A collection of LazyDatasets.

Constructors¶

LazyCollection(data, ...)

Initialize self. See help(type(self)) for accurate signature.

Config¶

set_scope(key: str | Iterable[str] | None = None) → Self

set_scope_by_index(idx: int | Iterable[int] | None = None) → Self

Delegated¶

set_sorted(column: str, *, descending: bool = False) → Self

collect(**kwargs: Any) → Collection

approx_n_unique() → Self

bottom_k(k: int, *, by: IntoExpr | Iterable[IntoExpr], ...) → Self

cache() → Self

cast(dtypes, ...) → Self

clear(n: int = 0) → Self

clone() → Self

collect_async(...) → dict[str, Awaitable[polars.DataFrame] | _GeventDataFrameResult[polars.DataFrame]]

collect_batches(*, ...) → dict[str, Iterator[polars.DataFrame]]

collect_model_blueprint(...) → dict[str, str]

collect_schema() → dict[str, Schema]

count() → Self

describe(...) → dict[str, polars.DataFrame]

drop(*columns, ...) → Self

drop_nans(...) → Self

drop_nulls(...) → Self

explain(*, format: ExplainFormat = 'plain', ...) → dict[str, str]

explode(columns, ...) → Self

fetch(...) → dict[str, TypeAliasForwardRef('polars.DataFrame')]

fill_nan(value: int | float | Expr | None) → Self

fill_null(value: Any | Expr | None = None, ...) → Self

filter(*predicates, ...) → Self

first() → Self

gather_every(n: int, offset: int = 0) → Self

head(n: int = 5) → Self

inspect(fmt: str = '{}') → Self

interpolate() → Self

last() → Self

limit(n: int = 5) → Self

map_batches(function, ...) → Self

match_to_schema(schema: SchemaDict | Schema, *, ...) → Self

max() → Self

mean() → Self

median() → Self

melt(...) → Self

merge_sorted(other: LazyDataset[U] | polars.LazyFrame, key) → Self

min() → Self

null_count() → Self

pipe(function, ...) → dict[str, T]

pipe_with_schema(function) → Self

profile(...) → dict[str, tuple[polars.DataFrame, polars.DataFrame]]

quantile(quantile: float | Expr, ...) → Self

remote(...) → dict[str, pc.LazyFrameRemote]

remove(*predicates, ...) → Self

rename(mapping, ...) → Self

reverse() → Self

select(*exprs: IntoExpr | Iterable[IntoExpr], **named_exprs) → Self

select_seq(*exprs: IntoExpr | Iterable[IntoExpr], ...) → Self

shift(n: int | IntoExprColumn = 1, *, ...) → Self

show_graph(*, optimized: bool = True, ...) → dict[str, str | None]

skim(...) → dict[str, Collection]

slice(offset: int, length: int | None = None) → Self

sort(by: IntoExpr | Iterable[IntoExpr], *more_by, ...) → Self

sql(query: str, *, table_name: str = 'self') → Self

std(ddof: int = 1) → Self

sum() → Self

tail(n: int = 5) → Self

top_k(k: int, *, by: IntoExpr | Iterable[IntoExpr], ...) → Self

unique(...) → Self

unnest(columns, ...) → Self

unpivot(...) → Self

update(other: polars.LazyFrame, ...) → Self

var(ddof: int = 1) → Self

with_columns(*exprs: IntoExpr | Iterable[IntoExpr], ...) → Self

with_columns_seq(*exprs: IntoExpr | Iterable[IntoExpr], ...) → Self

with_context(other: Self | list[Self]) → Self

with_name(name: str | None) → Self

with_row_count(name: str = 'row_nr', offset: int = 0) → Self

with_row_index(name: str = 'index', offset: int = 0) → Self

without_model() → dict[str, LazyDataset[Any]]

to_dataframe() → dict[str, TypeAliasForwardRef('polars.DataFrame')]

to_lazyframe() → dict[str, TypeAliasForwardRef('polars.LazyFrame')]

to_polars() → dict[str, TypeAliasForwardRef('polars.LazyFrame')]

Methods¶

items() → ItemsView[str, _DST]

keys() → KeysView[str]

values() → ValuesView[_DST]

concat(*, with_key_column: bool | str = False, ...) → _DST

Concatenate all items into a single Dataset/LazyDataset.

group_by(*by, ...) → _CollectionGroupBy

join(other, ...) → Self

Properties¶

property columns : dict[str, Any]

group: Delegated

property dtypes : dict[str, Any]

group: Delegated

property model : dict[str, Any]

group: Delegated

property schema : dict[str, Any]

group: Delegated

property vcol : dict[str, Any]

group: Delegated

property width : dict[str, Any]

group: Delegated

Export¶

to_dict(*, to_polars: bool = False) → dict