polars-df 0.21.0-aarch64-linux → 0.22.0-aarch64-linux

data/lib/polars/lazy_frame.rb

@@ -27,9 +27,6 @@ module Polars
       ldf
     end
 
-    # def self.from_json
-    # end
-
     # Read a logical plan from a JSON file to construct a LazyFrame.
     #
     # @param file [String]
@@ -41,7 +38,49 @@ module Polars
         file = Utils.normalize_filepath(file)
       end
 
-      Utils.wrap_ldf(RbLazyFrame.read_json(file))
+      Utils.wrap_ldf(RbLazyFrame.deserialize_json(file))
+    end
+
+    # Read a logical plan from a file to construct a LazyFrame.
+    #
+    # @param source [Object]
+    #   Path to a file or a file-like object (by file-like object, we refer to
+    #   objects that have a `read` method, such as a file handler or `StringIO`).
+    #
+    # @return [LazyFrame]
+    #
+    # @note
+    #   This function uses marshaling if the logical plan contains Ruby UDFs,
+    #   and as such inherits the security implications. Deserializing can execute
+    #   arbitrary code, so it should only be attempted on trusted data.
+    #
+    # @note
+    #   Serialization is not stable across Polars versions: a LazyFrame serialized
+    #   in one Polars version may not be deserializable in another Polars version.
+    #
+    # @example
+    #   lf = Polars::LazyFrame.new({"a" => [1, 2, 3]}).sum
+    #   bytes = lf.serialize
+    #   Polars::LazyFrame.deserialize(StringIO.new(bytes)).collect
+    #   # =>
+    #   # shape: (1, 1)
+    #   # ┌─────┐
+    #   # │ a   │
+    #   # │ --- │
+    #   # │ i64 │
+    #   # ╞═════╡
+    #   # │ 6   │
+    #   # └─────┘
+    def self.deserialize(source)
+      raise Todo unless RbLazyFrame.respond_to?(:deserialize_binary)
+
+      if Utils.pathlike?(source)
+        source = Utils.normalize_filepath(source)
+      end
+
+      deserializer = RbLazyFrame.method(:deserialize_binary)
+
+      _from_rbldf(deserializer.(source))
     end
 
     # Get or set column names.
@@ -151,6 +190,38 @@ module Polars
       nil
     end
 
+    # Serialize the logical plan of this LazyFrame to a file or string.
+    #
+    # @param file [Object]
+    #   File path to which the result should be written. If set to `nil`
+    #   (default), the output is returned as a string instead.
+    #
+    # @return [Object]
+    #
+    # @note
+    #   Serialization is not stable across Polars versions: a LazyFrame serialized
+    #   in one Polars version may not be deserializable in another Polars version.
+    #
+    # @example Serialize the logical plan into a binary representation.
+    #   lf = Polars::LazyFrame.new({"a" => [1, 2, 3]}).sum
+    #   bytes = lf.serialize
+    #   Polars::LazyFrame.deserialize(StringIO.new(bytes)).collect
+    #   # =>
+    #   # shape: (1, 1)
+    #   # ┌─────┐
+    #   # │ a   │
+    #   # │ --- │
+    #   # │ i64 │
+    #   # ╞═════╡
+    #   # │ 6   │
+    #   # └─────┘
+    def serialize(file = nil)
+      raise Todo unless _ldf.respond_to?(:serialize_binary)
+
+      serializer = _ldf.method(:serialize_binary)
+      Utils.serialize_polars_object(serializer, file)
+    end
+
     # Offers a structured way to apply a sequence of user-defined functions (UDFs).
     #
     # @param func [Object]
@@ -288,6 +359,201 @@ module Polars
       )
     end
 
