polars-df 0.4.0-x86_64-linux → 0.6.0-x86_64-linux

data/lib/polars/data_frame.rb

@@ -18,7 +18,10 @@ module Polars
     #   Whether to interpret two-dimensional data as columns or as rows. If `nil`,
     #   the orientation is inferred by matching the columns and data dimensions. If
     #   this does not yield conclusive results, column orientation is used.
-    def initialize(data = nil, columns: nil, orient: nil)
+    def initialize(data = nil, schema: nil, columns: nil, schema_overrides: nil, orient: nil, infer_schema_length: 100, nan_to_null: false)
+      schema ||= columns
+      raise Todo if schema_overrides
+
       # TODO deprecate in favor of read_sql
       if defined?(ActiveRecord) && (data.is_a?(ActiveRecord::Relation) || data.is_a?(ActiveRecord::Result))
         result = data.is_a?(ActiveRecord::Result) ? data : data.connection.select_all(data.to_sql)
@@ -29,14 +32,14 @@ module Polars
       end
 
       if data.nil?
-        self._df = self.class.hash_to_rbdf({}, columns: columns)
+        self._df = self.class.hash_to_rbdf({}, schema: schema, schema_overrides: schema_overrides)
       elsif data.is_a?(Hash)
         data = data.transform_keys { |v| v.is_a?(Symbol) ? v.to_s : v }
-        self._df = self.class.hash_to_rbdf(data, columns: columns)
-      elsif data.is_a?(Array)
-        self._df = self.class.sequence_to_rbdf(data, columns: columns, orient: orient)
+        self._df = self.class.hash_to_rbdf(data, schema: schema, schema_overrides: schema_overrides, nan_to_null: nan_to_null)
+      elsif data.is_a?(::Array)
+        self._df = self.class.sequence_to_rbdf(data, schema: schema, schema_overrides: schema_overrides, orient: orient, infer_schema_length: infer_schema_length)
       elsif data.is_a?(Series)
-        self._df = self.class.series_to_rbdf(data, columns: columns)
+        self._df = self.class.series_to_rbdf(data, schema: schema, schema_overrides: schema_overrides)
       else
         raise ArgumentError, "DataFrame constructor called with unsupported type; got #{data.class.name}"
       end
@@ -56,8 +59,8 @@ module Polars
     end
 
     # @private
-    def self._from_hash(data, columns: nil)
-      _from_rbdf(hash_to_rbdf(data, columns: columns))
+    def self._from_hash(data, schema: nil, schema_overrides: nil)
+      _from_rbdf(hash_to_rbdf(data, schema: schema, schema_overrides: schema_overrides))
     end
 
     # def self._from_records
@@ -113,7 +116,7 @@ module Polars
           dtypes.each do|k, v|
             dtype_list << [k, Utils.rb_type_to_dtype(v)]
           end
-        elsif dtypes.is_a?(Array)
+        elsif dtypes.is_a?(::Array)
           dtype_slice = dtypes
         else
           raise ArgumentError, "dtype arg should be list or dict"
@@ -336,6 +339,7 @@ module Polars
     end
     alias_method :count, :height
     alias_method :length, :height
+    alias_method :size, :height
 
     # Get the width of the DataFrame.
     #
@@ -546,6 +550,13 @@ module Polars
     end
     alias_method :inspect, :to_s
 
+    # Returns an array representing the DataFrame
+    #
+    # @return [Array]
+    def to_a
+      rows(named: true)
+    end
+
     # Check if DataFrame includes column.
     #
     # @return [Boolean]
@@ -579,7 +590,7 @@ module Polars
 
         # df[2, ..] (select row as df)
         if row_selection.is_a?(Integer)
-          if col_selection.is_a?(Array)
+          if col_selection.is_a?(::Array)
             df = self[0.., col_selection]
             return df.slice(row_selection, 1)
           end
@@ -600,7 +611,7 @@ module Polars
           return series[row_selection]
         end
 
-        if col_selection.is_a?(Array)
+        if col_selection.is_a?(::Array)
           # df[.., [1, 2]]
           if Utils.is_int_sequence(col_selection)
             series_list = col_selection.map { |i| to_series(i) }
@@ -630,7 +641,7 @@ module Polars
           return Slice.new(self).apply(item)
         end
 
