pandas 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 056b93d472f805d8d482c29957bd5d69f7dea651
-  data.tar.gz: c8bca642cea838cae4ec9629ef999ed69cb9d0dd
+  metadata.gz: 01ae8d45320fa67aa7d7ae6b131c777ec2cd88fb
+  data.tar.gz: 1cc5bffdfe6f376cc2bbd19c67354c70bec0dd8d
 SHA512:
-  metadata.gz: a0da4e097cb7c4621094ac780068c6834d893b1a31b5897269cf9832c5f1aa6b824fb7c85fcda14b0d7baf5e3c6b4ece0036a111ca1eed62a8a7e4fc8f0df5e5
-  data.tar.gz: c6df181b48f80c7618201549c1858ae531d840a01713d9b1adb47f1ddbae842a3c03e9996175af365ac00c2890ba88dd2d45fd394fdcd4c70f8e33073f1bf352
+  metadata.gz: 9b2457bd1efb1b291ff11570dd69f3ee9b95b52e4a631993833c962fd83a216e9b08afd52a2a1a41028c541a895ae3678296cd60244d263d91d601a0a8b0966a
+  data.tar.gz: 403ec721bc39c1245b1c82f1255dad2ad8462218b4d48fe30a94fbdba838bff17b124b5e731037c438fdcbdd5806878a166a9cc3dc94c28e4fe4351c5f80ae22

data/.travis.yml

@@ -1,5 +1,34 @@
 sudo: false
 language: ruby
+
 rvm:
-  - 2.4.1
-before_install: gem install bundler -v 1.15.4
+  - ruby-head
+  - 2.4.0
+  - 2.3.1
+  - 2.2.5
+  - 2.1.10
+
+addons:
+  apt:
+    packages:
+      - python3
+      - python3-dev
+      - python3-all
+      - python3-all-dev
+
+env:
+  matrix:
+  - PYTHON=python
+  - LIBPYTHON=/opt/python/3.5.3/lib/libpython3.5m.so
+
+before_install:
+  - gem update --system
+  - gem update bundler
+
+before_script:
+  - pip install pandas
+  - pip3 install numpy
+
+matrix:
+  allow_failures:
+  - env: PYTHON=python  # Ignore failed on python 2.7

data/CHANGES.md

@@ -0,0 +1,15 @@
+# The chenge history of Pandas wrapper for Ruby
+
+## 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

@@ -7,13 +7,54 @@ module Pandas
   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
+  LocIndexer.__send__ :register_python_type_mapping
+
   IXIndexer = self.core.indexing._IXIndexer
+  IXIndexer.__send__ :register_python_type_mapping
+
   MultiIndex = self.core.indexing.MultiIndex
+  MultiIndex.__send__ :register_python_type_mapping
+
   DatetimeIndex = self.core.indexes.datetimes.DatetimeIndex
+  DatetimeIndex.__send__ :register_python_type_mapping
+
   Index = self.core.index.Index
+  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, *args)
+    if IO.is_activerecord_datasource?(conn)
+      require 'pandas/io/active_record'
+      return IO::Helpers.read_sql_table_from_active_record(table_name, conn, *args)
+    end
+    super
+  end
+
+  def self.read_sql_query(query, conn, *args)
+    if IO.is_activerecord_datasource?(conn)
+      require 'pandas/io/active_record'
+      return IO::Helpers.read_sql_query_from_active_record(query, conn, *args)
+    end
+    super
+  end
+
+  require 'pandas/data_frame'
+  require 'pandas/io'
+  require 'pandas/options'
 end

data/lib/pandas/data_frame.rb

@@ -0,0 +1,12 @@
+require 'pandas'
+
+module Pandas
+  class DataFrame
+    def [](*key)
+      if key.length == 1 && key[0].is_a?(Array)
+        key[0] = PyCall::List.new(key[0])
+      end
+      super
+    end
+  end
+end

data/lib/pandas/io.rb

@@ -0,0 +1,11 @@
+require 'pandas'
+
+module Pandas
+  module IO
+    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/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/version.rb

@@ -1 +1 @@
-PANDAS_VERSION = "0.1.0"
+PANDAS_VERSION = "0.2.0"

data/pandas.gemspec

@@ -26,4 +26,6 @@ Gem::Specification.new do |spec|
   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 "activerecord", ">= 4.2"
+  spec.add_development_dependency "sqlite3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pandas
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Kenta Murata
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-09-07 00:00:00.000000000 Z
+date: 2017-09-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pycall
@@ -66,6 +66,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
+- !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: '0'
 description: Pandas wrapper for Ruby
 email:
 - mrkn@mrkn.jp
@@ -76,6 +104,7 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
+- CHANGES.md
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -84,6 +113,10 @@ files:
 - bin/setup
 - data/titanic.csv
 - lib/pandas.rb
+- lib/pandas/data_frame.rb
+- lib/pandas/io.rb
+- lib/pandas/io/active_record.rb
+- lib/pandas/options.rb
 - lib/pandas/version.rb
 - pandas.gemspec
 homepage: https://github.com/mrkn/pandas.rb