+    # Execute a SQL query against the LazyFrame.
+    #
+    # @note
+    #   This functionality is considered **unstable**, although it is close to
+    #   being considered stable. It may be changed at any point without it being
+    #   considered a breaking change.
+    #
+    # @param query [String]
+    #   SQL query to execute.
+    # @param table_name [String]
+    #   Optionally provide an explicit name for the table that represents the
+    #   calling frame (defaults to "self").
+    #
+    # @return [Expr]
+    #
+    # @note
+    #   * The calling frame is automatically registered as a table in the SQL context
+    #     under the name "self". If you want access to the DataFrames and LazyFrames
+    #     found in the current globals, use the top-level `Polars.sql`.
+    #   * More control over registration and execution behaviour is available by
+    #     using the `SQLContext` object.
+    #
+    # @example Query the LazyFrame using SQL:
+    #   lf1 = Polars::LazyFrame.new({"a" => [1, 2, 3], "b" => [6, 7, 8], "c" => ["z", "y", "x"]})
+    #   lf2 = Polars::LazyFrame.new({"a" => [3, 2, 1], "d" => [125, -654, 888]})
+    #   lf1.sql("SELECT c, b FROM self WHERE a > 1").collect
+    #   # =>
+    #   # shape: (2, 2)
+    #   # ┌─────┬─────┐
+    #   # │ c   ┆ b   │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ y   ┆ 7   │
+    #   # │ x   ┆ 8   │
+    #   # └─────┴─────┘
+    #
+    # @example Apply SQL transforms (aliasing "self" to "frame") then filter natively (you can freely mix SQL and native operations):
+    #   lf1.sql(
+    #     "
+    #       SELECT
+    #           a,
+    #           (a % 2 == 0) AS a_is_even,
+    #           (b::float4 / 2) AS \"b/2\",
+    #           CONCAT_WS(':', c, c, c) AS c_c_c
+    #       FROM frame
+    #       ORDER BY a
+    #     ",
+    #     table_name: "frame",
+    #   ).filter(~Polars.col("c_c_c").str.starts_with("x")).collect
+    #   # =>
+    #   # shape: (2, 4)
+    #   # ┌─────┬───────────┬─────┬───────┐
+    #   # │ a   ┆ a_is_even ┆ b/2 ┆ c_c_c │
+    #   # │ --- ┆ ---       ┆ --- ┆ ---   │
+    #   # │ i64 ┆ bool      ┆ f32 ┆ str   │
+    #   # ╞═════╪═══════════╪═════╪═══════╡
+    #   # │ 1   ┆ false     ┆ 3.0 ┆ z:z:z │
+    #   # │ 2   ┆ true      ┆ 3.5 ┆ y:y:y │
+    #   # └─────┴───────────┴─────┴───────┘
+    def sql(query, table_name: "self")
+      ctx = Polars::SQLContext.new
+      name = table_name || "self"
+      ctx.register(name, self)
+      ctx.execute(query)
+    end
+
+    # Return the `k` largest rows.
+    #
+    # Non-null elements are always preferred over null elements, regardless of
+    # the value of `reverse`. The output is not guaranteed to be in any
+    # particular order, call :func:`sort` after this function if you wish the
+    # output to be sorted.
+    #
+    # @param k [Integer]
+    #   Number of rows to return.
+    # @param by [Object]
+    #   Column(s) used to determine the top rows.
+    #   Accepts expression input. Strings are parsed as column names.
+    # @param reverse [Object]
+    #   Consider the `k` smallest elements of the `by` column(s) (instead of the `k`
+    #   largest). This can be specified per column by passing a sequence of
+    #   booleans.
+    #
+    # @return [LazyFrame]
+    #
+    # @example Get the rows which contain the 4 largest values in column b.
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "a" => ["a", "b", "a", "b", "b", "c"],
+    #       "b" => [2, 1, 1, 3, 2, 1]
+    #     }
+    #   )
+    #   lf.top_k(4, by: "b").collect
+    #   # =>
+    #   # shape: (4, 2)
+    #   # ┌─────┬─────┐
+    #   # │ a   ┆ b   │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ b   ┆ 3   │
+    #   # │ a   ┆ 2   │
+    #   # │ b   ┆ 2   │
+    #   # │ b   ┆ 1   │
+    #   # └─────┴─────┘
+    #
+    # @example Get the rows which contain the 4 largest values when sorting on column b and a.
+    #   lf.top_k(4, by: ["b", "a"]).collect
+    #   # =>
+    #   # shape: (4, 2)
+    #   # ┌─────┬─────┐
+    #   # │ a   ┆ b   │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ b   ┆ 3   │
+    #   # │ b   ┆ 2   │
+    #   # │ a   ┆ 2   │
+    #   # │ c   ┆ 1   │
+    #   # └─────┴─────┘
+    def top_k(
+      k,
+      by:,
+      reverse: false
+    )
+      by = Utils.parse_into_list_of_expressions(by)
+      reverse = Utils.extend_bool(reverse, by.length, "reverse", "by")
+      _from_rbldf(_ldf.top_k(k, by, reverse))
+    end
+
+    # Return the `k` smallest rows.
+    #
+    # Non-null elements are always preferred over null elements, regardless of
+    # the value of `reverse`. The output is not guaranteed to be in any
+    # particular order, call :func:`sort` after this function if you wish the
+    # output to be sorted.
+    #
+    # @param k [Integer]
+    #   Number of rows to return.
+    # @param by [Object]
+    #   Column(s) used to determine the bottom rows.
+    #   Accepts expression input. Strings are parsed as column names.
+    # @param reverse [Object]
+    #   Consider the `k` largest elements of the `by` column(s) (instead of the `k`
+    #   smallest). This can be specified per column by passing a sequence of
+    #   booleans.
+    #
+    # @return [LazyFrame]
+    #
+    # @example Get the rows which contain the 4 smallest values in column b.
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "a" => ["a", "b", "a", "b", "b", "c"],
+    #       "b" => [2, 1, 1, 3, 2, 1]
+    #     }
+    #   )
+    #   lf.bottom_k(4, by: "b").collect
+    #   # =>
+    #   # shape: (4, 2)
+    #   # ┌─────┬─────┐
+    #   # │ a   ┆ b   │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ b   ┆ 1   │
+    #   # │ a   ┆ 1   │
+    #   # │ c   ┆ 1   │
+    #   # │ a   ┆ 2   │
+    #   # └─────┴─────┘
+    #
+    # @example Get the rows which contain the 4 smallest values when sorting on column a and b.
+    #   lf.bottom_k(4, by: ["a", "b"]).collect
+    #   # =>
+    #   # shape: (4, 2)
+    #   # ┌─────┬─────┐
+    #   # │ a   ┆ b   │
+    #   # │ --- ┆ --- │
+    #   # │ str ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ a   ┆ 1   │
+    #   # │ a   ┆ 2   │
+    #   # │ b   ┆ 1   │
+    #   # │ b   ┆ 2   │
+    #   # └─────┴─────┘
+    def bottom_k(
+      k,
+      by:,
+      reverse: false
+    )
+      by = Utils.parse_into_list_of_expressions(by)
+      reverse = Utils.extend_bool(reverse, by.length, "reverse", "by")
+      _from_rbldf(_ldf.bottom_k(k, by, reverse))
+    end
+
     # def profile
     # end
 
