datachain 0.6.0__tar.gz → 0.6.1__tar.gz

{datachain-0.6.0/src/datachain.egg-info → datachain-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.0
+Version: 0.6.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -81,7 +81,7 @@ Requires-Dist: requests-mock; extra == "tests"
 Requires-Dist: scipy; extra == "tests"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests]; extra == "dev"
-Requires-Dist: mypy==1.11.2; extra == "dev"
+Requires-Dist: mypy==1.12.0; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"

{datachain-0.6.0 → datachain-0.6.1}/pyproject.toml

@@ -93,7 +93,7 @@ tests = [
 ]
 dev = [
   "datachain[docs,tests]",
-  "mypy==1.11.2",
+  "mypy==1.12.0",
   "types-python-dateutil",
   "types-pytz",
   "types-PyYAML",

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/__init__.py

@@ -1,3 +1,4 @@
+from datachain.lib import func
 from datachain.lib.data_model import DataModel, DataType, is_chain_type
 from datachain.lib.dc import C, Column, DataChain, Sys
 from datachain.lib.file import (
@@ -34,6 +35,7 @@ __all__ = [
     "Sys",
     "TarVFile",
     "TextFile",
+    "func",
     "is_chain_type",
     "metrics",
     "param",

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/catalog/catalog.py

@@ -989,13 +989,6 @@ class Catalog:
             c.name: c.type.to_dict() for c in columns if isinstance(c.type, SQLType)
         }
 
-        job_id = job_id or os.getenv("DATACHAIN_JOB_ID")
-        if not job_id:
-            from datachain.query.session import Session
-
-            session = Session.get(catalog=self)
-            job_id = session.job_id
-
         dataset = self.metastore.create_dataset_version(
             dataset,
             version,
@@ -1218,6 +1211,7 @@ class Catalog:
             preview=dataset_version.preview,
             job_id=dataset_version.job_id,
         )
+
         # to avoid re-creating rows table, we are just renaming it for a new version
         # of target dataset
         self.warehouse.rename_dataset_table(
@@ -1325,8 +1319,6 @@ class Catalog:
         if offset:
             q = q.offset(offset)
 
-        q = q.order_by("sys__id")
-
         return q.to_db_records()
 
     def signed_url(self, source: str, path: str, client_config=None) -> str:

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/data_storage/sqlite.py

@@ -763,6 +763,14 @@ class SQLiteWarehouse(AbstractWarehouse):
         query: Select,
         progress_cb: Optional[Callable[[int], None]] = None,
     ) -> None:
+        if len(query._group_by_clause) > 0:
+            select_q = query.with_only_columns(
+                *[c for c in query.selected_columns if c.name != "sys__id"]
+            )
+            q = table.insert().from_select(list(select_q.selected_columns), select_q)
+            self.db.execute(q)
+            return
+
         if "sys__id" in query.selected_columns:
             col_id = query.selected_columns.sys__id
         else:

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/data_storage/warehouse.py

@@ -215,10 +215,6 @@ class AbstractWarehouse(ABC, Serializable):
         limit = query._limit
         paginated_query = query.limit(page_size)
 
-        if not paginated_query._order_by_clauses:
-            # default order by is order by `sys__id`
-            paginated_query = paginated_query.order_by(query.selected_columns.sys__id)
-
         results = None
         offset = 0
         num_yielded = 0

datachain-0.6.1/src/datachain/lib/convert/sql_to_python.py

@@ -0,0 +1,14 @@
+from decimal import Decimal
+from typing import Any
+
+from sqlalchemy import ColumnElement
+
+
+def sql_to_python(sql_exp: ColumnElement) -> Any:
+    try:
+        type_ = sql_exp.type.python_type
+        if type_ == Decimal:
+            type_ = float
+    except NotImplementedError:
+        type_ = str
+    return type_

