field_measurements.Rd b/man/read_waterdata_field_measurements.Rd
index b4de841a8..b9543526c 100644
--- a/man/read_waterdata_field_measurements.Rd
+++ b/man/read_waterdata_field_measurements.Rd
@@ -50,7 +50,11 @@ The default (\code{NA}) will return all columns of the data.}
\item{field_visit_id}{A universally unique identifier (UUID) for the field visit. Multiple measurements may be made during a single field visit.}
-\item{field_measurements_series_id}{A unique identifier representing a single collection series. This corresponds to the \code{id} field in the \code{field-measurements-metadata} endpoint. Collection series are defined as the set of field measurements at a given monitoring location for a single parameter code using a single reading type.}
+\item{field_measurements_series_id}{A unique identifier representing a single
+collection series. This corresponds to the \code{field_measurements_series_id} field in the
+\code{read_waterdata_field_meta} endpoint. Collection series are defined as the
+set of field measurements at a given monitoring location for a single parameter
+code using a single reading type.}
\item{approval_status}{Some of the data that you have obtained from this U.S. Geological Survey database may not have received Director's approval. Any such data values are qualified as provisional and are subject to revision. Provisional data are released on the condition that neither the USGS nor the United States Government may be held liable for any damages resulting from its use. This field reflects the approval status of each record, and is either "Approved", meaining processing review has been completed and the data is approved for publication, or "Provisional" and subject to revision. For more information about provisional data, go to \url{https://waterdata.usgs.gov/provisional-data-statement/}.}
diff --git a/man/read_waterdata_peaks.Rd b/man/read_waterdata_peaks.Rd
new file mode 100644
index 000000000..b809a24c6
--- /dev/null
+++ b/man/read_waterdata_peaks.Rd
@@ -0,0 +1,168 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/read_waterdata_peaks.R
+\name{read_waterdata_peaks}
+\alias{read_waterdata_peaks}
+\title{Get USGS Peak Data}
+\usage{
+read_waterdata_peaks(
+ monitoring_location_id = NA_character_,
+ parameter_code = NA_character_,
+ properties = NA_character_,
+ time_series_id = NA_character_,
+ unit_of_measure = NA_character_,
+ value = NA,
+ last_modified = NA_character_,
+ water_year = NA_character_,
+ year = NA_character_,
+ month = NA_character_,
+ day = NA_character_,
+ time_of_day = NA_character_,
+ peak_since = NA_character_,
+ skipGeometry = NA,
+ time = NA_character_,
+ bbox = NA,
+ ...,
+ convertType = getOption("dataRetrieval.convertType"),
+ no_paging = getOption("dataRetrieval.no_paging"),
+ chunk_size = getOption("dataRetrieval.site_chunk_size_meta"),
+ limit = getOption("dataRetrieval.limit"),
+ attach_request = getOption("dataRetrieval.attach_request")
+)
+}
+\arguments{
+\item{monitoring_location_id}{A unique identifier representing a single monitoring location. This corresponds to the \code{id} field in the \code{monitoring-locations} endpoint. Monitoring location IDs are created by combining the agency code of the agency responsible for the monitoring location (e.g. USGS) with the ID number of the monitoring location (e.g. 02238500), separated by a hyphen (e.g. USGS-02238500).
+
+Multiple monitoring_location_ids can be requested as a character vector.}
+
+\item{parameter_code}{Parameter codes are 5-digit codes used to identify the constituent measured and the units of measure. A complete list of parameter codes and associated groupings can be found at \url{https://api.waterdata.usgs.gov/ogcapi/v0/collections/parameter-codes/items}.
+
+Multiple parameter_codes can be requested as a character vector.}
+
+\item{properties}{A vector of requested columns to be returned from the query.
+Available options are:
+geometry, time_series_id, monitoring_location_id, parameter_code, peak_id, unit_of_measure, value, last_modified, time, water_year, year, month, day, time_of_day, peak_since.
+The default (\code{NA}) will return all columns of the data.}
+
+\item{time_series_id}{A unique identifier representing a single time series. This corresponds to the \code{id} field in the \code{time-series-metadata} endpoint.}
+
+\item{unit_of_measure}{A human-readable description of the units of measurement associated with an observation.}
+
+\item{value}{The value of the observation. Values are transmitted as strings in the JSON response format in order to preserve precision.}
+
+\item{last_modified}{The last time a record was refreshed in our database. This may happen due to regular operational processes and does not necessarily indicate anything about the measurement has changed.
+You can query this field using date-times or intervals, adhering to RFC 3339, or using ISO 8601 duration objects. Intervals may be bounded or half-bounded (double-dots at start or end).
+Examples:
+\itemize{
+\item A date-time: "2018-02-12T23:20:50Z"
+\item A bounded interval: "2018-02-12T00:00:00Z/2018-03-18T12:31:12Z"
+\item Half-bounded intervals: "2018-02-12T00:00:00Z/.." or "../2018-03-18T12:31:12Z"
+\item Duration objects: "P1M" for data from the past month or "PT36H" for the last 36 hours
+}
+
+Only features that have a \code{last_modified} that intersects the value of datetime are selected.
+
+See also Details below for more information.}
+
+\item{water_year}{The water year (running from October 1st to September 30th) a peak occurred.}
+
+\item{year}{The calendar year a peak occurred.}
+
+\item{month}{The calendar month a peak occurred. If null, the month a peak occurred is unknown.}
+
+\item{day}{The day of the month a peak occurred. If null, the day a peak occurred is unknown.}
+
+\item{time_of_day}{The time of day a peak occurred. If null, the time of day a peak occurred is unknown.}
+
+\item{peak_since}{If not null, this record represents the peak value for the parameter code since the year contained in "peak_since".}
+
+\item{skipGeometry}{This parameter can be used to skip response geometries for
+each feature. The returning object will be a data frame with no spatial
+information. The default \code{NA} will not specify the argument in the request.}
+
+\item{time}{The date an observation represents. You can query this field using date-times or intervals, adhering to RFC 3339, or using ISO 8601 duration objects. Intervals may be bounded or half-bounded (double-dots at start or end).
+Examples:
+\itemize{
+\item A date-time: "2018-02-12T23:20:50Z"
+\item A bounded interval: "2018-02-12T00:00:00Z/2018-03-18T12:31:12Z"
+\item Half-bounded intervals: "2018-02-12T00:00:00Z/.." or "../2018-03-18T12:31:12Z"
+\item Duration objects: "P1M" for data from the past month or "PT36H" for the last 36 hours
+}
+
+Only features that have a \code{time} that intersects the value of datetime are selected. If a feature has multiple temporal properties, it is the decision of the server whether only a single temporal property is used to determine the extent or all relevant temporal properties.
+
+See also Details below for more information.}
+
+\item{bbox}{Only features that have a geometry that intersects the bounding
+box are selected.The bounding box is provided as four or six numbers, depending
+on whether the coordinate reference system includes a vertical axis (height or
+depth). Coordinates are assumed to be in crs 4326. The expected format is a numeric
+vector structured: c(xmin,ymin,xmax,ymax).
+Another way to think of it is c(Western-most longitude,
+Southern-most latitude, Eastern-most longitude, Northern-most longitude).}
+
+\item{...}{Not used. Included to help differentiate official Water Data API arguments
+from more seldom used, optional dataRetrieval-specific arguments.}
+
+\item{convertType}{logical, defaults to TRUE.
+If \code{TRUE}, the function will convert the data to dates, any qualifiers to string
+vector and reorder the returned data frame.}
+
+\item{no_paging}{logical, defaults to FALSE.
+If \code{TRUE}, the data will
+be requested from a native csv format. This can be dangerous because the
+data will cut off at 50,000 rows without indication that more data
+is available. Use \code{TRUE} with caution.}
+
+\item{chunk_size}{Number of monitoring_location_ids to chunk requests into.
+The default for functions that don't generally return long-term data records
+is 250, while
+the default for time series functions is
+10.
+Setting to \code{NA} will eliminate site chunking, giving users full control.}
+
+\item{limit}{numeric, The optional limit parameter is used to control the subset of the
+selected features that should be returned in each page. The maximum allowable
+limit is 50,000. It may be beneficial to set this number lower if your internet
+connection is spotty. The default (\code{NA}) will set the limit to the maximum
+allowable limit for the service.}
+
+\item{attach_request}{logical, defaults to TRUE.
+If set to \code{TRUE}, the full request sent to the Water Data API is attached
+as an attribute to the data set.}
+}
+\description{
+Annual peak flow values are the maximum instantaneous streamflow values recorded at a particular site for the entire water year from October 1 to September 30. Note that the annual peak flow value may not occur at the same time the maximum water level occurs due to conditions such as backwater, tidal fluctuations, etc.
+}
+\details{
+You can also use a vector of length 2 for any time queries (such as time
+or last_modified). The first value is the starting date (or datetime),
+the second value is the ending date(or datetime).
+NA's within the vector indicate a half-bound date.
+For example, \code{time = c("2024-01-01", NA)} will return all data starting
+at 2024-01-01.
+\code{time = c(NA, "2024-01-01")} will return all data from the beginning of
+the timeseries until 2024-01-01.
+By default, time is assumed UTC, although time zone attributes
+will be accommodated. As an example, setting \code{time = as.POSIXct(c("2021-01-01 12:00:00",
+"2021-01-01 14:00"), tz = "America/New_York")} will request data that between
+noon and 2pm eastern time on 2021-01-01.