@@ -379,6 +645,41 @@ module Polars
       Utils.wrap_df(ldf.collect)
     end
 
+    # Resolve the schema of this LazyFrame.
+    #
+    # @return [Schema]
+    #
+    # @example Determine the schema.
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "foo" => [1, 2, 3],
+    #       "bar" => [6.0, 7.0, 8.0],
+    #       "ham" => ["a", "b", "c"]
+    #     }
+    #   )
+    #   lf.collect_schema
+    #   # => Polars::Schema({"foo"=>Polars::Int64, "bar"=>Polars::Float64, "ham"=>Polars::String})
+    #
+    # @example Access various properties of the schema.
+    #   schema = lf.collect_schema
+    #   schema["bar"]
+    #   # => Polars::Float64
+    #
+    # @example
+    #   schema.names
+    #   # => ["foo", "bar", "ham"]
+    #
+    # @example
+    #   schema.dtypes
+    #   # => [Polars::Int64, Polars::Float64, Polars::String]
+    #
+    # @example
+    #   schema.length
+    #   # => 3
+    def collect_schema
+      Schema.new(_ldf.collect_schema, check_dtypes: false)
+    end
+
     # Persists a LazyFrame at the provided path.
     #
     # This allows streaming results that are larger than RAM to be written to disk.
@@ -544,6 +845,21 @@ module Polars
     # @param maintain_order [Boolean]
     #   Maintain the order in which data is processed.
     #   Setting this to `false` will  be slightly faster.
+    # @param storage_options [String]
+    #   Options that indicate how to connect to a cloud provider.
+    #
+    #   The cloud providers currently supported are AWS, GCP, and Azure.
+    #   See supported keys here:
+    #
+    #   * [aws](https://docs.rs/object_store/latest/object_store/aws/enum.AmazonS3ConfigKey.html)
+    #   * [gcp](https://docs.rs/object_store/latest/object_store/gcp/enum.GoogleConfigKey.html)
+    #   * [azure](https://docs.rs/object_store/latest/object_store/azure/enum.AzureConfigKey.html)
+    #   * Hugging Face (`hf://`): Accepts an API key under the `token` parameter: `{'token': '...'}`, or by setting the `HF_TOKEN` environment variable.
+    #
+    #   If `storage_options` is not provided, Polars will try to infer the
+    #   information from environment variables.
+    # @param retries [Integer]
+    #   Number of retries if accessing a cloud instance fails.
     # @param type_coercion [Boolean]
     #   Do type coercion optimization.
     # @param predicate_pushdown [Boolean]
@@ -576,6 +892,8 @@ module Polars
       path,
       compression: "zstd",
       maintain_order: true,
+      storage_options: nil,
+      retries: 2,
       type_coercion: true,
       predicate_pushdown: true,
       projection_pushdown: true,
@@ -586,10 +904,6 @@ module Polars
       mkdir: false,
       lazy: false
     )
-      # TODO support storage options in Rust
-      storage_options = nil
-      retries = 2
-
       lf = _set_sink_optimizations(
         type_coercion: type_coercion,
         predicate_pushdown: predicate_pushdown,
@@ -1147,6 +1461,140 @@ module Polars
       )
     end
 
+    # Remove rows, dropping those that match the given predicate expression(s).
+    #
+    # The original order of the remaining rows is preserved.
+    #
+    # Rows where the filter predicate does not evaluate to true are retained
+    # (this includes rows where the predicate evaluates as `null`).
+    #
+    # @param predicates [Array]
+    #   Expression that evaluates to a boolean Series.
+    # @param constraints [Hash]
+    #   Column filters; use `name = value` to filter columns using the supplied
+    #   value. Each constraint behaves the same as `Polars.col(name).eq(value)`,
+    #   and is implicitly joined with the other filter conditions using `&`.
+    #
+    # @return [LazyFrame]
+    #
+    # @example Remove rows matching a condition:
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "foo" => [2, 3, nil, 4, 0],
+    #       "bar" => [5, 6, nil, nil, 0],
+    #       "ham" => ["a", "b", nil, "c", "d"]
+    #     }
+    #   )
+    #   lf.remove(
+    #     Polars.col("bar") >= 5
+    #   ).collect
+    #   # =>
+    #   # shape: (3, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ i64  ┆ i64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ null ┆ null ┆ null │
+    #   # │ 4    ┆ null ┆ c    │
+    #   # │ 0    ┆ 0    ┆ d    │
+    #   # └──────┴──────┴──────┘
+    #
+    # @example Discard rows based on multiple conditions, combined with and/or operators:
+    #   lf.remove(
+    #     (Polars.col("foo") >= 0) & (Polars.col("bar") >= 0)
+    #   ).collect
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ i64  ┆ i64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ null ┆ null ┆ null │
+    #   # │ 4    ┆ null ┆ c    │
+    #   # └──────┴──────┴──────┘
+    #
+    # @example
+    #   lf.remove(
+    #     (Polars.col("foo") >= 0) | (Polars.col("bar") >= 0)
+    #   ).collect
+    #   # =>
+    #   # shape: (1, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ i64  ┆ i64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ null ┆ null ┆ null │
+    #   # └──────┴──────┴──────┘
+    #
+    # @example Provide multiple constraints using `*args` syntax:
+    #   lf.remove(
+    #     Polars.col("ham").is_not_null,
+    #     Polars.col("bar") >= 0
+    #   ).collect
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ i64  ┆ i64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ null ┆ null ┆ null │
+    #   # │ 4    ┆ null ┆ c    │
+    #   # └──────┴──────┴──────┘
+    #
+    # @example Provide constraints(s) using `**kwargs` syntax:
+    #   lf.remove(foo: 0, bar: 0).collect
+    #   # =>
+    #   # shape: (4, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ i64  ┆ i64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ 2    ┆ 5    ┆ a    │
+    #   # │ 3    ┆ 6    ┆ b    │
+    #   # │ null ┆ null ┆ null │
+    #   # │ 4    ┆ null ┆ c    │
+    #   # └──────┴──────┴──────┘
+    #
+    # @example Remove rows by comparing two columns against each other; in this case, we remove rows where the two columns are not equal (using `ne_missing` to ensure that null values compare equal):
+    #   lf.remove(
+    #     Polars.col("foo").ne_missing(Polars.col("bar"))
+    #   ).collect
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ i64  ┆ i64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ null ┆ null ┆ null │
+    #   # │ 0    ┆ 0    ┆ d    │
+    #   # └──────┴──────┴──────┘
+    def remove(
+      *predicates,
+      **constraints
+    )
+      if constraints.empty?
+        # early-exit conditions (exclude/include all rows)
+        if predicates.empty? || (predicates.length == 1 && predicates[0].is_a?(TrueClass))
+          return clear
+        end
+        if predicates.length == 1 && predicates[0].is_a?(FalseClass)
+          return dup
+        end
+      end
+
+      _filter(
+        predicates: predicates,
+        constraints: constraints,
+        invert: true
+      )
+    end
+
     # Select columns from this DataFrame.
     #
     # @param exprs [Array]
@@ -1244,6 +1692,29 @@ module Polars
       _from_rbldf(_ldf.select(rbexprs))
     end
 
