polars-df 0.18.0 → 0.20.0

data/lib/polars/expr.rb

@@ -1512,6 +1512,13 @@ module Polars
     #
     # @param element [Object]
     #   Expression or scalar value.
+    # @param side ['any', 'left', 'right']
+    #   If 'any', the index of the first suitable location found is given.
+    #   If 'left', the index of the leftmost suitable location found is given.
+    #   If 'right', return the rightmost suitable location found is given.
+    # @param descending [Boolean]
+    #   Boolean indicating whether the values are descending or not (they
+    #   are required to be sorted either way).
     #
     # @return [Expr]
     #
@@ -1537,9 +1544,9 @@ module Polars
     #   # ╞══════╪═══════╪═════╡
     #   # │ 0    ┆ 2     ┆ 4   │
     #   # └──────┴───────┴─────┘
-    def search_sorted(element, side: "any")
+    def search_sorted(element, side: "any", descending: false)
       element = Utils.parse_into_expression(element, str_as_lit: false)
-      _from_rbexpr(_rbexpr.search_sorted(element, side))
+      _from_rbexpr(_rbexpr.search_sorted(element, side, descending))
     end
 
     # Sort this column by the ordering of another column, or multiple other columns.
@@ -3734,15 +3741,7 @@ module Polars
     #   # │ [9, 10]   ┆ 3                ┆ false    │
     #   # └───────────┴──────────────────┴──────────┘
     def is_in(other, nulls_equal: false)
-      if other.is_a?(::Array)
-        if other.length == 0
-          other = Polars.lit(nil)._rbexpr
-        else
-          other = Polars.lit(Series.new(other))._rbexpr
-        end
-      else
-        other = Utils.parse_into_expression(other, str_as_lit: false)
-      end
+      other = Utils.parse_into_expression(other)
       _from_rbexpr(_rbexpr.is_in(other, nulls_equal))
     end
     alias_method :in?, :is_in
@@ -6659,6 +6658,8 @@ module Polars
     #   # │ 99     │
     #   # └────────┘
     def extend_constant(value, n)
+      value = Utils.parse_into_expression(value, str_as_lit: true)
+      n = Utils.parse_into_expression(n)
       _from_rbexpr(_rbexpr.extend_constant(value, n))
     end
 
@@ -6822,9 +6823,6 @@ module Polars
     # @param min_periods [Integer]
     #   Number of valid values there should be in the window before the expression
     #   is evaluated. valid values = `length - null_count`
-    # @param parallel [Boolean]
-    #   Run in parallel. Don't do this in a group by or another operation that
-    #   already has much parallelization.
     #
     # @return [Expr]
     #
@@ -6858,9 +6856,9 @@ module Polars
     #   # │ -15    │
     #   # │ -24    │
     #   # └────────┘
-    def cumulative_eval(expr, min_periods: 1, parallel: false)
+    def cumulative_eval(expr, min_periods: 1)
       _from_rbexpr(
-        _rbexpr.cumulative_eval(expr._rbexpr, min_periods, parallel)
+        _rbexpr.cumulative_eval(expr._rbexpr, min_periods)
       )
     end
 
@@ -7125,7 +7123,7 @@ module Polars
     #   Accepts expression input. Sequences are parsed as Series,
     #   other non-expression inputs are parsed as literals.
     #   Also accepts a mapping of values to their replacement as syntactic sugar for
-    #   `replace_all(old: Series.new(mapping.keys), new: Serie.new(mapping.values))`.
+    #   `replace_all(old: Series.new(mapping.keys), new: Series.new(mapping.values))`.
     # @param new [Object]
     #   Value or sequence of values to replace by.
     #   Accepts expression input. Sequences are parsed as Series,

data/lib/polars/functions/eager.rb

@@ -206,7 +206,7 @@ module Polars
       end
     end
 
-    # Align a sequence of frames using the uique values from one or more columns as a key.
+    # Align a sequence of frames using the unique values from one or more columns as a key.
     #
     # Frames that do not contain the given key values have rows injected (with nulls
     # filling the non-key columns), and each resulting frame is sorted by the key.