+All time values RETURNED from the service are UTC with the exception of
+daily data, which returns time values in local dates.
+}
+\examples{
+\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
+
+\donttest{
+wi_peaks <- read_waterdata_combined_meta(
+ state_name = "Wisconsin",
+ data_type = "Peaks",
+ parameter_code = "00060")
+
+
+dv_data_sf <- read_waterdata_peaks(
+ monitoring_location_id = wi_peaks$monitoring_location_id[1],
+ parameter_code = "00060")
+
+}
+\dontshow{\}) # examplesIf}
+}
diff --git a/man/read_waterdata_samples.Rd b/man/read_waterdata_samples.Rd
index 6ca606468..224ca4fc8 100644
--- a/man/read_waterdata_samples.Rd
+++ b/man/read_waterdata_samples.Rd
@@ -102,7 +102,7 @@ would be needed from prior project information.}
information would be needed from the data supplier.}
\item{siteTypeName}{Site type name query parameter. See available
-options by running \code{check_param("sitetype")$typeName}.}
+options by running \code{check_waterdata_sample_params("sitetype")$typeName}.}
\item{usgsPCode}{USGS parameter code. See available options by running
\code{check_waterdata_sample_params("characteristics")$parameterCode}.}
diff --git a/man/summarize_waterdata_samples.Rd b/man/summarize_waterdata_samples.Rd
index 3b5b7f17c..6afda5abd 100644
--- a/man/summarize_waterdata_samples.Rd
+++ b/man/summarize_waterdata_samples.Rd
@@ -10,10 +10,13 @@ summarize_waterdata_samples(monitoringLocationIdentifier)
summarize_USGS_samples(monitoringLocationIdentifier)
}
\arguments{
-\item{monitoringLocationIdentifier}{A monitoring location identifier has two parts,
-separated by a dash (-): the agency code and the location number. Location identifiers should be separated with commas,
-for example: AZ014-320821110580701, CAX01-15304600, USGS-040851385. Location
-numbers without an agency prefix are assumed to have the prefix USGS.}
+\item{monitoringLocationIdentifier}{A single monitoring location identifier
+with two parts, separated by a dash (-): the agency code and the location
+number. Examples: USGS-040851385, AZ014-320821110580701, CAX01-15304600.
+The summary service accepts only one site at a time; supplying a vector of
+length > 1 raises an error. The agency prefix is required: bare location
+numbers (e.g. "040851385") are accepted by the service but return an empty
+result.}
}
\value{
data frame with summary of data available based on the monitoringLocationIdentifier
diff --git a/man/whatWQPdata.Rd b/man/whatWQPdata.Rd
index 8b02c97fb..b16183d06 100644
--- a/man/whatWQPdata.Rd
+++ b/man/whatWQPdata.Rd
@@ -46,20 +46,20 @@ kind of data discovery see \code{readWQPsummary}.
\examples{
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
\donttest{
-site1 <- whatWQPdata(siteid = "USGS-01594440")
+#site1 <- whatWQPdata(siteid = "USGS-01594440")
-type <- "Stream"
-sites <- whatWQPdata(countycode = "US:55:025", siteType = type)
+#type <- "Stream"
+#sites <- whatWQPdata(countycode = "US:55:025", siteType = type)
-lakeSites <- whatWQPdata(siteType = "Lake, Reservoir, Impoundment",
- countycode = "US:55:025")
-lakeSites_chars <- whatWQPdata(
- siteType = "Lake, Reservoir, Impoundment",
- countycode = "US:55:025", convertType = FALSE)
+#lakeSites <- whatWQPdata(siteType = "Lake, Reservoir, Impoundment",
+# countycode = "US:55:025")
+#lakeSites_chars <- whatWQPdata(
+# siteType = "Lake, Reservoir, Impoundment",
+# countycode = "US:55:025", convertType = FALSE)
-bbox <- c(-86.9736, 34.4883, -86.6135, 34.6562)
-what_bb <- whatWQPdata(bBox = bbox)
+#bbox <- c(-86.9736, 34.4883, -86.6135, 34.6562)
+#what_bb <- whatWQPdata(bBox = bbox)
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/wqpSpecials.Rd b/man/wqpSpecials.Rd
index 233435505..a0d0fd848 100644
--- a/man/wqpSpecials.Rd
+++ b/man/wqpSpecials.Rd
@@ -51,34 +51,34 @@ not return information on what data was collected at the site.
\examples{
\donttest{
-site1 <- whatWQPsamples(siteid = "USGS-01594440")
+#site1 <- whatWQPsamples(siteid = "USGS-01594440")
-type <- "Stream"
+#type <- "Stream"
-sites <- whatWQPsamples(countycode = "US:55:025", siteType = type)
+#sites <- whatWQPsamples(countycode = "US:55:025", siteType = type)
-lakeSites_samples <- whatWQPsamples(siteType = "Lake, Reservoir, Impoundment",
- countycode = "US:55:025")
+#lakeSites_samples <- whatWQPsamples(siteType = "Lake, Reservoir, Impoundment",
+# countycode = "US:55:025")
}
\donttest{
-type <- "Stream"
+#type <- "Stream"
-sites <- whatWQPmetrics(countycode = "US:55:025", siteType = type)
-lakeSites_metrics <- whatWQPmetrics(siteType = "Lake, Reservoir, Impoundment",
- countycode = "US:55:025")
+#sites <- whatWQPmetrics(countycode = "US:55:025", siteType = type)
+#lakeSites_metrics <- whatWQPmetrics(siteType = "Lake, Reservoir, Impoundment",
+# countycode = "US:55:025")
}
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
\donttest{
-site1 <- whatWQPsites(siteid = "USGS-01594440")
+#site1 <- whatWQPsites(siteid = "USGS-01594440")
-type <- "Stream"
-sites <- whatWQPsites(
- countycode = "US:55:025",
- characteristicName = "Phosphorus",
- siteType = type
-)
+#type <- "Stream"
+#sites <- whatWQPsites(
+# countycode = "US:55:025",
+# characteristicName = "Phosphorus",
+# siteType = type
+#)
}
\dontshow{\}) # examplesIf}
}
diff --git a/man/wqp_check_status.Rd b/man/wqp_check_status.Rd
index cccd26900..492bc80a1 100644
--- a/man/wqp_check_status.Rd
+++ b/man/wqp_check_status.Rd
@@ -23,12 +23,12 @@ function will be attached as an attribute to the data.
\examples{
\dontshow{if (is_dataRetrieval_user()) withAutoprint(\{ # examplesIf}
\donttest{
-rawPcode <- readWQPqw("USGS-01594440", "01075",
- ignore_attributes = TRUE, legacy = FALSE)
-headerInfo <- attr(rawPcode, "headerInfo")
-wqp_request_id <- headerInfo$`wqp-request-id`
-count_info <- wqp_check_status(wqp_request_id)
-count_info[["dataProviders"]]
+#rawPcode <- readWQPqw("USGS-01594440", "01075",
+# ignore_attributes = TRUE, legacy = FALSE)
+# headerInfo <- attr(rawPcode, "headerInfo")
+#wqp_request_id <- headerInfo$`wqp-request-id`
+#count_info <- wqp_check_status(wqp_request_id)
+#count_info[["dataProviders"]]
}
\dontshow{\}) # examplesIf}
}
diff --git a/tests/testthat/tests_general.R b/tests/testthat/tests_general.R
index 8945174fe..25d272e57 100644
--- a/tests/testthat/tests_general.R
+++ b/tests/testthat/tests_general.R
@@ -243,16 +243,16 @@ test_that("read_waterdata_ts_meta", {
test_that("General WQP retrievals working", {
testthat::skip_on_cran()
testthat::skip_on_ci()
- nameToUse <- "pH"
- pHData <- readWQPdata(
- siteid = "USGS-04024315",
- characteristicName = nameToUse,
- service = "ResultWQX3"
- )
- expect_is(pHData$Activity_StartDateTime, "POSIXct")
- expect_type(pHData$USGSpcode, "character")
- expect_type(pHData$Result_Measure, "double")
- expect_type(pHData$SampleCollectionMethod_Identifier, "character")
+ # nameToUse <- "pH"
+ # pHData <- readWQPdata(
+ # siteid = "USGS-04024315",
+ # characteristicName = nameToUse,
+ # service = "ResultWQX3"
+ # )
+ # expect_is(pHData$Activity_StartDateTime, "POSIXct")
+ # expect_type(pHData$USGSpcode, "character")
+ # expect_type(pHData$Result_Measure, "double")
+ # expect_type(pHData$SampleCollectionMethod_Identifier, "character")
#
# # testing lists:
startDate <- as.Date("2022-01-01")
@@ -283,80 +283,80 @@ test_that("General WQP retrievals working", {
characteristicName = secchi.names
)
- wqp.summary_no_atts <- readWQPdata(
- siteid = "USGS-04024315",
- characteristicName = nameToUse,
- ignore_attributes = TRUE,
- service = "ResultWQX3"
- )
- expect_true(
- !all(
- c("siteInfo", "variableInfo") %in% names(attributes(wqp.summary_no_atts))
- )
- )
-
- rawPcode <- readWQPqw("USGS-01594440", "01075", "", "", legacy = FALSE)
- expect_true(all(
- c("url", "queryTime", "siteInfo") %in%
