datacommonsorg · antaresc · Aug 8, 2019 · Jan 30, 2019 · Jan 30, 2019 · Jun 21, 2019
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,124 @@
+__pycache__/
+.dat
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+### Ignore MAC OS System files ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+.profraw
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Ignore BAZEL BUILD System files ###
+/bazel-*
+
+### R and RStudio ###
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
+datacommons.RCheck
+*tar.gz
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1 @@
+# Changelog
diff --git a/Dockerfile b/Dockerfile
@@ -16,6 +16,7 @@ RUN apt-get -q update && \
 
 # Install python
 RUN python setup.py -q install
+RUN pip3 install --upgrade requests
 
 # Run the tests
 RUN ./build.sh
diff --git a/WORKSPACE b/WORKSPACE
@@ -2,6 +2,8 @@ workspace(name="datacommons")
 
 load("@bazel_tools//tools/build_defs/repo:git.bzl", "git_repository")
 
+load("@bazel_tools//tools/build_defs/repo:git.bzl", "git_repository")
+
 # The following rules are needed to perform pip-install of dependencies.
 # Reference: https://github.com/bazelbuild/rules_python
 git_repository(

diff --git a/api-R/.Rbuildignore b/api-R/.Rbuildignore
@@ -0,0 +1,2 @@
+^.*\.Rproj$
+^\.Rproj\.user$
diff --git a/api-R/DESCRIPTION b/api-R/DESCRIPTION
@@ -0,0 +1,26 @@
+Package: datacommons
+Title: Data Commons REST API R Client
+Version: 2.0
+Authors@R: person("Tiffany", "Jann", email = "[email protected]", role = c("aut", "cre"))
+Description: A RESTful R API Client for querying the DataCommons.org
+    Open Knowledge Graph. The Node API endpoint is wrapped using Reticulate.
+    The Query API endpoint is implemented in pure R.
+    WiFi is needed for all functions in this package.
+    You can find our code here:
+    https://github.com/google/datacommons/
+Depends: R (>= 3.6.0),
+         tidyverse,
+         httr,
+         jsonlite,
+         reticulate
+License: Apache License, Version 2.0, MIT+
+Encoding: UTF-8
+LazyData: true
+Imports:
+    tidyverse,
+    httr,
+    jsonlite,
+    reticulate
+RoxygenNote: 6.1.1
+Suggests: 
+    testthat
diff --git a/api-R/NAMESPACE b/api-R/NAMESPACE
@@ -0,0 +1,9 @@
+# Generated by roxygen2: do not edit by hand
+
+export(GetObservations)
+export(GetPlacesIn)
+export(GetPopulations)
+export(GetPropertyLabels)
+export(GetPropertyValues)
+export(GetTriples)
+export(Query)
diff --git a/api-R/R/node-core.R b/api-R/R/node-core.R
@@ -0,0 +1,112 @@
+# Data Commons Node API - Core Functions
+#
+# These functions provide R access to core
+#   Data Commons Node API functions:
+#   get_property_labels, get_property_values, get_triples.
+#   www.DataCommons.org
+
+
+#' Return property labels of specified nodes
+#'
+#' Returns a map between nodes and outgoing (default) or incoming
+#'   property labels.
+#'
+#' @param dcids required, vector of string(s) that identify node(s) to get
+#'   property labels for.
+#' @param outgoing optional, boolean indicating whether to get properties
+#'   originating from
+#'   the given node. TRUE by default.
+#' @return Named list of properties associated with the given dcid(s) via the
+#'   given direction.
+#' @export
+#' @examples
+#' # dcid string of Santa Clara County.
+#' sccDcid <- 'geoId/06085'
+#' # Get incoming and outgoing properties for Santa Clara County.
+#' inLabels <- GetPropertyLabels(sccDcid, outgoing = FALSE)
+#' outLabels <- GetPropertyLabels(sccDcid)
+#'
+#' # List of dcid strings of Florida, Planned Parenthood West, and the
+#' # Republican Party.
+#' dcids <- c('geoId/12', 'plannedParenthood-PlannedParenthoodWest',
+#'            'politicalParty/RepublicanParty')
+#' # Get incoming and outgoing properties for Santa Clara County.
+#' inLabels <- GetPropertyLabels(dcids, outgoing = FALSE)
+#' outLabels <- GetPropertyLabels(dcids)
+GetPropertyLabels <- function(dcids, outgoing = TRUE) {
+  dcids = ConvertibleToPythonList(dcids)
+  return(dc$get_property_labels(dcids, outgoing))
+}
+
+#' Return property values along a property for one or more nodes
+#'
+#' Returns all neighboring nodes of each specified node via the specified
+#'   property and direction. The neighboring nodes are "values" for the
+#'   property and can be leaf (primitive) nodes.
+#'
+#' @param dcids required, vector OR single-column tibble/data frame of
+#'   string(s) that uniquely identify node(s) to get property values for.
+#' @param prop required, string identifying the property to get the property
+#'   values for.
+#' @param outgoing optional, boolean indicating whether the property
+#'   originates from the given node. TRUE by default.
+#' @param valueType optional, string identifying the node type to filter the
+#'   results by. NULL by default.