+    # Select columns from this LazyFrame.
+    #
+    # This will run all expression sequentially instead of in parallel.
+    # Use this when the work per expression is cheap.
+    #
+    # @param exprs [Array]
+    #   Column(s) to select, specified as positional arguments.
+    #   Accepts expression input. Strings are parsed as column names,
+    #   other non-expression inputs are parsed as literals.
+    # @param named_exprs [Hash]
+    #   Additional columns to select, specified as keyword arguments.
+    #   The columns will be renamed to the keyword used.
+    #
+    # @return [LazyFrame]
+    def select_seq(*exprs, **named_exprs)
+      structify = ENV.fetch("POLARS_AUTO_STRUCTIFY", 0).to_i != 0
+
+      rbexprs = Utils.parse_into_list_of_expressions(
+        *exprs, **named_exprs, __structify: structify
+      )
+      _from_rbldf(_ldf.select_seq(rbexprs))
+    end
+
     # Start a group by operation.
     #
     # @param by [Array]
@@ -1440,9 +1911,9 @@ module Polars
     # @param every [Object]
     #   Interval of the window.
     # @param period [Object]
-    #   Length of the window, if None it is equal to 'every'.
+    #   Length of the window, if nil it is equal to 'every'.
     # @param offset [Object]
-    #   Offset of the window if None and period is None it will be equal to negative
+    #   Offset of the window if nil and period is nil it will be equal to negative
     #   `every`.
     # @param truncate [Boolean]
     #   Truncate the time value to the window lower bound.
@@ -1714,7 +2185,7 @@ module Polars
     #   Join column of the right DataFrame.
     # @param on [String]
     #   Join column of both DataFrames. If set, `left_on` and `right_on` should be
-    #   None.
+    #   nil.
     # @param by_left [Object]
     #   Join on these columns before doing asof join.
     # @param by_right [Object]
@@ -2039,7 +2510,7 @@ module Polars
     #   Join column of the right DataFrame.
     # @param on Object
     #   Join column of both DataFrames. If set, `left_on` and `right_on` should be
-    #   None.
+    #   nil.
     # @param how ["inner", "left", "full", "semi", "anti", "cross"]
     #   Join strategy.
     # @param suffix [String]
@@ -2234,6 +2705,103 @@ module Polars
       )
     end
 