- names(attributes(rawPcode))
- ))
-
- # This means wqp_check_status was called:
- expect_true("dataProviders" %in% names(attr(rawPcode, "headerInfo")))
-
- rawPcode2 <- readWQPqw(
- "USGS-01594440",
- "01075",
- "",
- "",
- ignore_attributes = TRUE
- )
- expect_true(all(
- !c("queryTime", "siteInfo") %in%
- names(attributes(rawPcode2))
- ))
-
- # This means wqp_check_status wasn't called:
- expect_false("dataProviders" %in% names(attr(rawPcode2, "headerInfo")))
-
- pHData <- readWQPdata(
- siteid = "USGS-04024315",
- characteristicName = "pH",
- service = "ResultWQX3"
- )
- expect_true(all(
- c("url", "queryTime", "siteInfo", "headerInfo") %in%
- names(attributes(pHData))
- ))
-
- # # This means wqp_check_status was called:
- expect_true("dataProviders" %in% names(attr(pHData, "headerInfo")))
-
- pHData2 <- readWQPdata(
- siteid = "USGS-04024315",
- characteristicName = "pH",
- ignore_attributes = TRUE,
- service = "ResultWQX3"
- )
- expect_true(all(
- !c("queryTime", "siteInfo") %in%
- names(attributes(pHData2))
- ))
-
+ # wqp.summary_no_atts <- readWQPdata(
+ # siteid = "USGS-04024315",
+ # characteristicName = nameToUse,
+ # ignore_attributes = TRUE,
+ # service = "ResultWQX3"
+ # )
+ # expect_true(
+ # !all(
+ # c("siteInfo", "variableInfo") %in% names(attributes(wqp.summary_no_atts))
+ # )
+ # )
+ #
+ # rawPcode <- readWQPqw("USGS-01594440", "01075", "", "", legacy = FALSE)
+ # expect_true(all(
+ # c("url", "queryTime", "siteInfo") %in%
+ # names(attributes(rawPcode))
+ # ))
+ #
# # This means wqp_check_status was called:
- expect_false("dataProviders" %in% names(attr(pHData2, "headerInfo")))
-
- rawPcode <- readWQPqw(
- "USGS-01594440",
- "01075",
- ignore_attributes = TRUE,
- legacy = FALSE
- )
- headerInfo <- attr(rawPcode, "headerInfo")
- wqp_request_id <- headerInfo$`wqp-request-id`
- count_info <- wqp_check_status(wqp_request_id)
-
- expect_true("dataProviders" %in% names(count_info))
+ # expect_true("dataProviders" %in% names(attr(rawPcode, "headerInfo")))
+ #
+ # rawPcode2 <- readWQPqw(
+ # "USGS-01594440",
+ # "01075",
+ # "",
+ # "",
+ # ignore_attributes = TRUE
+ # )
+ # expect_true(all(
+ # !c("queryTime", "siteInfo") %in%
+ # names(attributes(rawPcode2))
+ # ))
+ #
+ # # This means wqp_check_status wasn't called:
+ # expect_false("dataProviders" %in% names(attr(rawPcode2, "headerInfo")))
+ #
+ # pHData <- readWQPdata(
+ # siteid = "USGS-04024315",
+ # characteristicName = "pH",
+ # service = "ResultWQX3"
+ # )
+ # expect_true(all(
+ # c("url", "queryTime", "siteInfo", "headerInfo") %in%
+ # names(attributes(pHData))
+ # ))
+ #
+ # # # This means wqp_check_status was called:
+ # expect_true("dataProviders" %in% names(attr(pHData, "headerInfo")))
+ #
+ # pHData2 <- readWQPdata(
+ # siteid = "USGS-04024315",
+ # characteristicName = "pH",
+ # ignore_attributes = TRUE,
+ # service = "ResultWQX3"
+ # )
+ # expect_true(all(
+ # !c("queryTime", "siteInfo") %in%
+ # names(attributes(pHData2))
+ # ))
+ #
+ # # # This means wqp_check_status was called:
+ # expect_false("dataProviders" %in% names(attr(pHData2, "headerInfo")))
+ #
+ # rawPcode <- readWQPqw(
+ # "USGS-01594440",
+ # "01075",
+ # ignore_attributes = TRUE,
+ # legacy = FALSE
+ # )
+ # headerInfo <- attr(rawPcode, "headerInfo")
+ # wqp_request_id <- headerInfo$`wqp-request-id`
+ # count_info <- wqp_check_status(wqp_request_id)
+ #
+ # expect_true("dataProviders" %in% names(count_info))
})
diff --git a/tests/testthat/tests_userFriendly_fxns.R b/tests/testthat/tests_userFriendly_fxns.R
index c5c7f6d86..393c13b4b 100644
--- a/tests/testthat/tests_userFriendly_fxns.R
+++ b/tests/testthat/tests_userFriendly_fxns.R
@@ -113,11 +113,11 @@ context("Peak, rating, meas, site")
test_that("peak, rating curves, surface-water measurements", {
testthat::skip_on_cran()
testthat::skip_on_ci()
- siteNumbers <- c("01594440", "040851325")
- data <- readNWISpeak(siteNumbers)
- expect_is(data$agency_cd, "character")
+ siteNumbers <- c("USGS-01594440", "USGS-040851325")
+ data <- read_waterdata_peaks(monitoring_location_id = siteNumbers)
+ expect_true(ncol(data) > 10)
- # Rating curvs:
+ # Rating curves:
siteNumber <- "USGS-01594440"
data <- read_waterdata_ratings(
monitoring_location_id = siteNumber,
@@ -263,40 +263,40 @@ test_that("read_waterdata_daily", {
test_that("WQP qw tests", {
testthat::skip_on_cran()
skip_on_ci()
- nameToUse <- "Specific conductance"
- pcodeToUse <- "00095"
-
- INFO_WQP <- readWQPqw(
- "USGS-04024315",
- pcodeToUse,
- startDate = "",
- endDate = "",
- legacy = FALSE
- )
- expect_is(INFO_WQP$Activity_StartDateTime, "POSIXct")
-
- INFO2 <- readWQPqw(
- "WIDNR_WQX-10032762",
- nameToUse,
- startDate = "",
- endDate = "",
- legacy = FALSE
- )
- expect_is(INFO2$Activity_StartDateTime, "POSIXct")
-
- df <- readWQPqw("USGS-04193500", parameterCd = "00665", legacy = FALSE)
- expect_true(nrow(df) > 0)
-
- df2 <- readWQPqw("USGS-05427718", parameterCd = "all")
- expect_true(nrow(df2) > 0)
-
- #Empty legacy:
- df3 <- readWQPqw(
- siteNumbers = "USGS-385032115220501",
- parameterCd = "all",
- legacy = TRUE
- )
- expect_true(nrow(df3) == 0)
+ # nameToUse <- "Specific conductance"
+ # pcodeToUse <- "00095"
+ #
+ # INFO_WQP <- readWQPqw(
+ # "USGS-04024315",
+ # pcodeToUse,
+ # startDate = "",
+ # endDate = "",
+ # legacy = FALSE
+ # )
+ # expect_is(INFO_WQP$Activity_StartDateTime, "POSIXct")
+ #
+ # INFO2 <- readWQPqw(
+ # "WIDNR_WQX-10032762",
+ # nameToUse,
+ # startDate = "",
+ # endDate = "",
+ # legacy = FALSE
+ # )
+ # expect_is(INFO2$Activity_StartDateTime, "POSIXct")
+ #
+ # df <- readWQPqw("USGS-04193500", parameterCd = "00665", legacy = FALSE)
+ # expect_true(nrow(df) > 0)
+ #
+ # df2 <- readWQPqw("USGS-05427718", parameterCd = "all")
+ # expect_true(nrow(df2) > 0)
+ #
+ # #Empty legacy:
+ # df3 <- readWQPqw(
+ # siteNumbers = "USGS-385032115220501",
+ # parameterCd = "all",
+ # legacy = TRUE
+ # )
+ # expect_true(nrow(df3) == 0)
})
diff --git a/tutorials/basic_slides_deck.qmd b/tutorials/basic_slides_deck.qmd
index 180967958..5981d5c52 100644
--- a/tutorials/basic_slides_deck.qmd
+++ b/tutorials/basic_slides_deck.qmd
@@ -15,12 +15,15 @@ title-slide-attributes:
data-background-size: 15%
data-background-position: 2% 2%
editor: source
+engine: knitr
editor_options:
chunk_output_type: console
execute:
echo: true
warning: false
message: false
+params:
+ run_python: true
---
```{r}
@@ -29,30 +32,43 @@ execute:
# library(dataRetrieval)
library(ggplot2)
library(dplyr)
+library(reticulate)
+py_require("dataretrieval")
+py_require("panda")
+py_require("matplotlib")
options(dplyr.summarise.inform = FALSE)
-dt_me <- function(x,
- page_length = 8,
- paging = TRUE,
- font = "0.7em",
- escape = TRUE){
- DT::datatable(x,
- rownames = FALSE,
- options = list(pageLength = page_length,
- info = FALSE,
- searching = FALSE,
- paging = paging,
- lengthChange = FALSE,
- initComplete = htmlwidgets::JS(
- "function(settings, json) {",
- paste0("$(this.api().table().container()).css({'font-size': '",
- font, "'});"),
- "}")), escape = escape)
+evaluate_python <- params$run_python
+
+dt_me <- function(
+ x,
+ page_length = 8,
+ paging = TRUE,
+ font = "0.7em",
+ escape = TRUE
+) {
+ DT::datatable(
+ x,
+ rownames = FALSE,
+ options = list(
+ pageLength = page_length,
+ info = FALSE,
+ searching = FALSE,
+ paging = paging,
+ lengthChange = FALSE,
+ initComplete = htmlwidgets::JS(
+ "function(settings, json) {",
+ paste0(
+ "$(this.api().table().container()).css({'font-size': '",
+ font,
+ "'});"
+ ),
+ "}"
+ )
+ ),
+ escape = escape
+ )
}
-
-theme_set(theme_grey(base_size = 24))
-update_geom_defaults("point", list(size = 3))
-
```
@@ -151,13 +167,16 @@ Go to Tools -> Global Options -> Appearances to change style.
