rover-df 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2fb7c518e0c1d61e601012d0beff064fe04b6cfcfb852fd97d28b999f1173445
-  data.tar.gz: b1a3f177d05095799dc2f02082d921d87774375e3f91db468539540c0c5d9482
+  metadata.gz: 1c750c49e4cb313565a3b52a273c4820ae406471a1007ddb8e83742f3f2640f1
+  data.tar.gz: 2a7469abd672a87c9b4c874469baf07f42b22067ac2281c424eeb7b60841bbfe
 SHA512:
-  metadata.gz: 5a98bce5cdb1cd8ed2442dd54cdcc0bcb93f39ff0daa4c4386a5805b285bd898a10278aad2522947bc944e4f995c833ebbe96f08b29421e048fd850cb2cf7903
-  data.tar.gz: a64bdc8da3a2202f0b4583d02eb162e07d8ae387bacf4f434ab8b6377a8752da0919c24506616df0bb90667dc1eab9f7b4acd6076ef932d1fb69f57c395e6e00
+  metadata.gz: 24e7874a67e498cadb8c2b4773f00c5cf53ab76e8231b7c762b8f403c2d4783809beb44ba3b37cb50b801032c3a3a9c140b18e1a10967eb331c517b5dd5251aa
+  data.tar.gz: b62f4bfd7591e9c4869ab13e4e6efeba5c4e121c92470bc81d517ec85045a2fdc080a7a6ca3f61a15e7c98335543fcb11893d00d374cb5a3cf1294e12ed65130

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.2.1 (2020-11-23)
+
+- Added `plot` method to data frames
+- Improved error message when too few headers
+
 ## 0.2.0 (2020-08-17)
 
 - Added `numeric?` and `zip` methods to vectors

data/README.md

@@ -4,7 +4,9 @@ Simple, powerful data frames for Ruby
 
 :mountain: Designed for data exploration and machine learning, and powered by [Numo](https://github.com/ruby-numo/numo-narray)
 
-[![Build Status](https://travis-ci.org/ankane/rover.svg?branch=master)](https://travis-ci.org/ankane/rover)
+:evergreen_tree: Uses [Vega](https://github.com/ankane/vega) for visualization
+
+[![Build Status](https://github.com/ankane/rover/workflows/build/badge.svg?branch=master)](https://github.com/ankane/rover/actions)
 
 ## Installation
 
@@ -198,6 +200,20 @@ Multiple groups
 df.group([:a, :b]).count
 ```
 
+## Visualization [master]
+
+Add [Vega](https://github.com/ankane/vega) to your application’s Gemfile:
+
+```ruby
+gem 'vega'
+```
+
+And use:
+
+```ruby
+df.plot(:a, :b)
+```
+
 ## Updating Data
 
 Add a new column

data/lib/rover.rb

@@ -11,12 +11,12 @@ module Rover
   class << self
     def read_csv(path, types: nil, **options)
       require "csv"
-      csv_to_df(CSV.read(path, **csv_options(options)), types: types)
+      csv_to_df(CSV.read(path, **csv_options(options)), types: types, headers: options[:headers])
     end
 
     def parse_csv(str, types: nil, **options)
       require "csv"
-      csv_to_df(CSV.parse(str, **csv_options(options)), types: types)
+      csv_to_df(CSV.parse(str, **csv_options(options)), types: types, headers: options[:headers])
     end
 
     private
@@ -28,7 +28,11 @@ module Rover
       options
     end
 
-    def csv_to_df(table, types: nil)
+    def csv_to_df(table, types: nil, headers: nil)
+      if headers && headers.size < table.headers.size
+        raise ArgumentError, "Expected #{table.headers.size} headers, got #{headers.size}"
+      end
+
       table.by_col!
       data = {}
       table.each do |k, v|

data/lib/rover/data_frame.rb

@@ -237,7 +237,12 @@ module Rover
     # for IRuby
     def to_html
       require "iruby"
-      IRuby::HTML.table(to_h)
+      if size > 7
+        # pass 8 rows so maxrows is applied
+        IRuby::HTML.table((self[0..4] + self[-4..-1]).to_h, maxrows: 7)
+      else
+        IRuby::HTML.table(to_h)
+      end
     end
 
     # TODO handle long text better
@@ -291,8 +296,8 @@ module Rover
       dup.sort_by!(&block)
     end
 
-    def group(columns)
-      Group.new(self, columns)
+    def group(*columns)
+      Group.new(self, columns.flatten)
     end
 
     [:max, :min, :median, :mean, :percentile, :sum].each do |name|
@@ -357,6 +362,49 @@ module Rover
       keys.all? { |k| self[k] == other[k] }
     end
 
+    def plot(x = nil, y = nil, type: nil)
+      require "vega"
+
+      raise ArgumentError, "Must specify columns" if keys.size != 2 && (!x || !y)
+      x ||= keys[0]
+      y ||= keys[1]
+      type ||= begin
+        if self[x].numeric? && self[y].numeric?
+          "scatter"
+        elsif types[x] == :object && self[y].numeric?
+          "column"
+        else
+          raise "Cannot determine type"
+        end
+      end
+      data = self[[x, y]]
+
+      case type
+      when "scatter"
+        Vega.lite
+          .data(data)
+          .mark(type: "circle", tooltip: true)
+          .encoding(
+            x: {field: x, type: "quantitative", scale: {zero: false}},
+            y: {field: y, type: "quantitative", scale: {zero: false}},
+            size: {value: 60}
+          )
+          .config(axis: {title: nil, labelFontSize: 12})
+      when "column"
+        Vega.lite
+          .data(data)
+          .mark(type: "bar", tooltip: true)
+          .encoding(
+            # TODO determine label angle
+            x: {field: x, type: "nominal", sort: "none", axis: {labelAngle: 0}},
+            y: {field: y, type: "quantitative"}
+          )
+          .config(axis: {title: nil, labelFontSize: 12})
+      else
+        raise ArgumentError, "Invalid type: #{type}"
+      end
+    end
+
     private
 
     def check_key(key)

data/lib/rover/group.rb

@@ -2,7 +2,11 @@ module Rover
   class Group
     def initialize(df, columns)
       @df = df
-      @columns = Array(columns)
+      @columns = columns
+    end
+
+    def group(*columns)
+      Group.new(@df, @columns + columns.flatten)
     end
 
     [:count, :max, :min, :mean, :median, :percentile, :sum].each do |name|

data/lib/rover/vector.rb

@@ -95,7 +95,7 @@ module Rover
       define_method(op) do |other|
         other = other.to_numo if other.is_a?(Vector)
         # TODO better logic
-        if @data.is_a?(Numo::RObject)
+        if @data.is_a?(Numo::RObject) && !other.is_a?(Numo::RObject)
           map { |v| v.send(op, other) }
         else
           Vector.new(@data.send(op, other))

data/lib/rover/version.rb

@@ -1,3 +1,3 @@
 module Rover
-  VERSION = "0.2.0"
+  VERSION = "0.2.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rover-df
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Andrew Kane
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-08-17 00:00:00.000000000 Z
+date: 2020-11-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -108,7 +108,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: 
+description:
 email: andrew@chartkick.com
 executables: []
 extensions: []
@@ -127,7 +127,7 @@ homepage: https://github.com/ankane/rover
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -142,8 +142,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: Simple, powerful data frames for Ruby
 test_files: []