rdatasets 0.4.2 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a46abed3f289f2dfebb6f28071d802c05d8b2a4a227749a60680db49ae4723a8
-  data.tar.gz: 1926223ce67700e6f4bc2dceb0439092cc0e0e18c78040e0f6f77c599fd28e04
+  metadata.gz: 3a0ea0983b1aa1676ee7fa9f3ef1d425a77dcbcebfe8076063937db80ab07a2e
+  data.tar.gz: 4ce3fef0dfd07140504bf7a4dcf6ae0f8d99f6be6f8f203532b07318ec1470c1
 SHA512:
-  metadata.gz: 44e3e59bb2feb08c8baf583e4955c8da76292187d3d8e07feae9094fc4cf358d8824a8cce86143614ffdae122d57c6a41e57798b07faf9c12c327eb97ce65e67
-  data.tar.gz: 4c81ba19319dcb0ab6c59f6797e460d3ed02cfe7b7f65019bcc2ce74890bff14b5eddd8c3213b63e152ee82794f9612b904ac162e0cbcd94ebe45e2fc1d86f35
+  metadata.gz: 11810491ce07714ee2a5f7c9799d51541b530f7138754f5f5478e5bdff779c3a44906d8fe6f39e9451dba377318b8990eb26648c8e58cabbdee9c51a4a48935f
+  data.tar.gz: bc66e82486aee75f2609421a2bc86fa39075b903ac88b58ee312fc54e7f69464735f15fcaea7abf7bf343bc4b64a4f581f01bc7761ae9bbed58561409567f01f

data/Gemfile.lock

@@ -1,20 +1,20 @@
 PATH
   remote: .
   specs:
-    rdatasets (0.4.2)
+    rdatasets (0.5.0)
       daru
 
 GEM
   remote: https://rubygems.org/
   specs:
-    backports (3.11.4)
+    backports (3.12.0)
     daru (0.2.1)
       backports
       packable (~> 1.3.9)
     diff-lcs (1.3)
     packable (1.3.10)
       backports
-    parallel (1.13.0)
+    parallel (1.14.0)
     parallel_tests (2.28.0)
       parallel
     rake (10.5.0)
@@ -34,7 +34,6 @@ GEM
 
 PLATFORMS
   ruby
-  x64-mingw32
 
 DEPENDENCIES
   bundler (~> 2.0)

data/README.md

@@ -16,20 +16,22 @@ under development
 gem install rdatasets
 ```
 
-```bash
-git clone https://github.com/kojix2/rdatasets
-cd rdatasets
-bundle install
-bundle exec rake install
-```
-
 ## Usage
 
 ```ruby
 require 'rdatasets'
 df = Daru::DataFrame.from_rdatasets("datasets","iris")
-df = RDatasets.load("datasets", "iris")
+df = RDatasets.load "datasets", "iris"
+df = RDatasets.load :datasets, :iris
+df = RDatasets.datasets.iris
 # returns Daru::DataFrame
+
+# available datasets
+df = RDatasets.df
+
+# search
+RDatasets.search "diamonds"
+RDatasets.search /diamonds/
 ```
 
 ## Development

data/lib/rdatasets.rb

@@ -3,6 +3,31 @@ require 'daru'
 
 # Module for RDatasets
 module RDatasets
+  class Package
+    def initialize(package_name)
+      @package_name = package_name
+      @datasets = RDatasets.package package_name
+    end
+
+    private
+
+    def method_missing(name)
+      return RDatasets.load @package_name, name if @datasets.include? name
+
+      super
+    end
+  end
+
+  private_constant :Package
+
+  private
+
+  def self.method_missing(package_name)
+    return Package.new(package_name) if RDatasets.packages.include? package_name
+
+    super
+  end
+
   module_function
 
   # Load a certain dataset and returns a dataframe.
@@ -12,15 +37,15 @@ module RDatasets
   def load(package_name, dataset_name = nil)
     if dataset_name
       file_path = filepath(package_name, dataset_name)
-      df = Daru::DataFrame.from_csv(file_path)
-      if original_index_is_sequential? df
-        # `df.set_index` is slow
-        df.index = df[0]
-        df.delete_vector df[0].name
+      dataframe = Daru::DataFrame.from_csv(file_path)
+      if original_index_is_sequential? dataframe
+        # `dataframe.set_index` is slow
+        dataframe.index = dataframe.at 0
+        dataframe.delete_vector dataframe.at(0).name
       end
-      df
+      dataframe
     else
-      packages(package_name)
+      package(package_name)
     end
   end
 
@@ -42,44 +67,39 @@ module RDatasets
 
   # Display information of all data sets.
   # @return [Daru::DataFrame]
-  def datasets
+  def df
     file_path = File.expand_path('../data/datasets.csv', __dir__)
     Daru::DataFrame.from_csv(file_path)
   end
 
-  #
-  # @overload packages
-  #   Show a list of all packages.
-  #   @return [Array<Symbol>]
-  # @overload packages(package_name)
-  #   Show a list of datasets included in the package.
-  #   @param [String, Symbol] :R package name
-  #   @return [Array<Symbol>]
-  def packages(package_name = nil)
-    if package_name
-      df = datasets
-      ds = df.where(df['Package'].eq package_name.to_s)
-      ds['Item'].to_a.map(&:to_sym)
-    else
-      datasets['Package'].to_a.uniq.map(&:to_sym)
-    end
+  # Show a list of all packages.
+  # @return [Array<Symbol>]
+  def packages
+    df['Package'].to_a.uniq.map(&:to_sym)
+  end
+
+  # Show a list of datasets included in the package.
+  # @param [String, Symbol] :R package name
+  # @return [Array<Symbol>]
+  def package(package_name)
+    ds = df.where(df['Package'].eq package_name.to_s)
+    ds['Item'].to_a.map(&:to_sym)
   end
 
-  # Search available datasets. (items and titles) 
+  # Search available datasets. (items and titles)
   # If the argument is a string, ignore case.
   # @param pattern [String, Regexp] :The pattern to search for
   # @return [Daru::DataFrame]
   def search(pattern)
     pattern = /#{pattern}/i if pattern.is_a? String
-    p pattern
-    datasets.filter(:row) do |row|
+    df.filter(:row) do |row|
       row['Item'] =~ pattern || row['Title'] =~ pattern
     end
   end
 
   # Check if the index of original r dataset is sequential.
   def original_index_is_sequential?(dataframe)
-    dataframe[0].to_a == [*1..dataframe.size]
+    dataframe.at(0).to_a == [*1..dataframe.size]
   end
   private_class_method :original_index_is_sequential?
 end

data/lib/rdatasets/version.rb

@@ -1,3 +1,3 @@
 module RDatasets
-  VERSION = '0.4.2'.freeze
+  VERSION = '0.5.0'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rdatasets
 version: !ruby/object:Gem::Version
-  version: 0.4.2
+  version: 0.5.0
 platform: ruby
 authors:
 - kojix2
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-02-16 00:00:00.000000000 Z
+date: 2019-03-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daru