rover-df 0.2.1 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1c750c49e4cb313565a3b52a273c4820ae406471a1007ddb8e83742f3f2640f1
-  data.tar.gz: 2a7469abd672a87c9b4c874469baf07f42b22067ac2281c424eeb7b60841bbfe
+  metadata.gz: ca39a558c3c12103f03fed4cb8f007fbd00a1f8e84b839916fd0010aae4613ba
+  data.tar.gz: 43df8cdc415cc036ac383f30b7c91a35b644067a3cb8ea199abd7452b98298d5
 SHA512:
-  metadata.gz: 24e7874a67e498cadb8c2b4773f00c5cf53ab76e8231b7c762b8f403c2d4783809beb44ba3b37cb50b801032c3a3a9c140b18e1a10967eb331c517b5dd5251aa
-  data.tar.gz: b62f4bfd7591e9c4869ab13e4e6efeba5c4e121c92470bc81d517ec85045a2fdc080a7a6ca3f61a15e7c98335543fcb11893d00d374cb5a3cf1294e12ed65130
+  metadata.gz: 2724c7e85ee7921f277be833cf89be638c14cbb37a44411bba86c42cacffe7c0e4b82ea04d4dfb3d694c6429ba41bc8e8c10f7cb40e5d34bf59d14755858735f
+  data.tar.gz: fa860158decbca0a0b35ccb82e6f73d9a513c37b483eca52d140842d5dd255899a2e1ded3ec4375a492b86d3ec09ffa53d4871e05f1fdad39f3d2630215417dc

data/CHANGELOG.md

@@ -1,3 +1,24 @@
+## 0.2.5 (2021-09-25)
+
+- Fixed column types with joins
+
+## 0.2.4 (2021-06-03)
+
+- Added grouping for `std` and `var`
+- Fixed `==` for data frames
+- Fixed error with `first` and `last` for data frames
+- Fixed error with `last` when vector size is smaller than `n`
+
+## 0.2.3 (2021-02-08)
+
+- Added `select`, `reject`, and `map!` methods to vectors
+
+## 0.2.2 (2021-01-01)
+
+- Added line, pie, area, and bar charts
+- Added `|` and `^` for vectors
+- Fixed typecasting with `map`
+
 ## 0.2.1 (2020-11-23)
 
 - Added `plot` method to data frames

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2020 Andrew Kane
+Copyright (c) 2020-2021 Andrew Kane
 
 MIT License
 

data/README.md

@@ -20,7 +20,7 @@ gem 'rover-df'
 
 A data frame is an in-memory table. It’s a useful data structure for data analysis and machine learning. It uses columnar storage for fast operations on columns.
 
-Try it out for forecasting by clicking the button below:
+Try it out for forecasting by clicking the button below (it can take a few minutes to start):
 
 [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ankane/ml-stack/master?filepath=Forecasting.ipynb)
 
@@ -123,24 +123,53 @@ df[1..3]
 df[[1, 4, 5]]
 ```
 
+Iterate over rows
+
+```ruby
+df.each_row { |row| ... }
+```
+
+Iterate over a column
+
+```ruby
+df[:a].each { |item| ... }
+# or
+df[:a].each_with_index { |item, index| ... }
+```
+
 ## Filtering
 
 Filter on a condition
 
 ```ruby
+df[df[:a] == 100]
+df[df[:a] != 100]
 df[df[:a] > 100]
+df[df[:a] >= 100]
+df[df[:a] < 100]
+df[df[:a] <= 100]
 ```
 
-And
+In
 
 ```ruby
-df[df[:a] > 100 & df[:b] == "one"]
+df[df[:a].in?([1, 2, 3])]
+df[df[:a].in?(1..3)]
+df[df[:a].in?(["a", "b", "c"])]
 ```
 
-Or
+Not in
 
 ```ruby
-df[df[:a] > 100 | df[:b] == "one"]
+df[!df[:a].in?([1, 2, 3])]
+```
+
+And, or, and exclusive or
+
+```ruby
+df[(df[:a] > 100) & (df[:b] == "one")] # and
+df[(df[:a] > 100) | (df[:b] == "one")] # or
+df[(df[:a] > 100) ^ (df[:b] == "one")] # xor
 ```
 
 ## Operations
@@ -166,6 +195,8 @@ df[:a].median
 df[:a].percentile(90)
 df[:a].min
 df[:a].max
+df[:a].std
+df[:a].var
 ```
 
