polars-df 0.5.0-x86_64-darwin → 0.7.0-x86_64-darwin

data/lib/polars/data_frame.rb

@@ -20,15 +20,9 @@ module Polars
     #   this does not yield conclusive results, column orientation is used.
     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)
-        data = {}
-        result.columns.each_with_index do |k, i|
-          data[k] = result.rows.map { |r| r[i] }
-        end
+        raise ArgumentError, "Use read_database instead"
       end
 
       if data.nil?
@@ -36,7 +30,7 @@ module Polars
       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, schema: schema, schema_overrides: schema_overrides, nan_to_null: nan_to_null)
-      elsif data.is_a?(Array)
+      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, schema: schema, schema_overrides: schema_overrides)
@@ -116,7 +110,7 @@ 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"
@@ -590,7 +584,7 @@ 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
@@ -611,7 +605,7 @@ 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) }
@@ -641,7 +635,7 @@ 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)))
@@ -684,13 +678,13 @@ module Polars
       end
 
       if Utils.strlike?(key)
-        if value.is_a?(Array) || (defined?(Numo::NArray) && value.is_a?(Numo::NArray))
+        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)
+      elsif key.is_a?(::Array)
         row_selection, col_selection = key
 
         if Utils.strlike?(col_selection)
@@ -905,6 +899,7 @@ module Polars
     def write_csv(
       file = nil,
       has_header: true,
+      include_header: nil,
       sep: ",",
       quote: '"',
       batch_size: 1024,
@@ -914,6 +909,8 @@ module Polars
       float_precision: nil,
       null_value: nil
     )
+      include_header = has_header if include_header.nil?
+
       if sep.length > 1
         raise ArgumentError, "only single byte separator is allowed"
       elsif quote.length > 1
@@ -927,7 +924,7 @@ module Polars
         buffer.set_encoding(Encoding::BINARY)
         _df.write_csv(
           buffer,
-          has_header,
+          include_header,
           sep.ord,
           quote.ord,
           batch_size,
@@ -946,7 +943,7 @@ module Polars
 
       _df.write_csv(
         file,
-        has_header,
+        include_header,
         sep.ord,
         quote.ord,
         batch_size,
@@ -994,14 +991,21 @@ 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.
@@ -1144,22 +1148,8 @@ module Polars
     #   # │ b   ┆ 1   ┆ 2   ┆ 3   │
     #   # └─────┴─────┴─────┴─────┘
     def transpose(include_header: false, header_name: "column", column_names: nil)
-      df = _from_rbdf(_df.transpose(include_header, header_name))
-      if !column_names.nil?
-        names = []
-        n = df.width
-        if include_header
-          names << header_name
-          n -= 1
-        end
-
-        column_names = column_names.each
-        n.times do
-          names << column_names.next
-        end
-        df.columns = names
-      end
-      df
+      keep_names_as = include_header ? header_name : nil
+      _from_rbdf(_df.transpose(keep_names_as, column_names))
     end
 
     # Reverse the DataFrame.
@@ -1491,13 +1481,9 @@ 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.
@@ -1808,13 +1794,13 @@ module Polars
       _from_rbdf(_df.with_row_count(name, offset))
     end
 
-    # Start a groupby operation.
+    # Start a group by operation.
     #
     # @param by [Object]
     #   Column(s) to group by.
     # @param maintain_order [Boolean]
     #   Make sure that the order of the groups remain consistent. This is more
-    #   expensive than a default groupby. Note that this only works in expression
+    #   expensive than a default group by. Note that this only works in expression
     #   aggregations.
     #
     # @return [GroupBy]
@@ -1827,7 +1813,7 @@ module Polars
     #       "c" => [6, 5, 4, 3, 2, 1]
     #     }
     #   )
-    #   df.groupby("a").agg(Polars.col("b").sum).sort("a")
+    #   df.group_by("a").agg(Polars.col("b").sum).sort("a")
     #   # =>
     #   # shape: (3, 2)
     #   # ┌─────┬─────┐
@@ -1839,25 +1825,26 @@ module Polars
     #   # │ b   ┆ 11  │
     #   # │ c   ┆ 6   │
     #   # └─────┴─────┘
-    def groupby(by, maintain_order: false)
+    def group_by(by, maintain_order: false)
       if !Utils.bool?(maintain_order)
-        raise TypeError, "invalid input for groupby arg `maintain_order`: #{maintain_order}."
+        raise TypeError, "invalid input for group_by arg `maintain_order`: #{maintain_order}."
       end
       GroupBy.new(
-        _df,
+        self,
         by,
-        self.class,
         maintain_order: maintain_order
       )
     end
+    alias_method :groupby, :group_by
+    alias_method :group, :group_by
 