-        if item.is_a?(Array) && item.all? { |v| Utils.strlike?(v) }
+        if item.is_a?(::Array) && item.all? { |v| Utils.strlike?(v) }
           # select multiple columns
           # df[["foo", "bar"]]
           return _from_rbdf(_df.select(item.map(&:to_s)))
@@ -655,7 +666,7 @@ module Polars
       end
 
       # Ruby-specific
-      if item.is_a?(Expr)
+      if item.is_a?(Expr) || item.is_a?(Series)
         return filter(item)
       end
 
@@ -665,15 +676,42 @@ module Polars
     # Set item.
     #
     # @return [Object]
-    #
-    # def []=(key, value)
-    #   if key.is_a?(String)
-    #     raise TypeError, "'DataFrame' object does not support 'Series' assignment by index. Use 'DataFrame.with_columns'"
-    #   end
+    def []=(*key, value)
+      if key.length == 1
+        key = key.first
+      elsif key.length != 2
+        raise ArgumentError, "wrong number of arguments (given #{key.length + 1}, expected 2..3)"
+      end
 
-    #   raise Todo
-    # end
+      if Utils.strlike?(key)
+        if value.is_a?(::Array) || (defined?(Numo::NArray) && value.is_a?(Numo::NArray))
+          value = Series.new(value)
+        elsif !value.is_a?(Series)
+          value = Polars.lit(value)
+        end
+        self._df = with_column(value.alias(key.to_s))._df
+      elsif key.is_a?(::Array)
+        row_selection, col_selection = key
+
+        if Utils.strlike?(col_selection)
+          s = self[col_selection]
+        elsif col_selection.is_a?(Integer)
+          raise Todo
+        else
+          raise ArgumentError, "column selection not understood: #{col_selection}"
+        end
 
+        s[row_selection] = value
+
+        if col_selection.is_a?(Integer)
+          replace_at_idx(col_selection, s)
+        elsif Utils.strlike?(col_selection)
+          replace(col_selection, s)
+        end
+      else
+        raise Todo
+      end
+    end
 
     # Return the dataframe as a scalar.
     #
@@ -956,14 +994,21 @@ module Polars
     #
     # @return [nil]
     def write_ipc(file, compression: "uncompressed")
-      if compression.nil?
-        compression = "uncompressed"
+      return_bytes = file.nil?
+      if return_bytes
+        file = StringIO.new
+        file.set_encoding(Encoding::BINARY)
       end
       if Utils.pathlike?(file)
         file = Utils.normalise_filepath(file)
       end
 
+      if compression.nil?
+        compression = "uncompressed"
+      end
+
       _df.write_ipc(file, compression)
+      return_bytes ? file.string : nil
     end
 
     # Write to Apache Parquet file.
@@ -1453,13 +1498,23 @@ module Polars
     #   # │ 1   ┆ 6.0 ┆ a   │
     #   # └─────┴─────┴─────┘
     def sort(by, reverse: false, nulls_last: false)
-      if by.is_a?(Array) || by.is_a?(Expr)
-        lazy
-          .sort(by, reverse: reverse, nulls_last: nulls_last)
-          .collect(no_optimization: true, string_cache: false)
-      else
-        _from_rbdf(_df.sort(by, reverse, nulls_last))
-      end
+      lazy
+        .sort(by, reverse: reverse, nulls_last: nulls_last)
+        .collect(no_optimization: true)
+    end
+
+    # Sort the DataFrame by column in-place.
+    #
+    # @param by [String]
+    #   By which column to sort.
+    # @param reverse [Boolean]
+    #   Reverse/descending sort.
+    # @param nulls_last [Boolean]
+    #   Place null values last. Can only be used if sorted by a single column.
+    #
+    # @return [DataFrame]
+    def sort!(by, reverse: false, nulls_last: false)
+      self._df = sort(by, reverse: reverse, nulls_last: nulls_last)._df
     end
 
     # Check if DataFrame is equal to other.
@@ -1519,7 +1574,7 @@ module Polars
     #   # │ 30  ┆ 6   │
     #   # └─────┴─────┘
     def replace(column, new_col)
-      _df.replace(column, new_col._s)
+      _df.replace(column.to_s, new_col._s)
       self
     end
 
