polars-df 0.21.0-x86_64-linux-musl → 0.22.0-x86_64-linux-musl

data/lib/polars/functions/business.rb

@@ -0,0 +1,95 @@
+module Polars
+  module Functions
+    # Count the number of business days between `start` and `end` (not including `end`).
+    #
+    # @note
+    #   This functionality is considered **unstable**. It may be changed
+    #   at any point without it being considered a breaking change.
+    #
+    # @param start [Object]
+    #   Start dates.
+    # @param stop [Object]
+    #   End dates.
+    # @param week_mask [Array]
+    #   Which days of the week to count. The default is Monday to Friday.
+    #   If you wanted to count only Monday to Thursday, you would pass
+    #   `[true, true, true, true, false, false, false]`.
+    # @param holidays [Array]
+    #   Holidays to exclude from the count.
+    #
+    # @return [Expr]
+    #
+    # @example
+    #   df = Polars::DataFrame.new(
+    #     {
+    #       "start" => [Date.new(2020, 1, 1), Date.new(2020, 1, 2)],
+    #       "end" => [Date.new(2020, 1, 2), Date.new(2020, 1, 10)]
+    #     }
+    #   )
+    #   df.with_columns(
+    #     business_day_count: Polars.business_day_count("start", "end")
+    #   )
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌────────────┬────────────┬────────────────────┐
+    #   # │ start      ┆ end        ┆ business_day_count │
+    #   # │ ---        ┆ ---        ┆ ---                │
+    #   # │ date       ┆ date       ┆ i32                │
+    #   # ╞════════════╪════════════╪════════════════════╡
+    #   # │ 2020-01-01 ┆ 2020-01-02 ┆ 1                  │
+    #   # │ 2020-01-02 ┆ 2020-01-10 ┆ 6                  │
+    #   # └────────────┴────────────┴────────────────────┘
+    #
+    # @example You can pass a custom weekend - for example, if you only take Sunday off:
+    #   week_mask = [true, true, true, true, true, true, false]
+    #   df.with_columns(
+    #     business_day_count: Polars.business_day_count(
+    #       "start", "end", week_mask: week_mask
+    #     )
+    #   )
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌────────────┬────────────┬────────────────────┐
+    #   # │ start      ┆ end        ┆ business_day_count │
+    #   # │ ---        ┆ ---        ┆ ---                │
+    #   # │ date       ┆ date       ┆ i32                │
+    #   # ╞════════════╪════════════╪════════════════════╡
+    #   # │ 2020-01-01 ┆ 2020-01-02 ┆ 1                  │
+    #   # │ 2020-01-02 ┆ 2020-01-10 ┆ 7                  │
+    #   # └────────────┴────────────┴────────────────────┘
+    #
+    # @example You can also pass a list of holidays to exclude from the count:
+    #   holidays = [Date.new(2020, 1, 1), Date.new(2020, 1, 2)]
+    #   df.with_columns(
+    #     business_day_count: Polars.business_day_count("start", "end", holidays: holidays)
+    #   )
+    #   # =>
+    #   # shape: (2, 3)
+    #   # ┌────────────┬────────────┬────────────────────┐
+    #   # │ start      ┆ end        ┆ business_day_count │
+    #   # │ ---        ┆ ---        ┆ ---                │
+    #   # │ date       ┆ date       ┆ i32                │
+    #   # ╞════════════╪════════════╪════════════════════╡
+    #   # │ 2020-01-01 ┆ 2020-01-02 ┆ 0                  │
+    #   # │ 2020-01-02 ┆ 2020-01-10 ┆ 5                  │
+    #   # └────────────┴────────────┴────────────────────┘
+    def business_day_count(
+      start,
+      stop,
+      week_mask: [true, true, true, true, true, false, false],
+      holidays: []
+    )
+      start_rbexpr = Utils.parse_into_expression(start)
+      end_rbexpr = Utils.parse_into_expression(stop)
+      unix_epoch = ::Date.new(1970, 1, 1)
+      Utils.wrap_expr(
+        Plr.business_day_count(
+          start_rbexpr,
+          end_rbexpr,
+          week_mask,
+          holidays.map { |holiday| holiday - unix_epoch }
+        )
+      )
+    end
+  end
+end

