polars-df 0.6.0 → 0.8.0

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?
@@ -125,10 +119,10 @@ module Polars
 
       processed_null_values = Utils._process_null_values(null_values)
 
-      if columns.is_a?(String)
+      if columns.is_a?(::String)
         columns = [columns]
       end
-      if file.is_a?(String) && file.include?("*")
+      if file.is_a?(::String) && file.include?("*")
         dtypes_dict = nil
         if !dtype_list.nil?
           dtypes_dict = dtype_list.to_h
@@ -212,11 +206,11 @@ module Polars
       if Utils.pathlike?(source)
         source = Utils.normalise_filepath(source)
       end
-      if columns.is_a?(String)
+      if columns.is_a?(::String)
         columns = [columns]
       end
 
-      if source.is_a?(String) && source.include?("*") && Utils.local_file?(source)
+      if source.is_a?(::String) && source.include?("*") && Utils.local_file?(source)
         scan =
           Polars.scan_parquet(
             source,
@@ -275,11 +269,11 @@ module Polars
       if Utils.pathlike?(file)
         file = Utils.normalise_filepath(file)
       end
-      if columns.is_a?(String)
+      if columns.is_a?(::String)
         columns = [columns]
       end
 
-      if file.is_a?(String) && file.include?("*")
+      if file.is_a?(::String) && file.include?("*")
         raise Todo
       end
 
@@ -417,7 +411,7 @@ module Polars
     #     }
     #   )
     #   df.dtypes
-    #   # => [Polars::Int64, Polars::Float64, Polars::Utf8]
+    #   # => [Polars::Int64, Polars::Float64, Polars::String]
     def dtypes
       _df.dtypes
     end
@@ -435,7 +429,7 @@ module Polars
     #     }
     #   )
     #   df.schema
-    #   # => {"foo"=>Polars::Int64, "bar"=>Polars::Float64, "ham"=>Polars::Utf8}
+    #   # => {"foo"=>Polars::Int64, "bar"=>Polars::Float64, "ham"=>Polars::String}
     def schema
       columns.zip(dtypes).to_h
     end
@@ -595,13 +589,13 @@ module Polars
             return df.slice(row_selection, 1)
           end
           # df[2, "a"]
-          if col_selection.is_a?(String) || col_selection.is_a?(Symbol)
+          if col_selection.is_a?(::String) || col_selection.is_a?(Symbol)
             return self[col_selection][row_selection]
           end
         end
 
         # column selection can be "a" and ["a", "b"]
-        if col_selection.is_a?(String) || col_selection.is_a?(Symbol)
+        if col_selection.is_a?(::String) || col_selection.is_a?(Symbol)
           col_selection = [col_selection]
         end
 
@@ -627,7 +621,7 @@ module Polars
 
         # select single column
         # df["foo"]
-        if item.is_a?(String) || item.is_a?(Symbol)
+        if item.is_a?(::String) || item.is_a?(Symbol)
           return Utils.wrap_s(_df.column(item.to_s))
         end
 
@@ -653,7 +647,7 @@ module Polars
 
         if item.is_a?(Series)
           dtype = item.dtype
-          if dtype == Utf8
+          if dtype == String
             return _from_rbdf(_df.select(item))
           elsif dtype == UInt32
             return _from_rbdf(_df.take_with_series(item._s))
@@ -704,7 +698,7 @@ module Polars
         s[row_selection] = value
 