## Installation
+::: {.panel-tabset}
+
+### R
+
`dataRetrieval` is available on the Comprehensive R Archive Network (CRAN) repository. To install `dataRetrieval` on your computer, open RStudio and run this line of code in the Console:
```{r}
#| echo: true
#| eval: false
install.packages("dataRetrieval")
-
```
Then each time you open R, you'll need to load the library:
@@ -167,6 +186,33 @@ Then each time you open R, you'll need to load the library:
library(dataRetrieval)
```
+### Python
+
+Whether you are a user or developer we recommend installing `dataretrieval` in a virtual environment. This can be done using something like virtualenv or conda.
+
+```{bash}
+#| echo: true
+#| eval: false
+pip install dataretrieval
+```
+
+or
+
+```{bash}
+#| echo: true
+#| eval: false
+conda -c conda-forge install dataretrieval
+```
+
+Then each time you open Python, you'll need to load the library:
+
+```{python}
+#| eval: !expr evaluate_python
+from dataretrieval import waterdata
+```
+
+:::
+
::: footer
:::
@@ -194,19 +240,23 @@ library(dataRetrieval)
## Documentation within R: function help pages {.smaller}
+::: {.panel-tabset}
+
+### R
+
Within R, you can call help files for any `dataRetrieval` function:
```{r}
#| echo: true
#| eval: false
-?readWQPdata
+?read_waterdata_daily
```
:::: {.columns}
::: {.column width="50%"}
-Click here to open a new window:
+Click here to open a new window in RStudio:
@@ -221,20 +271,30 @@ Examples
```{r}
#| eval: false
-# Legacy:
-nameToUse <- "pH"
-pHData <- readWQPdata(siteid = "USGS-04024315",
- characteristicName = nameToUse)
-ncol(pHData)
-attr(pHData, "siteInfo")
-attr(pHData, "queryTime")
-attr(pHData, "url")
+site <- "USGS-02238500"
+dv_data_sf <- read_waterdata_daily(
+ monitoring_location_id = site,
+ parameter_code = "00060",
+ time = c("2021-01-01", "2022-01-01")
+)
```
:::
::::
+### Python
+
+Within Python, you can call help for any `dataretrieval` function:
+
+```{python}
+#| eval: !expr evaluate_python
+help(waterdata.get_daily)
+```
+
+:::
+
+
::: footer
:::
@@ -447,9 +507,13 @@ We're going walk through 3 retrievals:
:::
-## Workflow 1: Daily data for known site
+## Workflow 1: Daily data for known site {.smaller}
+
+Let's pull daily mean discharge data for site "USGS-0940550", getting all the data from the last year.
-Let's pull daily mean discharge data for site "USGS-0940550", getting all the data from October 10, 2024 onward.
+::: {.panel-tabset}
+
+### R
```{r}
#| message: true
@@ -457,15 +521,38 @@ library(dataRetrieval)
site <- "USGS-09405500"
pcode <- "00060" # Discharge
stat_cd <- "00003" # Mean
-range <- c("2024-10-01", NA)
-df <- read_waterdata_daily(monitoring_location_id = site,
- parameter_code = pcode,
- statistic_id = stat_cd,
- time = range)
+df <- read_waterdata_daily(
+ monitoring_location_id = site,
+ parameter_code = pcode,
+ statistic_id = stat_cd,
+ time = "P365D"
+)
+nrow(df)
+```
+
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+from dataretrieval import waterdata
+
+site = "USGS-09405500"
+pcode = "00060" # Discharge
+stat_cd = "00003" # Mean
+
+df, md = waterdata.get_daily(
+ monitoring_location_id=site,
+ parameter_code=pcode,
+ statistic_id=stat_cd,
+ time="P365D",
+)
+df.shape[0]
```
+:::
+
::: footer
:::
@@ -476,12 +563,11 @@ In RStudio, click on the data frame in the upper right Environment tab to open a
```{r}
#| echo: false
-
-dt_me(df |>
- sf::st_drop_geometry(),
- page_length = 3)
-
-
+dt_me(
+ df |>
+ sf::st_drop_geometry(),
+ page_length = 3
+)
```
::: footer
@@ -490,27 +576,56 @@ dt_me(df |>
## Workflow 1: Plot Daily Data
+::: {.panel-tabset}
+
+### R
+
Let's use `ggplot2` to visualize the data.
```{r}
#| echo: true
#| output-location: column
library(ggplot2)
+theme_set(theme_bw(base_size = 24))
+update_geom_defaults("point", list(size = 3, color = "steelblue"))
+options(ggplot2.discrete.colour = "viridis")
ggplot(data = df) +
- geom_point(aes(x = time,
- y = value,
- color = approval_status))
+ geom_point(aes(x = time, y = value, color = approval_status))
+```
+
+### Python
+Let's use `matplotlib` to visualize the data.
+
+```{python}
+#| echo: true
+#| output-location: column
+import matplotlib.pyplot as plt
+import pandas as pd
+
+plt.rcParams["font.size"] = 20
+
+levels, categories = pd.factorize(df["approval_status"])
+
+fig, ax = plt.subplots()
+scatter = ax.scatter(x=df.time, y=df.value, c=levels)
+fig.legend(scatter.legend_elements()[0], categories, title="Status")
```
-## Water Data API Notes: Argument input
+:::
+
+::: footer
+
+:::
+
+## Water Data API Notes: Argument input
Use your "tab" key!
-## Water Data API Notes: Arguments
+## Water Data API Notes: Arguments {.smaller}
* When you look at the help file for the new functions, you’ll notice there are lots of possible inputs (arguments).
@@ -521,9 +636,10 @@ Use your "tab" key!
```{r}
#| eval: false
#| echo: true
-discharge <- read_waterdata_daily(parameter_code = "00060",
- statistic_id = "00003")
-
+discharge <- read_waterdata_daily(
+ parameter_code = "00060",
+ statistic_id = "00003"
+)
```
::: {.fragment}
@@ -564,14 +680,16 @@ The "time" argument has a few options:
Here are a bunch of valid inputs:
```{r}
-#| code-line-numbers: "1-7|8-9|10-13|14-17"
+#| code-line-numbers: "1-9|10-11|12-15|16-19"
# Ask for exact times:
time = "2025-01-01"
time = as.Date("2025-01-01")
time = "2025-01-01T23:20:50Z"
-time = as.POSIXct("2025-01-01T23:20:50Z",
- format = "%Y-%m-%dT%H:%M:%S",
- tz = "UTC")
+time = as.POSIXct(
+ "2025-01-01T23:20:50Z",
+ format = "%Y-%m-%dT%H:%M:%S",
+ tz = "UTC"
+)
# Ask for specific range
time = c("2024-01-01", "2025-01-01") # or Dates or POSIXs
# Asking beginning of record to specific end:
@@ -594,22 +712,49 @@ Use your "tab" key!
-## Workflow 2: Discrete data for known site
+## Workflow 2: Discrete data for known site {.smaller}
Let's get orthophosphate ("00660") data from the Shenandoah River at Front Royal, VA ("USGS-01631000").
+::: {.panel-tabset}
+
+### R
+
```{r}
#| message: true
site <- "USGS-01631000"
pcode <- "00660"
-qw_data <- read_waterdata_samples(monitoringLocationIdentifier = site,
- usgsPCode = pcode,
- dataType = "results",
- dataProfile = "basicphyschem")
+qw_data <- read_waterdata_samples(
+ monitoringLocationIdentifier = site,
+ usgsPCode = pcode,
+ dataType = "results",
+ dataProfile = "basicphyschem"
+)
ncol(qw_data)
```
+R generates a few POSIXct columns to combine date, time, timezone information.
+
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+site = "USGS-01631000"
+pcode = "00660"
+
+qw_data, md_qw = waterdata.get_samples(
+ monitoringLocationIdentifier = site,
+ usgsPCode = pcode,
+ service = "results",
+ profile = "basicphyschem",
+)
+
+qw_data.shape[1]
+```
+
+:::
+
That's a LOT of columns returned. We won't look at them here, but you can use `View` in RStudio to explore on your own.