     # Create rolling groups based on a time column.
     #
     # Also works for index values of type `:i32` or `:i64`.
     #
-    # Different from a `dynamic_groupby` the windows are now determined by the
+    # Different from a `dynamic_group_by` the windows are now determined by the
     # individual values and are not of constant intervals. For constant intervals use
-    # *groupby_dynamic*
+    # *group_by_dynamic*
     #
     # The `period` and `offset` arguments are created either from a timedelta, or
     # by using the following string language:
@@ -1877,7 +1864,7 @@ module Polars
     # Or combine them:
     # "3d12h4m25s" # 3 days, 12 hours, 4 minutes, and 25 seconds
     #
-    # In case of a groupby_rolling on an integer column, the windows are defined by:
+    # In case of a group_by_rolling on an integer column, the windows are defined by:
     #
     # - **"1i"      # length 1**
     # - **"10i"     # length 10**
@@ -1888,7 +1875,7 @@ module Polars
     #   This column must be sorted in ascending order. If not the output will not
     #   make sense.
     #
-    #   In case of a rolling groupby on indices, dtype needs to be one of
+    #   In case of a rolling group by on indices, dtype needs to be one of
     #   `:i32`, `:i64`. Note that `:i32` gets temporarily cast to `:i64`, so if
     #   performance matters use an `:i64` column.
     # @param period [Object]
@@ -1899,6 +1886,12 @@ 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]
     #
@@ -1912,9 +1905,9 @@ 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(Polars::Datetime)
+    #     Polars.col("dt").str.strptime(Polars::Datetime).set_sorted
     #   )
-    #   df.groupby_rolling(index_column: "dt", period: "2d").agg(
+    #   df.group_by_rolling(index_column: "dt", period: "2d").agg(
     #     [
     #       Polars.sum("a").alias("sum_a"),
     #       Polars.min("a").alias("min_a"),
@@ -1935,20 +1928,22 @@ module Polars
     #   # │ 2020-01-03 19:45:32 ┆ 11    ┆ 2     ┆ 9     │
     #   # │ 2020-01-08 23:16:43 ┆ 1     ┆ 1     ┆ 1     │
     #   # └─────────────────────┴───────┴───────┴───────┘
-    def groupby_rolling(
+    def group_by_rolling(
       index_column:,
       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
+    alias_method :groupby_rolling, :group_by_rolling
 