         if col_selection.is_a?(Integer)
-          replace_at_idx(col_selection, s)
+          replace_column(col_selection, s)
         elsif Utils.strlike?(col_selection)
           replace(col_selection, s)
         end
@@ -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,
@@ -1151,22 +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.
@@ -1239,7 +1222,7 @@ module Polars
     # @example
     #   df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
     #   s = Polars::Series.new("baz", [97, 98, 99])
-    #   df.insert_at_idx(1, s)
+    #   df.insert_column(1, s)
     #   # =>
     #   # shape: (3, 3)
     #   # ┌─────┬─────┬─────┐
@@ -1261,7 +1244,7 @@ module Polars
     #     }
     #   )
     #   s = Polars::Series.new("d", [-2.5, 15, 20.5, 0])
-    #   df.insert_at_idx(3, s)
+    #   df.insert_column(3, s)
     #   # =>
     #   # shape: (4, 4)
     #   # ┌─────┬──────┬───────┬──────┐
@@ -1274,13 +1257,14 @@ module Polars
     #   # │ 3   ┆ 10.0 ┆ false ┆ 20.5 │
     #   # │ 4   ┆ 13.0 ┆ true  ┆ 0.0  │
     #   # └─────┴──────┴───────┴──────┘
-    def insert_at_idx(index, series)
+    def insert_column(index, series)
       if index < 0
         index = columns.length + index
       end
-      _df.insert_at_idx(index, series._s)
+      _df.insert_column(index, series._s)
       self
     end
+    alias_method :insert_at_idx, :insert_column
 
     # Filter the rows in the DataFrame based on a predicate expression.
     #
@@ -1384,7 +1368,7 @@ module Polars
           ]
         )._df
       )
-      summary.insert_at_idx(
+      summary.insert_column(
         0,
         Polars::Series.new(
           "describe",
@@ -1405,11 +1389,12 @@ module Polars
     #   df = Polars::DataFrame.new(
     #     {"foo" => [1, 2, 3], "bar" => [6, 7, 8], "ham" => ["a", "b", "c"]}
     #   )
-    #   df.find_idx_by_name("ham")
+    #   df.get_column_index("ham")
     #   # => 2
-    def find_idx_by_name(name)
-      _df.find_idx_by_name(name)
+    def get_column_index(name)
+      _df.get_column_index(name)
     end
+    alias_method :find_idx_by_name, :get_column_index
 
     # Replace a column at an index location.
     #
@@ -1429,7 +1414,7 @@ module Polars
     #     }
     #   )
     #   s = Polars::Series.new("apple", [10, 20, 30])
-    #   df.replace_at_idx(0, s)
+    #   df.replace_column(0, s)
     #   # =>
     #   # shape: (3, 3)
     #   # ┌───────┬─────┬─────┐
@@ -1441,13 +1426,14 @@ module Polars
     #   # │ 20    ┆ 7   ┆ b   │
     #   # │ 30    ┆ 8   ┆ c   │
     #   # └───────┴─────┴─────┘
-    def replace_at_idx(index, series)
+    def replace_column(index, series)
       if index < 0
         index = columns.length + index
       end
-      _df.replace_at_idx(index, series._s)
+      _df.replace_column(index, series._s)
       self
     end
+    alias_method :replace_at_idx, :replace_column
 
     # Sort the DataFrame by column.
     #
@@ -1541,13 +1527,14 @@ module Polars
     #       "ham" => ["c", "b", "a"]
     #     }
     #   )
-    #   df1.frame_equal(df1)
+    #   df1.equals(df1)
     #   # => true
-    #   df1.frame_equal(df2)
+    #   df1.equals(df2)
     #   # => false
-    def frame_equal(other, null_equal: true)
-      _df.frame_equal(other._df, null_equal)
+    def equals(other, null_equal: true)
+      _df.equals(other._df, null_equal)
     end
+    alias_method :frame_equal, :equals
 
