polars-df 0.12.0-x86_64-linux → 0.14.0-x86_64-linux

data/lib/polars/data_frame.rb

@@ -2426,15 +2426,15 @@ module Polars
     #   df.map_rows { |t| t[0] * 2 + t[1] }
     #   # =>
     #   # shape: (3, 1)
-    #   # ┌───────┐
-    #   # │ apply │
-    #   # │ ---   │
-    #   # │ i64   │
-    #   # ╞═══════╡
-    #   # │ 1     │
-    #   # │ 9     │
-    #   # │ 14    │
-    #   # └───────┘
+    #   # ┌─────┐
+    #   # │ map │
+    #   # │ --- │
+    #   # │ i64 │
+    #   # ╞═════╡
+    #   # │ 1   │
+    #   # │ 9   │
+    #   # │ 14  │
+    #   # └─────┘
     def map_rows(return_dtype: nil, inference_size: 256, &f)
       out, is_df = _df.map_rows(f, return_dtype, inference_size)
       if is_df
@@ -4234,7 +4234,7 @@ module Polars
       if n.nil? && !frac.nil?
         frac = Series.new("frac", [frac]) unless frac.is_a?(Series)
 
-        _from_rbdf(
+        return _from_rbdf(
           _df.sample_frac(frac._s, with_replacement, shuffle, seed)
         )
       end

data/lib/polars/expr.rb

@@ -1182,7 +1182,7 @@ module Polars
     #       "b" => [1, 1, 2, 2]
     #     }
     #   )
-    #   df.select(Polars.all.mode)
+    #   df.select(Polars.all.mode.first)
     #   # =>
     #   # shape: (2, 2)
     #   # ┌─────┬─────┐
@@ -6015,12 +6015,12 @@ module Polars
     #   # ┌──────┐
     #   # │ a    │
     #   # │ ---  │
-    #   # │ i64  │
+    #   # │ f64  │
     #   # ╞══════╡
-    #   # │ -1   │
-    #   # │ 0    │
-    #   # │ 0    │
-    #   # │ 1    │
+    #   # │ -1.0 │
+    #   # │ -0.0 │
+    #   # │ 0.0  │
+    #   # │ 1.0  │
     #   # │ null │
     #   # └──────┘
     def sign

data/lib/polars/io/ipc.rb

@@ -189,10 +189,18 @@ module Polars
     #   Offset to start the row_count column (only use if the name is set).
     # @param storage_options [Hash]
     #   Extra options that make sense for a particular storage connection.
-    # @param memory_map [Boolean]
-    #   Try to memory map the file. This can greatly improve performance on repeated
-    #   queries as the OS may cache pages.
-    #   Only uncompressed IPC files can be memory mapped.
+    # @param hive_partitioning [Boolean]
+    #   Infer statistics and schema from Hive partitioned URL and use them
+    #   to prune reads. This is unset by default (i.e. `nil`), meaning it is
+    #   automatically enabled when a single directory is passed, and otherwise
+    #   disabled.
+    # @param hive_schema [Hash]
+    #   The column names and data types of the columns by which the data is partitioned.
+    #   If set to `nil` (default), the schema of the Hive partitions is inferred.
+    # @param try_parse_hive_dates [Boolean]
+    #   Whether to try parsing hive values as date/datetime types.
+    # @param include_file_paths [String]
+    #   Include the path of the source file(s) as a column with this name.
     #
     # @return [LazyFrame]
     def scan_ipc(
@@ -203,7 +211,10 @@ module Polars
       row_count_name: nil,
       row_count_offset: 0,
       storage_options: nil,
-      memory_map: true
+      hive_partitioning: nil,
+      hive_schema: nil,
+      try_parse_hive_dates: true,
+      include_file_paths: nil
     )
       _scan_ipc_impl(
         source,
@@ -213,7 +224,10 @@ module Polars
         row_count_name: row_count_name,
         row_count_offset: row_count_offset,
         storage_options: storage_options,
-        memory_map: memory_map
+        hive_partitioning: hive_partitioning,
+        hive_schema: hive_schema,
+        try_parse_hive_dates: try_parse_hive_dates,
+        include_file_paths: include_file_paths
       )
     end
 