 Count occurrences
@@ -200,7 +231,7 @@ Multiple groups
 df.group([:a, :b]).count
 ```
 
-## Visualization [master]
+## Visualization
 
 Add [Vega](https://github.com/ankane/vega) to your application’s Gemfile:
 
@@ -214,6 +245,12 @@ And use:
 df.plot(:a, :b)
 ```
 
+Specify the chart type (`line`, `pie`, `column`, `bar`, `area`, or `scatter`)
+
+```ruby
+df.plot(:a, :b, type: "pie")
+```
+
 ## Updating Data
 
 Add a new column
@@ -238,6 +275,14 @@ df[:a][0..2] = 1
 df[:a][0..2] = [1, 2, 3]
 ```
 
+Update all elements
+
+```ruby
+df[:a] = df[:a].map { |v| v.gsub("a", "b") }
+# or
+df[:a].map! { |v| v.gsub("a", "b") }
+```
+
 Update elements matching a condition
 
 ```ruby

data/lib/rover/data_frame.rb

@@ -72,6 +72,7 @@ module Rover
         # multiple columns
         df = DataFrame.new
         where.each do |k|
+          check_column(k, true)
           df[k] = @vectors[k]
         end
         df
@@ -162,7 +163,7 @@ module Rover
       last(n)
     end
 
-    def first(n = nil)
+    def first(n = 1)
       new_vectors = {}
       @vectors.each do |k, v|
         new_vectors[k] = v.first(n)
@@ -170,7 +171,7 @@ module Rover
       DataFrame.new(new_vectors)
     end
 
-    def last(n = nil)
+    def last(n = 1)
       new_vectors = {}
       @vectors.each do |k, v|
         new_vectors[k] = v.last(n)
@@ -300,7 +301,7 @@ module Rover
       Group.new(self, columns.flatten)
     end
 
-    [:max, :min, :median, :mean, :percentile, :sum].each do |name|
+    [:max, :min, :median, :mean, :percentile, :sum, :std, :var].each do |name|
       define_method(name) do |column, *args|
         check_column(column)
         self[column].send(name, *args)
@@ -359,7 +360,7 @@ module Rover
     def ==(other)
       size == other.size &&
       keys == other.keys &&
-      keys.all? { |k| self[k] == other[k] }
+      keys.all? { |k| self[k].to_numo == other[k].to_numo }
     end
 
     def plot(x = nil, y = nil, type: nil)
@@ -374,22 +375,41 @@ module Rover
         elsif types[x] == :object && self[y].numeric?
           "column"
         else
-          raise "Cannot determine type"
+          raise "Cannot determine type. Use the type option."
         end
       end
       data = self[[x, y]]
 
       case type
-      when "scatter"
+      when "line", "area"
+        x_type =
+          if data[x].numeric?
+            "quantitative"
+          elsif data[x].all? { |v| v.is_a?(Date) || v.is_a?(Time) }
+            "temporal"
+          else
+            "nominal"
+          end
+
+        scale = x_type == "temporal" ? {type: "utc"} : {}
+
         Vega.lite
           .data(data)
-          .mark(type: "circle", tooltip: true)
+          .mark(type: type, tooltip: true, interpolate: "cardinal", point: {size: 60})
           .encoding(
-            x: {field: x, type: "quantitative", scale: {zero: false}},
-            y: {field: y, type: "quantitative", scale: {zero: false}},
-            size: {value: 60}
+            x: {field: x, type: x_type, scale: scale},
+            y: {field: y, type: "quantitative"}
           )
-          .config(axis: {title: nil, labelFontSize: 12})
+          .config(axis: {labelFontSize: 12})
+      when "pie"
+        Vega.lite
+          .data(data)
+          .mark(type: "arc", tooltip: true)
+          .encoding(
+            color: {field: x, type: "nominal", sort: "none", axis: {title: nil}, legend: {labelFontSize: 12}},
+            theta: {field: y, type: "quantitative"}
+          )
+          .view(stroke: nil)
       when "column"
         Vega.lite
           .data(data)
@@ -399,7 +419,27 @@ module Rover
             x: {field: x, type: "nominal", sort: "none", axis: {labelAngle: 0}},
             y: {field: y, type: "quantitative"}
           )
-          .config(axis: {title: nil, labelFontSize: 12})
+          .config(axis: {labelFontSize: 12})
+      when "bar"
+        Vega.lite
+          .data(data)
+          .mark(type: "bar", tooltip: true)
+          .encoding(
+            # TODO determine label angle
+            y: {field: x, type: "nominal", sort: "none", axis: {labelAngle: 0}},
+            x: {field: y, type: "quantitative"}
+          )
+          .config(axis: {labelFontSize: 12})
+      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: {labelFontSize: 12})
       else
         raise ArgumentError, "Invalid type: #{type}"
       end
@@ -435,10 +475,12 @@ module Rover
 
       left = how == "left"
 
