pandas 0.1.0 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 056b93d472f805d8d482c29957bd5d69f7dea651
-  data.tar.gz: c8bca642cea838cae4ec9629ef999ed69cb9d0dd
+SHA256:
+  metadata.gz: 952bd0798aaf70a04aad070946185ba24462c5ba88d68650d65c096bcb3a8e81
+  data.tar.gz: fb70cd2d1f07485ea94fbab52ed054be9d14cbe35948a297d5f011b60f9353cb
 SHA512:
-  metadata.gz: a0da4e097cb7c4621094ac780068c6834d893b1a31b5897269cf9832c5f1aa6b824fb7c85fcda14b0d7baf5e3c6b4ece0036a111ca1eed62a8a7e4fc8f0df5e5
-  data.tar.gz: c6df181b48f80c7618201549c1858ae531d840a01713d9b1adb47f1ddbae842a3c03e9996175af365ac00c2890ba88dd2d45fd394fdcd4c70f8e33073f1bf352
+  metadata.gz: d21e7f9c032f5efae82689ac111167bdc3f9db844748aa2b148261750d39f54a17f3ce5c1578121238ef0dc5af7d04564672a18525f3394157dea4ba0f60b73a
+  data.tar.gz: 15bfd63048f2cbbc2f602ad08626a2d2fe838cf026eeaaa583a27223e9255291bea113ae97d23286fbcd89c249b1effb65235b3b18b5620f99446f9eb723e97c

data/.github/workflows/ci.yml

@@ -0,0 +1,69 @@
+name: CI
+
+on:
+  push:
+    branches:
+    - master
+  pull_request:
+    types:
+    - opened
+    - synchronize
+    - reopened
+
+jobs:
+  test:
+    name: ${{ matrix.os}} ${{ matrix.ruby }} ${{ matrix.python }}-${{ matrix.python_arch }}
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      fail-fast: false
+      matrix:
+        os:
+        - ubuntu-latest
+        - macos-latest
+        ruby:
+        - 3.0
+        - 2.7
+        - 2.6
+        - 2.5
+        - 2.4
+        - debug
+        python:
+        - 3.8.x
+        - 3.7.x
+        - 3.6.x
+        - 2.7.x
+        python_arch:
+        - x64
+
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        fetch-depth: 1
+
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+
+    - uses: actions/setup-python@v1
+      with:
+        python-version: ${{ matrix.python }}
+        architecture: ${{ matrix.python_arch }}
+
+    - run: sudo apt-get install libsqlite3-dev
+      if: matrix.os == 'ubuntu-latest'
+
+    - run: brew install sqlite3
+      if: matrix.os == 'macos-latest'
+
+    - run: pip install -r requirements.txt
+
+    - run: gem install bundler
+    - run: bundle install
+
+    - run: bundle exec rake
+      env:
+        PYTHON: python
+
+    - run: rake build
+    - run: gem install pkg/*.gem

data/CHANGES.md

@@ -0,0 +1,45 @@
+# The chenge history of Pandas wrapper for Ruby
+
+## 0.3.3
+
+* Support array index in `Pandas::Series#[]`
+
+* Add predicate methods for `Pandas::Index` and `Pandas::Series`
+
+* Support closed-end string ranges in `Pandas::Series#[]`
+
+* Support string array index in `Pandas::DataFrame#loc[]`
+
+* Support array index in `Pandas::DataFrame#iloc[]`
+
+## 0.3.2
+
+* Fix for pandas 1.0
+
+## 0.3.1
+
+* Fix `Pandas.read_sql_table` for passing optional parameters such as `index_col`
+
+## 0.3.0
+
+* Fix the module path of `DatetimeIndex` to support pandas < 0.20
+
+  Fixes #5
+
+  *Daniel Baark*
+
+* Support to pass an AR model class to `read_sql_table` instead of both `table_name` and `conn`
+
+## 0.2.0
+
+* Support a connection of ActiveRecord in `read_sql_table` and `read_sql_query`
+
+* Call `register_python_type_mapping` for all wrapper classes
+
+* Support an array index in `DataFrame#[]`
+
+* Fix `Pandas.options.display`
+
+## 0.1.0
+
+* Define some wrapper classes

data/README.md

@@ -1,5 +1,7 @@
 # Pandas wrapper for Ruby
 
+[![Build Status](https://travis-ci.org/mrkn/pandas.rb.svg)](https://travis-ci.org/mrkn/pandas.rb)
+
 This library enables to directry call [pandas](http://pandas.pydata.org/) from Ruby language.
 This uses [pycall](https://github.com/mrkn/pycall).
 

