daru 0.2.2 → 0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 617e082fd3366f695622071cf630690d102552821e82926af81a7007bb09093d
-  data.tar.gz: b6b995e35e8124768a15a3e32d1fc38515aecc55f070510d7a51b45945520eb7
+  metadata.gz: 264a0549062a2c6b062f8c031b4e03524fd1bd852d59927a54722e8b8e68a2e8
+  data.tar.gz: 2dee6ded3fb009045a6ef13203c8ebe4251458e64b3e41a737b8bc04d4d0b91f
 SHA512:
-  metadata.gz: 8ae029cac761e4a7164b472ad6ef5275d18aa7d6dace9f61ab4553cc288a1d95e80412804e28a4405444a97dfd1e850ce00783d9b45126c0cb8e0c4dafa09e63
-  data.tar.gz: e8aa0aed6c05ec54ba4f5083ed3baa47b6eb02c3304bb0152beea1e57e181aafe45ebc779bbdec76b22b6c86b29f71dc16d013250870589cb93eeae0b8ca0917
+  metadata.gz: 1cb5cf9a2aa1660e9cd0d0a286af6d3dcbe987b5001f15a90e5b89394c36fdaedd8e29e742f591c36de64e61363ba66ceff8ae9f075c2ce1a4352a56584b4c24
+  data.tar.gz: 8e3d5843f871c0fba685430e27ff91090db4873da8edbfe2d1095b12a24a06dcda7ae1b198b9a3f7fcc013aeb757560088bcbb507a70ece4a4976eda63094cd8

data/.travis.yml

@@ -2,11 +2,8 @@ language:
   ruby
 
 rvm:
-  - '2.0'
-  - '2.1'
-  - '2.2'
-  - '2.3.0'
-  - '2.4.0'
+  - '2.5.1'
+  - '2.7.1'
 
 matrix:
   allow_failures:
@@ -14,6 +11,9 @@ matrix:
   fast_finish:
     true
 
+env:
+  - DARU_TEST_NMATRIX=1 DARU_TEST_GSL=1
+
 script:
   - bundle add yard-junk
   - bundle install
@@ -22,10 +22,7 @@ script:
   - bundle exec yard-junk
 
 install:
-  - if [ $TRAVIS_RUBY_VERSION == '2.2' ] || [ $TRAVIS_RUBY_VERSION == '2.1' ] || [ $TRAVIS_RUBY_VERSION == '2.0' ];
-      then gem install bundler -v '~> 1.6';
-      else gem install bundler;
-      fi
+  - gem install bundler
   - gem install rainbow -v '2.2.1'
   - bundle install
 

data/CONTRIBUTING.md

@@ -6,15 +6,18 @@ Either nmatrix or rb-gsl are NOT NECESSARY for using daru. They are just require
 
 To install dependencies, execute the following commands:
 
-*  `sudo apt-get update -qq`
-*  `sudo apt-get install -y libgsl0-dev r-base r-base-dev`
-*  `sudo Rscript -e "install.packages(c('Rserve','irr'),,'http://cran.us.r-project.org')"`
-*  `sudo apt-get install libmagickwand-dev imagemagick`
-
-
-Then install remaining dependencies:
-
-  `bundle install`
+``` bash
+sudo apt-get update -qq
+sudo apt-get install -y libgsl0-dev r-base r-base-dev
+sudo Rscript -e "install.packages(c('Rserve','irr'),,'http://cran.us.r-project.org')"
+sudo apt-get install libmagickwand-dev imagemagick
+export DARU_TEST_NMATRIX=1  # for running nmatrix tests.
+export DARU_TEST_GSL=1 # for running rb-GSL tests.
+bundle install
+```
+You don't need `DARU_TEST_NMATRIX` or `DARU_TEST_GSL` if you don't want to make changes
+to those parts of the code. However, they will be set in CI and will raise a test failure
+if something goes wrong.
 
 And run the test suite (should be all green with pending tests):
 
@@ -22,13 +25,6 @@ And run the test suite (should be all green with pending tests):
 
 If you have problems installing nmatrix, please consult the [nmatrix installation wiki](https://github.com/SciRuby/nmatrix/wiki/Installation) or the [mailing list](https://groups.google.com/forum/#!forum/sciruby-dev).
 