::: footer
@@ -626,48 +771,94 @@ That's a LOT of columns returned. We won't look at them here, but you can use `V
```{r}
#| echo: false
-
-df <- tibble(dataType = c("results", "locations", "activities", "projects", "organizations"),
- Description = c("Results data and metadata for measures and observations matching your query",
- "Find monitoring locations that have data matching your query",
- "Information about the monitoring activities conducted that produced data",
- "Information on the projects that have results matching your data query",
- "Information about the organizations that have provided data that matches your query"),
- dataProfile = c('fullphyschem
basicphyschem
fullbio
basicbio
narrow
resultdetectionquantitationlimit
labsampleprep
count',
- 'site
count',
- 'sampact
actmetric
actgroup
ncount',
- 'project
projectmonitoringlocationweight',
- 'organization
count'))
+df <- tibble(
+ dataType = c(
+ "results",
+ "locations",
+ "activities",
+ "projects",
+ "organizations"
+ ),
+ Description = c(
+ "Results data and metadata for measures and observations matching your query",
+ "Find monitoring locations that have data matching your query",
+ "Information about the monitoring activities conducted that produced data",
+ "Information on the projects that have results matching your data query",
+ "Information about the organizations that have provided data that matches your query"
+ ),
+ dataProfile = c(
+ 'fullphyschem
basicphyschem
fullbio
basicbio
narrow
resultdetectionquantitationlimit
labsampleprep
count',
+ 'site
count',
+ 'sampact
actmetric
actgroup
ncount',
+ 'project
projectmonitoringlocationweight',
+ 'organization
count'
+ )
+)
dt_me(df, escape = FALSE, paging = FALSE)
-
```
::: footer
:::
-## Workflow 2: Discrete data censoring
+## Workflow 2: Discrete data censoring {.smaller}
Let's pull a few columns out and look at those:
+::: {.panel-tabset}
+
+### R
+
```{r}
library(dplyr)
-qw_data_slim <- qw_data |>
- select(Date = Activity_StartDate,
- Result_Measure,
- DL_cond = Result_ResultDetectionCondition,
- DL_val = DetectionLimit_MeasureA,
- DL_type = DetectionLimit_TypeA) |>
- mutate(Result = if_else(!is.na(DL_cond), DL_val, Result_Measure),
- Detected = if_else(!is.na(DL_cond), "Not Detected", "Detected")) |>
+qw_data_slim <- qw_data |>
+ select(
+ Date = Activity_StartDate,
+ Result_Measure,
+ DL_cond = Result_ResultDetectionCondition,
+ DL_val = DetectionLimit_MeasureA,
+ DL_type = DetectionLimit_TypeA
+ ) |>
+ mutate(
+ Result = if_else(!is.na(DL_cond), DL_val, Result_Measure),
+ Detected = if_else(!is.na(DL_cond), "Not Detected", "Detected")
+ ) |>
arrange(Detected)
-
```
* What is `|>`? It's a pipe! It says take 'this thing' and put it in 'that thing'. You'll also see `%>%` in code, it is also a pipe - they are basically the same.
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+import numpy as np
+
+qw_data_slim = (
+ qw_data.rename(
+ columns={
+ "Activity_StartDate": "Date",
+ "Result_ResultDetectionCondition": "DL_cond",
+ "DetectionLimit_MeasureA": "DL_val",
+ "DetectionLimit_TypeA": "DL_type",
+ }
+ )[["Date", "Result_Measure", "DL_cond", "DL_val", "DL_type"]]
+ .assign(
+ Result=lambda x: np.where(
+ x["DL_cond"].notna(), x["DL_val"], x["Result_Measure"]
+ )
+ )
+ .assign(
+ Detected=lambda x: np.where(x["DL_cond"].notna(), "Not Detected", "Detected")
+ )
+ .sort_values(by="Detected", ascending=False)
+)
+```
+
+:::
+
::: footer
:::
@@ -676,8 +867,7 @@ qw_data_slim <- qw_data |>
```{r}
#| echo: false
-
-dt_me(qw_data_slim, page_length = 8, font = "0.7em")
+dt_me(qw_data_slim, page_length = 8, font = "0.7em")
```
::: footer
@@ -696,7 +886,11 @@ dt_me(qw_data_slim, page_length = 8, font = "0.7em")
:::
-## Step 1: Get the data
+## Step 1: Get the data {.smaller}
+
+::: {.panel-tabset}
+
+### R
```{r}
site <- "USGS-04183500"
@@ -706,33 +900,91 @@ p_code_qw <- "00665"
start_date <- "2015-07-03"
end_date <- "2025-07-03"
-qw_data <- read_waterdata_samples(monitoringLocationIdentifier = site,
- usgsPCode = p_code_qw,
- activityStartDateLower = start_date,
- activityStartDateUpper = end_date,
- dataProfile = "basicphyschem")
+qw_data <- read_waterdata_samples(
+ monitoringLocationIdentifier = site,
+ usgsPCode = p_code_qw,
+ activityStartDateLower = start_date,
+ activityStartDateUpper = end_date,
+ dataProfile = "basicphyschem"
+)
-dv_data <- read_waterdata_daily(monitoring_location_id = site,
- parameter_code = p_code_dv,
- statistic_id = stat_cd,
- time = c(start_date, end_date))
+dv_data <- read_waterdata_daily(
+ monitoring_location_id = site,
+ parameter_code = p_code_dv,
+ statistic_id = stat_cd,
+ time = c(start_date, end_date)
+)
```
-## Step 2: Join
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+site = "USGS-04183500"
+p_code_dv = "00060"
+stat_cd = "00003"
+p_code_qw = "00665"
+start_date = "2015-07-03"
+end_date = "2025-07-03"
+
+qw_data, md_qw = waterdata.get_samples(
+ monitoringLocationIdentifier=site,
+ usgsPCode=p_code_qw,
+ activityStartDateLower=start_date,
+ activityStartDateUpper=end_date,
+ profile="basicphyschem",
+)
+
+dv_data, md_dv = waterdata.get_daily(
+ monitoring_location_id=site,
+ parameter_code=p_code_dv,
+ statistic_id=stat_cd,
+ time=(start_date + "/" + end_date),
+)
+```
-```{r}
-library(dplyr)
+:::
+
+::: footer
+
+:::
+
+## Step 2: Join
+
+::: {.panel-tabset}
+
+### R
+
+```{r}
little_dv <- dv_data |>
select(time, Flow = value, monitoring_location_id)
-qw_data_joined <- qw_data |>
- left_join(little_dv,
- by = c("Activity_StartDate" = "time"))
+qw_data_joined <- qw_data |>
+ left_join(little_dv, by = c("Activity_StartDate" = "time"))
+```
+
+
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+little_dv = dv_data.rename(columns={"value": "Flow"})[
+ ["time", "Flow", "monitoring_location_id"]
+]
+
+qw_data["Activity_StartDate"] = pd.to_datetime(
+ qw_data["Activity_StartDate"], format="%Y-%m-%d"
+)
+
+qw_data_joined = pd.merge(
+ qw_data, little_dv, left_on="Activity_StartDate", right_on="time", how="left"
+)
```
+:::
+
* "Activity_StartDate" (on the left side data frame) and "time" (on the right side data frame) need to be the same type (in this case, both are Date objects).
-
::: footer
@@ -742,17 +994,39 @@ qw_data_joined <- qw_data |>
* You could join on multiple columns:
+::: {.panel-tabset}
+
+### R
+
```{r}
#| eval: false
-qw_data <- qw_data |>
- left_join(little_dv,
- by = c("Activity_StartDate" = "time",
- "Location_Identifier" = "monitoring_location_id"))
-
+qw_data <- qw_data |>
+ left_join(
+ little_dv,
+ by = c(
+ "Activity_StartDate" = "time",
+ "Location_Identifier" = "monitoring_location_id"
+ )
+ )
```
See `dplyr` documentation for lots of joining options, but I find `left_join` my "go-to" for straightforward joins.
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+qw_data = pd.merge(
+ qw_data,
+ little_dv,
+ left_on=["Activity_StartDate", "Location_Identifier"],
+ right_on=["time", "monitoring_location_id"],
+ how="left",
+)
+```
+
+:::
+
::: footer
:::
@@ -761,15 +1035,28 @@ See `dplyr` documentation for lots of joining options, but I find `left_join` my
Let's take a quick peak:
+::: {.panel-tabset}
+
+### R
+
```{r}
#| output-location: column
ggplot(data = qw_data_joined) +
- geom_point(aes(x = Flow,
- y = Result_Measure))
+ geom_point(aes(x = Flow, y = Result_Measure))
+```
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+#| output-location: column
+plt.figure()
+plt.scatter(x=qw_data_joined.Flow, y=qw_data_joined.Result_Measure)
```
+:::
+
## Exercise 2: Joins {.smaller}
::: {.panel-tabset}
@@ -794,12 +1081,11 @@ band_instruments <- band_instruments
```{r}
-band_members |>
+band_members |>
left_join(band_instruments, by = "name")
-band_instruments |>
+band_instruments |>
left_join(band_members, by = "name")
-
```
@@ -816,67 +1102,156 @@ band_instruments |>
* We'll look at Suisun Bay a Van Sickle Island NR Pittsburg CA ("USGS-11455508"), with parameter code "99133" which is Nitrate plus Nitrite.