+    # Perform a join based on one or multiple (in)equality predicates.
+    #
+    # This performs an inner join, so only rows where all predicates are true
+    # are included in the result, and a row from either DataFrame may be included
+    # multiple times in the result.
+    #
+    # @note
+    #   The row order of the input DataFrames is not preserved.
+    #
+    # @note
+    #   This functionality is experimental. It may be
+    #   changed at any point without it being considered a breaking change.
+    #
+    # @param other [Object]
+    #   DataFrame to join with.
+    # @param predicates [Object]
+    #   (In)Equality condition to join the two tables on.
+    #   When a column name occurs in both tables, the proper suffix must
+    #   be applied in the predicate.
+    # @param suffix [String]
+    #   Suffix to append to columns with a duplicate name.
+    #
+    # @return [LazyFrame]
+    #
+    # @example Join two lazyframes together based on two predicates which get AND-ed together.
+    #   east = Polars::LazyFrame.new(
+    #     {
+    #       "id" => [100, 101, 102],
+    #       "dur" => [120, 140, 160],
+    #       "rev" => [12, 14, 16],
+    #       "cores" => [2, 8, 4]
+    #     }
+    #   )
+    #   west = Polars::LazyFrame.new(
+    #     {
+    #       "t_id" => [404, 498, 676, 742],
+    #       "time" => [90, 130, 150, 170],
+    #       "cost" => [9, 13, 15, 16],
+    #       "cores" => [4, 2, 1, 4]
+    #     }
+    #   )
+    #   east.join_where(
+    #     west,
+    #     Polars.col("dur") < Polars.col("time"),
+    #     Polars.col("rev") < Polars.col("cost")
+    #   ).collect
+    #   # =>
+    #   # shape: (5, 8)
+    #   # ┌─────┬─────┬─────┬───────┬──────┬──────┬──────┬─────────────┐
+    #   # │ id  ┆ dur ┆ rev ┆ cores ┆ t_id ┆ time ┆ cost ┆ cores_right │
+    #   # │ --- ┆ --- ┆ --- ┆ ---   ┆ ---  ┆ ---  ┆ ---  ┆ ---         │
+    #   # │ i64 ┆ i64 ┆ i64 ┆ i64   ┆ i64  ┆ i64  ┆ i64  ┆ i64         │
+    #   # ╞═════╪═════╪═════╪═══════╪══════╪══════╪══════╪═════════════╡
+    #   # │ 100 ┆ 120 ┆ 12  ┆ 2     ┆ 498  ┆ 130  ┆ 13   ┆ 2           │
+    #   # │ 100 ┆ 120 ┆ 12  ┆ 2     ┆ 676  ┆ 150  ┆ 15   ┆ 1           │
+    #   # │ 100 ┆ 120 ┆ 12  ┆ 2     ┆ 742  ┆ 170  ┆ 16   ┆ 4           │
+    #   # │ 101 ┆ 140 ┆ 14  ┆ 8     ┆ 676  ┆ 150  ┆ 15   ┆ 1           │
+    #   # │ 101 ┆ 140 ┆ 14  ┆ 8     ┆ 742  ┆ 170  ┆ 16   ┆ 4           │
+    #   # └─────┴─────┴─────┴───────┴──────┴──────┴──────┴─────────────┘
+    #
+    # @example To OR them together, use a single expression and the `|` operator.
+    #   east.join_where(
+    #     west,
+    #     (Polars.col("dur") < Polars.col("time")) | (Polars.col("rev") < Polars.col("cost"))
+    #   ).collect
+    #   # =>
+    #   # shape: (6, 8)
+    #   # ┌─────┬─────┬─────┬───────┬──────┬──────┬──────┬─────────────┐
+    #   # │ id  ┆ dur ┆ rev ┆ cores ┆ t_id ┆ time ┆ cost ┆ cores_right │
+    #   # │ --- ┆ --- ┆ --- ┆ ---   ┆ ---  ┆ ---  ┆ ---  ┆ ---         │
+    #   # │ i64 ┆ i64 ┆ i64 ┆ i64   ┆ i64  ┆ i64  ┆ i64  ┆ i64         │
+    #   # ╞═════╪═════╪═════╪═══════╪══════╪══════╪══════╪═════════════╡
+    #   # │ 100 ┆ 120 ┆ 12  ┆ 2     ┆ 498  ┆ 130  ┆ 13   ┆ 2           │
+    #   # │ 100 ┆ 120 ┆ 12  ┆ 2     ┆ 676  ┆ 150  ┆ 15   ┆ 1           │
+    #   # │ 100 ┆ 120 ┆ 12  ┆ 2     ┆ 742  ┆ 170  ┆ 16   ┆ 4           │
+    #   # │ 101 ┆ 140 ┆ 14  ┆ 8     ┆ 676  ┆ 150  ┆ 15   ┆ 1           │
+    #   # │ 101 ┆ 140 ┆ 14  ┆ 8     ┆ 742  ┆ 170  ┆ 16   ┆ 4           │
+    #   # │ 102 ┆ 160 ┆ 16  ┆ 4     ┆ 742  ┆ 170  ┆ 16   ┆ 4           │
+    #   # └─────┴─────┴─────┴───────┴──────┴──────┴──────┴─────────────┘
+    def join_where(
+      other,
+      *predicates,
+      suffix: "_right"
+    )
+      Utils.require_same_type(self, other)
+
+      rbexprs = Utils.parse_into_list_of_expressions(*predicates)
+
+      _from_rbldf(
+        _ldf.join_where(
+          other._ldf,
+          rbexprs,
+          suffix
+        )
+      )
+    end
+
     # Add or overwrite multiple columns in a DataFrame.
     #
     # @param exprs [Object]
@@ -2279,6 +2847,34 @@ module Polars
       _from_rbldf(_ldf.with_columns(rbexprs))
     end
 
+    # Add columns to this LazyFrame.
+    #
+    # Added columns will replace existing columns with the same name.
+    #
+    # This will run all expression sequentially instead of in parallel.
+    # Use this when the work per expression is cheap.
+    #
+    # @param exprs [Array]
+    #   Column(s) to add, specified as positional arguments.
+    #   Accepts expression input. Strings are parsed as column names, other
+    #   non-expression inputs are parsed as literals.
+    # @param named_exprs [Hash]
+    #   Additional columns to add, specified as keyword arguments.
+    #   The columns will be renamed to the keyword used.
+    #
+    # @return [LazyFrame]
+    def with_columns_seq(
+      *exprs,
+      **named_exprs
+    )
+      structify = ENV.fetch("POLARS_AUTO_STRUCTIFY", 0).to_i != 0
+
+      rbexprs = Utils.parse_into_list_of_expressions(
+        *exprs, **named_exprs, __structify: structify
+      )
+      _from_rbldf(_ldf.with_columns_seq(rbexprs))
+    end
+
     # Add an external context to the computation graph.
     #
     # This allows expressions to also access columns from DataFrames
@@ -2887,7 +3483,7 @@ module Polars
     #
     # @example
     #   s = Polars::DataFrame.new({"a" => [1, 2, 3, 4], "b" => [5, 6, 7, 8]}).lazy
-    #   s.take_every(2).collect
+    #   s.gather_every(2).collect
     #   # =>
     #   # shape: (2, 2)
     #   # ┌─────┬─────┐
@@ -2898,9 +3494,10 @@ module Polars
     #   # │ 1   ┆ 5   │
     #   # │ 3   ┆ 7   │
     #   # └─────┴─────┘
-    def take_every(n)
-      select(F.col("*").take_every(n))
+    def gather_every(n)
+      select(F.col("*").gather_every(n))
     end
+    alias_method :take_every, :gather_every
 
     # Fill null values using the specified value or strategy.
     #
@@ -3177,6 +3774,32 @@ module Polars
       _from_rbldf(_ldf.median)
     end
 
