red_amber 0.1.3 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '0308ff686bf7b49b767b7cd28ddc068e02170c00c093dcd42c7187e438e0adf3'
-  data.tar.gz: 98397e31bce1a440e951357d5d3b475814a6ecc08f21a0908c0fdf58c6189be4
+  metadata.gz: ae6a6696e0f01ae7d621d11542e203803ba117fc1ee3d286a1444b3c4ac746fc
+  data.tar.gz: 722d4ad538fe4f0c85db4911e773e1f87eb03f47fa63c954529bf04babc55d8c
 SHA512:
-  metadata.gz: 7ad71d8259d04535d08567bde6ca0fc419e0d9de15d1e812dbc642fb3901f1c744c69766dbf409e876212e426e309ac0032968b767df3a960a8e6eb40d4f3c19
-  data.tar.gz: eee78ae4316b007d95714d6e2920ad32518497942d9cd5adb373476321e6f9e6e8099f9c721ee8bac05df2617fb3f3c747ce92ec74b1cb84da0b0bd4664051cf
+  metadata.gz: 96887abfbdd44330e80a6a97f91597c00706fc99492d086683702f1d3e757331e90fb275e5796a2b7b3228b476f8c7799ab22727411baedb79ae39acafd2d3f0
+  data.tar.gz: c020bba60734fccdeb4a18efecb98260f70fa76c5b8ba2c7f2830d2dac6de66e9776a1fa2ffc5d396e7270b29c5e4dd9737dee70b5dcc47dd3113aaafe4f4d22

data/.rubocop.yml

@@ -53,9 +53,12 @@ Layout/LineLength:
 # 18..30 unsatisfactory
 # > 30 dangerous
 Metrics/AbcSize:
-  Max: 23
+  Max: 30
   Exclude:
-    - 'lib/red_amber/data_frame_output.rb' # Max: 51
+    - 'lib/red_amber/data_frame_displayable.rb' # Max: 55
+    - 'lib/red_amber/data_frame_selectable.rb' # Max: 51
+    - 'lib/red_amber/vector_updatable.rb' # Max: 36
+    - 'lib/red_amber/vector_selectable.rb' # Max: 33
 
 # Max: 25
 Metrics/BlockLength:
@@ -68,33 +71,54 @@ Metrics/ClassLength:
   Max: 100
   Exclude:
     - 'test/**/*'
+    - 'lib/red_amber/data_frame.rb' #Max: 131
+    - 'lib/red_amber/vector.rb' #Max: 102
 
 # Max: 7
 Metrics/CyclomaticComplexity:
-  Max: 10
+  Max: 12
+  Exclude:
+    - 'lib/red_amber/data_frame_selectable.rb' # Max: 14
+    - 'lib/red_amber/vector_updatable.rb' # Max: 14
 
 # Max: 10
 Metrics/MethodLength:
-  Max: 18
+  Max: 30
   Exclude:
-    - 'lib/red_amber/data_frame_output.rb' # Max: 31
+    - 'lib/red_amber/data_frame_displayable.rb' # Max: 33
 
 # Max: 100
 Metrics/ModuleLength:
   Max: 100
   Exclude:
+    - 'lib/red_amber/data_frame_selectable.rb' # Max: 141
     - 'lib/red_amber/vector_functions.rb' # Max: 114
 
 # Max: 8
 Metrics/PerceivedComplexity:
-  Max: 11
+  Max: 13
+  Exclude:
+    - 'lib/red_amber/data_frame_selectable.rb' # Max: 14
+    - 'lib/red_amber/vector_updatable.rb' # Max: 15
+
+Naming/FileName:
+  Exclude:
+    - 'lib/red-amber.rb'
 
-# Necessary to define is_na
+# Necessary to define is_na, is_in, etc.
 Naming/PredicateName:
   Exclude:
     - 'lib/red_amber/vector_functions.rb'
+    - 'lib/red_amber/vector.rb'
+    - 'lib/red_amber/vector_selectable.rb'
 
 # Necessary to test when range.end == -1
 Style/SlicingWithRange:
   Exclude:
     - 'test/test_data_frame_selectable.rb'
+
+# Necessary to Vector < 0 element-wise comparison
+Style/NumericPredicate:
+  Exclude:
+    - 'lib/red_amber/data_frame_selectable.rb'
+    - 'lib/red_amber/vector_selectable.rb'

data/CHANGELOG.md

@@ -1,17 +1,221 @@
-## [0.1.4] - Unreleased
+## - unreleased
 
-- Prepare documents for the 'Transposed DataFrame Representation'
-- Feedback to Red Arrow
-- Separate documents
+- Document
+  - YARD support
+
+- `datasets-red-amber` gem
+- `red-amber` gem
+
+- `Vector#divmod`
+  - Introduce if Arrow's function is ready
+
+## - Unreleased, will be after Arrow 9.0.0 released
 