     # Replace a column by a new Series.
     #
@@ -1733,7 +1720,7 @@ module Polars
     #   # │ 3   ┆ 8   ┆ c   │
     #   # └─────┴─────┴─────┘
     def drop_nulls(subset: nil)
-      if subset.is_a?(String)
+      if subset.is_a?(::String)
         subset = [subset]
       end
       _from_rbdf(_df.drop_nulls(subset))
@@ -1811,13 +1798,13 @@ 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]
@@ -1830,7 +1817,7 @@ 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)
     #   # ┌─────┬─────┐
@@ -1842,25 +1829,26 @@ 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:
@@ -1880,7 +1868,7 @@ 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**
@@ -1891,7 +1879,7 @@ 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]
@@ -1923,7 +1911,7 @@ module Polars
     #   df = Polars::DataFrame.new({"dt" => dates, "a" => [3, 7, 5, 9, 2, 1]}).with_column(
     #     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"),
@@ -1944,7 +1932,7 @@ 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,
@@ -1954,11 +1942,12 @@ module Polars
     )
       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.
     #
@@ -1986,7 +1975,7 @@ 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
@@ -1997,7 +1986,7 @@ 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
@@ -2048,7 +2037,7 @@ 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")
@@ -2068,7 +2057,7 @@ 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")])
     #   # =>
@@ -2085,7 +2074,7 @@ 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").alias("time_agg_list")
@@ -2105,7 +2094,7 @@ module Polars
     #   # └─────────────────────┴────────────┴───────────────────────────────────┘
     #
     # @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")]
     #   )
     #   # =>
@@ -2122,7 +2111,7 @@ 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(
@@ -2133,7 +2122,7 @@ module Polars
     #       "groups" => ["a", "a", "a", "b", "b", "a", "a"]
     #     }
     #   )
-    #   df.groupby_dynamic(
+    #   df.group_by_dynamic(
     #     "time",
     #     every: "1h",
     #     closed: "both",
@@ -2156,14 +2145,14 @@ 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",
@@ -2181,7 +2170,7 @@ module Polars
     #   # │ 2               ┆ 5               ┆ 2   ┆ ["B", "B", "C"] │
     #   # │ 4               ┆ 7               ┆ 4   ┆ ["C"]           │
     #   # └─────────────────┴─────────────────┴─────┴─────────────────┘
-    def groupby_dynamic(
+    def group_by_dynamic(
       index_column,
       every:,
       period: nil,
@@ -2205,6 +2194,7 @@ module Polars
         start_by
       )
     end
+    alias_method :groupby_dynamic, :group_by_dynamic
 
     # Upsample a DataFrame at a regular frequency.
     #
@@ -2281,7 +2271,7 @@ module Polars
       if by.nil?
         by = []
       end
-      if by.is_a?(String)
+      if by.is_a?(::String)
         by = [by]
       end
       if offset.nil?
@@ -2475,17 +2465,17 @@ module Polars
     # @example
     #   df.join(other_df, on: "ham", how: "outer")
     #   # =>
-    #   # shape: (4, 4)
-    #   # ┌──────┬──────┬─────┬───────┐
-    #   # │ foo  ┆ bar  ┆ ham ┆ apple │
-    #   # │ ---  ┆ ---  ┆ --- ┆ ---   │
-    #   # │ i64  ┆ f64  ┆ str ┆ str   │
-    #   # ╞══════╪══════╪═════╪═══════╡
-    #   # │ 1    ┆ 6.0  ┆ a   ┆ x     │
-    #   # │ 2    ┆ 7.0  ┆ b   ┆ y     │
-    #   # │ null ┆ null ┆ d   ┆ z     │
-    #   # │ 3    ┆ 8.0  ┆ c   ┆ null  │
-    #   # └──────┴──────┴─────┴───────┘
+    #   # shape: (4, 5)
+    #   # ┌──────┬──────┬──────┬───────┬───────────┐
+    #   # │ foo  ┆ bar  ┆ ham  ┆ apple ┆ ham_right │
+    #   # │ ---  ┆ ---  ┆ ---  ┆ ---   ┆ ---       │
+    #   # │ i64  ┆ f64  ┆ str  ┆ str   ┆ str       │
+    #   # ╞══════╪══════╪══════╪═══════╪═══════════╡
+    #   # │ 1    ┆ 6.0  ┆ a    ┆ x     ┆ a         │
+    #   # │ 2    ┆ 7.0  ┆ b    ┆ y     ┆ b         │
+    #   # │ null ┆ null ┆ null ┆ z     ┆ d         │
+    #   # │ 3    ┆ 8.0  ┆ c    ┆ null  ┆ null      │
+    #   # └──────┴──────┴──────┴───────┴───────────┘
     #
     # @example
     #   df.join(other_df, on: "ham", how: "left")
@@ -3125,17 +3115,17 @@ module Polars
       sort_columns: false,
       separator: "_"
     )
-      if values.is_a?(String)
+      if values.is_a?(::String)
         values = [values]
       end
-      if index.is_a?(String)
+      if index.is_a?(::String)
         index = [index]
       end
-      if columns.is_a?(String)
+      if columns.is_a?(::String)
         columns = [columns]
       end
 
