q-PhddlmZddlZddlZddlmZddlmZmZddl m Z ddl m Z erddlmZddlmZddlmZmZmZddlmZe d d ddZe dd ddZdS)) annotationsN)Iterator) TYPE_CHECKINGCallable)unstable)r) DataFrameExpr LazyFrame) SchemaDictF)validate_schema io_sourceVCallable[[list[str] | None, Expr | None, int | None, int | None], Iterator[DataFrame]]schema%Callable[[], SchemaDict] | SchemaDictr boolreturnr cVd fd }tj||d | S)a Register your IO plugin and initialize a LazyFrame. See the `user guide `_ for more information about plugins. .. warning:: This functionality is considered **unstable**. It may be changed at any point without it being considered a breaking change. Parameters ---------- io_source Function that accepts the following arguments: with_columns Columns that are projected. The reader must project these columns if applied predicate Polars expression. The reader must filter their rows accordingly. n_rows Materialize only n rows from the source. The reader can stop when `n_rows` are read. batch_size A hint of the ideal batch size the reader's generator must produce. The function should return a an iterator/generator that produces DataFrames. schema Schema or function that when called produces the schema that the reader will produce before projection pushdown. validate_schema Whether the engine should validate if the batches generated match the given schema. It's an implementation error if this isn't the case and can lead to bugs that are hard to solve. Returns ------- LazyFrame with_columnslist[str] | None predicate bytes | Nonen_rows int | None batch_sizer tuple[Iterator[DataFrame], bool]cd}d}|rw tj|}nV#t$rI}tjdrtd|tj d}Yd}~nd}~wwxYw|||||fS)NTPOLARS_VERBOSEzMfailed parsing IO plugin expression filter will be handled on Polars' side: )fileF) plr deserialize Exceptionosenvirongetprintsysstderr)rrrrparsed_predicate_successparsed_predicateer s Q/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/polars/io/plugins.pywrapz register_io_source..wrapGs $(   1 1#%7#6#6y#A#A   1 1 1:>>"233mjkmm Z,1((((((  1y *FJ  #$ $s) A<?A77A<F)rscan_fnpyarrowr ) rrrrrrrrrr)rr _scan_python_function)r rr r,s` r+register_io_sourcer0sLh$$$$$$. < - -tUO .  TfunctionCallable[[], DataFrame]%SchemaDict | Callable[[], SchemaDict]c4d fd }t||| S) u Deferred execution. Takes a function that produces a `DataFrame` but defers execution until the `LazyFrame` is collected. Parameters ---------- function Function that takes no arguments and produces a `DataFrame`. schema Schema of the `DataFrame` the deferred function will return. The caller must ensure this schema is correct. validate_schema Whether the engine should validate if the batches generated match the given schema. It's an implementation error if this isn't the case and can lead to bugs that are hard to solve. Examples -------- Delay DataFrame execution until query is executed. >>> import numpy as np >>> np.random.seed(0) >>> lf = pl.defer( ... lambda: pl.DataFrame({"a": np.random.randn(3)}), schema={"a": pl.Float64} ... ) >>> lf.collect() shape: (3, 1) ┌──────────┐ │ a │ │ --- │ │ f64 │ ╞══════════╡ │ 1.764052 │ │ 0.400157 │ │ 0.978738 │ └──────────┘ Run an eager source in Polars Cloud >>> ( ... pl.defer( ... lambda: pl.read_database("select * from tbl"), ... schema={"a": pl.Float64, "b": pl.Boolean}, ... ) ... .filter("b") ... .sum("a") ... .remote() ... .collect() ... ) # doctest: +SKIP rrr Expr | NonerrrrIterator[DataFrame]c3K}|||}|||}|||}|VdS)N)lazyselectfilterlimitcollect)rrrrlfr2s r+sourcez_defer..sources} XZZ__    #<((B  9%%B  &!!Bjjllr1)r rr ) rrrr6rrrrrr7)r0)r2rr r?s` r+_deferr@csB|          r1)r rrrr rrr )r2r3rr4r rrr ) __future__rr"r&collections.abcrtypingrrpolars._reexport _reexportrpolars._utils.unstablerpolarsrr r polars._typingr r0r@r1r+rJsV"""""" $$$$$$********++++++*((((((1111111111)))))) " LLLLL L^  ! NNNNN NNNr1