data/lib/polars/functions/lit.rb

@@ -16,20 +16,15 @@ module Polars
       elsif value.is_a?(::Date)
         return lit(::Time.utc(value.year, value.month, value.day)).cast(Date)
       elsif value.is_a?(Polars::Series)
-        name = value.name
         value = value._s
-        e = Utils.wrap_expr(Plr.lit(value, allow_object))
-        if name == ""
-          return e
-        end
-        return e.alias(name)
+        return Utils.wrap_expr(Plr.lit(value, allow_object, false))
       elsif (defined?(Numo::NArray) && value.is_a?(Numo::NArray)) || value.is_a?(::Array)
-        return lit(Series.new("", value))
+        return Utils.wrap_expr(Plr.lit(Series.new("literal", [value.to_a], dtype: dtype)._s, allow_object, true))
       elsif dtype
-        return Utils.wrap_expr(Plr.lit(value, allow_object)).cast(dtype)
+        return Utils.wrap_expr(Plr.lit(value, allow_object, true)).cast(dtype)
       end
 
-      Utils.wrap_expr(Plr.lit(value, allow_object))
+      Utils.wrap_expr(Plr.lit(value, allow_object, true))
     end
   end
 end

data/lib/polars/list_expr.rb

@@ -245,6 +245,11 @@ module Polars
 
     # Sort the arrays in the list.
     #
+    # @param reverse [Boolean]
+    #   Sort in descending order.
+    # @param nulls_last [Boolean]
+    #   Place null values last.
+    #
     # @return [Expr]
     #
     # @example
@@ -264,8 +269,8 @@ module Polars
     #   # │ [1, 2, 3] │
     #   # │ [1, 2, 9] │
     #   # └───────────┘
-    def sort(reverse: false)
-      Utils.wrap_expr(_rbexpr.list_sort(reverse))
+    def sort(reverse: false, nulls_last: false)
+      Utils.wrap_expr(_rbexpr.list_sort(reverse, nulls_last))
     end
 
     # Reverse the arrays in the list.
@@ -481,6 +486,8 @@ module Polars
     #
     # @param item [Object]
     #   Item that will be checked for membership
+    # @param nulls_equal [Boolean]
+    #   If true, treat null as a distinct value. Null values will not propagate.
     #
     # @return [Expr]
     #
@@ -498,8 +505,8 @@ module Polars
     #   # │ false │
     #   # │ true  │
     #   # └───────┘
-    def contains(item)
-      Utils.wrap_expr(_rbexpr.list_contains(Utils.parse_into_expression(item)))
+    def contains(item, nulls_equal: true)
+      Utils.wrap_expr(_rbexpr.list_contains(Utils.parse_into_expression(item), nulls_equal))
     end
 
     # Join all string items in a sublist and place a separator between them.
@@ -746,9 +753,9 @@ module Polars
     #   # │ {1,2,3}    │
     #   # │ {1,2,null} │
     #   # └────────────┘
-    def to_struct(n_field_strategy: "first_non_null", name_generator: nil)
+    def to_struct(n_field_strategy: "first_non_null", name_generator: nil, upper_bound: nil)
       raise Todo if name_generator
-      Utils.wrap_expr(_rbexpr.list_to_struct(n_field_strategy, name_generator, 0))
+      Utils.wrap_expr(_rbexpr.list_to_struct(n_field_strategy, name_generator, nil))
     end
 
     # Run any polars expression against the lists' elements.
@@ -756,12 +763,6 @@ module Polars
     # @param expr [Expr]
     #   Expression to run. Note that you can select an element with `Polars.first`, or
     #   `Polars.col`
-    # @param parallel [Boolean]
-    #   Run all expression parallel. Don't activate this blindly.
-    #   Parallelism is worth it if there is enough work to do per thread.
-    #
-    #   This likely should not be use in the group by context, because we already
-    #   parallel execution per group
     #
     # @return [Expr]
     #
@@ -781,8 +782,8 @@ module Polars
     #   # │ 8   ┆ 5   ┆ [2.0, 1.0] │
     #   # │ 3   ┆ 2   ┆ [2.0, 1.0] │
     #   # └─────┴─────┴────────────┘
-    def eval(expr, parallel: false)
-      Utils.wrap_expr(_rbexpr.list_eval(expr._rbexpr, parallel))
+    def eval(expr)
+      Utils.wrap_expr(_rbexpr.list_eval(expr._rbexpr))
     end
   end
 end