-      if aggregate_fn.is_a?(String)
+      if aggregate_fn.is_a?(::String)
         case aggregate_fn
         when "first"
           aggregate_expr = Polars.element.first._rbexpr
@@ -3220,10 +3210,10 @@ module Polars
     #   # │ z   ┆ c        ┆ 6     │
     #   # └─────┴──────────┴───────┘
     def melt(id_vars: nil, value_vars: nil, variable_name: nil, value_name: nil)
-      if value_vars.is_a?(String)
+      if value_vars.is_a?(::String)
         value_vars = [value_vars]
       end
-      if id_vars.is_a?(String)
+      if id_vars.is_a?(::String)
         id_vars = [id_vars]
       end
       if value_vars.nil?
@@ -3437,7 +3427,7 @@ module Polars
     #   # │ C   ┆ 2   ┆ l   │
     #   # └─────┴─────┴─────┘}
     def partition_by(groups, maintain_order: true, include_key: true, as_dict: false)
-      if groups.is_a?(String)
+      if groups.is_a?(::String)
         groups = [groups]
       elsif !groups.is_a?(::Array)
         groups = Array(groups)
@@ -3464,8 +3454,10 @@ module Polars
 
     # 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]
     #
@@ -3503,8 +3495,8 @@ 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.
@@ -3537,9 +3529,7 @@ 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.
@@ -3788,9 +3778,9 @@ module Polars
     #   # └─────┴─────┴─────┘
     def max(axis: 0)
       if axis == 0
-        _from_rbdf(_df.max)
+        lazy.max.collect(_eager: true)
       elsif axis == 1
-        Utils.wrap_s(_df.hmax)
+        Utils.wrap_s(_df.max_horizontal)
       else
         raise ArgumentError, "Axis should be 0 or 1."
       end
@@ -3820,9 +3810,9 @@ module Polars
     #   # └─────┴─────┴─────┘
     def min(axis: 0)
       if axis == 0
-        _from_rbdf(_df.min)
+        lazy.min.collect(_eager: true)
       elsif axis == 1
-        Utils.wrap_s(_df.hmin)
+        Utils.wrap_s(_df.min_horizontal)
       else
         raise ArgumentError, "Axis should be 0 or 1."
       end
@@ -3869,9 +3859,9 @@ module Polars
     def sum(axis: 0, null_strategy: "ignore")
       case axis
       when 0
-        _from_rbdf(_df.sum)
+        lazy.sum.collect(_eager: true)
       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
@@ -3907,9 +3897,9 @@ module Polars
     def mean(axis: 0, null_strategy: "ignore")
       case axis
       when 0
-        _from_rbdf(_df.mean)
+        lazy.mean.collect(_eager: true)
       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
@@ -3953,7 +3943,7 @@ module Polars
     #   # │ 0.816497 ┆ 0.816497 ┆ null │
     #   # └──────────┴──────────┴──────┘
     def std(ddof: 1)
-      _from_rbdf(_df.std(ddof))
+      lazy.std(ddof: ddof).collect(_eager: true)
     end
 