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/lib/dc.py

@@ -29,6 +29,7 @@ from datachain.lib.data_model import DataModel, DataType, dict_to_data_model
 from datachain.lib.dataset_info import DatasetInfo
 from datachain.lib.file import ArrowRow, File, get_file_type
 from datachain.lib.file import ExportPlacement as FileExportPlacement
+from datachain.lib.func import Func
 from datachain.lib.listing import (
     is_listing_dataset,
     is_listing_expired,
@@ -42,21 +43,12 @@ from datachain.lib.meta_formats import read_meta, read_schema
 from datachain.lib.model_store import ModelStore
 from datachain.lib.settings import Settings
 from datachain.lib.signal_schema import SignalSchema
-from datachain.lib.udf import (
-    Aggregator,
-    BatchMapper,
-    Generator,
-    Mapper,
-    UDFBase,
-)
+from datachain.lib.udf import Aggregator, BatchMapper, Generator, Mapper, UDFBase
 from datachain.lib.udf_signature import UdfSignature
-from datachain.lib.utils import DataChainParamsError
+from datachain.lib.utils import DataChainColumnError, DataChainParamsError
 from datachain.query import Session
-from datachain.query.dataset import (
-    DatasetQuery,
-    PartitionByType,
-)
-from datachain.query.schema import DEFAULT_DELIMITER, Column, DatasetRow
+from datachain.query.dataset import DatasetQuery, PartitionByType
+from datachain.query.schema import DEFAULT_DELIMITER, Column, ColumnMeta
 from datachain.sql.functions import path as pathfunc
 from datachain.telemetry import telemetry
 from datachain.utils import batched_it, inside_notebook
@@ -149,11 +141,6 @@ class DatasetMergeError(DataChainParamsError):  # noqa: D101
         super().__init__(f"Merge error on='{on_str}'{right_on_str}: {msg}")
 
 
-class DataChainColumnError(DataChainParamsError):  # noqa: D101
-    def __init__(self, col_name, msg):  # noqa: D107
-        super().__init__(f"Error for column {col_name}: {msg}")
-
-
 OutputType = Union[None, DataType, Sequence[str], dict[str, DataType]]
 
 
@@ -982,10 +969,9 @@ class DataChain:
         row is left in the result set.
 
         Example:
-        ```py
-         dc.distinct("file.parent", "file.name")
-        )
-        ```
+            ```py
+            dc.distinct("file.parent", "file.name")
+            ```
         """
         return self._evolve(
             query=self._query.distinct(
@@ -1011,6 +997,60 @@ class DataChain:
             query=self._query.select(*columns), signal_schema=new_schema
         )
 
+    def group_by(
+        self,
+        *,
+        partition_by: Union[str, Sequence[str]],
+        **kwargs: Func,
+    ) -> "Self":
+        """Group rows by specified set of signals and return new signals
+        with aggregated values.
+
+        Example:
+            ```py
+            chain = chain.group_by(
+                cnt=func.count(),
+                partition_by=("file_source", "file_ext"),
+            )
+            ```
+        """
+        if isinstance(partition_by, str):
+            partition_by = [partition_by]
+        if not partition_by:
+            raise ValueError("At least one column should be provided for partition_by")
+
+        if not kwargs:
+            raise ValueError("At least one column should be provided for group_by")
+        for col_name, func in kwargs.items():
+            if not isinstance(func, Func):
+                raise DataChainColumnError(
+                    col_name,
+                    f"Column {col_name} has type {type(func)} but expected Func object",
+                )
+
+        partition_by_columns: list[Column] = []
+        signal_columns: list[Column] = []
+        schema_fields: dict[str, DataType] = {}
+
+        # validate partition_by columns and add them to the schema
+        for col_name in partition_by:
+            col_db_name = ColumnMeta.to_db_name(col_name)
+            col_type = self.signals_schema.get_column_type(col_db_name)
+            col = Column(col_db_name, python_to_sql(col_type))
+            partition_by_columns.append(col)
+            schema_fields[col_db_name] = col_type
+
+        # validate signal columns and add them to the schema
+        for col_name, func in kwargs.items():
+            col = func.get_column(self.signals_schema, label=col_name)
+            signal_columns.append(col)
+            schema_fields[col_name] = func.get_result_type(self.signals_schema)
+
+        return self._evolve(
+            query=self._query.group_by(signal_columns, partition_by_columns),
+            signal_schema=SignalSchema(schema_fields),
+        )
+
     def mutate(self, **kwargs) -> "Self":
         """Create new signals based on existing signals.
 