 - `DataFrame`
-  - Introduce updating capabilities
-  - Introduce NA support
-  - Add slice method
+  - Introduce `summary` or ``describe`
+    - `Quantile` will be available
+
+## [0.1.7] - Unreleased, may be 2022-07-10
+
+- Feedback something to Red Data Tools
+- Support more functions
+- Improve as more performant
+- More examples of frequently needed tasks
+
+- New `Group` API
+- `DataFrame#join features
+
+## [0.1.6] - 2022-06-26 (experimental)
+
+- Bug fixes
+  - Fix mime-type of empty DataFrame in `#to_iruby` (#31)
+  - Fix mime setting in `DataFrame#to_iruby` (#36)
+  - Fix unmatched return val in Selectable (#34)
+  - Fix to return same error as `#[]` in `DataFrame#slice` (#34)
+
+- New features and improvements
+  - Introduce Jupyter support (#29, #30, #31, #32)
+    - Add `DataFrame#to_html (changed to use #to_iruby)
+    - Add feature to show nil in to_iruby
+      - nil is expressed as (nil)
+      - empty string('') is ""
+      - blank spaces are " "
+
+  - Enable to change DataFrame display mode by ENV (#36)
+    - Support ENV['RED_AMBER_OUTPUT_STYLE'] to change display mode in `#inspect` and `#to_iruby`
+      - ENV['RED_AMBER_OUTPUT_STYLE'] = 'table' # => Table mode
+      - ENV['RED_AMBER_OUTPUT_STYLE'] = nil or other than 'table' # => TDR mode
+
+  - Support `require 'red-amber'`, as well (#34)
+
+  - Refine Vector slicing methods (#31)
+    - Introduce `Vector#take` method
+    - Introduce `Vector#filter` method
+    - Improve `Vector#[]` to overload take and filter
+    - Introduce `Vector#drop_nil` method
+    - Introduce `Vector#if_else` method
+    - Intorduce `Vector#is_in` method
+    - Add alias `Vector#all?`, `#any?` methods (#32)
+    - Add `Vector#has_nil?` method(#32)
+    - Add `Vector#empty?` method
+    - Add `Vector#primitive_invert` method
+    - Refactor `Vector#take`, `#filter`
+    - Move `Vector#if_else` from function to Updatable
+    - Move if_else test to updatable
+    - Rename updatable in test
+    - Remove method `Vector#take_out_element_wise`
+    - Rename inner metthod name
+
+  - Refine DataFrame slicing methods (#31)
+    - Introduce `DataFrame#take method
+      - #take is implemented as vector calculation by #if_else
+    - Introduce `DataFrame#fliter method
+    - Change `DataFrame#[] to use take and filter
+      - Float indices is acceptable (#10)
+      - Negative index (like Array) is also acceptable
+
+  - Further refinement in DataFrame slicing methods (#34)
+   -  Improve `DataFrame#[]`, `#slice`, `#remove` by a new engine
+      -  It parses arguments to Vector internally.
+      -  Used Kernel#Array to simplify code (#16) .
+    - recycle: Move `DataFrame#slice`, `#remove` to Selectable
+    - Refine `DataFrame#take`, `#filter` (undocumented)
+
+  - Introduce coerce in Vector (#35)
+    - Introduce `Vector#coerce`
+      - Now we can `-1 * Vector.new([1, 2, 3])`
+    - Add `Vector#to_ary` method
+      - Now we can `[1, 2] + Vector.new([3, 4, 5])`
+
+  - Other new feature or refinements
+    - Common
+      - Refactor helper as common for DataFrame and Vector (#35)
+      - Change name row/col to obs/var (#34)
+      - Rename internal function name (#34)
+      - Delete unused methods (#34)
+    - DataFrame
+      - Change to return instance variable in `#to_arrow`, `#keys` and `#key_index` (#34)
+      - Change to return an Array in `DataFrame#indices` (#35)
+    - Vector
+      - Introduce `Vector#replace` method
+      - Accept Range and expanded Array in `Vector#new`
+      - Add `Vector#indices` method (#35)
+      - Add `Vector#index` method (#35)
+      - Rename VectorCompensable to *Updatable (#33)
+
+  - Documentation
+    - Fix typo in DataFrame.md
+
+## [0.1.5] - 2022-06-12 (experimental)
+
+- Bug fixes
+  - Fix DataFrame#tdr to display timestamp type (#19)
+  - Add TZ setting in CI test to pass temporal tests (#19)
+  - Fix example in document of #load(csv_from_URI) (#23)
+
+- New features and improvements
+  - Improve usability of DataFrame manipulating block (#19)
+    - Add `DataFrame#v` to select a Vector
+    - Add `DataFrame#variables` method
+    - Add `DataFrame#to_arrow`
+    - Add instance variables in DataFrame with lazy initialization
+    - Add `Vector#key` to get key name