     # Aggregate the columns of this DataFrame to their variance value.
@@ -3994,7 +3984,7 @@ module Polars
     #   # │ 0.666667 ┆ 0.666667 ┆ null │
     #   # └──────────┴──────────┴──────┘
     def var(ddof: 1)
-      _from_rbdf(_df.var(ddof))
+      lazy.var(ddof: ddof).collect(_eager: true)
     end
 
     # Aggregate the columns of this DataFrame to their median value.
@@ -4020,7 +4010,7 @@ module Polars
     #   # │ 2.0 ┆ 7.0 ┆ null │
     #   # └─────┴─────┴──────┘
     def median
-      _from_rbdf(_df.median)
+      lazy.median.collect(_eager: true)
     end
 
     # Aggregate the columns of this DataFrame to their product values.
@@ -4077,7 +4067,7 @@ module Polars
     #   # │ 2.0 ┆ 7.0 ┆ null │
     #   # └─────┴─────┴──────┘
     def quantile(quantile, interpolation: "nearest")
-      _from_rbdf(_df.quantile(quantile, interpolation))
+      lazy.quantile(quantile, interpolation: interpolation).collect(_eager: true)
     end
 
     # Get one hot encoded dummy variables.
@@ -4108,7 +4098,7 @@ module Polars
     #   # │ 0     ┆ 1     ┆ 0     ┆ 1     ┆ 0     ┆ 1     │
     #   # └───────┴───────┴───────┴───────┴───────┴───────┘
     def to_dummies(columns: nil, separator: "_", drop_first: false)
-      if columns.is_a?(String)
+      if columns.is_a?(::String)
         columns = [columns]
       end
       _from_rbdf(_df.to_dummies(columns, separator, drop_first))
@@ -4294,15 +4284,20 @@ 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.
@@ -4601,7 +4596,7 @@ 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)
     #   # ┌─────┬─────┐
@@ -4612,9 +4607,10 @@ module Polars
     #   # │ 1   ┆ 5   │
     #   # │ 3   ┆ 7   │
     #   # └─────┴─────┘
-    def take_every(n)
-      select(Utils.col("*").take_every(n))
+    def gather_every(n, offset = 0)
+      select(Utils.col("*").gather_every(n, offset))
     end
+    alias_method :take_every, :gather_every
 
     # Hash and combine the rows in this DataFrame.
     #
@@ -4671,16 +4667,16 @@ 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
@@ -4762,7 +4758,7 @@ module Polars
     #   # │ bar    ┆ 2   ┆ b   ┆ null ┆ [3]       ┆ womp  │
     #   # └────────┴─────┴─────┴──────┴───────────┴───────┘
     def unnest(names)
-      if names.is_a?(String)
+      if names.is_a?(::String)
         names = [names]
       end
       _from_rbdf(_df.unnest(names))
@@ -4875,10 +4871,10 @@ module Polars
             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) }
+              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)
+              updated_data[name] = Series.new(::String.new(name), [val], dtype: dtype).extend_constant(val, array_len - 1)
             else
               raise Todo
             end
@@ -4935,7 +4931,7 @@ module Polars
       end
       column_names =
         (schema || []).map.with_index do |col, i|
-          if col.is_a?(String)
+          if col.is_a?(::String)
             col || "column_#{i}"
           else
             col[0]
@@ -4948,12 +4944,12 @@ module Polars
       lookup = column_names.zip(lookup_names || []).to_h
 
       column_dtypes =
-        (schema || []).select { |col| !col.is_a?(String) && col[1] }.to_h do |col|
+        (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
+      if schema_overrides && schema_overrides.any?
+        column_dtypes.merge!(schema_overrides)
       end
 
       column_dtypes.each do |col, dtype|
@@ -5056,13 +5052,54 @@ module Polars
         return rbdf
       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
@@ -5108,10 +5145,10 @@ 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"