data/lib/pandas.rb

@@ -1,19 +1,88 @@
 require "pandas/version"
-require "pycall"
+require "numpy"
 
-Pandas = PyCall.import_module('pandas')
+Pandas = PyCall.import_module("pandas")
 module Pandas
   VERSION = PANDAS_VERSION
   Object.send :remove_const, :PANDAS_VERSION
 
   DataFrame = self.core.frame.DataFrame
+  DataFrame.__send__ :register_python_type_mapping
+
   Series = self.core.series.Series
+  Series.__send__ :register_python_type_mapping
+
   IlocIndexer = self.core.indexing._iLocIndexer
+  IlocIndexer.__send__ :register_python_type_mapping
+
   LocIndexer = self.core.indexing._LocIndexer
-  IXIndexer = self.core.indexing._IXIndexer
-  MultiIndex = self.core.indexing.MultiIndex
-  DatetimeIndex = self.core.indexes.datetimes.DatetimeIndex
-  Index = self.core.index.Index
+  LocIndexer.__send__ :register_python_type_mapping
+
+  if self.__version__ < "1.0"
+    IXIndexer = self.core.indexing._IXIndexer
+    IXIndexer.__send__ :register_python_type_mapping
+  end
+
+  if self.__version__ >= "1.0"
+    MultiIndex = self.core.indexes.multi.MultiIndex
+  else
+    MultiIndex = self.core.indexing.MultiIndex
+  end
+  MultiIndex.__send__ :register_python_type_mapping
+
+  DatetimeIndex = if self.__version__ >= "0.20"
+                    self.core.indexes.datetimes.DatetimeIndex
+                  else
+                    self.tseries.index.DatetimeIndex
+                  end
+  DatetimeIndex.__send__ :register_python_type_mapping
+
+  if self.__version__ >= "1.0"
+    Index = self.core.indexes.base.Index
+  else
+    Index = self.core.index.Index
+  end
+  Index.__send__ :register_python_type_mapping
+
   DataFrameGroupBy = self.core.groupby.DataFrameGroupBy
+  DataFrameGroupBy.__send__ :register_python_type_mapping
+
   SeriesGroupBy = self.core.groupby.SeriesGroupBy
+  SeriesGroupBy.__send__ :register_python_type_mapping
+
+  IO = self.io
+
+  def self.read_sql_table(table_name, conn=nil, *args, **kwargs)
+    if conn.nil? && IO.is_activerecord_model?(table_name)
+      unless table_name.table_name
+        raise ArgumentError, "The given model does not have its table_name"
+      end
+      table_name, conn = table_name.table_name, table_name.connection
+    end
+
+    unless conn
+      raise ArgumentError, "wrong number of arguments (given 1, expected 2+)"
+    end
+
+    if IO.is_activerecord_datasource?(conn)
+      require 'pandas/io/active_record'
+      return IO::Helpers.read_sql_table_from_active_record(table_name, conn, *args, **kwargs)
+    end
+    super
+  end
+
+  def self.read_sql_query(query, conn, *args, **kwargs)
+    if IO.is_activerecord_datasource?(conn)
+      require 'pandas/io/active_record'
+      return IO::Helpers.read_sql_query_from_active_record(query, conn, *args, **kwargs)
+    end
+    super
+  end
+
+  require 'pandas/data_frame'
+  require 'pandas/index'
+  require 'pandas/io'
+  require 'pandas/loc_indexer'
+  require 'pandas/options'
+  require 'pandas/series'
 end

data/lib/pandas/data_frame.rb

@@ -0,0 +1,10 @@
+require 'pandas'
+
+module Pandas
+  class DataFrame
+    def [](key)
+      key = PyCall::List.new(key) if key.is_a?(Array)
+      super
+    end
+  end
+end