data/lib/polars/functions/datatype.rb

@@ -0,0 +1,21 @@
+module Polars
+  module Functions
+    # Get a lazily evaluated :class:`DataType` of a column or expression.
+    #
+    # @note
+    #   This functionality is considered **unstable**. It may be changed
+    #   at any point without it being considered a breaking change.
+    #
+    # @return [DataTypeExpr]
+    def dtype_of(col_or_expr)
+      e = nil
+      if col_or_expr.is_a?(::String)
+        e = F.col(col_or_expr)
+      else
+        e = col_or_expr
+      end
+
+      DataTypeExpr._from_rbdatatype_expr(RbDataTypeExpr.of_expr(e._rbexpr))
+    end
+  end
+end

data/lib/polars/functions/lazy.rb

@@ -1,5 +1,18 @@
 module Polars
   module Functions
+    # Select a field in the current `struct.with_fields` scope.
+    #
+    # @param name [Object]
+    #   Name of the field(s) to select.
+    #
+    # @return [Expr]
+    def field(name)
+      if name.is_a?(::String)
+        name = [name]
+      end
+      Utils.wrap_expr(Plr.field(name))
+    end
+
     # Alias for an element in evaluated in an `eval` expression.
     #
     # @return [Expr]
@@ -810,7 +823,7 @@ module Polars
     #   # ┌─────┐
     #   # │ sum │
     #   # │ --- │
-    #   # │ i64 │
+    #   # │ i32 │
     #   # ╞═════╡
     #   # │ 10  │
     #   # │ 13  │

data/lib/polars/io/csv.rb

@@ -499,7 +499,7 @@ module Polars
     #   for instance `#`.
     # @param quote_char [String]
     #   Single byte character used for csv quoting.
-    #   Set to None to turn off special handling and escaping of quotes.
+    #   Set to nil to turn off special handling and escaping of quotes.
     # @param skip_rows [Integer]
     #   Start reading after `skip_rows` lines. The header will be parsed at this
     #   offset.

data/lib/polars/io/iceberg.rb

@@ -0,0 +1,27 @@
+module Polars
+  module IO
+    # Lazily read from an Apache Iceberg table.
+    #
+    # @param source [Object]
+    #   A Iceberg Ruby table, or a direct path to the metadata.
+    # @param snapshot_id [Integer]
+    #   The snapshot ID to scan from.
+    # @param storage_options [Hash]
+    #   Extra options for the storage backends.
+    #
+    # @return [LazyFrame]
+    def scan_iceberg(
+      source,
+      snapshot_id: nil,
+      storage_options: nil
+    )
+      require "iceberg"
+
+      unless source.is_a?(Iceberg::Table)
+        raise Todo
+      end
+
+      source.to_polars(snapshot_id:, storage_options:)
+    end
+  end
+end

data/lib/polars/io/json.rb

@@ -7,11 +7,11 @@ module Polars
     # @param schema [Object]
     #   The DataFrame schema may be declared in several ways:
     #
-    #   * As a dict of {name:type} pairs; if type is None, it will be auto-inferred.
-    #   * As a list of column names; in this case types are automatically inferred.
-    #   * As a list of (name,type) pairs; this is equivalent to the dictionary form.
+    #   * As a hash of \\\\{name:type} pairs; if type is nil, it will be auto-inferred.
+    #   * As an array of column names; in this case types are automatically inferred.
+    #   * As an array of [name,type] pairs; this is equivalent to the hash form.
     #
-    #   If you supply a list of column names that does not match the names in the
+    #   If you supply an array of column names that does not match the names in the
     #   underlying data, the names given here will overwrite them. The number
     #   of names given in the schema should match the underlying data dimensions.
     # @param schema_overrides [Hash]

data/lib/polars/io/ndjson.rb

@@ -7,11 +7,11 @@ module Polars
     # @param schema [Object]
     #   The DataFrame schema may be declared in several ways:
     #
-    #   * As a dict of {name:type} pairs; if type is None, it will be auto-inferred.
-    #   * As a list of column names; in this case types are automatically inferred.
-    #   * As a list of (name,type) pairs; this is equivalent to the dictionary form.
+    #   * As a hash of \\\\{name:type} pairs; if type is nil, it will be auto-inferred.
+    #   * As an array of column names; in this case types are automatically inferred.
+    #   * As an array of [name,type] pairs; this is equivalent to the hash form.
     #
-    #   If you supply a list of column names that does not match the names in the
+    #   If you supply an array of column names that does not match the names in the
     #   underlying data, the names given here will overwrite them. The number
     #   of names given in the schema should match the underlying data dimensions.
     # @param schema_overrides [Hash]

