polars-df 0.15.0-arm64-darwin → 0.17.0-arm64-darwin

data/lib/polars/lazy_frame.rb

@@ -431,7 +431,9 @@ module Polars
       projection_pushdown: true,
       simplify_expression: true,
       no_optimization: false,
-      slice_pushdown: true
+      slice_pushdown: true,
+      storage_options: nil,
+      retries: 2
     )
       lf = _set_sink_optimizations(
         type_coercion: type_coercion,
@@ -460,6 +462,12 @@ module Polars
         }
       end
 
+      if storage_options&.any?
+        storage_options = storage_options.to_a
+      else
+        storage_options = nil
+      end
+
       lf.sink_parquet(
         path,
         compression,
@@ -467,7 +475,9 @@ module Polars
         statistics,
         row_group_size,
         data_pagesize_limit,
-        maintain_order
+        maintain_order,
+        storage_options,
+        retries
       )
     end
 
@@ -512,6 +522,10 @@ module Polars
       slice_pushdown: true,
       no_optimization: false
     )
+      # TODO support storage options in Rust
+      storage_options = nil
+      retries = 2
+
       lf = _set_sink_optimizations(
         type_coercion: type_coercion,
         predicate_pushdown: predicate_pushdown,
@@ -521,10 +535,18 @@ module Polars
         no_optimization: no_optimization
       )
 
+      if storage_options&.any?
+        storage_options = storage_options.to_a
+      else
+        storage_options = nil
+      end
+
       lf.sink_ipc(
         path,
         compression,
-        maintain_order
+        maintain_order,
+        storage_options,
+        retries
       )
     end
 
@@ -692,7 +714,9 @@ module Polars
       projection_pushdown: true,
       simplify_expression: true,
       slice_pushdown: true,
-      no_optimization: false
+      no_optimization: false,
+      storage_options: nil,
+      retries: 2
     )
       lf = _set_sink_optimizations(
         type_coercion: type_coercion,
@@ -703,7 +727,13 @@ module Polars
         no_optimization: no_optimization
       )
 
-      lf.sink_json(path, maintain_order)
+      if storage_options&.any?
+        storage_options = storage_options.to_a
+      else
+        storage_options = nil
+      end
+
+      lf.sink_json(path, maintain_order, storage_options, retries)
     end
 
     # @private
@@ -1586,6 +1616,14 @@ module Polars
     #     - true: -> Always coalesce join columns.
     #     - false: -> Never coalesce join columns.
     #   Note that joining on any other expressions than `col` will turn off coalescing.
+    # @param allow_exact_matches [Boolean]
+    #   Whether exact matches are valid join predicates.
+    #     - If true, allow matching with the same `on` value (i.e. less-than-or-equal-to / greater-than-or-equal-to).
+    #     - If false, don't match the same `on` value (i.e., strictly less-than / strictly greater-than).
+    # @param check_sortedness [Boolean]
+    #   Check the sortedness of the asof keys. If the keys are not sorted Polars
+    #   will error, or in case of 'by' argument raise a warning. This might become
+    #   a hard error in the future.
     #
     # @return [LazyFrame]
     #
@@ -1785,7 +1823,9 @@ module Polars
       tolerance: nil,
       allow_parallel: true,
       force_parallel: false,
-      coalesce: true
+      coalesce: true,
+      allow_exact_matches: true,
+      check_sortedness: true
     )
       if !other.is_a?(LazyFrame)
         raise ArgumentError, "Expected a `LazyFrame` as join table, got #{other.class.name}"
@@ -1841,7 +1881,9 @@ module Polars
           strategy,
           tolerance_num,
           tolerance_str,
-          coalesce
+          coalesce,
+          allow_exact_matches,
+          check_sortedness
         )
       )
     end

