lint

DESCRIPTION

@@ -15,7 +15,7 @@ Suggests:
     rmarkdown
 Author: Norwin Roosen
 Maintainer: Norwin Roosen <noerw@gmx.de>
-Description: This packages ingests data (measurements, sensorstations) from the
+Description: This package ingests data (measurements, sensorstations) from the
     API of opensensemap.org for analysis in R.
     The package aims to be compatible with sf and the tidyverse.
 License: GPL-2

R/api.R

@@ -4,8 +4,6 @@
 #  for CSV responses (get_measurements) the readr package is a hidden dependency
 # ==============================================================================
 
-# does not actually get called by the user. ... contains all the query parameters.
-# the proxy is just for parameter autocompletion, filtering out the endpoint
 get_boxes_ = function (..., endpoint) {
   response = httr::GET(endpoint, path = c('boxes'), query = list(...)) %>%
     httr::content() %>%

R/box.R

@@ -25,7 +25,15 @@
 #' @seealso \code{\link{osem_phenomena}}
 #' @export
 #' @examples
-#' # TODO
+#' # get *all* boxes available on the API
+#' b = osem_boxes()
+#'
+#' # get all boxes with grouptag 'ifgi' that are placed outdoors
+#' b = osem_boxes(grouptag = 'ifgi', exposure = 'outdoor')
+#'
+#' # get all boxes that have measured PM2.5 in the last 4 hours
+#' b = osem_boxes(date = Sys.time(), phenomenon = 'PM2.5')
+#'
 osem_boxes = function (exposure = NA, model = NA, grouptag = NA,
                       date = NA, from = NA, to = NA, phenomenon = NA,
                       endpoint = 'https://api.opensensemap.org') {
@@ -52,14 +60,10 @@ osem_boxes = function (exposure = NA, model = NA, grouptag = NA,
   if (!is.na(grouptag)) query$grouptag = grouptag
   if (!is.na(phenomenon)) query$phenomenon = phenomenon
 
-  if (!is.na(to) && !is.na(from)) {
+  if (!is.na(to) && !is.na(from))
-    # error, if from is after to
-    # convert dates to commaseparated UTC ISOdates
     query$date = parse_dateparams(from, to) %>% paste(collapse = ',')
-
+  else if (!is.na(date))
-  } else if (!is.na(date)) {
     query$date = utc_date(date) %>% date_as_isostring()
-  }
 
   do.call(get_boxes_, query)
 }
@@ -76,7 +80,9 @@ osem_boxes = function (exposure = NA, model = NA, grouptag = NA,
 #' @seealso \code{\link{osem_phenomena}}
 #' @export
 #' @examples
-#' # TODO
+#' # get a specific box by ID
+#' b = osem_box('593bcd656ccf3b0011791f5a')
+#'
 osem_box = function (boxId, endpoint = 'https://api.opensensemap.org') {
   get_box_(boxId, endpoint = endpoint)
 }

R/box_utils.R

@@ -14,7 +14,7 @@ plot.sensebox = function (x, ...) {
 #' @export
 print.sensebox = function(x, ...) {
   important_columns = c('name', 'exposure', 'lastMeasurement', 'phenomena')
-  data = as.data.frame(x) # to get rid of the sf::`<-[` override..
+  data = as.data.frame(x)
   print(data[important_columns], ...)
 
   invisible(x)
@@ -39,8 +39,7 @@ summary.sensebox = function(object, ...) {
       '365d' = nrow(object[diffNow <= 8760, ]) - neverActive,
       'never' = neverActive
     )
-  ) %>%
+  ) %>% print()
-    print()
 
   oldest = object[object$createdAt == min(object$createdAt), ]
   newest = object[object$createdAt == max(object$createdAt), ]

R/measurement.R

@@ -53,7 +53,7 @@ osem_measurements.default = function (x, ...) {
 #' bbox = structure(c(7, 51, 8, 52), class = 'bbox')
 #' osem_measurements(bbox, 'Temperatur')
 #'
-#' points = sf::st_multipoint(x = matrix(c(7,8,51,52),2,2))
+#' points = sf::st_multipoint(matrix(c(7, 8, 51, 52), 2, 2))
 #' bbox2 = sf::st_bbox(points)
 #' osem_measurements(bbox2, 'Temperatur', exposure = 'outdoor')
 #'
@@ -98,7 +98,10 @@ osem_measurements.sensebox = function (x, phenomenon, exposure = NA,
 parse_get_measurements_params = function (params) {
   if (is.null(params$phenomenon) | is.na(params$phenomenon))
     stop('Parameter "phenomenon" is required')
-  if (!is.na(params$from) && is.na(params$to)) stop('specify "from" only together with "to"')
+
+  if (!is.na(params$from) && is.na(params$to))
+    stop('specify "from" only together with "to"')
+
   if (
     (!is.null(params$bbox) && !is.null(params$boxes)) ||
     (is.null(params$bbox) && is.null(params$boxes))
@@ -113,6 +116,7 @@ parse_get_measurements_params = function (params) {
     query$`from-date` = utc_date(params$from) %>% date_as_isostring()
   if (!is.na(params$to))
     query$`to-date` = utc_date(params$to) %>% date_as_isostring()
+
   if (!is.na(params$exposure)) query$exposure = params$exposure
   if (!is.na(params$columns))  query$columns = paste(params$columns, collapse = ',')
 