data/lib/polars/io/parquet.rb

@@ -43,7 +43,7 @@ module Polars
     #   Extra options that make sense for a particular storage connection.
     # @param credential_provider [Object]
     #   Provide a function that can be called to provide cloud storage
-    #   credentials. The function is expected to return a dictionary of
+    #   credentials. The function is expected to return a hash of
     #   credential keys along with an optional credential expiry time.
     # @param retries [Integer]
     #   Number of retries if accessing a cloud instance fails.
@@ -117,13 +117,31 @@ module Polars
     # @param source [Object]
     #   Path to a file or a file-like object.
     #
-    # @return [Hash]
+    # @return [Schema]
     def read_parquet_schema(source)
       if Utils.pathlike?(source)
         source = Utils.normalize_filepath(source)
       end
 
-      Plr.parquet_schema(source)
+      scan_parquet(source).collect_schema
+    end
+
+    # Get file-level custom metadata of a Parquet file without reading data.
+    #
+    # @note
+    #   This functionality is considered **experimental**. It may be removed or
+    #   changed at any point without it being considered a breaking change.
+    #
+    # @param source [Object]
+    #   Path to a file or a file-like object.
+    #
+    # @return [Hash]
+    def read_parquet_metadata(source)
+      if Utils.pathlike?(source)
+        source = Utils.normalize_filepath(source, check_not_directory: false)
+      end
+
+      Plr.read_parquet_metadata(source)
     end
 
     # Lazily read from a parquet file or multiple files via glob patterns.
@@ -171,7 +189,7 @@ module Polars
     #   Extra options that make sense for a particular storage connection.
     # @param credential_provider [Object]
     #   Provide a function that can be called to provide cloud storage
-    #   credentials. The function is expected to return a dictionary of
+    #   credentials. The function is expected to return a hash of
     #   credential keys along with an optional credential expiry time.
     # @param retries [Integer]
     #   Number of retries if accessing a cloud instance fails.
@@ -188,6 +206,9 @@ module Polars
     #   defined schema are encountered in the data:
     #     * `ignore`: Silently ignores.
     #     * `raise`: Raises an error.
+    # @param cast_options [Object]
+    #   Configuration for column type-casting during scans. Useful for datasets
+    #   containing files that have differing schemas.
     #
     # @return [LazyFrame]
     def scan_parquet(
@@ -210,7 +231,10 @@ module Polars
       retries: 2,
       include_file_paths: nil,
       allow_missing_columns: false,
-      extra_columns: "raise"
+      extra_columns: "raise",
+      cast_options: nil,
+      _column_mapping: nil,
+      _deletion_files: nil
     )
       missing_columns = allow_missing_columns ? "insert" : "raise"
 
@@ -247,7 +271,7 @@ module Polars
           ScanOptions.new(
             row_index: !row_index_name.nil? ? [row_index_name, row_index_offset] : nil,
             pre_slice: !n_rows.nil? ? [0, n_rows] : nil,
-            # cast_options: cast_options,
+            cast_options: cast_options,
             extra_columns: extra_columns,
             missing_columns: missing_columns,
             include_file_paths: include_file_paths,
@@ -260,7 +284,8 @@ module Polars
             storage_options: storage_options,
             # credential_provider: credential_provider_builder,
             retries: retries,
-            # deletion_files: _deletion_files
+            deletion_files: _deletion_files,
+            column_mapping: _column_mapping
           ),
           parallel,
           low_memory,

data/lib/polars/io/scan_options.rb

@@ -3,7 +3,8 @@ module Polars
     class ScanOptions
       attr_reader :row_index, :pre_slice, :cast_options, :extra_columns, :missing_columns,
         :include_file_paths, :glob, :hive_partitioning, :hive_schema, :try_parse_hive_dates,
-        :rechunk, :cache, :storage_options, :credential_provider, :retries, :column_mapping, :deletion_files
+        :rechunk, :cache, :storage_options, :credential_provider, :retries, :column_mapping,
+        :default_values, :deletion_files
 
       def initialize(
         row_index: nil,
@@ -22,6 +23,7 @@ module Polars
         credential_provider: nil,
         retries: 2,
         column_mapping: nil,
+        default_values: nil,
         deletion_files: nil
       )
         @row_index = row_index
@@ -40,6 +42,7 @@ module Polars
         @credential_provider = credential_provider
         @retries = retries
         @column_mapping = column_mapping
+        @default_values = default_values
         @deletion_files = deletion_files
       end
     end