     # Group based on a time value (or index value of type `:i32`, `:i64`).
     #
     # Time windows are calculated and rows are assigned to windows. Different from a
-    # normal groupby is that a row can be member of multiple groups. The time/index
+    # normal group by is that a row can be member of multiple groups. The time/index
     # window could be seen as a rolling window, with a window size determined by
     # dates/times/values instead of slots in the DataFrame.
     #
@@ -1976,7 +1971,7 @@ module Polars
     # Or combine them:
     # "3d12h4m25s" # 3 days, 12 hours, 4 minutes, and 25 seconds
     #
-    # In case of a groupby_dynamic on an integer column, the windows are defined by:
+    # In case of a group_by_dynamic on an integer column, the windows are defined by:
     #
     # - "1i"      # length 1
     # - "10i"     # length 10
@@ -1987,7 +1982,7 @@ module Polars
     #   This column must be sorted in ascending order. If not the output will not
     #   make sense.
     #
-    #   In case of a dynamic groupby on indices, dtype needs to be one of
+    #   In case of a dynamic group by on indices, dtype needs to be one of
     #   `:i32`, `:i64`. Note that `:i32` gets temporarily cast to `:i64`, so if
     #   performance matters use an `:i64` column.
     # @param every
@@ -2038,7 +2033,7 @@ module Polars
     #   # └─────────────────────┴─────┘
     #
     # @example Group by windows of 1 hour starting at 2021-12-16 00:00:00.
-    #   df.groupby_dynamic("time", every: "1h", closed: "right").agg(
+    #   df.group_by_dynamic("time", every: "1h", closed: "right").agg(
     #     [
     #       Polars.col("time").min.alias("time_min"),
     #       Polars.col("time").max.alias("time_max")
@@ -2058,7 +2053,7 @@ module Polars
     #   # └─────────────────────┴─────────────────────┴─────────────────────┘
     #
     # @example The window boundaries can also be added to the aggregation result.
-    #   df.groupby_dynamic(
+    #   df.group_by_dynamic(
     #     "time", every: "1h", include_boundaries: true, closed: "right"
     #   ).agg([Polars.col("time").count.alias("time_count")])
     #   # =>
@@ -2075,27 +2070,27 @@ module Polars
     #   # └─────────────────────┴─────────────────────┴─────────────────────┴────────────┘
     #
     # @example When closed="left", should not include right end of interval.
-    #   df.groupby_dynamic("time", every: "1h", closed: "left").agg(
+    #   df.group_by_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(
+    #   df.group_by_dynamic("time", every: "1h", closed: "both").agg(
     #     [Polars.col("time").count.alias("time_count")]
     #   )
     #   # =>
@@ -2112,7 +2107,7 @@ module Polars
     #   # │ 2021-12-16 03:00:00 ┆ 1          │
     #   # └─────────────────────┴────────────┘
     #
-    # @example Dynamic groupbys can also be combined with grouping on normal keys.
+    # @example Dynamic group bys can also be combined with grouping on normal keys.
     #   df = Polars::DataFrame.new(
     #     {
     #       "time" => Polars.date_range(
@@ -2123,7 +2118,7 @@ module Polars
     #       "groups" => ["a", "a", "a", "b", "b", "a", "a"]
     #     }
     #   )
-    #   df.groupby_dynamic(
+    #   df.group_by_dynamic(
     #     "time",
     #     every: "1h",
     #     closed: "both",
@@ -2146,20 +2141,20 @@ module Polars
     #   # │ b      ┆ 2021-12-16 02:00:00 ┆ 2021-12-16 03:00:00 ┆ 2021-12-16 02:00:00 ┆ 1          │
     #   # └────────┴─────────────────────┴─────────────────────┴─────────────────────┴────────────┘
     #
-    # @example Dynamic groupby on an index column.
+    # @example Dynamic group by on an index column.
     #   df = Polars::DataFrame.new(
     #     {
     #       "idx" => Polars.arange(0, 6, eager: true),
     #       "A" => ["A", "A", "B", "B", "B", "C"]
     #     }
     #   )
-    #   df.groupby_dynamic(
+    #   df.group_by_dynamic(
     #     "idx",
     #     every: "2i",
     #     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)
     #   # ┌─────────────────┬─────────────────┬─────┬─────────────────┐
@@ -2171,7 +2166,7 @@ module Polars
     #   # │ 2               ┆ 5               ┆ 2   ┆ ["B", "B", "C"] │
     #   # │ 4               ┆ 7               ┆ 4   ┆ ["C"]           │
     #   # └─────────────────┴─────────────────┴─────┴─────────────────┘
-    def groupby_dynamic(
+    def group_by_dynamic(
       index_column,
       every:,
       period: nil,
@@ -2195,6 +2190,7 @@ module Polars
         start_by
       )
     end
+    alias_method :groupby_dynamic, :group_by_dynamic
 
     # Upsample a DataFrame at a regular frequency.
     #
@@ -2242,7 +2238,7 @@ 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)
@@ -2360,7 +2356,7 @@ module Polars
     #       ],  # note record date: Jan 1st (sorted!)
     #       "gdp" => [4164, 4411, 4566, 4696]
     #     }
-    #   )
+    #   ).set_sorted("date")
     #   population = Polars::DataFrame.new(
     #     {
     #       "date" => [
@@ -2371,7 +2367,7 @@ 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"
     #   )
@@ -2674,7 +2670,7 @@ 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
@@ -2804,7 +2800,7 @@ 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)
@@ -3317,7 +3313,7 @@ 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
 