@@ -1477,12 +1517,6 @@ class DataChain:
         fr_map = {col.lower(): df[col].tolist() for col in df.columns}
 
         for column in fr_map:
-            if column in DatasetRow.schema:
-                raise DatasetPrepareError(
-                    name,
-                    f"import from pandas error - column '{column}' conflicts with"
-                    " default schema",
-                )
             if not column.isidentifier():
                 raise DatasetPrepareError(
                     name,
@@ -1994,6 +2028,8 @@ class DataChain:
             ),
         )
 
+        session.add_dataset_version(dsr, dsr.latest_version)
+
         if isinstance(to_insert, dict):
             to_insert = [to_insert]
         elif not to_insert:

datachain-0.6.1/src/datachain/lib/func/__init__.py

@@ -0,0 +1,14 @@
+from .aggregate import any_value, avg, collect, concat, count, max, min, sum
+from .func import Func
+
+__all__ = [
+    "Func",
+    "any_value",
+    "avg",
+    "collect",
+    "concat",
+    "count",
+    "max",
+    "min",
+    "sum",
+]

datachain-0.6.1/src/datachain/lib/func/aggregate.py

@@ -0,0 +1,42 @@
+from typing import Optional
+
+from sqlalchemy import func as sa_func
+
+from datachain.sql import functions as dc_func
+
+from .func import Func
+
+
+def count(col: Optional[str] = None) -> Func:
+    return Func(inner=sa_func.count, col=col, result_type=int)
+
+
+def sum(col: str) -> Func:
+    return Func(inner=sa_func.sum, col=col)
+
+
+def avg(col: str) -> Func:
+    return Func(inner=dc_func.aggregate.avg, col=col)
+
+
+def min(col: str) -> Func:
+    return Func(inner=sa_func.min, col=col)
+
+
+def max(col: str) -> Func:
+    return Func(inner=sa_func.max, col=col)
+
+
+def any_value(col: str) -> Func:
+    return Func(inner=dc_func.aggregate.any_value, col=col)
+
+
+def collect(col: str) -> Func:
+    return Func(inner=dc_func.aggregate.collect, col=col, is_array=True)
+
+
+def concat(col: str, separator="") -> Func:
+    def inner(arg):
+        return dc_func.aggregate.group_concat(arg, separator)
+
+    return Func(inner=inner, col=col, result_type=str)

datachain-0.6.1/src/datachain/lib/func/func.py

@@ -0,0 +1,64 @@
+from typing import TYPE_CHECKING, Callable, Optional
+
+from datachain.lib.convert.python_to_sql import python_to_sql
+from datachain.lib.utils import DataChainColumnError
+from datachain.query.schema import Column, ColumnMeta
+
+if TYPE_CHECKING:
+    from datachain import DataType
+    from datachain.lib.signal_schema import SignalSchema
+
+
+class Func:
+    def __init__(
+        self,
+        inner: Callable,
+        col: Optional[str] = None,
+        result_type: Optional["DataType"] = None,
+        is_array: bool = False,
+    ) -> None:
+        self.inner = inner
+        self.col = col
+        self.result_type = result_type
+        self.is_array = is_array
+
+    @property
+    def db_col(self) -> Optional[str]:
+        return ColumnMeta.to_db_name(self.col) if self.col else None
+
+    def db_col_type(self, signals_schema: "SignalSchema") -> Optional["DataType"]:
+        if not self.db_col:
+            return None
+        col_type: type = signals_schema.get_column_type(self.db_col)
+        return list[col_type] if self.is_array else col_type  # type: ignore[valid-type]
+
+    def get_result_type(self, signals_schema: "SignalSchema") -> "DataType":
+        col_type = self.db_col_type(signals_schema)
+
+        if self.result_type:
+            return self.result_type
+
+        if col_type:
+            return col_type
+
+        raise DataChainColumnError(
+            str(self.inner),
+            "Column name is required to infer result type",
+        )
+
+    def get_column(
+        self, signals_schema: "SignalSchema", label: Optional[str] = None
+    ) -> Column:
+        if self.col:
+            if label == "collect":
+                print(label)
+            col_type = self.get_result_type(signals_schema)
+            col = Column(self.db_col, python_to_sql(col_type))
+            func_col = self.inner(col)
+        else:
+            func_col = self.inner()
+
+        if label:
+            func_col = func_col.label(label)
+
+        return func_col

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/lib/signal_schema.py

@@ -400,6 +400,12 @@ class SignalSchema:
             if ModelStore.is_pydantic(finfo.annotation):
                 SignalSchema._set_file_stream(getattr(obj, field), catalog, cache)
 
+    def get_column_type(self, col_name: str) -> DataType:
+        for path, _type, has_subtree, _ in self.get_flat_tree():
+            if not has_subtree and DEFAULT_DELIMITER.join(path) == col_name:
+                return _type
+        raise SignalResolvingError([col_name], "is not found")
+
     def db_signals(
         self, name: Optional[str] = None, as_columns=False
     ) -> Union[list[str], list[Column]]:
@@ -490,7 +496,7 @@ class SignalSchema:
                 new_values[name] = args_map[name]
             else:
                 # adding new signal
-                new_values.update(sql_to_python({name: value}))
+                new_values[name] = sql_to_python(value)
 
         return SignalSchema(new_values)
 