data/lib/pandas/index.rb

@@ -0,0 +1,21 @@
+require 'pandas'
+
+module Pandas
+  class Index
+    def monotonic?
+      is_monotonic
+    end
+
+    def monotonic_decreasing?
+      is_monotonic_decreasing
+    end
+
+    def monotonic_increasing?
+      is_monotonic_increasing
+    end
+
+    def unique?
+      is_unique
+    end
+  end
+end

data/lib/pandas/io.rb

@@ -0,0 +1,17 @@
+require 'pandas'
+
+module Pandas
+  module IO
+    def self.is_activerecord_model?(obj)
+      return false unless defined?(::ActiveRecord)
+      return true if obj.is_a?(Class) && obj < ActiveRecord::Base
+      false
+    end
+
+    def self.is_activerecord_datasource?(obj)
+      return false unless defined?(::ActiveRecord)
+      return true if obj.is_a?(::ActiveRecord::ConnectionAdapters::AbstractAdapter)
+      false
+    end
+  end
+end

data/lib/pandas/io/active_record.rb

@@ -0,0 +1,101 @@
+require 'pandas'
+require 'active_record'
+
+module Pandas
+  module IO
+    module Helpers
+      module_function
+
+      def read_sql_table_from_active_record(table_name, conn, *args)
+        case conn
+        when ActiveRecord::ConnectionAdapters::AbstractAdapter
+          read_sql_table_from_active_record_connection(table_name, conn, *args)
+        else
+          raise TypeError, "unexpected type of argument #{conn.class}"
+        end
+      end
+
+      def read_sql_query_from_active_record(query, conn, *args)
+        case conn
+        when ActiveRecord::ConnectionAdapters::AbstractAdapter
+          read_sql_query_from_active_record_connection(query, conn, *args)
+        else
+          raise TypeError, "unexpected type of argument #{conn.class}"
+        end
+      end
+
+      def read_sql_table_from_active_record_connection(table_name, conn, *args)
+        args = parse_read_sql_table_args(*args)
+        index_col, coerce_float, parse_dates, columns, schema, chunksize = *args
+        if columns
+          table_columns = conn.columns(table_name)
+          column_names = columns.select {|c| table_columns.include?(c) }.map do |c|
+            conn.quote_column_name(c.to_s)
+          end
+        else
+          column_names = '*'
+        end
+        query = <<-SQL
+  select #{column_names} from #{conn.quote_table_name(table_name)};
+        SQL
+        # TODO: chunksize
+        result = conn.exec_query(query, 'pandas_sql')
+        data_frame_from_query_result(result, index_col, coerce_float, parse_dates)
+      end
+
+      def read_sql_query_from_active_record_connection(query, conn, *args)
+        args = parse_read_sql_query_args(*args)
+        index_col, coerce_float, parse_dates, chunksize = *args
+        # TODO: chunksize
+        result = conn.exec_query(query, 'pandas_sql')
+        data_frame_from_query_result(result, index_col, coerce_float, parse_dates)
+      end
+
+      def data_frame_from_query_result(result, index_col, coerce_float, parse_dates)
+        records = result.map {|row| row.values }
+        df = Pandas::DataFrame.from_records(
+          records,
+          columns: result.columns,
+          coerce_float: coerce_float
+        )
+        # TODO: self.sql._harmonize_columns(parse_dates: parse_dates)
+        df.set_index(index_col, inplace: true) if index_col
+        df
+      end
+
+      def parse_read_sql_table_args(*args)
+        kwargs = args.pop if args.last.is_a? Hash
+        if kwargs
+          names = [:index_col, :coerce_float, :parse_dates, :columns, :schema, :chunksize]
+          names.each_with_index do |name, index|
+            if kwargs.has_key? name
+              if args[index]
+                warn "#{name} is given as both positional and keyword arguments"
+              else
+                args[index] = kwargs[name]
+              end
+            end
+          end
+        end
+        args
+      end
+
+      def parse_read_sql_query_args(*args)
+        kwargs = args.pop if args.last.is_a? Hash
+        if kwargs
+          names = [:index_col, :coerce_float, :parse_dates, :chunksize]
+          names.each_with_index do |name, index|
+            if kwargs.has_key? name
+              if args[index]
+                warn "#{name} is given as both positional and keyword arguments"
+              else
+                args[index] = kwargs[name]
+              end
+            end
+          end
+        end
+        args
+      end
+    end
+  end
+end