-## Workflow 4: Continuous data for known site
+## Workflow 4: Continuous data for known site {.smaller}
+
+::: {.panel-tabset}
+
+### R
:::: {.columns}
-::: {.column width="70%"}
+::: {.column width="65%"}
```{r}
-#| results: markup
+#| eval: false
site_id <- "USGS-11455508"
p_code_rt <- "99133"
start_date <- "2024-01-01"
end_date <- "2024-06-01"
-continuous_data <- read_waterdata_continuous(monitoring_location_id = site_id,
- parameter_code = p_code_rt,
- time = c(start_date, end_date))
-
+continuous_data <- read_waterdata_continuous(
+ monitoring_location_id = site_id,
+ parameter_code = p_code_rt,
+ time = c(start_date, end_date)
+)
names(continuous_data)
```
:::
-::: {.column width="30%"}
+::: {.column width="35%"}
+```{r}
+#| results: markup
+#| echo: false
+options(width = 30)
+site_id <- "USGS-11455508"
+p_code_rt <- "99133"
+start_date <- "2024-01-01"
+end_date <- "2024-06-01"
+
+continuous_data <- read_waterdata_continuous(
+ monitoring_location_id = site_id,
+ parameter_code = p_code_rt,
+ time = c(start_date, end_date)
+)
+names(continuous_data)
```
- [4] "time" "unit_of_measure" "parameter_code"
- [7] "statistic_id" "value" "approval_status"
-[10] "last_modified" "qualifier"
-```
+
:::
::::
+### Python
+
+:::: {.columns}
+
+::: {.column width="65%"}
+
+```{python}
+#| eval: false
+site_id = "USGS-11455508"
+p_code_rt = "99133"
+date_range = "2024-01-01/2024-06-01"
+
+continuous_data, md_cont = waterdata.get_continuous(
+ monitoring_location_id=site_id, parameter_code=p_code_rt, time=date_range
+)
```
-Requesting:
-https://api.waterdata.usgs.gov/ogcapi/v0/collections/continuous/items?f=json&lang=en-US&skipGeometry=TRUE&limit=50000&monitoring_location_id=USGS-11455508¶meter_code=99133&time=2024-01-01T00%3A00%3A00Z%2F2024-06-01T00%3A00%3A00Z
+
+:::
+
+::: {.column width="35%"}
+
+```{python}
+#| eval: !expr evaluate_python
+#| results: markup
+#| echo: false
+pd.set_option("display.width", 30)
+site_id = "USGS-11455508"
+p_code_rt = "99133"
+date_range = "2024-01-01/2024-06-01"
+
+continuous_data, md_cont = waterdata.get_continuous(
+ monitoring_location_id=site_id, parameter_code=p_code_rt, time=date_range
+)
+continuous_data.columns
```
+:::
+
+::::
+
+:::
+
+
## Workflow 4: Inspect
+::: {.panel-tabset}
+
+### R
+
```{r}
#| output-location: column
ggplot(data = continuous_data) +
- geom_point(aes(x = time,
- y = value))
+ geom_point(aes(x = time, y = value))
+```
+
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+#| output-location: column
+plt.figure()
+plt.scatter(x=continuous_data.time, y=continuous_data.value)
```
+:::
+
## Workflow 5: Join Discrete and Continuous
That same site also measures discrete Nitrate plus Nitrite, which is parameter code "00631". Let's first grab that data:
+::: {.panel-tabset}
+
+### R
+
```{r}
#| message: true
-discrete_data <- read_waterdata_samples(monitoringLocationIdentifier = "USGS-11455508",
- usgsPCode = "00631",
- activityStartDateLower = start_date,
- activityStartDateUpper = end_date,
- dataProfile = "basicphyschem")
+discrete_data <- read_waterdata_samples(
+ monitoringLocationIdentifier = "USGS-11455508",
+ usgsPCode = "00631",
+ activityStartDateLower = start_date,
+ activityStartDateUpper = end_date,
+ dataProfile = "basicphyschem"
+)
+```
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+discrete_data, md_qw = waterdata.get_samples(
+ monitoringLocationIdentifier = "USGS-11455508",
+ usgsPCode = "00631",
+ activityStartDateLower = "2024-01-01",
+ activityStartDateUpper = "2024-06-01",
+ profile = "basicphyschem"
+)
```
+:::
+
## Workflow 5: Join Discrete and Continuous
* We now want to join the **closest** continuous sensor time with the discrete sample time.
@@ -889,17 +1264,26 @@ discrete_data <- read_waterdata_samples(monitoringLocationIdentifier = "USGS-114
## Workflow 5: Join Discrete and Continuous
+::: {.panel-tabset}
+
+### R
```{r}
-#| code-line-numbers: "1|2-3|5|6|1-6"
+#| code-line-numbers: "1|2-3|5-10"
library(data.table)
setDT(discrete_data)[, join_date := Activity_StartDateTime]
setDT(continuous_data)[, join_date := time]
-
-closest_dt <- continuous_data[discrete_data, on = .(join_date), roll = "nearest"]
+
+closest_dt <- continuous_data[
+ discrete_data,
+ on = .(join_date),
+ roll = "nearest"
+]
closest_dt <- data.frame(closest_dt)
```
+:::
+
::: footer
:::
@@ -909,13 +1293,11 @@ closest_dt <- data.frame(closest_dt)
```{r}
#| output-location: column
ggplot(data = closest_dt) +
- geom_point(aes(x = Result_Measure,
- y = value)) +
+ geom_point(aes(x = Result_Measure, y = value)) +
geom_abline() +
expand_limits(x = 0, y = 0) +
xlab("Discrete") +
ylab("Continuous")
-
```
@@ -931,19 +1313,37 @@ The next slides will demo how to use those.
## Data Discovery: Time Series {.smaller}
+::: {.panel-tabset}
+
+### R
```{r}
ts_available <- read_waterdata_ts_meta(monitoring_location_id = "USGS-04183500")
```
-```{r}
-#| echo: false
+### Python
-dt_me(ts_available |>
- sf::st_drop_geometry() |>
- select(parameter_name,
- parameter_code, statistic_id, begin, end,
- computation_identifier), page_length = 6)
+```{python}
+#| eval: !expr evaluate_python
+ts_avail, ts_me = waterdata.get_time_series_metadata(monitoring_location_id="USGS-04183500")
+```
+
+:::
+```{r}
+#| echo: false
+dt_me(
+ ts_available |>
+ sf::st_drop_geometry() |>
+ select(
+ parameter_name,
+ parameter_code,
+ statistic_id,
+ begin,
+ end,
+ computation_identifier
+ ),
+ page_length = 6
+)
```
::: footer
@@ -952,20 +1352,32 @@ dt_me(ts_available |>
## Data Discovery: Discrete {.smaller}
-```{r}
-discrete_available <- summarize_waterdata_samples(monitoringLocationIdentifier = "USGS-04183500")
+::: {.panel-tabset}
-```
+### R
```{r}
-#| echo: false
+discrete_available <- summarize_waterdata_samples(
+ monitoringLocationIdentifier = "USGS-04183500"
+)
+```
+
-dt_me(discrete_available |>
- select(characteristicUserSupplied,
- resultCount, activityCount,
- firstActivity, mostRecentActivity),
- page_length = 6)
+:::
+```{r}
+#| echo: false
+dt_me(
+ discrete_available |>
+ select(
+ characteristicUserSupplied,
+ resultCount,
+ activityCount,
+ firstActivity,
+ mostRecentActivity
+ ),
+ page_length = 6
+)
```
::: footer
@@ -976,21 +1388,41 @@ dt_me(discrete_available |>
* characteristicUserSupplied can be an input to `read_waterdata_sample`
+::: {.panel-tabset}
+
+### R
+
```{r}
-discrete1 <- read_waterdata_samples(characteristicUserSupplied = "Phosphorus as phosphorus, water, unfiltered",
- monitoringLocationIdentifier = "USGS-04183500")
+discrete1 <- read_waterdata_samples(
+ characteristicUserSupplied = "Phosphorus as phosphorus, water, unfiltered",
+ monitoringLocationIdentifier = "USGS-04183500"
+)
nrow(discrete1)
```
+### Python
+```{python}
+#| eval: !expr evaluate_python
+discrete1, discrete1_me = waterdata.get_samples(
+ characteristicUserSupplied = "Phosphorus as phosphorus, water, unfiltered",
+ monitoringLocationIdentifier = "USGS-04183500"
+)
+discrete1.shape[1]
+```
+
+:::
## More Information {.smaller}
-- dataRetrieval repository:
+- dataRetrieval R repository:
-
- [Documentation](https://doi-usgs.github.io/dataRetrieval)
- [dataRetrieval New Features](https://doi-usgs.github.io/dataRetrieval/articles/read_waterdata_functions.html)
- - [General Tutorial](https://rconnect.usgs.gov/NMC_dataRetrieval_1/dataRetrieval_1.html)
+
+- dataretrieval Python repository:
+ -
+ - [Documentation](https://doi-usgs.github.io/dataretrieval-python/)
- Contact:
- Computational Tools Email: comptools@usgs.gov
diff --git a/tutorials/quick_intro_deck.qmd b/tutorials/quick_intro_deck.qmd
index b332a4427..f80367aa3 100644
--- a/tutorials/quick_intro_deck.qmd
+++ b/tutorials/quick_intro_deck.qmd
@@ -33,7 +33,11 @@ params:
library(ggplot2)
library(dplyr)
library(reticulate)
+
py_require("dataretrieval")
+py_require("panda")
+py_require("matplotlib")
+
options(dplyr.summarise.inform = FALSE)
evaluate_python <- params$run_python
@@ -67,9 +71,6 @@ dt_me <- function(
escape = escape
)
}
-
-theme_set(theme_grey(base_size = 24))
-update_geom_defaults("point", list(size = 3))
```
@@ -126,12 +127,12 @@ In this ~45 minute introduction, the goal is:
## Installation
-`dataRetrieval` is available on the Comprehensive R Archive Network (CRAN) repository. To install `dataRetrieval` on your computer, open RStudio and run this line of code in the Console:
-
::: {.panel-tabset}
### R
+`dataRetrieval` is available on the Comprehensive R Archive Network (CRAN) repository. To install `dataRetrieval` on your computer, open RStudio and run this line of code in the Console:
+
```{r}
#| echo: true
#| eval: false
@@ -144,14 +145,19 @@ Then each time you open R, you'll need to load the library:
#| message: true
library(dataRetrieval)
```
+### Python
-### Python
```{bash}
#| echo: true
#| eval: false
pip install dataretrieval
+```
+```{bash}
+#| echo: true
+#| eval: false
+conda -c conda-forge install dataretrieval
```
Then each time you open Python, you'll need to load the library:
@@ -190,6 +196,10 @@ from dataretrieval import waterdata
## Documentation within R: function help pages {.smaller}
+::: {.panel-tabset}
+
+### R
+
Within R, you can call help files for any `dataRetrieval` function:
```{r}
@@ -202,7 +212,7 @@ Within R, you can call help files for any `dataRetrieval` function:
::: {.column width="50%"}
-Click here to open a new window:
+Click here to open a new window in RStudio:
@@ -229,6 +239,18 @@ dv_data_sf <- read_waterdata_daily(
::::
+### Python
+
+Within Python, you can call help for any `dataretrieval` function:
+
+```{python}
+#| eval: !expr evaluate_python
+help(waterdata.get_daily)
+```
+
+:::
+
+
::: footer
:::
@@ -408,7 +430,7 @@ We're going walk through 3 retrievals:
## Workflow 1: Daily data for known site {.smaller}
-Let's pull daily mean discharge data for site "USGS-0940550", getting all the data from October 10, 2024 onward.