data/lib/polars/list_name_space.rb

@@ -586,12 +586,6 @@ module Polars
     # @param expr [Expr]
     #   Expression to run. Note that you can select an element with `Polars.first`, or
     #   `Polars.col`
-    # @param parallel [Boolean]
-    #   Run all expression parallel. Don't activate this blindly.
-    #   Parallelism is worth it if there is enough work to do per thread.
-    #
-    #   This likely should not be use in the group by context, because we already
-    #   parallel execution per group
     #
     # @return [Series]
     #
@@ -611,7 +605,7 @@ module Polars
     #   # │ 8   ┆ 5   ┆ [2.0, 1.0] │
     #   # │ 3   ┆ 2   ┆ [2.0, 1.0] │
     #   # └─────┴─────┴────────────┘
-    def eval(expr, parallel: false)
+    def eval(expr)
       super
     end
   end

data/lib/polars/meta_expr.rb

@@ -125,14 +125,14 @@ module Polars
     # @return [Array]
     #
     # @example
-    #   e = Polars.col("foo").alias("bar")
+    #   e = Polars.col("foo") + Polars.col("bar")
     #   first = e.meta.pop[0]
-    #   _ = first.meta == Polars.col("foo")
-    #   # => true
     #   _ = first.meta == Polars.col("bar")
+    #   # => true
+    #   _ = first.meta == Polars.col("foo")
     #   # => false
-    def pop
-      _rbexpr.meta_pop.map { |e| Utils.wrap_expr(e) }
+    def pop(schema: nil)
+      _rbexpr.meta_pop(schema).map { |e| Utils.wrap_expr(e) }
     end
 
     # Get a list with the root column name.
@@ -209,8 +209,8 @@ module Polars
     # @example
     #   e = (Polars.col("foo") * Polars.col("bar")).sum.over(Polars.col("ham")) / 2
     #   e.meta.tree_format(return_as_string: true)
-    def tree_format(return_as_string: false)
-      s = _rbexpr.meta_tree_format
+    def tree_format(return_as_string: false, schema: nil)
+      s = _rbexpr.meta_tree_format(schema)
       if return_as_string
         s
       else

data/lib/polars/series.rb

@@ -1321,9 +1321,6 @@ module Polars
     # @param min_periods [Integer]
     #   Number of valid values there should be in the window before the expression
     #   is evaluated. valid values = `length - null_count`
-    # @param parallel [Boolean]
-    #   Run in parallel. Don't do this in a group by or another operation that
-    #   already has much parallelization.
     #
     # @return [Series]
     #
@@ -1348,7 +1345,7 @@ module Polars
     #   #         -15
     #   #         -24
     #   # ]
-    def cumulative_eval(expr, min_periods: 1, parallel: false)
+    def cumulative_eval(expr, min_periods: 1)
       super
     end
 
@@ -1879,6 +1876,13 @@ module Polars
     #
     # @param element [Object]
     #   Expression or scalar value.
+    # @param side ['any', 'left', 'right']
+    #   If 'any', the index of the first suitable location found is given.
+    #   If 'left', the index of the leftmost suitable location found is given.
+    #   If 'right', return the rightmost suitable location found is given.
+    # @param descending [Boolean]
+    #   Boolean indicating whether the values are descending or not (they
+    #   are required to be sorted either way).
     #
     # @return [Integer]
     #
@@ -1927,12 +1931,12 @@ module Polars
     #   #         5
     #   #         6
     #   # ]
-    def search_sorted(element, side: "any")
+    def search_sorted(element, side: "any", descending: false)
       if element.is_a?(Integer) || element.is_a?(Float)
-        return Polars.select(Polars.lit(self).search_sorted(element, side: side)).item
+        return Polars.select(Polars.lit(self).search_sorted(element, side: side, descending: descending)).item
       end
       element = Series.new(element)
-      Polars.select(Polars.lit(self).search_sorted(element, side: side)).to_series
+      Polars.select(Polars.lit(self).search_sorted(element, side: side, descending: descending)).to_series
     end
 