+    # Aggregate the columns in the LazyFrame as the sum of their null value count.
+    #
+    # @return [LazyFrame]
+    #
+    # @example
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "foo" => [1, nil, 3],
+    #       "bar" => [6, 7, nil],
+    #       "ham" => ["a", "b", "c"]
+    #     }
+    #   )
+    #   lf.null_count.collect
+    #   # =>
+    #   # shape: (1, 3)
+    #   # ┌─────┬─────┬─────┐
+    #   # │ foo ┆ bar ┆ ham │
+    #   # │ --- ┆ --- ┆ --- │
+    #   # │ u32 ┆ u32 ┆ u32 │
+    #   # ╞═════╪═════╪═════╡
+    #   # │ 1   ┆ 1   ┆ 0   │
+    #   # └─────┴─────┴─────┘
+    def null_count
+      _from_rbldf(_ldf.null_count)
+    end
+
     # Aggregate the columns in the DataFrame to their quantile value.
     #
     # @param quantile [Float]
@@ -3307,37 +3930,103 @@ module Polars
       _from_rbldf(_ldf.unique(maintain_order, selector_subset, keep))
     end
 
-    # Drop rows with null values from this LazyFrame.
+    # Drop all rows that contain one or more NaN values.
+    #
+    # The original order of the remaining rows is preserved.
     #
     # @param subset [Object]
-    #   Subset of column(s) on which `drop_nulls` will be applied.
+    #   Column name(s) for which NaN values are considered; if set to `nil`
+    #   (default), use all columns (note that only floating-point columns
+    #   can contain NaNs).
     #
     # @return [LazyFrame]
     #
     # @example
-    #   df = Polars::DataFrame.new(
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "foo" => [-20.5, Float::NAN, 80.0],
+    #       "bar" => [Float::NAN, 110.0, 25.5],
+    #       "ham" => ["xxx", "yyy", nil]
+    #     }
+    #   )
+    #   lf.drop_nans.collect
+    #   # =>
+    #   # shape: (1, 3)
+    #   # ┌──────┬──────┬──────┐
+    #   # │ foo  ┆ bar  ┆ ham  │
+    #   # │ ---  ┆ ---  ┆ ---  │
+    #   # │ f64  ┆ f64  ┆ str  │
+    #   # ╞══════╪══════╪══════╡
+    #   # │ 80.0 ┆ 25.5 ┆ null │
+    #   # └──────┴──────┴──────┘
+    #
+    # @example
+    #   lf.drop_nans(subset: ["bar"]).collect
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌──────┬───────┬──────┐
+    #   # │ foo  ┆ bar   ┆ ham  │
+    #   # │ ---  ┆ ---   ┆ ---  │
+    #   # │ f64  ┆ f64   ┆ str  │
+    #   # ╞══════╪═══════╪══════╡
+    #   # │ NaN  ┆ 110.0 ┆ yyy  │
+    #   # │ 80.0 ┆ 25.5  ┆ null │
+    #   # └──────┴───────┴──────┘
+    def drop_nans(subset: nil)
+      selector_subset = nil
+      if !subset.nil?
+        selector_subset = Utils.parse_list_into_selector(subset)._rbselector
+      end
+      _from_rbldf(_ldf.drop_nans(selector_subset))
+    end
+
+    # Drop all rows that contain one or more null values.
+    #
+    # The original order of the remaining rows is preserved.
+    #
+    # @param subset [Object]
+    #   Column name(s) for which null values are considered.
+    #   If set to `nil` (default), use all columns.
+    #
+    # @return [LazyFrame]
+    #
+    # @example
+    #   lf = Polars::LazyFrame.new(
     #     {
     #       "foo" => [1, 2, 3],
     #       "bar" => [6, nil, 8],
-    #       "ham" => ["a", "b", "c"]
+    #       "ham" => ["a", "b", nil]
     #     }
     #   )
-    #   df.lazy.drop_nulls.collect
+    #   lf.drop_nulls.collect
     #   # =>
-    #   # shape: (2, 3)
+    #   # shape: (1, 3)
     #   # ┌─────┬─────┬─────┐
     #   # │ foo ┆ bar ┆ ham │
     #   # │ --- ┆ --- ┆ --- │
     #   # │ i64 ┆ i64 ┆ str │
     #   # ╞═════╪═════╪═════╡
     #   # │ 1   ┆ 6   ┆ a   │
-    #   # │ 3   ┆ 8   ┆ c   │
     #   # └─────┴─────┴─────┘
+    #
+    # @example
+    #   lf.drop_nulls(subset: Polars.cs.integer).collect
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌─────┬─────┬──────┐
+    #   # │ foo ┆ bar ┆ ham  │
+    #   # │ --- ┆ --- ┆ ---  │
+    #   # │ i64 ┆ i64 ┆ str  │
+    #   # ╞═════╪═════╪══════╡
+    #   # │ 1   ┆ 6   ┆ a    │
+    #   # │ 3   ┆ 8   ┆ null │
+    #   # └─────┴─────┴──────┘
     def drop_nulls(subset: nil)
-      if !subset.nil? && !subset.is_a?(::Array)
-        subset = [subset]
+      selector_subset = nil
+      if !subset.nil?
+        selector_subset = Utils.parse_list_into_selector(subset)._rbselector
       end
-      _from_rbldf(_ldf.drop_nulls(subset))
+      _from_rbldf(_ldf.drop_nulls(selector_subset))
     end
 
     # Unpivot a DataFrame from wide to long format.
@@ -3571,9 +4260,261 @@ module Polars
       with_columns(F.col(column).set_sorted(descending: descending))
     end
 