+      types = {}
       vectors = {}
       keys = (self.keys + other.keys).uniq
       keys.each do |k|
         vectors[k] = []
+        types[k] = join_type(self.types[k], other.types[k])
       end
 
       each_row do |r|
@@ -458,7 +500,7 @@ module Rover
         end
       end
 
-      DataFrame.new(vectors)
+      DataFrame.new(vectors, types: types)
     end
 
     def check_join_keys(df, keys)
@@ -467,8 +509,33 @@ module Rover
       raise ArgumentError, "Missing keys: #{missing_keys.join(", ")}" if missing_keys.any?
     end
 
-    def check_column(key)
-      raise ArgumentError, "Missing column: #{key}" unless include?(key)
+    # TODO in 0.3.0
+    # always use did_you_mean
+    def check_column(key, did_you_mean = false)
+      unless include?(key)
+        if did_you_mean
+          if RUBY_VERSION.to_f >= 2.6
+            raise KeyError.new("Missing column: #{key}", receiver: self, key: key)
+          else
+            raise KeyError.new("Missing column: #{key}")
+          end
+        else
+          raise ArgumentError, "Missing column: #{key}"
+        end
+      end
+    end
+
+    def join_type(a, b)
+      if a.nil?
+        b
+      elsif b.nil?
+        a
+      elsif a == b
+        a
+      else
+        # TODO specify
+        nil
+      end
     end
 
     def to_vector(v, size: nil, type: nil)

data/lib/rover/group.rb

@@ -9,7 +9,7 @@ module Rover
       Group.new(@df, @columns + columns.flatten)
     end
 
-    [:count, :max, :min, :mean, :median, :percentile, :sum].each do |name|
+    [:count, :max, :min, :mean, :median, :percentile, :sum, :std, :var].each do |name|
       define_method(name) do |*args|
         n = [name, args.first].compact.join("_")
 

data/lib/rover/vector.rb

@@ -91,7 +91,7 @@ module Rover
       @data[k] = v
     end
 
-    %w(+ - * / % ** &).each do |op|
+    %w(+ - * / % ** & | ^).each do |op|
       define_method(op) do |other|
         other = other.to_numo if other.is_a?(Vector)
         # TODO better logic
@@ -161,9 +161,22 @@ module Rover
     end
 
     def map(&block)
-      mapped = @data.map(&block)
-      mapped = mapped.to_a if mapped.is_a?(Numo::RObject) # re-evaluate cast
-      Vector.new(mapped)
+      # convert to Ruby first to cast properly
+      # https://github.com/ruby-numo/numo-narray/issues/181
+      Vector.new(@data.to_a.map(&block))
+    end
+
+    def map!(&block)
+      @data = cast_data(@data.to_a.map(&block))
+      self
+    end
+
+    def select(&block)
+      Vector.new(@data.to_a.select(&block))
+    end
+
+    def reject(&block)
+      Vector.new(@data.to_a.reject(&block))
     end
 
     def tally
@@ -250,7 +263,11 @@ module Rover
     end
 
     def last(n = 1)
-      Vector.new(@data[-n..-1])
+      if n >= size
+        Vector.new(@data)
+      else
+        Vector.new(@data[-n..-1])
+      end
     end
 
     def take(n)
@@ -306,7 +323,12 @@ module Rover
     # for IRuby
     def to_html
       require "iruby"
-      IRuby::HTML.table(to_a)
+      if size > 7
+        # pass 8 rows so maxrows is applied
+        IRuby::HTML.table(first(4).to_a + last(4).to_a, maxrows: 7)
+      else
+        IRuby::HTML.table(to_a)
+      end
     end
 
     private

data/lib/rover/version.rb

@@ -1,3 +1,3 @@
 module Rover
-  VERSION = "0.2.1"
+  VERSION = "0.2.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rover-df
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.5
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-11-24 00:00:00.000000000 Z
+date: 2021-09-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -16,100 +16,16 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.9.1.7
+        version: 0.9.1.9
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.9.1.7
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: minitest
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '5'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '5'
-- !ruby/object:Gem::Dependency
-  name: activerecord
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '5'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '5'
-- !ruby/object:Gem::Dependency
-  name: sqlite3
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: iruby
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.9.1.9
 description:
-email: andrew@chartkick.com
+email: andrew@ankane.org
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -142,7 +58,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
+rubygems_version: 3.2.22
 signing_key:
 specification_version: 4
 summary: Simple, powerful data frames for Ruby