     # Get unique elements in series.
@@ -2144,18 +2148,33 @@ module Polars
 
     # Check if elements of this Series are in the other Series.
     #
+    # @param nulls_equal [Boolean]
+    #   If true, treat null as a distinct value. Null values will not propagate.
+    #
     # @return [Series]
     #
     # @example
     #   s = Polars::Series.new("a", [1, 2, 3])
-    #   s2 = Polars::Series.new("b", [2, 4])
+    #   s2 = Polars::Series.new("b", [2, 4, nil])
     #   s2.is_in(s)
     #   # =>
-    #   # shape: (2,)
+    #   # shape: (3,)
     #   # Series: 'b' [bool]
     #   # [
     #   #         true
     #   #         false
+    #   #         null
+    #   # ]
+    #
+    # @example
+    #   s2.is_in(s, nulls_equal: true)
+    #   # =>
+    #   # shape: (3,)
+    #   # Series: 'b' [bool]
+    #   # [
+    #   #         true
+    #   #         false
+    #   #         false
     #   # ]
     #
     # @example
@@ -2190,7 +2209,7 @@ module Polars
     #   #         true
     #   #         false
     #   # ]
-    def is_in(other)
+    def is_in(other, nulls_equal: false)
       super
     end
     alias_method :in?, :is_in
@@ -4351,7 +4370,7 @@ module Polars
     #   #         99
     #   # ]
     def extend_constant(value, n)
-      Utils.wrap_s(_s.extend_constant(value, n))
+      super
     end
 
     # Flags the Series as sorted.

data/lib/polars/string_expr.rb

@@ -1403,7 +1403,7 @@ module Polars
     #   # │ Can you feel the love tonight   ┆ true         │
     #   # └─────────────────────────────────┴──────────────┘
     def contains_any(patterns, ascii_case_insensitive: false)
-      patterns = Utils.parse_into_expression(patterns, str_as_lit: false, list_as_series: true)
+      patterns = Utils.parse_into_expression(patterns, str_as_lit: false)
       Utils.wrap_expr(
         _rbexpr.str_contains_any(patterns, ascii_case_insensitive)
       )
@@ -1474,9 +1474,9 @@ module Polars
     #   # │ Can you feel the love tonight   ┆ Can me feel the love tonight    │
     #   # └─────────────────────────────────┴─────────────────────────────────┘
     def replace_many(patterns, replace_with, ascii_case_insensitive: false)
-      patterns = Utils.parse_into_expression(patterns, str_as_lit: false, list_as_series: true)
+      patterns = Utils.parse_into_expression(patterns, str_as_lit: false)
       replace_with = Utils.parse_into_expression(
-        replace_with, str_as_lit: true, list_as_series: true
+        replace_with, str_as_lit: true
       )
       Utils.wrap_expr(
         _rbexpr.str_replace_many(

data/lib/polars/string_name_space.rb

@@ -120,7 +120,7 @@ module Polars
     # Parse a Series of dtype Utf8 to a Date/Datetime Series.
     #
     # @param datatype [Symbol]
-    #   `:date`, `:dateime`, or `:time`.
+    #   `:date`, `:datetime`, or `:time`.
     # @param fmt [String]
     #   Format to use, refer to the
     #   [chrono strftime documentation](https://docs.rs/chrono/latest/chrono/format/strftime/index.html)

data/lib/polars/version.rb

@@ -1,4 +1,4 @@
 module Polars
   # @private
-  VERSION = "0.18.0"
+  VERSION = "0.20.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: polars-df
 version: !ruby/object:Gem::Version
-  version: 0.18.0
+  version: 0.20.0
 platform: ruby
 authors:
 - Andrew Kane