@@ -1847,6 +1902,12 @@ module Polars
     #   Define whether the temporal window interval is closed or not.
     # @param by [Object]
     #   Also group by this column/these columns.
+    # @param check_sorted [Boolean]
+    #   When the `by` argument is given, polars can not check sortedness
+    #   by the metadata and has to do a full scan on the index column to
+    #   verify data is sorted. This is expensive. If you are sure the
+    #   data within the by groups is sorted, you can set this to `false`.
+    #   Doing so incorrectly will lead to incorrect output
     #
     # @return [RollingGroupBy]
     #
@@ -1860,7 +1921,7 @@ module Polars
     #     "2020-01-08 23:16:43"
     #   ]
     #   df = Polars::DataFrame.new({"dt" => dates, "a" => [3, 7, 5, 9, 2, 1]}).with_column(
-    #     Polars.col("dt").str.strptime(:datetime)
+    #     Polars.col("dt").str.strptime(Polars::Datetime).set_sorted
     #   )
     #   df.groupby_rolling(index_column: "dt", period: "2d").agg(
     #     [
@@ -1888,9 +1949,10 @@ module Polars
       period:,
       offset: nil,
       closed: "right",
-      by: nil
+      by: nil,
+      check_sorted: true
     )
-      RollingGroupBy.new(self, index_column, period, offset, closed, by)
+      RollingGroupBy.new(self, index_column, period, offset, closed, by, check_sorted)
     end
 
     # Group based on a time value (or index value of type `:i32`, `:i64`).
@@ -2026,21 +2088,21 @@ module Polars
     #   df.groupby_dynamic("time", every: "1h", closed: "left").agg(
     #     [
     #       Polars.col("time").count.alias("time_count"),
-    #       Polars.col("time").list.alias("time_agg_list")
+    #       Polars.col("time").alias("time_agg_list")
     #     ]
     #   )
     #   # =>
     #   # shape: (4, 3)
-    #   # ┌─────────────────────┬────────────┬─────────────────────────────────────┐
-    #   # │ time                ┆ time_count ┆ time_agg_list                       │
-    #   # │ ---                 ┆ ---        ┆ ---                                 │
-    #   # │ datetime[μs]        ┆ u32        ┆ list[datetime[μs]]                  │
-    #   # ╞═════════════════════╪════════════╪═════════════════════════════════════╡
-    #   # │ 2021-12-16 00:00:00 ┆ 2          ┆ [2021-12-16 00:00:00, 2021-12-16... │
-    #   # │ 2021-12-16 01:00:00 ┆ 2          ┆ [2021-12-16 01:00:00, 2021-12-16... │
-    #   # │ 2021-12-16 02:00:00 ┆ 2          ┆ [2021-12-16 02:00:00, 2021-12-16... │
-    #   # │ 2021-12-16 03:00:00 ┆ 1          ┆ [2021-12-16 03:00:00]               │
-    #   # └─────────────────────┴────────────┴─────────────────────────────────────┘
+    #   # ┌─────────────────────┬────────────┬───────────────────────────────────┐
+    #   # │ time                ┆ time_count ┆ time_agg_list                     │
+    #   # │ ---                 ┆ ---        ┆ ---                               │
+    #   # │ datetime[μs]        ┆ u32        ┆ list[datetime[μs]]                │
+    #   # ╞═════════════════════╪════════════╪═══════════════════════════════════╡
+    #   # │ 2021-12-16 00:00:00 ┆ 2          ┆ [2021-12-16 00:00:00, 2021-12-16… │
+    #   # │ 2021-12-16 01:00:00 ┆ 2          ┆ [2021-12-16 01:00:00, 2021-12-16… │
+    #   # │ 2021-12-16 02:00:00 ┆ 2          ┆ [2021-12-16 02:00:00, 2021-12-16… │
+    #   # │ 2021-12-16 03:00:00 ┆ 1          ┆ [2021-12-16 03:00:00]             │
+    #   # └─────────────────────┴────────────┴───────────────────────────────────┘
     #
     # @example When closed="both" the time values at the window boundaries belong to 2 groups.
     #   df.groupby_dynamic("time", every: "1h", closed: "both").agg(
@@ -2107,7 +2169,7 @@ module Polars
     #     period: "3i",
     #     include_boundaries: true,
     #     closed: "right"
-    #   ).agg(Polars.col("A").list.alias("A_agg_list"))
+    #   ).agg(Polars.col("A").alias("A_agg_list"))
     #   # =>
     #   # shape: (3, 4)
     #   # ┌─────────────────┬─────────────────┬─────┬─────────────────┐
@@ -2190,7 +2252,7 @@ module Polars
     #       "groups" => ["A", "B", "A", "B"],
     #       "values" => [0, 1, 2, 3]
     #     }
-    #   )
+    #   ).set_sorted("time")
     #   df.upsample(
     #     time_column: "time", every: "1mo", by: "groups", maintain_order: true
     #   ).select(Polars.all.forward_fill)
@@ -2308,7 +2370,7 @@ module Polars
     #       ],  # note record date: Jan 1st (sorted!)
     #       "gdp" => [4164, 4411, 4566, 4696]
     #     }
-    #   )
+    #   ).set_sorted("date")
     #   population = Polars::DataFrame.new(
     #     {
     #       "date" => [
@@ -2319,7 +2381,7 @@ module Polars
     #       ],  # note record date: May 12th (sorted!)
     #       "population" => [82.19, 82.66, 83.12, 83.52]
     #     }
-    #   )
+    #   ).set_sorted("date")
     #   population.join_asof(
     #     gdp, left_on: "date", right_on: "date", strategy: "backward"
     #   )
@@ -2622,7 +2684,7 @@ module Polars
     #   # │ 3   ┆ 8   ┆ c   ┆ 30    │
     #   # └─────┴─────┴─────┴───────┘
     def hstack(columns, in_place: false)
-      if !columns.is_a?(Array)
+      if !columns.is_a?(::Array)
         columns = columns.get_columns
       end
       if in_place
@@ -2752,7 +2814,7 @@ module Polars
     #   # │ 3   ┆ 8.0 │
     #   # └─────┴─────┘
     def drop(columns)
-      if columns.is_a?(Array)
+      if columns.is_a?(::Array)
         df = clone
         columns.each do |n|
           df._df.drop_in_place(n)
@@ -2791,6 +2853,16 @@ module Polars
       Utils.wrap_s(_df.drop_in_place(name))
     end
 