+#' @param limit optional, integer indicating the maximum number of values to
+#'   return across all properties. 100 by default.
+#' @return Named list or column of values associated to given dcid(s) via the
+#'   given property and direction.
+#'   Will be encapsulated in a named list if dcids input is vector of strings,
+#'   or a new single column tibble if dcids input is tibble/data frame.
+#' @export
+#' @examples
+#' # Set the dcid to be that of Santa Clara County.
+#' sccDcid <- 'geoId/06085'
+#' # Get the landArea value of Santa Clara (a leaf node).
+#' landArea <- GetPropertyValues(sccDcid, 'landArea')
+#'
+#' # Create a vector with Santa Clara and Miami-Dade County dcids
+#' countyDcids <- c('geoId/06085', 'geoId/12086')
+#' # Get all containing Cities.
+#' cities <- GetPropertyValues(countyDcids, 'containedInPlace',
+#'                             outgoing = FALSE, valueType = 'City')
+#'
+#'# Create a data frame with Santa Clara and Miami-Dade County dcids
+#' df <- data.frame(countyDcid = c('geoId/06085', 'geoId/12086'))
+#' # Get all containing Cities.
+#' df$cityDcid <- GetPropertyValues(select(df, countyDcid), 'containedInPlace',
+#'                                  outgoing = FALSE, valueType = 'City')
+GetPropertyValues <- function(dcids, prop, outgoing = TRUE, valueType = NULL,
+                              limit = 100) {
+  dcids = ConvertibleToPythonList(dcids)
+  return(dc$get_property_values(dcids, prop, outgoing, valueType, limit))
+}
+
+#' Return all triples involving specified nodes
+#'
+#' Returns all triples (subject-predicate-object) where the specified node is
+#' either a subject or an object.
+#'
+#' @param dcids required, vector of string(s) that uniquely identify
+#'   the node(s) to get triples for.
+#' @param limit optional, integer indicating the max number of triples to get
+#' for each property. 100 by default.
+#' @return Map between each dcid and all triples with the dcid as the subject or
+#' object. Triples are represented as (subject, predicate, object).
+#' @export
+#' @examples
+#' # Set the dcid to be that of Santa Clara County.
+#' sccDcid <- 'geoId/06085'
+#' # Get triples.
+#' triples <- GetTriples(sccDcid)
+#'
+#' # List of dcid strings of Florida, Planned Parenthood West, and the
+#' # Republican Party.
+#' dcids <- c('geoId/12', 'plannedParenthood-PlannedParenthoodWest',
+#'            'politicalParty/RepublicanParty')
+#' # Get triples.
+#' triples <- GetPropertyLabels(dcids)
+GetTriples <- function(dcids, limit = 100) {
+  dcids = ConvertibleToPythonList(dcids)
+  return(dc$get_triples(dcids, limit))
+}
diff --git a/api-R/R/places.R b/api-R/R/places.R
@@ -0,0 +1,46 @@
+# Data Commons Node API - Places Convenience Function
+#
+# GetPlacesIn
+#
+# These functions provide R access to
+#   Data Commons Node API Places convenience functions.
+#   These functions are designed to making adding a new column
+#   to a data frame convenient!
+#   www.DataCommons.org
+
+#' Return places of a specified type contained in specified places
+#'
+#' Returns a mapping between the specified places
+#'   and the places of a specified type contained in them.
+#'
+#' Assigning output to a tibble/data frame will yield a list of contained
+#' places. To convert this to 1-to-1 mapping (the containing place will
+#' be repeated), use \code{tidyr::unnest}.
+#'
+#' @param dcids required, dcid(s) identifying a containing place.
+#'   This parameter will accept a vector of strings
+#'   or a single-column tibble/data frame of strings.
+#'   To select a single column, use \code{select(df, col)}.
+#' @param placeType required, string identifying the type of place to query for.
+#' @return Named list or column of places contained in each given dcid of the
+#'   given placeType. If dcids input is vector of strings, will return a named
+#'   list. If dcids input is tibble/data frame, will return a new single-column
+#'   tibble/data frame.
+#' @export
+#' @examples
+#' # Atomic vector of the dcids of Santa Clara and Montgomery County.
+#' countyDcids <- c('geoId/06085', 'geoId/24031')
+#' # Get towns in Santa Clara and Montgomery County.
+#' towns <- GetPlacesIn(countyDcids, 'Town')
+#'
+#' # Tibble of the dcids of Santa Clara and Montgomery County.
+#' df <- tibble(countyDcid = c('geoId/06085', 'geoId/24031'))
+#' # Get towns in Santa Clara and Montgomery County.
+#' df$townDcid <- GetPlacesIn(df, 'Town')
+#' # Since GetPlacesIn returned a mapping between counties and
+#' # a list of towns, use you can use tidyr::unnest to create
+#' # a 1-1 mapping between each county and its towns.
+GetPlacesIn <- function(dcids, placeType) {
+  dcids = ConvertibleToPythonList(dcids)
+  return(dc$get_places_in(dcids, placeType))
+}