polars-df 0.17.0 → 0.17.1

data/lib/polars/lazy_frame.rb

@@ -619,6 +619,10 @@ module Polars
     #   Slice pushdown optimization.
     # @param no_optimization [Boolean]
     #   Turn off (certain) optimizations.
+    # @param storage_options [Object]
+    #   Options that indicate how to connect to a cloud provider.
+    # @param retries [Integer]
+    #   Number of retries if accessing a cloud instance fails.
     #
     # @return [DataFrame]
     #
@@ -646,7 +650,9 @@ module Polars
       projection_pushdown: true,
       simplify_expression: true,
       slice_pushdown: true,
-      no_optimization: false
+      no_optimization: false,
+      storage_options: nil,
+      retries: 2
     )
       Utils._check_arg_is_1byte("separator", separator, false)
       Utils._check_arg_is_1byte("quote_char", quote_char, false)
@@ -660,6 +666,12 @@ module Polars
         no_optimization: no_optimization
       )
 
+      if storage_options&.any?
+        storage_options = storage_options.to_a
+      else
+        storage_options = nil
+      end
+
       lf.sink_csv(
         path,
         include_bom,
@@ -675,7 +687,9 @@ module Polars
         float_precision,
         null_value,
         quote_style,
-        maintain_order
+        maintain_order,
+        storage_options,
+        retries
       )
     end
 
@@ -1923,6 +1937,24 @@ 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 maintain_order ['none', 'left', 'right', 'left_right', 'right_left']
+    #   Which DataFrame row order to preserve, if any.
+    #   Do not rely on any observed ordering without explicitly
+    #   setting this parameter, as your code may break in a future release.
+    #   Not specifying any ordering can improve performance
+    #   Supported for inner, left, right and full joins
+    #
+    #   * *none*
+    #       No specific ordering is desired. The ordering might differ across
+    #       Polars versions or even between different runs.
+    #   * *left*
+    #       Preserves the order of the left DataFrame.
+    #   * *right*
+    #       Preserves the order of the right DataFrame.
+    #   * *left_right*
+    #       First preserves the order of the left DataFrame, then the right.
+    #   * *right_left*
+    #       First preserves the order of the right DataFrame, then the left.
     #
     # @return [LazyFrame]
     #
@@ -2016,18 +2048,33 @@ module Polars
       join_nulls: false,
       allow_parallel: true,
       force_parallel: false,
-      coalesce: nil
+      coalesce: nil,
+      maintain_order: nil
     )
       if !other.is_a?(LazyFrame)
         raise ArgumentError, "Expected a `LazyFrame` as join table, got #{other.class.name}"
       end
 
+      if maintain_order.nil?
+        maintain_order = "none"
+      end
+
       if how == "outer"
         how = "full"
       elsif how == "cross"
         return _from_rbldf(
           _ldf.join(
-            other._ldf, [], [], allow_parallel, join_nulls, force_parallel, how, suffix, validate, coalesce
+            other._ldf,
+            [],
+            [],
+            allow_parallel,
+            join_nulls,
+            force_parallel,
+            how,
+            suffix,
+            validate,
+            maintain_order,
+            coalesce
           )
         )
       end
@@ -2054,6 +2101,7 @@ module Polars
           how,
           suffix,
           validate,
+          maintain_order,
           coalesce
         )
       )
@@ -3347,12 +3395,17 @@ module Polars
       _from_rbldf(_ldf.merge_sorted(other._ldf, key))
     end
 