-**NOTE**: `Daru` is compatible with Ruby versions < 2.5; for later Ruby versions it breaks, returning the following error in versions >= 2.5.
-```
-/gems/packable-1.3.10/lib/packable/extensions/io.rb:86:in `pos': Illegal seek @ rb_io_tell - <STDOUT> (Errno::ESPIPE)
-```
-To reproduce this issue or explore this error further, head over to 
-[issue #500](https://github.com/SciRuby/daru/issues/500),
-[issue #503](https://github.com/SciRuby/daru/issues/503). Also, if you want to fix this issue, then please discuss it here : [#505](https://github.com/SciRuby/daru/issues/500)
 
 While preparing your pull requests, don't forget to check your code with Rubocop:
 

data/History.md

@@ -1,3 +1,20 @@
+# 0.3 (30 May 2020)
+* Major Enhacements
+  - Remove official support for Ruby < 2.5.1. Now we only test with 2.5.1 and 2.7.1. (@v0dro)
+  - Make nmatrix and gsl optional dependencies for testing. (@v0dro)
+  - Update sqlite, activerecord, nokogiri, packable, rake dependencies. (@v0dro)
+  - Remove runtime dependency on backports. (@v0dro)
+  - Add `Daru::Vector#match and Daru::Vector#apply_where` methods (@athityakumar).
+  - Add support for options to the `Daru` module. Adds a separate module `Daru::Configuration` that
+  can hold data for overall configuration of daru's execution. (@kojix2)
+* Minor Enhancements
+  - Add new `DataFrame#insert_vector` method. (@cyrillefr)
+  - Add `Vector#last`. (@kojix2)
+  - Add `DataFrame#rename_vectors!`. (@neumanrq)
+  - Refactor `GroupBy#apply_method`. (@paisible-wanderer)
+  - Auto-adjust header parameters when printing to terminal. (@ncs1)
+  - Infer offsets of timeseries automatically when they are a natural number multiple of seconds. (@jpaulgs)
+
 # 0.2.2 (8 August 2019)
 
 * Minor Enhancements

data/README.md

@@ -9,8 +9,9 @@
 
 daru (Data Analysis in RUby) is a library for storage, analysis, manipulation and visualization of data in Ruby.
 
-daru makes it easy and intuitive to process data predominantly through 2 data structures: `Daru::DataFrame` and `Daru::Vector`. Written in pure Ruby works with all ruby implementations. Tested with MRI 2.0, 2.1, 2.2, 2.3, and 2.4.
-
+daru makes it easy and intuitive to process data predominantly through 2 data structures:
+`Daru::DataFrame` and `Daru::Vector`. Written in pure Ruby works with all ruby implementations.
+Tested with MRI 2.5.1 and 2.7.1.
 
 ## daru plugin gems
 

data/daru.gemspec

@@ -19,7 +19,7 @@ Gem::Specification.new do |spec|
   spec.email         = ['sameer.deshmukh93@gmail.com']
   spec.summary       = %q{Data Analysis in RUby}
   spec.description   = Daru::DESCRIPTION
-  spec.homepage      = "http://github.com/v0dro/daru"
+  spec.homepage      = "http://github.com/SciRuby/daru"
   spec.license       = 'BSD-2'
 
   spec.files         = `git ls-files -z`.split("\x0")
@@ -27,14 +27,12 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib"]
 