@@ -3426,36 +3422,38 @@ 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
 
     # Shift values by the given period.
     #
-    # @param periods [Integer]
+    # @param n [Integer]
     #   Number of places to shift (may be negative).
+    # @param fill_value [Object]
+    #  Fill the resulting null values with this value.
     #
     # @return [DataFrame]
     #
@@ -3493,8 +3491,8 @@ module Polars
     #   # │ 3    ┆ 8    ┆ c    │
     #   # │ null ┆ null ┆ null │
     #   # └──────┴──────┴──────┘
-    def shift(periods)
-      _from_rbdf(_df.shift(periods))
+    def shift(n, fill_value: nil)
+      lazy.shift(n, fill_value: fill_value).collect(_eager: true)
     end
 
     # Shift the values by a given period and fill the resulting null values.
@@ -3527,9 +3525,7 @@ module Polars
     #   # │ 2   ┆ 7   ┆ b   │
     #   # └─────┴─────┴─────┘
     def shift_and_fill(periods, fill_value)
-      lazy
-        .shift_and_fill(periods, fill_value)
-        .collect(no_optimization: true, string_cache: false)
+      shift(periods, fill_value: fill_value)
     end
 
     # Get a mask of all duplicated rows in this DataFrame.
@@ -3716,7 +3712,7 @@ 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
@@ -3780,7 +3776,7 @@ module Polars
       if axis == 0
         _from_rbdf(_df.max)
       elsif axis == 1
-        Utils.wrap_s(_df.hmax)
+        Utils.wrap_s(_df.max_horizontal)
       else
         raise ArgumentError, "Axis should be 0 or 1."
       end
@@ -3812,7 +3808,7 @@ module Polars
       if axis == 0
         _from_rbdf(_df.min)
       elsif axis == 1
-        Utils.wrap_s(_df.hmin)
+        Utils.wrap_s(_df.min_horizontal)
       else
         raise ArgumentError, "Axis should be 0 or 1."
       end
@@ -3861,7 +3857,7 @@ module Polars
       when 0
         _from_rbdf(_df.sum)
       when 1
-        Utils.wrap_s(_df.hsum(null_strategy))
+        Utils.wrap_s(_df.sum_horizontal(null_strategy))
       else
         raise ArgumentError, "Axis should be 0 or 1."
       end
@@ -3899,7 +3895,7 @@ module Polars
       when 0
         _from_rbdf(_df.mean)
       when 1
-        Utils.wrap_s(_df.hmean(null_strategy))
+        Utils.wrap_s(_df.mean_horizontal(null_strategy))
       else
         raise ArgumentError, "Axis should be 0 or 1."
       end
@@ -4097,11 +4093,11 @@ 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.
@@ -4189,7 +4185,7 @@ 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
@@ -4284,15 +4280,20 @@ module Polars
       end
 
       if n.nil? && !frac.nil?
+        frac = Series.new("frac", [frac]) unless frac.is_a?(Series)
+
         _from_rbdf(
-          _df.sample_frac(frac, with_replacement, shuffle, seed)
+          _df.sample_frac(frac._s, with_replacement, shuffle, seed)
         )
       end
 
       if n.nil?
         n = 1
       end
-      _from_rbdf(_df.sample_n(n, with_replacement, shuffle, seed))
+
+      n = Series.new("", [n]) unless n.is_a?(Series)
+
+      _from_rbdf(_df.sample_n(n._s, with_replacement, shuffle, seed))
     end
 
     # Apply a horizontal reduction on a DataFrame.
@@ -4591,7 +4592,7 @@ module Polars
     #
     # @example
     #   s = Polars::DataFrame.new({"a" => [1, 2, 3, 4], "b" => [5, 6, 7, 8]})
-    #   s.take_every(2)
+    #   s.gather_every(2)
     #   # =>
     #   # shape: (2, 2)
     #   # ┌─────┬─────┐
@@ -4602,9 +4603,10 @@ module Polars
     #   # │ 1   ┆ 5   │
     #   # │ 3   ┆ 7   │
     #   # └─────┴─────┘
-    def take_every(n)
-      select(Utils.col("*").take_every(n))
+    def gather_every(n)
+      select(Utils.col("*").gather_every(n))
     end
+    alias_method :take_every, :gather_every
 