+Let's pull daily mean discharge data for site "USGS-0940550", getting all the data from October 10, 2025 onward.
::: {.panel-tabset}
@@ -420,7 +442,7 @@ library(dataRetrieval)
site <- "USGS-09405500"
pcode <- "00060" # Discharge
stat_cd <- "00003" # Mean
-range <- c("2024-10-01", NA)
+range <- c("2025-10-01", NA)
df <- read_waterdata_daily(
monitoring_location_id = site,
@@ -442,14 +464,14 @@ site = "USGS-09405500"
pcode = "00060" # Discharge
stat_cd = "00003" # Mean
-df = waterdata.get_daily(
+df, md = waterdata.get_daily(
monitoring_location_id=site,
parameter_code=pcode,
statistic_id=stat_cd,
- time="2024-10-01/..",
+ time="2025-10-01/..",
)
-df[0].shape[0]
+df.shape[0]
```
@@ -478,6 +500,10 @@ dt_me(
## Workflow 1: Plot Daily Data
+::: {.panel-tabset}
+
+### R
+
Let's use `ggplot2` to visualize the data.
```{r}
@@ -485,10 +511,37 @@ Let's use `ggplot2` to visualize the data.
#| output-location: column
library(ggplot2)
+theme_set(theme_bw(base_size = 24))
+update_geom_defaults("point", list(size = 3, color = "steelblue"))
+options(ggplot2.discrete.colour = "viridis")
+options(ggplot2.discrete.fill = "viridis")
+
ggplot(data = df) +
geom_point(aes(x = time, y = value, color = approval_status))
```
+### Python
+
+Let's use `matplotlib` to visualize the data.
+
+```{python}
+#| echo: true
+#| output-location: column
+import matplotlib.pyplot as plt
+import pandas as pd
+
+plt.rcParams["font.size"] = 20
+
+levels, categories = pd.factorize(df["approval_status"])
+
+fig, ax = plt.subplots()
+scatter = ax.scatter(x=df.time, y=df.value, c=levels)
+fig.legend(scatter.legend_elements()[0], categories, title="Status")
+```
+
+
+:::
+
## Water Data API Notes: Argument input
Use your "tab" key!
@@ -550,7 +603,7 @@ The "time" argument has a few options:
Here are a bunch of valid inputs:
```{r}
-#| code-line-numbers: "1-7|8-9|10-13|14-17"
+#| code-line-numbers: "1-9|10-11|12-15|16-19"
# Ask for exact times:
time = "2025-01-01"
time = as.Date("2025-01-01")
@@ -604,20 +657,22 @@ qw_data <- read_waterdata_samples(
ncol(qw_data)
```
+R generates a few POSIXct columns to combine date, time, timezone information.
+
### Python
```{python}
#| eval: !expr evaluate_python
site = "USGS-01631000"
pcode = "00660"
-qw_data = waterdata.get_samples(
- monitoringLocationIdentifier=site,
- usgsPCode=pcode,
- service="results",
- profile="basicphyschem",
+qw_data, md_qw = waterdata.get_samples(
+ monitoringLocationIdentifier = site,
+ usgsPCode = pcode,
+ service = "results",
+ profile = "basicphyschem",
)
-qw_data[0].shape[1]
+qw_data.shape[1]
```
:::
@@ -676,14 +731,18 @@ dt_me(df, escape = FALSE, paging = FALSE)
* We'll look at Suisun Bay a Van Sickle Island NR Pittsburg CA ("USGS-11455508"), with parameter code "99133" which is Nitrate plus Nitrite.
-## Workflow 3: Continuous data for known site
+## Workflow 3: Continuous data for known site {.smaller}
+
+::: {.panel-tabset}
+
+### R
:::: {.columns}
::: {.column width="65%"}
```{r}
-#| results: markup
+#| eval: false
site_id <- "USGS-11455508"
p_code_rt <- "99133"
start_date <- "2024-01-01"
@@ -694,41 +753,100 @@ continuous_data <- read_waterdata_continuous(
parameter_code = p_code_rt,
time = c(start_date, end_date)
)
+names(continuous_data)
```
:::
::: {.column width="35%"}
+```{r}
+#| results: markup
+#| echo: false
+options(width = 30)
+site_id <- "USGS-11455508"
+p_code_rt <- "99133"
+start_date <- "2024-01-01"
+end_date <- "2024-06-01"
+
+continuous_data <- read_waterdata_continuous(
+ monitoring_location_id = site_id,
+ parameter_code = p_code_rt,
+ time = c(start_date, end_date)
+)
+names(continuous_data)
```
- [1] "monitoring_location_id"
- [2] "parameter_code"
- [3] "statistic_id"
- [4] "time"
- [5] "value"
- [6] "unit_of_measure"
- [7] "approval_status"
- [8] "last_modified"
- [9] "qualifier"
-[10] "time_series_id"
-```
+
:::
::::
+### Python
+
+:::: {.columns}
+
+::: {.column width="65%"}
+
+```{python}
+#| eval: false
+site_id = "USGS-11455508"
+p_code_rt = "99133"
+date_range = "2024-01-01/2024-06-01"
+
+continuous_data, md_cont = waterdata.get_continuous(
+ monitoring_location_id=site_id, parameter_code=p_code_rt, time=date_range
+)
```
-Requesting:
-https://api.waterdata.usgs.gov/ogcapi/v0/collections/continuous/items?f=json&lang=en-US&skipGeometry=TRUE&limit=50000&monitoring_location_id=USGS-11455508¶meter_code=99133&time=2024-01-01T00%3A00%3A00Z%2F2024-06-01T00%3A00%3A00Z
+
+:::
+
+::: {.column width="35%"}
+
+```{python}
+#| eval: !expr evaluate_python
+#| results: markup
+#| echo: false
+pd.set_option("display.width", 30)
+site_id = "USGS-11455508"
+p_code_rt = "99133"
+date_range = "2024-01-01/2024-06-01"
+
+continuous_data, md_cont = waterdata.get_continuous(
+ monitoring_location_id=site_id, parameter_code=p_code_rt, time=date_range
+)
+continuous_data.columns
```
+:::
+
+::::
+
+:::
+
+
## Workflow 3: Inspect
+::: {.panel-tabset}
+
+### R
+
```{r}
#| output-location: column
ggplot(data = continuous_data) +
geom_point(aes(x = time, y = value))
```
+### Python
+
+```{python}
+#| eval: !expr evaluate_python
+#| output-location: column
+plt.figure()
+plt.scatter(x=continuous_data.time, y=continuous_data.value)
+```
+
+:::
+
## Data Discovery
@@ -743,6 +861,10 @@ ggplot(data = continuous_data) +
The next slides will demo how to use those.