data/lib/polars/selectors.rb

@@ -372,9 +372,91 @@ module Polars
     # def by_index
     # end
 
-    # TODO
-    # def by_name
-    # end
+    # Select all columns matching the given names.
+    #
+    # @param names [Array]
+    #   One or more names of columns to select.
+    # @param require_all [Boolean]
+    #   Whether to match *all* names (the default) or *any* of the names.
+    #
+    # @return [SelectorProxy]
+    #
+    # @note
+    #   Matching columns are returned in the order in which they are declared in
+    #   the selector, not the underlying schema order.
+    #
+    # @example
+    #   df = Polars::DataFrame.new(
+    #     {
+    #       "foo" => ["x", "y"],
+    #       "bar" => [123, 456],
+    #       "baz" => [2.0, 5.5],
+    #       "zap" => [false, true]
+    #     }
+    #   )
+    #
+    # @example Select columns by name:
+    #   df.select(Polars.cs.by_name("foo", "bar"))
+    #   # =>
+    #   # shape: (2, 2)
+    #   # ┌─────┬─────┐
+    #   # │ foo ┆ bar │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ x   ┆ 123 │
+    #   # │ y   ┆ 456 │
+    #   # └─────┴─────┘
+    #
+    # @example Match *any* of the given columns by name:
+    #   df.select(Polars.cs.by_name("baz", "moose", "foo", "bear", require_all: false))
+    #   # =>
+    #   # shape: (2, 2)
+    #   # ┌─────┬─────┐
+    #   # │ foo ┆ baz │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ f64 │
+    #   # ╞═════╪═════╡
+    #   # │ x   ┆ 2.0 │
+    #   # │ y   ┆ 5.5 │
+    #   # └─────┴─────┘
+    #
+    # @example Match all columns *except* for those given:
+    #   df.select(~Polars.cs.by_name("foo", "bar"))
+    #   # =>
+    #   # shape: (2, 2)
+    #   # ┌─────┬───────┐
+    #   # │ baz ┆ zap   │
+    #   # │ --- ┆ ---   │
+    #   # │ f64 ┆ bool  │
+    #   # ╞═════╪═══════╡
+    #   # │ 2.0 ┆ false │
+    #   # │ 5.5 ┆ true  │
+    #   # └─────┴───────┘
+    def self.by_name(*names, require_all: true)
+      all_names = []
+      names.each do |nm|
+        if nm.is_a?(::String)
+          all_names << nm
+        else
+          msg = "invalid name: #{nm.inspect}"
+          raise TypeError, msg
+        end
+      end
+
+      selector_params = {"*names" => all_names}
+      match_cols = all_names
+      if !require_all
+        match_cols = "^(#{all_names.map { |nm| Utils.re_escape(nm) }.join("|")})$"
+        selector_params["require_all"] = require_all
+      end
+
+      _selector_proxy_(
+        F.col(match_cols),
+        name: "by_name",
+        parameters: selector_params
+      )
+    end
 
     # Select all categorical columns.
     #

data/lib/polars/series.rb

@@ -4696,7 +4696,12 @@ module Polars
         end
 
         constructor = polars_type_to_constructor(dtype)
-        rbseries = constructor.call(name, values, strict)
+        rbseries =
+          if dtype == Array
+            constructor.call(name, values, strict)
+          else
+            construct_series_with_fallbacks(constructor, name, values, dtype, strict: strict)
+          end
 
         base_type = dtype.is_a?(DataType) ? dtype.class : dtype
         if [Date, Datetime, Duration, Time, Categorical, Boolean, Enum, Decimal].include?(base_type)

data/lib/polars/version.rb

@@ -1,4 +1,4 @@
 module Polars
   # @private
-  VERSION = "0.15.0"
+  VERSION = "0.17.0"
 end

data/lib/polars.rb

@@ -49,6 +49,7 @@ require_relative "polars/group_by"
 require_relative "polars/io/avro"
 require_relative "polars/io/csv"
 require_relative "polars/io/database"
+require_relative "polars/io/delta"
 require_relative "polars/io/ipc"
 require_relative "polars/io/json"
 require_relative "polars/io/ndjson"
@@ -89,4 +90,18 @@ module Polars
 
   # @private
   N_INFER_DEFAULT = 100
+
+  # @private
+  class ArrowArrayStream
+    def arrow_c_stream
+      self
+    end
+  end
+
+  # Return the number of threads in the Polars thread pool.
+  #
+  # @return [Integer]
+  def self.thread_pool_size
+    Plr.thread_pool_size
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: polars-df
 version: !ruby/object:Gem::Version
-  version: 0.15.0
+  version: 0.17.0
 platform: arm64-darwin
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-11-20 00:00:00.000000000 Z
+date: 2025-01-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bigdecimal
@@ -24,7 +24,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  force_ruby_platform: false
 description: 
 email: andrew@ankane.org
 executables: []
@@ -40,9 +39,9 @@ files:
 - README.md
 - lib/polars-df.rb
 - lib/polars.rb
-- lib/polars/3.1/polars.bundle
 - lib/polars/3.2/polars.bundle
 - lib/polars/3.3/polars.bundle
+- lib/polars/3.4/polars.bundle
 - lib/polars/array_expr.rb
 - lib/polars/array_name_space.rb
 - lib/polars/batched_csv_reader.rb
@@ -80,6 +79,7 @@ files:
 - lib/polars/io/avro.rb
 - lib/polars/io/csv.rb
 - lib/polars/io/database.rb
+- lib/polars/io/delta.rb
 - lib/polars/io/ipc.rb
 - lib/polars/io/json.rb
 - lib/polars/io/ndjson.rb
@@ -122,17 +122,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.1'
+      version: '3.2'
   - - "<"
     - !ruby/object:Gem::Version
-      version: 3.4.dev
+      version: 3.5.dev
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.4
+rubygems_version: 3.5.23
 signing_key: 
 specification_version: 4
 summary: Blazingly fast DataFrames for Ruby