-    # TODO
-    # def update
-    # end
+    # Update the values in this `LazyFrame` with the values in `other`.
+    #
+    # @note
+    #   This functionality is considered **unstable**. It may be changed
+    #   at any point without it being considered a breaking change.
+    #
+    # @param other [LazyFrame]
+    #   LazyFrame that will be used to update the values
+    # @param on [Object]
+    #   Column names that will be joined on. If set to `nil` (default),
+    #   the implicit row index of each frame is used as a join key.
+    # @param how ['left', 'inner', 'full']
+    #   * 'left' will keep all rows from the left table; rows may be duplicated
+    #     if multiple rows in the right frame match the left row's key.
+    #   * 'inner' keeps only those rows where the key exists in both frames.
+    #   * 'full' will update existing rows where the key matches while also
+    #     adding any new rows contained in the given frame.
+    # @param left_on [Object]
+    #  Join column(s) of the left DataFrame.
+    # @param right_on [Object]
+    #  Join column(s) of the right DataFrame.
+    # @param include_nulls [Boolean]
+    #   Overwrite values in the left frame with null values from the right frame.
+    #   If set to `false` (default), null values in the right frame are ignored.
+    # @param maintain_order ['none', 'left', 'right', 'left_right', 'right_left']
+    #   Which order of rows from the inputs to preserve. See `LazyFrame.join`
+    #   for details. Unlike `join` this function preserves the left order by
+    #   default.
+    #
+    # @return [LazyFrame]
+    #
+    # @note
+    #   This is syntactic sugar for a left/inner join that preserves the order
+    #   of the left `DataFrame` by default, with an optional coalesce when
+    #   `include_nulls: False`.
+    #
+    # @example Update `df` values with the non-null values in `new_df`, by row index:
+    #   lf = Polars::LazyFrame.new(
+    #     {
+    #       "A" => [1, 2, 3, 4],
+    #       "B" => [400, 500, 600, 700]
+    #     }
+    #   )
+    #   new_lf = Polars::LazyFrame.new(
+    #     {
+    #       "B" => [-66, nil, -99],
+    #       "C" => [5, 3, 1]
+    #     }
+    #   )
+    #   lf.update(new_lf).collect
+    #   # =>
+    #   # shape: (4, 2)
+    #   # ┌─────┬─────┐
+    #   # │ A   ┆ B   │
+    #   # │ --- ┆ --- │
+    #   # │ i64 ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ 1   ┆ -66 │
+    #   # │ 2   ┆ 500 │
+    #   # │ 3   ┆ -99 │
+    #   # │ 4   ┆ 700 │
+    #   # └─────┴─────┘
+    #
+    # @example Update `df` values with the non-null values in `new_df`, by row index, but only keeping those rows that are common to both frames:
+    #   lf.update(new_lf, how: "inner").collect
+    #   # =>
+    #   # shape: (3, 2)
+    #   # ┌─────┬─────┐
+    #   # │ A   ┆ B   │
+    #   # │ --- ┆ --- │
+    #   # │ i64 ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ 1   ┆ -66 │
+    #   # │ 2   ┆ 500 │
+    #   # │ 3   ┆ -99 │
+    #   # └─────┴─────┘
+    #
+    # @example Update `df` values with the non-null values in `new_df`, using a full outer join strategy that defines explicit join columns in each frame:
+    #   lf.update(new_lf, left_on: ["A"], right_on: ["C"], how: "full").collect
+    #   # =>
+    #   # shape: (5, 2)
+    #   # ┌─────┬─────┐
+    #   # │ A   ┆ B   │
+    #   # │ --- ┆ --- │
+    #   # │ i64 ┆ i64 │
+    #   # ╞═════╪═════╡
+    #   # │ 1   ┆ -99 │
+    #   # │ 2   ┆ 500 │
+    #   # │ 3   ┆ 600 │
+    #   # │ 4   ┆ 700 │
+    #   # │ 5   ┆ -66 │
+    #   # └─────┴─────┘
+    #
+    # @example Update `df` values including null values in `new_df`, using a full outer join strategy that defines explicit join columns in each frame:
+    #   lf.update(
+    #     new_lf, left_on: "A", right_on: "C", how: "full", include_nulls: true
+    #   ).collect
+    #   # =>
+    #   # shape: (5, 2)
+    #   # ┌─────┬──────┐
+    #   # │ A   ┆ B    │
+    #   # │ --- ┆ ---  │
+    #   # │ i64 ┆ i64  │
+    #   # ╞═════╪══════╡
+    #   # │ 1   ┆ -99  │
+    #   # │ 2   ┆ 500  │
+    #   # │ 3   ┆ null │
+    #   # │ 4   ┆ 700  │
+    #   # │ 5   ┆ -66  │
+    #   # └─────┴──────┘
+    def update(
+      other,
+      on: nil,
+      how: "left",
+      left_on: nil,
+      right_on: nil,
+      include_nulls: false,
+      maintain_order: "left"
+    )
+      Utils.require_same_type(self, other)
+      if ["outer", "outer_coalesce"].include?(how)
+        how = "full"
+      end
+
+      if !["left", "inner", "full"].include?(how)
+        msg = "`how` must be one of {{'left', 'inner', 'full'}}; found #{how.inspect}"
+        raise ArgumentError, msg
+      end
+
+      slf = self
+      row_index_used = false
+      if on.nil?
+        if left_on.nil? && right_on.nil?
+          # no keys provided--use row index
+          row_index_used = true
+          row_index_name = "__POLARS_ROW_INDEX"
+          slf = slf.with_row_index(name: row_index_name)
+          other = other.with_row_index(name: row_index_name)
+          left_on = right_on = [row_index_name]
+        else
+          # one of left or right is missing, raise error
+          if left_on.nil?
+            msg = "missing join columns for left frame"
+            raise ArgumentError, msg
+          end
+          if right_on.nil?
+            msg = "missing join columns for right frame"
+            raise ArgumentError, msg
+          end
+        end
+      else
+        # move on into left/right_on to simplify logic
+        left_on = right_on = on
+      end
+
+      if left_on.is_a?(::String)
+        left_on = [left_on]
+      end
+      if right_on.is_a?(::String)
+        right_on = [right_on]
+      end
+
+      left_schema = slf.collect_schema
+      left_on.each do |name|
+        if !left_schema.include?(name)
+          msg = "left join column #{name.inspect} not found"
+          raise ArgumentError, msg
+        end
+      end
+      right_schema = other.collect_schema
+      right_on.each do |name|
+        if !right_schema.include?(name)
+          msg = "right join column #{name.inspect} not found"
+          raise ArgumentError, msg
+        end
+      end
+
+      # no need to join if *only* join columns are in other (inner/left update only)
+      if how != "full" && right_schema.length == right_on.length
+        if row_index_used
+          return slf.drop(row_index_name)
+        end
+        return slf
+      end
+
+      # only use non-idx right columns present in left frame
+      right_other = Set.new(right_schema.to_h.keys).intersection(left_schema.to_h.keys) - Set.new(right_on)
+
+      # When include_nulls is True, we need to distinguish records after the join that
+      # were originally null in the right frame, as opposed to records that were null
+      # because the key was missing from the right frame.
+      # Add a validity column to track whether row was matched or not.
+      if include_nulls
+        validity = ["__POLARS_VALIDITY"]
+        other = other.with_columns(F.lit(true).alias(validity[0]))
+      else
+        validity = []
+      end
+
+      tmp_name = "__POLARS_RIGHT"
+      drop_columns = right_other.map { |name| "#{name}#{tmp_name}" } + validity
+      result = (
+        slf.join(
+          other.select(*right_on, *right_other, *validity),
+          left_on: left_on,
+          right_on: right_on,
+          how: how,
+          suffix: tmp_name,
+          coalesce: true,
+          maintain_order: maintain_order
+        )
+        .with_columns(
+          right_other.map do |name|
+            (
+              if include_nulls
+                # use left value only when right value failed to join
+                F.when(F.col(validity).is_null)
+                .then(F.col(name))
+                .otherwise(F.col("#{name}#{tmp_name}"))
+              else
+                F.coalesce(["#{name}#{tmp_name}", F.col(name)])
+              end
+            ).alias(name)
+          end
+        )
+        .drop(drop_columns)
+      )
+      if row_index_used
+        result = result.drop(row_index_name)
+      end
+
+      _from_rbldf(result._ldf)
+    end
+
+    # Return the number of non-null elements for each column.
+    #
+    # @return [LazyFrame]
+    #
+    # @example
+    #   lf = Polars::LazyFrame.new(
+    #     {"a" => [1, 2, 3, 4], "b" => [1, 2, 1, nil], "c" => [nil, nil, nil, nil]}
+    #   )
+    #   lf.count.collect
+    #   # =>
+    #   # shape: (1, 3)
+    #   # ┌─────┬─────┬─────┐
+    #   # │ a   ┆ b   ┆ c   │
+    #   # │ --- ┆ --- ┆ --- │
+    #   # │ u32 ┆ u32 ┆ u32 │
+    #   # ╞═════╪═════╪═════╡
+    #   # │ 4   ┆ 3   ┆ 0   │
+    #   # └─────┴─────┴─────┘
+    def count
+      _from_rbldf(_ldf.count)
+    end
 