+    # Drop in place if exists.
+    #
+    # @param name [Object]
+    #   Column to drop.
+    #
+    # @return [Series]
+    def delete(name)
+      drop_in_place(name) if include?(name)
+    end
+
     # Create an empty copy of the current DataFrame.
     #
     # Returns a DataFrame with identical schema but no data.
@@ -3202,7 +3274,7 @@ module Polars
     #   # │ B    ┆ 1    │
     #   # │ C    ┆ 2    │
     #   # │ D    ┆ 3    │
-    #   # │ …    ┆ …    │
+    #   # │ E    ┆ 4    │
     #   # │ F    ┆ 5    │
     #   # │ G    ┆ 6    │
     #   # │ H    ┆ 7    │
@@ -3255,7 +3327,7 @@ module Polars
       n_fill = n_cols * n_rows - height
 
       if n_fill > 0
-        if !fill_values.is_a?(Array)
+        if !fill_values.is_a?(::Array)
           fill_values = [fill_values] * df.width
         end
 
@@ -3364,29 +3436,29 @@ module Polars
     #   # ╞═════╪═════╪═════╡
     #   # │ C   ┆ 2   ┆ l   │
     #   # └─────┴─────┴─────┘}
-    def partition_by(groups, maintain_order: true, as_dict: false)
+    def partition_by(groups, maintain_order: true, include_key: true, as_dict: false)
       if groups.is_a?(String)
         groups = [groups]
-      elsif !groups.is_a?(Array)
+      elsif !groups.is_a?(::Array)
         groups = Array(groups)
       end
 
       if as_dict
         out = {}
         if groups.length == 1
-          _df.partition_by(groups, maintain_order).each do |df|
+          _df.partition_by(groups, maintain_order, include_key).each do |df|
             df = _from_rbdf(df)
             out[df[groups][0, 0]] = df
           end
         else
-          _df.partition_by(groups, maintain_order).each do |df|
+          _df.partition_by(groups, maintain_order, include_key).each do |df|
             df = _from_rbdf(df)
             out[df[groups].row(0)] = df
           end
         end
         out
       else
-        _df.partition_by(groups, maintain_order).map { |df| _from_rbdf(df) }
+        _df.partition_by(groups, maintain_order, include_key).map { |df| _from_rbdf(df) }
       end
     end
 