     # Hash and combine the rows in this DataFrame.
     #
@@ -4661,16 +4663,16 @@ module Polars
     #   df.interpolate
     #   # =>
     #   # shape: (4, 3)
-    #   # ┌─────┬──────┬─────┐
-    #   # │ foo ┆ bar  ┆ baz │
-    #   # │ --- ┆ ---  ┆ --- │
-    #   # │ i64 ┆ i64  ┆ i64 │
-    #   # ╞═════╪══════╪═════╡
-    #   # │ 1   ┆ 6    ┆ 1   │
-    #   # │ 5   ┆ 7    ┆ 3   │
-    #   # │ 9   ┆ 9    ┆ 6   │
-    #   # │ 10  ┆ null ┆ 9   │
-    #   # └─────┴──────┴─────┘
+    #   # ┌──────┬──────┬──────────┐
+    #   # │ foo  ┆ bar  ┆ baz      │
+    #   # │ ---  ┆ ---  ┆ ---      │
+    #   # │ f64  ┆ f64  ┆ f64      │
+    #   # ╞══════╪══════╪══════════╡
+    #   # │ 1.0  ┆ 6.0  ┆ 1.0      │
+    #   # │ 5.0  ┆ 7.0  ┆ 3.666667 │
+    #   # │ 9.0  ┆ 9.0  ┆ 6.333333 │
+    #   # │ 10.0 ┆ null ┆ 9.0      │
+    #   # └──────┴──────┴──────────┘
     def interpolate
       select(Utils.col("*").interpolate)
     end
@@ -4758,6 +4760,38 @@ 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)
@@ -4910,8 +4944,8 @@ module Polars
           [lookup[col[0]] || col[0], col[1]]
         end
 
-      if schema_overrides
-        raise Todo
+      if schema_overrides && schema_overrides.any?
+        column_dtypes.merge!(schema_overrides)
       end
 
       column_dtypes.each do |col, dtype|
@@ -4967,7 +5001,7 @@ 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
@@ -5012,15 +5046,56 @@ module Polars
           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"
+          first_element = data[0]
+          row_types = first_element.filter_map { |value| value.class }.uniq
+          if row_types.include?(Integer) && row_types.include?(Float)
+            row_types.delete(Integer)
+          end
+          orient = row_types.length == 1 ? "col" : "row"
         end
 
         if orient == "row"
-          raise Todo
+          column_names, schema_overrides = _unpack_schema(
+            schema, schema_overrides: schema_overrides, n_expected: first_element.length
+          )
+          local_schema_override = (
+            schema_overrides.any? ? (raise Todo) : {}
+          )
+          if column_names.any? && first_element.length > 0 && first_element.length != column_names.length
+            raise ArgumentError, "the row data does not match the number of columns"
+          end
+
+          unpack_nested = false
+          local_schema_override.each do |col, tp|
+            raise Todo
+          end
+
+          if unpack_nested
+            raise Todo
+          else
+            rbdf = RbDataFrame.read_rows(
+              data,
+              infer_schema_length,
+              local_schema_override.any? ? local_schema_override : nil
+            )
+          end
+          if column_names.any? || schema_overrides.any?
+            rbdf = _post_apply_columns(
+              rbdf, column_names, schema_overrides: schema_overrides
+            )
+          end
+          return rbdf
         elsif orient == "col" || orient.nil?
-          raise Todo
+          column_names, schema_overrides = _unpack_schema(
+            schema, schema_overrides: schema_overrides, n_expected: data.length
+          )
+          data_series =
+            data.map.with_index do |element, i|
+              Series.new(column_names[i], element, dtype: schema_overrides[column_names[i]])._s
+            end
+          return RbDataFrame.new(data_series)
         else
           raise ArgumentError, "orient must be one of {{'col', 'row', nil}}, got #{orient} instead."
         end
@@ -5066,10 +5141,10 @@ module Polars
 
     def _compare_to_other_df(other, op)
       if columns != other.columns
-        raise ArgmentError, "DataFrame columns do not match"
+        raise ArgumentError, "DataFrame columns do not match"
       end
       if shape != other.shape
-        raise ArgmentError, "DataFrame dimensions do not match"
+        raise ArgumentError, "DataFrame dimensions do not match"
       end
 
       suffix = "__POLARS_CMP_OTHER"
@@ -5117,7 +5192,7 @@ 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