+::: footer
+
+:::
+
## Data Discovery: Time Series {.smaller}
```{r}
@@ -808,11 +930,14 @@ nrow(discrete1)
## More Information {.smaller}
-- dataRetrieval repository:
+- dataRetrieval R repository:
-
- [Documentation](https://doi-usgs.github.io/dataRetrieval)
- [dataRetrieval New Features](https://doi-usgs.github.io/dataRetrieval/articles/read_waterdata_functions.html)
- - [General Tutorial](https://rconnect.usgs.gov/NMC_dataRetrieval_1/dataRetrieval_1.html)
+
+- dataretrieval Python repository:
+ -
+ - [Documentation](https://doi-usgs.github.io/dataretrieval-python/)
- Contact:
- Computational Tools Email: comptools@usgs.gov
diff --git a/vignettes/Contributing.Rmd b/vignettes/Contributing.Rmd
index 97e4be399..823be0d58 100644
--- a/vignettes/Contributing.Rmd
+++ b/vignettes/Contributing.Rmd
@@ -15,9 +15,7 @@ editor_options:
```{r setup, include=FALSE}
library(knitr)
-opts_chunk$set(echo = TRUE,
- warning = FALSE,
- message = FALSE)
+opts_chunk$set(echo = TRUE, warning = FALSE, message = FALSE)
```
@@ -388,6 +386,20 @@ git pull codeusgs main
In general, create a pull request to push to the DOI-USGS/dataRetrieval main branch or a merge request to push to the main branch of code.usgs.gov/water/dataRetrieval.
+# Setting up Quarto Slides
+
+Slide decks are produced using Quarto in the "tutorials" folder. They require both R and Python to be installed. To install, download and install Miniforge. For Windows, open the "Miniforge Prompt", for MacOS and Linux open a terminal. Navigate to the dataRetrieval directory and type the following:
+
+```
+mamba env create -f environment.yml
+```
+
+Then activate the environment (still in Miniforge) using `conda`:
+```
+conda activate pyclass
+```
+The slides will use the R package `reticulate` to manage flipping back and forth between R and Python. To help `reticulate` know where Python is installed, you will need to add an envionmnental variable to your .Renviorn file "RETICULATE_PYTHON". Run `usethis::edit_r_environ()`, then add the path to your Python installation, and restart R. RStudio can render both the R and Python in the Quarto slides. However, if you want to do troubleshooting on individual code chunks, you might want to switch to Positron which allows seamless transition between R and Python consoles.
+
# References
diff --git a/vignettes/Status.Rmd b/vignettes/Status.Rmd
index f0fcd3a21..f6aab2006 100644
--- a/vignettes/Status.Rmd
+++ b/vignettes/Status.Rmd
@@ -60,18 +60,20 @@ df <- data.frame(
"`read_waterdata_field_measurements`, `read_waterdata_channel`",
"`read_waterdata`",
"`read_waterdata_continuous`",
- "", #rating
+ "`read_waterdata_rating`", #rating
"`read_waterdata_stats_por`, `read_waterdata_stats_daterange`",
- rep("", 2),
+ "`read_waterdata_peaks`",
+ "",
"`read_waterdata_ts_meta`, `read_waterdata_field_meta`, `read_waterdata_combined_meta`"
),
"Available on (branch)" = c(rep("main (CRAN)", 6),
"main (CRAN)",
"main (CRAN)",
"main (CRAN)",
- "",
+ "develop",
"main (CRAN)",
- rep("", 2),
+ "develop",
+ "",
"main (CRAN)")
)
diff --git a/vignettes/dataRetrieval.Rmd b/vignettes/dataRetrieval.Rmd
index a89c25566..d5b3c69ca 100644
--- a/vignettes/dataRetrieval.Rmd
+++ b/vignettes/dataRetrieval.Rmd
@@ -71,9 +71,9 @@ Functions <- c(
"read_waterdata",
"read_waterdata_daily",
"read_waterdata_continuous",
- "readNWISrating",
+ "read_waterdata_rating",
"read_waterdata_field_measurements",
- "readNWISpeak",
+ "read_waterdata_peaks",
"read_waterdata_field_measurements",
"readNWISuse",
"read_waterdata_stats_por, read_waterdata_stats_daterange",
@@ -81,7 +81,7 @@ Functions <- c(
"read_waterdata_monitoring_location",
"read_waterdata_samples",
"summarize_waterdata_samples",
- "whatNWISsites",
+ "read_waterdata_combined_meta",
"read_waterdata_ts_meta",
"readWQPdata",
"readWQPqw",
@@ -119,16 +119,17 @@ Description <- c(
Source <- c("USGS Water Data API",
"USGS Water Data API",
"USGS Water Data API",
- "NWIS",
+ "USGS Water Data API",
+ "USGS Water Data API",
+ "USGS Water Data API",
"USGS Water Data API",
"NWIS",
"USGS Water Data API",
- rep("NWIS",2),
"USGS Water Data API",
"USGS Water Data API",
"USGS Samples Data",
"USGS Samples Data",
- "NWIS",
+ "USGS Water Data API",
"USGS Water Data API",
rep("WQP", 7))
@@ -139,7 +140,7 @@ data.df <- data.frame(
Source, stringsAsFactors = FALSE
)
-kable(data.df,
+kable(data.df, col.names = c("Name", "Data Returned", "Source"),
caption = "Table 1: dataRetrieval functions"
)
```
@@ -381,11 +382,11 @@ groundWater <- read_waterdata_field_measurements(monitoring_location_id = siteNu
## Peak Flow Data
-Peak flow data are instantaneous discharge or stage data that record the maximum values of these variables during a flood event. They include the annual peak flood event but can also include records of other peaks that are lower than the annual maximum. Peak discharge measurements can be obtained with the `readNWISpeak` function. Information on the returned data can be found with the `comment` function and attached attributes as described in the [metadata](#embedded-metadata) section.
+Peak flow data are instantaneous discharge or stage data that record the maximum values of these variables during a flood event. They include the annual peak flood event but can also include records of other peaks that are lower than the annual maximum. Peak discharge measurements can be obtained with the `read_waterdata_peaks` function.
```{r peakexample, echo=TRUE, eval=FALSE}
-siteNumber <- "01594440"
-peakData <- readNWISpeak(siteNumber)
+siteNumber <- "USGS-01594440"
+peakData <- read_waterdata_peaks(monitoring_location_id = siteNumber)
```
@@ -393,11 +394,12 @@ peakData <- readNWISpeak(siteNumber)
Rating curves are the calibration curves that are used to convert measurements of stage to discharge. Because of changing hydrologic conditions these rating curves change over time. Information on the returned data can be found with the `comment` function and attached attributes as described in the [metadata](#embedded-metadata) section.
-Rating curves can be obtained with the `readNWISrating` function.
+Rating curves can be obtained with the `read_waterdata_ratings` function.
```{r ratingexample, echo=TRUE, eval=FALSE}
-ratingData <- readNWISrating(siteNumber, "base")
-attr(ratingData, "RATING")
+ratingData <- read_waterdata_ratings(monitoring_location_id = siteNumber,
+ file_type = "base")
+comment(ratingData[[1]])
```
diff --git a/vignettes/join_by_closest.Rmd b/vignettes/join_by_closest.Rmd
index 8341c4df8..f8018466c 100644
--- a/vignettes/join_by_closest.Rmd
+++ b/vignettes/join_by_closest.Rmd
@@ -46,9 +46,13 @@ pcode_uv <- "99133"
pcode_samples <- "00631"
start_date <- as.Date("2018-01-01")
end_date <- as.Date("2020-01-01")
-samples_data <- readWQPqw(site_samples, pcode_samples,
- startDate = start_date,
- endDate = end_date)
+
+samples_data <- read_waterdata_samples(
+ monitoringLocationIdentifier = site_samples,
+ usgsPCode = pcode_samples,
+ activityStartDateUpper = end_date,
+ activityStartDateLower = start_date,
+ dataProfile = "fullphyschem")
uv_data <- read_waterdata_continuous(monitoring_location_id = site_uv,
parameter_code = c(pcode_uv),
@@ -60,11 +64,11 @@ Next we'll clean up the discrete water quality data to make it easy to follow in
```{r trimsamplesdata}
samples_trim <- samples_data |>
- filter(ActivityTypeCode == "Sample-Routine",
- !is.na(ActivityStartDateTime)) |>
- select(samples_date = ActivityStartDateTime,
- val_samples = ResultMeasureValue,
- det_txt = ResultDetectionConditionText)
+ filter(Activity_TypeCode == "Sample-Routine",
+ !is.na(Activity_StartDateTime)) |>
+ select(samples_date = Activity_StartDateTime,
+ val_samples = Result_Measure,
+ det_txt = Result_ResultDetectionCondition)
```
```{r showsamplestrim, echo=FALSE}
diff --git a/vignettes/tutorial.Rmd b/vignettes/tutorial.Rmd
index 19651ee65..e97fa1cf5 100644
--- a/vignettes/tutorial.Rmd
+++ b/vignettes/tutorial.Rmd
@@ -112,8 +112,8 @@ There are many types of data available from `dataRetrieval`. To understand how t
|site|`readNWISsite`|Site metadata| `read_waterdata_monitoring_location` |
|pcode|`readNWISpCode`|Parameter code metadata | `read_waterdata_parameter_codes` |
|stat|`readNWISstat`| Site statistics | `read_waterdata_stats_por`, `read_waterdata_stats_daterange` |
-|rating|`readNWISrating`| Rating curves| None yet |
-|peak|`readNWISpeak`|Peak flow| None yet |
+|rating|`readNWISrating`| Rating curves| `read_waterdata_ratings` |
+|peak|`readNWISpeak`|Peak flow| `read_waterdata_peaks` |
|use|`readNWISuse`|Water Use| None yet |
|meas|`readNWISmeas`|Discrete surface water| `read_waterdata_field_measurements`|
| | `readNWISdata` | General data import | `read_waterdata` |