@@ -226,7 +240,10 @@ module Polars
       row_count_name: nil,
       row_count_offset: 0,
       storage_options: nil,
-      memory_map: true
+      hive_partitioning: nil,
+      hive_schema: nil,
+      try_parse_hive_dates: true,
+      include_file_paths: nil
     )
       if Utils.pathlike?(file)
         file = Utils.normalize_filepath(file)
@@ -239,7 +256,10 @@ module Polars
           cache,
           rechunk,
           Utils.parse_row_index_args(row_count_name, row_count_offset),
-          memory_map
+          hive_partitioning,
+          hive_schema,
+          try_parse_hive_dates,
+          include_file_paths
         )
       Utils.wrap_ldf(rblf)
     end

data/lib/polars/io/parquet.rb

@@ -158,6 +158,8 @@ module Polars
     #   Extra options that make sense for a particular storage connection.
     # @param low_memory [Boolean]
     #   Reduce memory pressure at the expense of performance.
+    # @param include_file_paths [String]
+    #  Include the path of the source file(s) as a column with this name.
     #
     # @return [LazyFrame]
     def scan_parquet(
@@ -170,7 +172,8 @@ module Polars
       row_count_name: nil,
       row_count_offset: 0,
       storage_options: nil,
-      low_memory: false
+      low_memory: false,
+      include_file_paths: nil
     )
       if Utils.pathlike?(source)
         source = Utils.normalize_filepath(source)
@@ -186,7 +189,8 @@ module Polars
         row_count_offset: row_count_offset,
         storage_options: storage_options,
         low_memory: low_memory,
-        glob: glob
+        glob: glob,
+        include_file_paths: include_file_paths
       )
     end
 
@@ -203,7 +207,8 @@ module Polars
       low_memory: false,
       use_statistics: true,
       hive_partitioning: nil,
-      glob: true
+      glob: true,
+      include_file_paths: nil
     )
       rblf =
         RbLazyFrame.new_from_parquet(
@@ -219,7 +224,8 @@ module Polars
           hive_partitioning,
           nil,
           true,
-          glob
+          glob,
+          include_file_paths
         )
       Utils.wrap_ldf(rblf)
     end

data/lib/polars/lazy_frame.rb

@@ -2526,11 +2526,15 @@ module Polars
       value_name: nil,
       streamable: true
     )
+      if !streamable
+        warn "The `streamable` parameter for `LazyFrame.unpivot` is deprecated"
+      end
+
       on = on.nil? ? [] : Utils._expand_selectors(self, on)
       index = index.nil? ? [] : Utils._expand_selectors(self, index)
 
       _from_rbldf(
-        _ldf.unpivot(on, index, value_name, variable_name, streamable)
+        _ldf.unpivot(on, index, value_name, variable_name)
       )
     end
     alias_method :melt, :unpivot

data/lib/polars/series.rb

@@ -1790,9 +1790,10 @@ module Polars
     # Use this to swiftly assert a Series does not have null values.
     #
     # @return [Boolean]
-    def has_validity
-      _s.has_validity
+    def has_nulls
+      _s.has_nulls
     end
+    alias_method :has_validity, :has_nulls
 
     # Check if the Series is empty.
     #
@@ -2605,12 +2606,12 @@ module Polars
     #   s.sign
     #   # =>
     #   # shape: (5,)
-    #   # Series: 'a' [i64]
+    #   # Series: 'a' [f64]
     #   # [
-    #   #         -1
-    #   #         0
-    #   #         0
-    #   #         1
+    #   #         -1.0
+    #   #         -0.0
+    #   #         0.0
+    #   #         1.0
     #   #         null
     #   # ]
     def sign

data/lib/polars/string_expr.rb

@@ -792,15 +792,15 @@ module Polars
     #   df.select(Polars.col("json").str.json_decode(dtype))
     #   # =>
     #   # shape: (3, 1)
-    #   # ┌─────────────┐
-    #   # │ json        │
-    #   # │ ---         │
-    #   # │ struct[2]   │
-    #   # ╞═════════════╡
-    #   # │ {1,true}    │
-    #   # │ {null,null} │
-    #   # │ {2,false}   │
-    #   # └─────────────┘
+    #   # ┌───────────┐
+    #   # │ json      │
+    #   # │ ---       │
+    #   # │ struct[2] │
+    #   # ╞═══════════╡
+    #   # │ {1,true}  │
+    #   # │ null      │
+    #   # │ {2,false} │
+    #   # └───────────┘
     def json_decode(dtype = nil, infer_schema_length: 100)
       if !dtype.nil?
         dtype = Utils.rb_type_to_dtype(dtype)

data/lib/polars/version.rb

@@ -1,4 +1,4 @@
 module Polars
   # @private
-  VERSION = "0.12.0"
+  VERSION = "0.14.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: polars-df
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 0.14.0
 platform: x86_64-linux
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-07-11 00:00:00.000000000 Z
+date: 2024-09-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bigdecimal