     private
 
@@ -3585,5 +4526,64 @@ module Polars
     def _from_rbldf(rb_ldf)
       self.class._from_rbldf(rb_ldf)
     end
+
+    def _filter(
+      predicates:,
+      constraints:,
+      invert: false
+    )
+      all_predicates = []
+      boolean_masks = []
+
+      predicates.each do |p|
+        # quick exit/skip conditions
+        if (p.is_a?(FalseClass) && invert) || (p.is_a?(TrueClass) && !invert)
+          next # ignore; doesn't filter/remove anything
+        end
+        if (p.is_a?(TrueClass) && invert) || (p.is_a?(FalseClass) && !invert)
+          return clear # discard all rows
+        end
+
+        # note: identify masks separately from predicates
+        if Utils.is_bool_sequence(p, include_series: true)
+          boolean_masks << Polars::Series.new(p, dtype: Boolean)
+        elsif (
+          (is_seq = Utils.is_sequence(p)) && p.any? { |x| !x.is_a?(Expr) }) ||
+          (!is_seq && !p.is_a?(Expr) && !(p.is_a?(::String) && collect_schema.include?(p))
+        )
+          err = p.is_a?(Series) ? "Series(…, dtype: #{p.dtype})" : p.inspect
+          msg = "invalid predicate for `filter`: #{err}"
+          raise TypeError, msg
+        else
+          all_predicates.concat(
+            Utils.parse_into_list_of_expressions(p).map { |x| Utils.wrap_expr(x) }
+          )
+        end
+      end
+
+      # unpack equality constraints from kwargs
+      all_predicates.concat(
+        constraints.map { |name, value| F.col(name).eq(value) }
+      )
+      if !(all_predicates.any? || boolean_masks.any?)
+        msg = "at least one predicate or constraint must be provided"
+        raise TypeError, msg
+      end
+
+      # if multiple predicates, combine as 'horizontal' expression
+      combined_predicate = all_predicates ? (all_predicates.length > 1 ? F.all_horizontal(*all_predicates) : all_predicates[0]) : nil
+
+      # apply reduced boolean mask first, if applicable, then predicates
+      if boolean_masks.any?
+        raise Todo
+      end
+
+      if combined_predicate.nil?
+        return _from_rbldf(_ldf)
+      end
+
+      filter_method = invert ? _ldf.method(:remove) : _ldf.method(:filter)
+      _from_rbldf(filter_method.(combined_predicate._rbexpr))
+    end
   end
 end