@@ -3654,7 +3726,7 @@ module Polars
     #   # │ 4   ┆ 13.0 ┆ true  ┆ 16.0 ┆ 6.5  ┆ false │
     #   # └─────┴──────┴───────┴──────┴──────┴───────┘
     def with_columns(exprs)
-      if !exprs.nil? && !exprs.is_a?(Array)
+      if !exprs.nil? && !exprs.is_a?(::Array)
         exprs = [exprs]
       end
       lazy
@@ -4035,11 +4107,11 @@ module Polars
     #   # │ 1     ┆ 0     ┆ 1     ┆ 0     ┆ 1     ┆ 0     │
     #   # │ 0     ┆ 1     ┆ 0     ┆ 1     ┆ 0     ┆ 1     │
     #   # └───────┴───────┴───────┴───────┴───────┴───────┘
-    def to_dummies(columns: nil, separator: "_")
+    def to_dummies(columns: nil, separator: "_", drop_first: false)
       if columns.is_a?(String)
         columns = [columns]
       end
-      _from_rbdf(_df.to_dummies(columns, separator))
+      _from_rbdf(_df.to_dummies(columns, separator, drop_first))
     end
 
     # Drop duplicate rows from this DataFrame.
@@ -4127,7 +4199,7 @@ module Polars
         subset = [subset]
       end
 
-      if subset.is_a?(Array) && subset.length == 1
+      if subset.is_a?(::Array) && subset.length == 1
         expr = Utils.expr_to_lit_or_expr(subset[0], str_to_lit: false)
       else
         struct_fields = subset.nil? ? Polars.all : subset
@@ -4428,7 +4500,7 @@ module Polars
       end
     end
 
-    # Returns an iterator over the DataFrame of rows of python-native values.
+    # Returns an iterator over the DataFrame of rows of Ruby-native values.
     #
     # @param named [Boolean]
     #   Return hashes instead of arrays. The hashes are a mapping of
@@ -4489,6 +4561,24 @@ module Polars
       end
     end
 
+    # Returns an iterator over the DataFrame of rows of Ruby-native values.
+    #
+    # @param named [Boolean]
+    #   Return hashes instead of arrays. The hashes are a mapping of
+    #   column name to row value. This is more expensive than returning an
+    #   array, but allows for accessing values by column name.
+    # @param buffer_size [Integer]
+    #   Determines the number of rows that are buffered internally while iterating
+    #   over the data; you should only modify this in very specific cases where the
+    #   default value is determined not to be a good fit to your access pattern, as
+    #   the speedup from using the buffer is significant (~2-4x). Setting this
+    #   value to zero disables row buffering.
+    #
+    # @return [Object]
+    def each_row(named: true, buffer_size: 500, &block)
+      iter_rows(named: named, buffer_size: buffer_size, &block)
+    end
+
     # Shrink DataFrame memory usage.
     #
     # Shrinks to fit the exact capacity needed to hold the data.
@@ -4678,6 +4768,38 @@ module Polars
       _from_rbdf(_df.unnest(names))
     end
 
+    # TODO
+    # def corr
+    # end
+
+    # TODO
+    # def merge_sorted
+    # end
+
+    # Indicate that one or multiple columns are sorted.
+    #
+    # @param column [Object]
+    #   Columns that are sorted
+    # @param more_columns [Object]
+    #   Additional columns that are sorted, specified as positional arguments.
+    # @param descending [Boolean]
+    #   Whether the columns are sorted in descending order.
+    #
+    # @return [DataFrame]
+    def set_sorted(
+      column,
+      *more_columns,
+      descending: false
+    )
+      lazy
+        .set_sorted(column, *more_columns, descending: descending)
+        .collect(no_optimization: true)
+    end
+
+    # TODO
+    # def update
+    # end
+
     private
 