+    - Add `Vector#temporal?` to check if temporal type
+    - Refine around DataFrame#variables
+    - Refine init of instance variables
+    - Refine DataFrame#type_classes, Vector#ectortype_class
+    - Refine DataFrame#tdr to shorten temporal data
+
+  - Add supports to make up for missing values (#20)
+    - Add VectorArgumentError
+    - Add `Vector#replace_with`
+    - Add helper function to assert with NaN
+      - To assert NaN == NaN
+    - Add `Vector#fill_nil_backward`, `Vector#forward`
+    - Add `DataFrame#remove_nil` method
+    - Change to accept nil as replacement in Vector#replace_with
+
+  - Introduce index related methods (#22)
+    - Add `Vector#sort_indexes` method
+    - Add `Vector#uniq` method
+    - Add `Vector#tally` and `Vectorvalue_counts` methods
+    - Add `DataFrame#sort` method
+    - Add `DataFrame#group` method
+    - Change to use DataFrame#map_indices in #[]
+
+  - Add rounding functions with opts (#21)
+    -  With options :mode and :n_digits 
+    -  :n_digits also can be specified with :multiple option in `Vector#round_to_multiple`
+    - `Vector#round`
+    - `Vector#ceil`
+    - `Vector#floor`
+    - `Vector#trunc`
+
+  - Documentation
+    - Update TDR, TDR_ja documents to latest (#18)
+    - Refinement and small fix in DataFrame.md (#18)
+    - Update README to use more effective example (#18)
+    - Delete expired TDR_operations.pdf (#23)
+    - Update README and dataframe_model image (#23)
+    - Update description about rover-df in README (#23)
+    - Add installation of Arrow in README (#23)
+
+  - Others
+    - Tried but cannot use bundler cache in ci test (#17)
+    - Bump up requirements to Arrow 8.0.0 (#25)
+      - Arrow 7.0.0 with Ubuntu 21.04 causes an fatal error in replace_with_mask function.
+    - Update the description of gem (#23)
+    - Add benchmark tests (#26)
+
+## [0.1.4] - 2022-05-29 (experimental)
+
+- Bug fixes
+  - Fix missing support for scalar argument (#1)
+  - Fix type name of boolean in DataFrame#types to be same as Vector#type (#6, #7)
+  - Fix zero picking to return empty DataFrame (#8)
+  - Fix code at both args and a block given (#8)
+
+- New features and improvements
+  - `DataFrame`
+    - Refine module name `Displayable`
+    - Rename nrow/ncol methods to `size`/`n_keys` to align with TDR concept (#4)
+      - Remain `n_row`/`n_col` for compatibility
+    - Rename `ls` method to `tdr` (#4)
+      - Add limit option to `tdr`
+      - Shorten option name (#11)
+    - Introduce `pick` method to create sub DataFrame (#8)
+      - Add boolean support (#8)
+      - Refactor `pick` (#9)
+    - Introduce `drop` method to create sub DataFrame (#8)
+      - Add boolean support (#8)
+      - Refactor `drop` (#9)
+    - Add boolean array support for `[]` (#9)
+    - Add `indexes`/`indices` to use with selecting observations (#9)
+    - Introduce `slice` method to create sub DataFrame (#8)
+      - Refactor `slice` (#9)
+    - Introduce `remove` method to create sub DataFrame (#9)
+    - Introduce `rename` method to create sub DataFrame (#14)
+    - Introduce `assign` method to create sub DataFrame (#14)
+    - Improve to call block by instance_eval (#13)
+
+  - `Vector`
+    - Refine `find(function)`
+    - Add `min_max` method (#2)
+    - Add `std`/`sd` method (ddof=0 version: `stddev`) (#2)
+    - Add `var` method (ddof=0 version: `variance`) (#2)
+    - Add `VectorFunctions.arrow_doc(func_name)` (temporally)
 
-- `Vector`
-  - Add NaN support for functions
-  - Support more functions
+  - Documentation
+    - Show code in README
+    - Change row/column names for **TDR** concept (#4)
+    - Add documents about **TDR** concept (#4)
+    - Add example about TDR (#4)
+    - Separate README to create DataFrame and Vector documents (#12)
+    - Add DataFrame model concept image to README (#12)
+  
+  - GitHub site
+    - Switched to use merge on GitHub (not to push merged master) (#1)
+    - Create lifetime issue #3 to show the goal of this project (#3)
 
 ## [0.1.3] - 2022-05-15 (experimental)
 

data/Gemfile

@@ -12,6 +12,10 @@ group :test do
   gem 'rubocop-rake'
   gem 'rubocop-rubycw', require: false
 
+  gem 'iruby'
   gem 'test-unit'
   gem 'webrick'
+
+  gem 'benchmark_driver'
+  gem 'red-datasets-arrow'
 end