-  spec.add_runtime_dependency 'backports'
-
   # it is required by NMatrix, yet we want to specify clearly which minimal version is OK
-  spec.add_runtime_dependency 'packable', '~> 1.3.9'
+  spec.add_runtime_dependency 'packable', '~> 1.3.13'
 
   spec.add_development_dependency 'spreadsheet', '~> 1.1.1'
   spec.add_development_dependency 'bundler', '>= 1.10'
-  spec.add_development_dependency 'rake', '~>10.5'
+  spec.add_development_dependency 'rake', '~>13.0'
   spec.add_development_dependency 'pry', '~> 0.10'
   spec.add_development_dependency 'pry-byebug'
   spec.add_development_dependency 'rserve-client', '~> 0.3'
@@ -42,28 +40,22 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'rspec-its'
   spec.add_development_dependency 'awesome_print'
   spec.add_development_dependency 'nyaplot', '~> 0.1.5'
-  spec.add_development_dependency 'nmatrix', '~> 0.2.1'
+  spec.add_development_dependency 'nmatrix', '~> 0.2.1' if ENV['DARU_TEST_NMATRIX']
   spec.add_development_dependency 'distribution', '~> 0.7'
-  spec.add_development_dependency 'gsl', '~>2.1.0.2'
+  spec.add_development_dependency 'gsl', '~>2.1.0.2' if ENV['DARU_TEST_GSL']
   spec.add_development_dependency 'dbd-sqlite3'
   spec.add_development_dependency 'dbi'
-  spec.add_development_dependency 'activerecord', '~> 4.0'
+  spec.add_development_dependency 'activerecord', '~> 6.0'
   spec.add_development_dependency 'mechanize'
   # issue : https://github.com/SciRuby/daru/issues/493 occured 
   # with latest version of sqlite3
-  spec.add_development_dependency  'sqlite3', '~> 1.3.13'
+  spec.add_development_dependency  'sqlite3'
   spec.add_development_dependency 'rubocop', '~> 0.49.0'
   spec.add_development_dependency 'ruby-prof'
   spec.add_development_dependency 'simplecov'
   spec.add_development_dependency 'gruff'
   spec.add_development_dependency 'webmock'
 
-  if RUBY_VERSION < '2.1.0'
-    spec.add_development_dependency 'nokogiri', '<= 1.6.8.1'
-  else
-    spec.add_development_dependency 'nokogiri'
-  end
-  if RUBY_VERSION >= '2.2.5'
-    spec.add_development_dependency 'guard-rspec'
-  end
+  spec.add_development_dependency 'nokogiri'
+  spec.add_development_dependency 'guard-rspec'
 end

data/lib/daru.rb

@@ -95,13 +95,13 @@ require 'date'
 require 'daru/version.rb'
 
 require 'open-uri'
-require 'backports/2.1.0/array/to_h'
 
 require 'daru/index/index.rb'
 require 'daru/index/multi_index.rb'
 require 'daru/index/categorical_index.rb'
 
 require 'daru/helpers/array.rb'
+require 'daru/configuration.rb'
 require 'daru/vector.rb'
 require 'daru/dataframe.rb'
 require 'daru/monkeys.rb'

data/lib/daru/configuration.rb

@@ -0,0 +1,34 @@
+module Daru
+  # Defines constants and methods related to configuration
+  module Configuration
+    INSPECT_OPTIONS_KEYS = [
+      :max_rows,
+      # Terminal
+      :spacing
+    ].freeze
+
+    # Jupyter
+    DEFAULT_MAX_ROWS = 30
+
+    # Terminal
+    DEFAULT_SPACING = 10
+
+    attr_accessor(*INSPECT_OPTIONS_KEYS)
+
+    def configure
+      yield self
+    end
+
+    def self.extended(base)
+      base.reset_options
+    end
+
+    def reset_options
+      self.max_rows  = DEFAULT_MAX_ROWS
+
+      self.spacing   = DEFAULT_SPACING
+    end
+  end
+
+  extend Configuration
+end

data/lib/daru/core/group_by.rb

@@ -2,21 +2,25 @@ module Daru
   module Core
     class GroupBy
       class << self
+        extend Gem::Deprecate
+
         # @private
-        def get_positions_group_map_on(indexes_with_positions, sort: false)
-          group_map = {}
+        def group_by_index_to_positions(indexes_with_positions, sort: false)
+          index_to_positions = {}
 
           indexes_with_positions.each do |idx, position|
-            (group_map[idx] ||= []) << position
+            (index_to_positions[idx] ||= []) << position
           end
 
           if sort # TODO: maybe add a more "stable" sorting option?
-            sorted_keys = group_map.keys.sort(&Daru::Core::GroupBy::TUPLE_SORTER)
-            group_map = sorted_keys.map { |k| [k, group_map[k]] }.to_h
+            sorted_keys = index_to_positions.keys.sort(&Daru::Core::GroupBy::TUPLE_SORTER)
+            index_to_positions = sorted_keys.map { |k| [k, index_to_positions[k]] }.to_h
           end
 
