polars-df 0.21.0 → 0.21.1

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]

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/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.
@@ -123,7 +123,26 @@ module Polars
         source = Utils.normalize_filepath(source)
       end
 
-      Plr.parquet_schema(source)
+      # TODO return Schema
+      scan_parquet(source).collect_schema.to_h
+    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 +190,7 @@ 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.
@@ -210,7 +229,9 @@ module Polars
       retries: 2,
       include_file_paths: nil,
       allow_missing_columns: false,
-      extra_columns: "raise"
+      extra_columns: "raise",
+      _column_mapping: nil,
+      _deletion_files: nil
     )
       missing_columns = allow_missing_columns ? "insert" : "raise"
 
@@ -260,7 +281,8 @@ 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,