     def initialize_copy(other)
@@ -4742,20 +4864,63 @@ module Polars
     end
 
     # @private
-    def self.hash_to_rbdf(data, columns: nil)
-      if !columns.nil?
-        columns, dtypes = _unpack_columns(columns, lookup_names: data.keys)
+    def self.expand_hash_scalars(data, schema_overrides: nil, order: nil, nan_to_null: false)
+      updated_data = {}
+      unless data.empty?
+        dtypes = schema_overrides || {}
+        array_len = data.values.map { |val| Utils.arrlen(val) || 0 }.max
+        if array_len > 0
+          data.each do |name, val|
+            dtype = dtypes[name]
+            if val.is_a?(Hash) && dtype != Struct
+              updated_data[name] = DataFrame.new(val).to_struct(name)
+            elsif !Utils.arrlen(val).nil?
+              updated_data[name] = Series.new(String.new(name), val, dtype: dtype)
+            elsif val.nil? || [Integer, Float, TrueClass, FalseClass, String, ::Date, ::DateTime, ::Time].any? { |cls| val.is_a?(cls) }
+              dtype = Polars::Float64 if val.nil? && dtype.nil?
+              updated_data[name] = Series.new(String.new(name), [val], dtype: dtype).extend_constant(val, array_len - 1)
+            else
+              raise Todo
+            end
+          end
+        elsif data.values.all? { |val| Utils.arrlen(val) == 0 }
+          data.each do |name, val|
+            updated_data[name] = Series.new(name, val, dtype: dtypes[name])
+          end
+        elsif data.values.all? { |val| Utils.arrlen(val).nil? }
+          data.each do |name, val|
+            updated_data[name] = Series.new(name, [val], dtype: dtypes[name])
+          end
+        end
+      end
+      updated_data
+    end
 
-        if data.empty? && dtypes
-          data_series = columns.map { |name| Series.new(name, [], dtype: dtypes[name])._s }
-        else
-          data_series = data.map { |name, values| Series.new(name, values, dtype: dtypes[name])._s }
+    # @private
+    def self.hash_to_rbdf(data, schema: nil, schema_overrides: nil, nan_to_null: nil)
+      if schema.is_a?(Hash) && !data.empty?
+        if !data.all? { |col, _| schema[col] }
+          raise ArgumentError, "The given column-schema names do not match the data dictionary"
         end
-        data_series = _handle_columns_arg(data_series, columns: columns)
-        return RbDataFrame.new(data_series)
+
+        data = schema.to_h { |col| [col, data[col]] }
       end
 
-      RbDataFrame.read_hash(data)
+      column_names, schema_overrides = _unpack_schema(
+        schema, lookup_names: data.keys, schema_overrides: schema_overrides
+      )
+      if column_names.empty?
+        column_names = data.keys
+      end
+
+      if data.empty? && !schema_overrides.empty?
+        data_series = column_names.map { |name| Series.new(name, [], dtype: schema_overrides[name], nan_to_null: nan_to_null)._s }
+      else
+        data_series = expand_hash_scalars(data, schema_overrides: schema_overrides, nan_to_null: nan_to_null).values.map(&:_s)
+      end
+
+      data_series = _handle_columns_arg(data_series, columns: column_names, from_hash: true)
+      RbDataFrame.new(data_series)
     end
 
     # @private
@@ -4764,14 +4929,12 @@ module Polars
     end
 
     # @private
-    def self._unpack_columns(columns, schema_overrides: nil, lookup_names: nil, n_expected: nil)
-      raise Todo if schema_overrides
-
-      if columns.is_a?(Hash)
-        columns = columns.to_a
+    def self._unpack_schema(schema, schema_overrides: nil, n_expected: nil, lookup_names: nil, include_overrides_in_columns: false)
+      if schema.is_a?(Hash)
+        schema = schema.to_a
       end
       column_names =
-        (columns || []).map.with_index do |col, i|
+        (schema || []).map.with_index do |col, i|
           if col.is_a?(String)
             col || "column_#{i}"
           else
@@ -4784,21 +4947,38 @@ module Polars
       # TODO zip_longest
       lookup = column_names.zip(lookup_names || []).to_h
 
-      [
-        column_names,
-        (columns || []).select { |col| !col.is_a?(String) && col[1] }.to_h do |col|
+      column_dtypes =
+        (schema || []).select { |col| !col.is_a?(String) && col[1] }.to_h do |col|
           [lookup[col[0]] || col[0], col[1]]
         end
-      ]
+
+      if schema_overrides
+        raise Todo
+      end
+
+      column_dtypes.each do |col, dtype|
+        if !Utils.is_polars_dtype(dtype, include_unknown: true) && !dtype.nil?
+          column_dtypes[col] = Utils.rb_type_to_dtype(dtype)
+        end
+      end
+
+      [column_names, column_dtypes]
     end
 