data/lib/pandas/loc_indexer.rb

@@ -0,0 +1,25 @@
+require 'pandas'
+
+module Pandas
+  class LocIndexer
+    def [](*keys)
+      for i in 0...keys.length
+        if keys[i].is_a? Array
+          keys[i] = PyCall::List.new(keys[i])
+        end
+      end
+      super
+    end
+  end
+
+  class IlocIndexer
+    def [](*keys)
+      for i in 0...keys.length
+        if keys[i].is_a? Array
+          keys[i] = PyCall::List.new(keys[i])
+        end
+      end
+      super
+    end
+  end
+end

data/lib/pandas/options.rb

@@ -0,0 +1,17 @@
+module Pandas
+  module OptionsHelper
+    module_function
+
+    def setup_options(options)
+      PyCall::LibPython::Helpers.define_wrapper_method(options, :display)
+      options
+    end
+  end
+
+  def self.options
+    @options ||= begin
+                   o = PyCall::LibPython::Helpers.getattr(__pyptr__, :options)
+                   OptionsHelper.setup_options(o)
+                 end
+  end
+end

data/lib/pandas/series.rb

@@ -0,0 +1,36 @@
+require 'pandas'
+
+module Pandas
+  class Series
+    def [](*key)
+      if key.length == 1
+        case key[0]
+        when Array
+          key[0] = PyCall::List.new(key[0])
+        when Range
+          case key[0].begin
+          when String
+            key[0] = key[0].begin ... key[0].end # force exclude-end
+          end
+        end
+      end
+      super
+    end
+
+    def monotonic?
+      is_monotonic
+    end
+
+    def monotonic_decreasing?
+      is_monotonic_decreasing
+    end
+
+    def monotonic_increasing?
+      is_monotonic_increasing
+    end
+
+    def unique?
+      is_unique
+    end
+  end
+end

data/lib/pandas/version.rb

@@ -1 +1 @@
-PANDAS_VERSION = "0.1.0"
+PANDAS_VERSION = "0.3.3"

data/pandas.gemspec

@@ -22,8 +22,11 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_dependency "pycall", ">= 1.0.0"
+  spec.add_dependency "numpy"
 
-  spec.add_development_dependency "bundler", "~> 1.15"
-  spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "bundler", ">= 1.17.2"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "activerecord", ">= 4.2"
+  spec.add_development_dependency "sqlite3"
 end

data/requirements.txt

@@ -0,0 +1,2 @@
+pandas
+sqlalchemy

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pandas
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.3.3
 platform: ruby
 authors:
 - Kenta Murata
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2017-09-07 00:00:00.000000000 Z
+date: 2021-01-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pycall
@@ -24,48 +24,90 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.0
+- !ruby/object:Gem::Dependency
+  name: numpy
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.15'
+        version: 1.17.2
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.15'
+        version: 1.17.2
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: activerecord
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.2'
+- !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: '3.0'
+        version: '0'
 description: Pandas wrapper for Ruby
 email:
 - mrkn@mrkn.jp
@@ -73,9 +115,10 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/ci.yml"
 - ".gitignore"
 - ".rspec"
-- ".travis.yml"
+- CHANGES.md
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -84,13 +127,21 @@ files:
 - bin/setup
 - data/titanic.csv
 - lib/pandas.rb
+- lib/pandas/data_frame.rb
+- lib/pandas/index.rb
+- lib/pandas/io.rb
+- lib/pandas/io/active_record.rb
+- lib/pandas/loc_indexer.rb
+- lib/pandas/options.rb
+- lib/pandas/series.rb
 - lib/pandas/version.rb
 - pandas.gemspec
+- requirements.txt
 homepage: https://github.com/mrkn/pandas.rb
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -105,9 +156,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.12
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: Pandas wrapper for Ruby
 test_files: []

data/.travis.yml

@@ -1,5 +0,0 @@
-sudo: false
-language: ruby
-rvm:
-  - 2.4.1
-before_install: gem install bundler -v 1.15.4