-    # Indicate that one or multiple columns are sorted.
+    # Flag a column as sorted.
+    #
+    # This can speed up future operations.
+    #
+    # @note
+    #   This can lead to incorrect results if the data is NOT sorted! Use with care!
     #
     # @param column [Object]
-    #   Columns that are sorted
+    #   Column that is sorted.
     # @param descending [Boolean]
-    #   Whether the columns are sorted in descending order.
+    #   Whether the column is sorted in descending order.
     #
     # @return [LazyFrame]
     def set_sorted(

data/lib/polars/schema.rb

@@ -0,0 +1,29 @@
+module Polars
+  class Schema
+    def initialize(schema, check_dtypes: true)
+      raise Todo if check_dtypes
+      @schema = schema.to_h
+    end
+
+    def [](key)
+      @schema[key]
+    end
+
+    def names
+      @schema.keys
+    end
+
+    def dtypes
+      @schema.values
+    end
+
+    def length
+      @schema.length
+    end
+
+    def to_s
+      "#{self.class.name}(#{@schema})"
+    end
+    alias_method :inspect, :to_s
+  end
+end

data/lib/polars/series.rb

@@ -2554,29 +2554,7 @@ module Polars
     #   # Numo::Int64#shape=[3]
     #   # [1, 2, 3]
     def to_numo
-      if !has_validity
-        if is_datelike
-          Numo::RObject.cast(to_a)
-        elsif is_numeric
-          # TODO make more efficient
-          {
-            UInt8 => Numo::UInt8,
-            UInt16 => Numo::UInt16,
-            UInt32 => Numo::UInt32,
-            UInt64 => Numo::UInt64,
-            Int8 => Numo::Int8,
-            Int16 => Numo::Int16,
-            Int32 => Numo::Int32,
-            Int64 => Numo::Int64,
-            Float32 => Numo::SFloat,
-            Float64 => Numo::DFloat
-          }.fetch(dtype.class).cast(to_a)
-        elsif is_boolean
-          Numo::Bit.cast(to_a)
-        else
-          _s.to_numo
-        end
-      elsif is_datelike
+      if is_datelike
         Numo::RObject.cast(to_a)
       else
         _s.to_numo
@@ -3815,6 +3793,30 @@ module Polars
       super
     end
 
+    # Fill null values using interpolation based on another column.
+    #
+    # @param by [Expr]
+    #   Column to interpolate values based on.
+    #
+    # @return [Series]
+    #
+    # @example Fill null values using linear interpolation.
+    #   s = Polars::Series.new("a", [1, nil, nil, 3])
+    #   by = Polars::Series.new("b", [1, 2, 7, 8])
+    #   s.interpolate_by(by)
+    #   # =>
+    #   # shape: (4,)
+    #   # Series: 'a' [f64]
+    #   # [
+    #   #         1.0
+    #   #         1.285714
+    #   #         2.714286
+    #   #         3.0
+    #   # ]
+    def interpolate_by(by)
+      super
+    end
+
     # Compute absolute values.
     #
     # @return [Series]

data/lib/polars/version.rb

@@ -1,4 +1,4 @@
 module Polars
   # @private
-  VERSION = "0.17.0"
+  VERSION = "0.17.1"
 end

data/lib/polars.rb

@@ -61,6 +61,7 @@ require_relative "polars/list_name_space"
 require_relative "polars/meta_expr"
 require_relative "polars/name_expr"
 require_relative "polars/rolling_group_by"
+require_relative "polars/schema"
 require_relative "polars/selectors"
 require_relative "polars/series"
 require_relative "polars/slice"

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: polars-df
 version: !ruby/object:Gem::Version
-  version: 0.17.0
+  version: 0.17.1
 platform: ruby
 authors:
 - Andrew Kane
 bindir: bin
 cert_chain: []
-date: 2025-01-28 00:00:00.000000000 Z
+date: 2025-04-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bigdecimal
@@ -93,6 +93,7 @@ files:
 - ext/polars/src/interop/arrow/to_ruby.rs
 - ext/polars/src/interop/mod.rs
 - ext/polars/src/interop/numo/mod.rs
+- ext/polars/src/interop/numo/numo_rs.rs
 - ext/polars/src/interop/numo/to_numo_df.rs
 - ext/polars/src/interop/numo/to_numo_series.rs
 - ext/polars/src/lazyframe/general.rs
@@ -171,6 +172,7 @@ files:
 - lib/polars/name_expr.rb
 - lib/polars/plot.rb
 - lib/polars/rolling_group_by.rb
+- lib/polars/schema.rb
 - lib/polars/selectors.rb
 - lib/polars/series.rb
 - lib/polars/slice.rb