-    def self._handle_columns_arg(data, columns: nil)
-      if columns.nil?
+    def self._handle_columns_arg(data, columns: nil, from_hash: false)
+      if columns.nil? || columns.empty?
         data
       else
         if data.empty?
           columns.map { |c| Series.new(c, nil)._s }
         elsif data.length == columns.length
+          if from_hash
+            series_map = data.to_h { |s| [s.name, s] }
+            if columns.all? { |col| series_map.key?(col) }
+              return columns.map { |col| series_map[col] }
+            end
+          end
+
           columns.each_with_index do |c, i|
             # not in-place?
             data[i].rename(c)
@@ -4813,7 +4993,7 @@ module Polars
     def self._post_apply_columns(rbdf, columns, structs: nil, schema_overrides: nil)
       rbdf_columns = rbdf.columns
       rbdf_dtypes = rbdf.dtypes
-      columns, dtypes = _unpack_columns(
+      columns, dtypes = _unpack_schema(
         (columns || rbdf_columns), schema_overrides: schema_overrides
       )
       column_subset = []
@@ -4829,7 +5009,7 @@ module Polars
       columns.each do |col, i|
         if dtypes[col] == Categorical # != rbdf_dtypes[i]
           column_casts << Polars.col(col).cast(Categorical)._rbexpr
-        elsif structs.any? && structs.include?(col) && structs[col] != rbdf_dtypes[i]
+        elsif structs&.any? && structs.include?(col) && structs[col] != rbdf_dtypes[i]
           column_casts << Polars.col(col).cast(structs[col])._rbexpr
         elsif dtypes.include?(col) && dtypes[col] != rbdf_dtypes[i]
           column_casts << Polars.col(col).cast(dtypes[col])._rbexpr
@@ -4851,27 +5031,30 @@ module Polars
     end
 
     # @private
-    def self.sequence_to_rbdf(data, columns: nil, orient: nil, infer_schema_length: 50)
+    def self.sequence_to_rbdf(data, schema: nil, schema_overrides: nil, orient: nil, infer_schema_length: 50)
+      raise Todo if schema_overrides
+      columns = schema
+
       if data.length == 0
-        return hash_to_rbdf({}, columns: columns)
+        return hash_to_rbdf({}, schema: schema, schema_overrides: schema_overrides)
       end
 
       if data[0].is_a?(Series)
         # series_names = data.map(&:name)
-        # columns, dtypes = _unpack_columns(columns || series_names, n_expected: data.length)
+        # columns, dtypes = _unpack_schema(columns || series_names, n_expected: data.length)
         data_series = []
         data.each do |s|
           data_series << s._s
         end
       elsif data[0].is_a?(Hash)
-        column_names, dtypes = _unpack_columns(columns)
+        column_names, dtypes = _unpack_schema(columns)
         schema_overrides = dtypes ? include_unknowns(dtypes, column_names) : nil
         rbdf = RbDataFrame.read_hashes(data, infer_schema_length, schema_overrides)
         if column_names
           rbdf = _post_apply_columns(rbdf, column_names)
         end
         return rbdf
-      elsif data[0].is_a?(Array)
+      elsif data[0].is_a?(::Array)
         if orient.nil? && !columns.nil?
           orient = columns.length == data.length ? "col" : "row"
         end
@@ -4890,11 +5073,21 @@ module Polars
     end
 
     # @private
-    def self.series_to_rbdf(data, columns: nil)
-      if columns
-        raise Todo
+    def self.series_to_rbdf(data, schema: nil, schema_overrides: nil)
+      data_series = [data._s]
+      series_name = data_series.map(&:name)
+      column_names, schema_overrides = _unpack_schema(
+        schema || series_name, schema_overrides: schema_overrides, n_expected: 1
+      )
+      if schema_overrides.any?
+        new_dtype = schema_overrides.values[0]
+        if new_dtype != data.dtype
+          data_series[0] = data_series[0].cast(new_dtype, true)
+        end
       end
-      RbDataFrame.new([data._s])
+
+      data_series = _handle_columns_arg(data_series, columns: column_names)
+      RbDataFrame.new(data_series)
     end
 
     def wrap_ldf(ldf)
@@ -4966,7 +5159,7 @@ module Polars
 
     def _prepare_other_arg(other)
       if !other.is_a?(Series)
-        if other.is_a?(Array)
+        if other.is_a?(::Array)
           raise ArgumentError, "Operation not supported."
         end