R/utils.R

@@ -1,3 +1,5 @@
+# ==============================================================================
+#
 #' Convert a \code{sensebox} or \code{osem_measurements} dataframe to an
 #' \code{\link[sf]{st_sf}} object.
 #'
@@ -18,6 +20,7 @@ osem_remote_error = function (response) {
   invisible(response)
 }
 
+# parses from/to params for get_measurements_ and get_boxes_
 parse_dateparams = function (from, to) {
   from = utc_date(from)
   to = utc_date(to)
@@ -35,4 +38,4 @@ utc_date = function (date) {
 }
 
 # NOTE: cannot handle mixed vectors of POSIXlt and POSIXct
-date_as_isostring = function (date) format(date, format = '%FT%TZ')
+date_as_isostring = function (date) format.Date(date, format = '%FT%TZ')

vignettes/osem-intro.Rmd

@@ -16,7 +16,7 @@ knitr::opts_chunk$set(echo = TRUE)
 ## Analyzing environmental sensor data from openSenseMap.org in R
 
 This package provides data ingestion functions for almost any data stored on the
-open data platform <https://opensensemap.org>.
+open data platform for environemental sensordata <https://opensensemap.org>.
 Its main goals are to provide means for:
 
 - big data analysis of the measurements stored on the platform
@@ -24,7 +24,7 @@ Its main goals are to provide means for:
 
 > *Please note:* The openSenseMap API is sometimes a bit unstable when streaming
 long responses, which results in `curl` complaining about `Unexpected EOF`. This
-bug is beeing worked on upstream. Meanwhile you have to retry the request when
+bug is being worked on upstream. Meanwhile you have to retry the request when
 this occurs.
 
 ### Exploring the dataset
@@ -40,8 +40,8 @@ summary(all_sensors)
 ```
 
 This gives a good overview already: As of writing this, there are more than 600
-sensor stations, of which ~50% are running. Most of them are placed outdoors and
+sensor stations, of which ~50% are currently running. Most of them are placed
-have around 5 sensors each.
+outdoors and have around 5 sensors each.
 The oldest station is from May 2014, while the latest station was registered a
 couple of minutes ago.
 
@@ -52,7 +52,7 @@ can help us out here:
 plot(all_sensors)
 ```
 
-Seems like we have to reduce our area of interest to Germany.
+It seems we have to reduce our area of interest to Germany.
 
 But what do these sensor stations actually measure? Lets find out.
 `osem_phenomena()` gives us a named list of of the counts of each observed
@@ -66,14 +66,14 @@ str(phenoms)
 Thats quite some noise there, with many phenomena being measured by a single
 sensor only, or many duplicated phenomena due to slightly different spellings.
 We should clean that up, but for now let's just filter out the noise and find
-those phenomena with the high sensor numbers:
+those phenomena with high sensor numbers:
 
 ```{r}
 phenoms[phenoms > 20]
 ```
 
-Alright, temperature it is! PM2.5 seems to be more interesting to analyze though.
+Alright, temperature it is! Fine particulate matter (PM2.5) seems to be more
-
+interesting to analyze though. 
 We should check how many sensor stations provide useful data: We want only those
 boxes with a PM2.5 sensor, that are placed outdoors and are currently submitting
 measurements:
@@ -94,11 +94,12 @@ Thats still more than 200 measuring stations, we can work with that.
 ### Analyzing sensor data
 Having analyzed the available data sources, let's finally get some measurements.
 We could call `osem_measurements(pm25_sensors)` now, however we are focussing on
-a restricted area of interest, the city of Berlin
+a restricted area of interest, the city of Berlin.
-Luckily we can get the measurements filtered by a bounding box as well:
+Luckily we can get the measurements filtered by a bounding box:
 
 ```{r}
 library(sf)
+library(units)
 library(lubridate)
 
 # construct a bounding box: 12 kilometers around Berlin
@@ -131,7 +132,7 @@ plot(st_geometry(pm25_sf))
 `TODO`
 
 ### Monitoring growth of the dataset
-We can get the total size of the data set using `osem_counts()`. Lets create a
+We can get the total size of the dataset using `osem_counts()`. Lets create a
 time series of that.
 To do so, we create a function that attaches a timestamp to the data, and adds
 the new results to an existing `data.frame`:
@@ -141,7 +142,7 @@ build_osem_counts_timeseries = function (existing_data) {
   osem_counts() %>%
     list(time = Sys.time()) %>%     # attach a timestamp
     as.data.frame() %>%             # make it a dataframe.
-    dplyr::bind_rows(existing_data) # combine with existing data
+    rbind(existing_data) # combine with existing data
 }
 ```
 
@@ -153,7 +154,7 @@ osem_counts_ts = build_osem_counts_timeseries(osem_counts_ts)
 osem_counts_ts
 ```
 
-Once we have some data, we can plot the growth of data set over time:
+Once we have some data, we can plot the growth of dataset over time:
 
 ```{r}
 plot(measurements~time, osem_counts_ts)
@@ -163,7 +164,7 @@ Further analysis: `TODO`
 
 ### Outlook
 
-Next iterations of this package could include the following features
+Next iterations of this package could include the following features:
 
 - improved utility functions (`plot`, `summary`) for measurements and boxes
 - better integration of `sf` for spatial analysis