-          group_map
+          index_to_positions
         end
+        alias get_positions_group_map_on group_by_index_to_positions
+        deprecate :get_positions_group_map_on, :group_by_index_to_positions, 2019, 10
 
         # @private
         def get_positions_group_for_aggregation(multi_index, level=-1)
@@ -25,14 +29,14 @@ module Daru
           new_index = multi_index.dup
           new_index.remove_layer(level) # TODO: recheck code of Daru::MultiIndex#remove_layer
 
-          get_positions_group_map_on(new_index.each_with_index)
+          group_by_index_to_positions(new_index.each_with_index)
         end
 
         # @private
         def get_positions_group_map_for_df(df, group_by_keys, sort: true)
           indexes_with_positions = df[*group_by_keys].to_df.each_row.map(&:to_a).each_with_index
 
-          get_positions_group_map_on(indexes_with_positions, sort: sort)
+          group_by_index_to_positions(indexes_with_positions, sort: sort)
         end
 
         # @private
@@ -57,6 +61,9 @@ module Daru
         end
       end
 
+      # The group_by was done over the vectors in group_vectors; the remaining vectors are the non_group_vectors
+      attr_reader :group_vectors, :non_group_vectors
+
       # lazy accessor/attr_reader for the attribute groups
       def groups
         @groups ||= GroupBy.group_map_from_positions_to_indexes(@groups_by_pos, @context.index)
@@ -93,7 +100,7 @@ module Daru
         @group_vectors     = names
         @non_group_vectors = context.vectors.to_a - names
 
-        @context = context # TODO: maybe rename in @original_df or @grouped_db
+        @context = context # TODO: maybe rename in @original_df
 
         # FIXME: It feels like we don't want to sort here. Ruby's #group_by
         # never sorts:
@@ -362,21 +369,15 @@ module Daru
         Daru::DataFrame.rows(rows, order: @context.vectors, index: indexes)
       end
 
-      def apply_method method_type, method
-        order = @non_group_vectors.select do |ngvec|
-          method_type == :numeric && @context[ngvec].type == :numeric
-        end
+      def select_numeric_non_group_vectors
+        @non_group_vectors.select { |ngvec| @context[ngvec].type == :numeric }
+      end
 
-        rows = groups_by_idx.map do |_group, indexes|
-          order.map do |ngvector|
-            slice = @context[ngvector][*indexes]
-            slice.is_a?(Daru::Vector) ? slice.send(method) : slice
-          end
-        end
+      def apply_method method_type, method
+        raise 'To implement' if method_type != :numeric
+        aggregation_options = select_numeric_non_group_vectors.map { |k| [k, method] }.to_h
 
-        index = get_grouped_index
-        order = Daru::Index.new(order)
-        Daru::DataFrame.new(rows.transpose, index: index, order: order)
+        aggregate(aggregation_options)
       end
 
       def get_grouped_index(index_tuples=nil)

data/lib/daru/core/query.rb

@@ -70,6 +70,22 @@ module Daru
           resultant_dv
         end
 
+        def vector_apply_where dv, bool_array
+          _data, new_index = fetch_new_data_and_index dv, bool_array
+          all_index        = dv.index
+          all_data         = all_index.map { |idx| new_index.include?(idx) ? yield(dv[idx]) : dv[idx] }
+
+          resultant_dv = Daru::Vector.new all_data,
+            index: dv.index.class.new(all_index),
+            dtype: dv.dtype,
+            type: dv.type,
+            name: dv.name
+
+          # Preserve categories order for category vector
+          resultant_dv.categories = dv.categories if dv.category?
+          resultant_dv
+        end
+
         private
 
         def fetch_new_data_and_index dv, bool_array

data/lib/daru/dataframe.rb

@@ -12,6 +12,8 @@ module Daru
     # TODO: Remove this line but its causing erros due to unkown reason
     Daru.has_nyaplot?
 
+    attr_accessor(*Configuration::INSPECT_OPTIONS_KEYS)
+
     extend Gem::Deprecate
 
     class << self
@@ -545,6 +547,17 @@ module Daru
       self[n] = vector
     end
 
+    def insert_vector n, name, source
+      raise ArgumentError unless source.is_a? Array
+      vector = Daru::Vector.new(source, index: @index, name: @name)
+      @data << vector
+      @vectors = @vectors.add name
+      ordr = @vectors.dup.to_a
+      elmnt = ordr.pop
+      ordr = ordr.insert n, elmnt
+      self.order=ordr
+    end
+
     # Access a row or set/create a row. Refer #[] and #[]= docs for details.
     #
     # == Usage
@@ -1696,6 +1709,24 @@ module Daru
       self.vectors = Daru::Index.new new_names
     end
 
+    # Renames the vectors and returns itself
+    #
+    # == Arguments
+    #
+    # * name_map - A hash where the keys are the exising vector names and
+    #              the values are the new names.  If a vector is renamed
+    #              to a vector name that is already in use, the existing
+    #              one is overwritten.
+    #
+    # == Usage
+    #
+    #   df = Daru::DataFrame.new({ a: [1,2,3,4], b: [:a,:b,:c,:d], c: [11,22,33,44] })
+    #   df.rename_vectors! :a => :alpha, :c => :gamma # df
+    def rename_vectors! name_map
+      rename_vectors(name_map)
+      self
+    end
+
     # Return the indexes of all the numeric vectors. Will include vectors with nils
     # alongwith numbers.
     def numeric_vectors
@@ -2091,7 +2122,7 @@ module Daru
     end
 
     # Convert to html for IRuby.
-    def to_html(threshold=30)
+    def to_html(threshold=Daru.max_rows)
       table_thead = to_html_thead
       table_tbody = to_html_tbody(threshold)
       path = if index.is_a?(MultiIndex)
@@ -2112,7 +2143,8 @@ module Daru
       ERB.new(File.read(table_thead_path).strip).result(binding)
     end
 
-    def to_html_tbody(threshold=30)
+    def to_html_tbody(threshold=Daru.max_rows)
+      threshold ||= @size
       table_tbody_path =
         if index.is_a?(MultiIndex)
           File.expand_path('../iruby/templates/dataframe_mi_tbody.html.erb', __FILE__)
@@ -2229,10 +2261,11 @@ module Daru
     end
 
     # Pretty print in a nice table format for the command line (irb/pry/iruby)
-    def inspect spacing=10, threshold=15
+    def inspect spacing=Daru.spacing, threshold=Daru.max_rows
       name_part = @name ? ": #{@name} " : ''
+      spacing = [headers.to_a.map(&:length).max, spacing].max
 
-      "#<#{self.class}#{name_part}(#{nrows}x#{ncols})>\n" +
+      "#<#{self.class}#{name_part}(#{nrows}x#{ncols})>#{$INPUT_RECORD_SEPARATOR}" +
         Formatters::Table.format(
           each_row.lazy,
           row_headers: row_headers,

data/lib/daru/date_time/index.rb

@@ -93,11 +93,12 @@ module Daru
       def infer_offset data
         diffs = data.each_cons(2).map { |d1, d2| d2 - d1 }
 
-        if diffs.uniq.count == 1
-          TIME_INTERVALS[diffs.first].new
-        else
-          nil
-        end
+        return nil unless diffs.uniq.count == 1
+
+        return TIME_INTERVALS[diffs.first].new if TIME_INTERVALS.include?(diffs.first)
+
+        number_of_seconds = diffs.first / Daru::Offsets::Second.new.multiplier
+        Daru::Offsets::Second.new(number_of_seconds.numerator) if number_of_seconds.denominator == 1
       end
 
       def find_index_of_date data, date_time