@@ -534,12 +540,12 @@ class SignalSchema:
             for name, val in values.items()
         }
 
-    def get_flat_tree(self) -> Iterator[tuple[list[str], type, bool, int]]:
+    def get_flat_tree(self) -> Iterator[tuple[list[str], DataType, bool, int]]:
         yield from self._get_flat_tree(self.tree, [], 0)
 
     def _get_flat_tree(
         self, tree: dict, prefix: list[str], depth: int
-    ) -> Iterator[tuple[list[str], type, bool, int]]:
+    ) -> Iterator[tuple[list[str], DataType, bool, int]]:
         for name, (type_, substree) in tree.items():
             suffix = name.split(".")
             new_prefix = prefix + suffix

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/lib/utils.py

@@ -23,3 +23,8 @@ class DataChainError(Exception):
 class DataChainParamsError(DataChainError):
     def __init__(self, message):
         super().__init__(message)
+
+
+class DataChainColumnError(DataChainParamsError):
+    def __init__(self, col_name, msg):
+        super().__init__(f"Error for column {col_name}: {msg}")

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/query/__init__.py

@@ -1,12 +1,11 @@
 from .dataset import DatasetQuery
 from .params import param
-from .schema import C, DatasetRow, LocalFilename, Object, Stream
+from .schema import C, LocalFilename, Object, Stream
 from .session import Session
 
 __all__ = [
     "C",
     "DatasetQuery",
-    "DatasetRow",
     "LocalFilename",
     "Object",
     "Session",

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/query/batch.py

@@ -97,7 +97,6 @@ class Partition(BatchingStrategy):
 
         ordered_query = query.order_by(None).order_by(
             PARTITION_COLUMN_ID,
-            "sys__id",
             *query._order_by_clauses,
         )
 

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/query/dataset.py

@@ -591,10 +591,6 @@ class UDFSignal(UDFStep):
             return query, []
         table = self.catalog.warehouse.create_pre_udf_table(query)
         q: Select = sqlalchemy.select(*table.c)
-        if query._order_by_clauses:
-            # we are adding ordering only if it's explicitly added by user in
-            # query part before adding signals
-            q = q.order_by(table.c.sys__id)
         return q, [table]
 
     def create_result_query(
@@ -630,11 +626,6 @@ class UDFSignal(UDFStep):
             else:
                 res = sqlalchemy.select(*cols1).select_from(subq)
 
-            if query._order_by_clauses:
-                # if ordering is used in query part before adding signals, we
-                # will have it as order by id from select from pre-created udf table
-                res = res.order_by(subq.c.sys__id)
-
             if self.partition_by is not None:
                 subquery = res.subquery()
                 res = sqlalchemy.select(*subquery.c).select_from(subquery)
@@ -666,13 +657,6 @@ class RowGenerator(UDFStep):
     def create_result_query(
         self, udf_table, query: Select
     ) -> tuple[QueryGeneratorFunc, list["sqlalchemy.Column"]]:
-        if not query._order_by_clauses:
-            # if we are not selecting all rows in UDF, we need to ensure that
-            # we get the same rows as we got as inputs of UDF since selecting
-            # without ordering can be non deterministic in some databases
-            c = query.selected_columns
-            query = query.order_by(c.sys__id)
-
         udf_table_query = udf_table.select().subquery()
         udf_table_cols: list[sqlalchemy.Label[Any]] = [
             label(c.name, c) for c in udf_table_query.columns
@@ -957,24 +941,24 @@ class SQLJoin(Step):
 
 
 @frozen
-class GroupBy(Step):
-    """Group rows by a specific column."""
-
-    cols: PartitionByType
+class SQLGroupBy(SQLClause):
+    cols: Sequence[Union[str, ColumnElement]]
+    group_by: Sequence[Union[str, ColumnElement]]
 
-    def clone(self) -> "Self":
-        return self.__class__(self.cols)
+    def apply_sql_clause(self, query) -> Select:
+        if not self.cols:
+            raise ValueError("No columns to select")
+        if not self.group_by:
+            raise ValueError("No columns to group by")
 
-    def apply(
-        self, query_generator: QueryGenerator, temp_tables: list[str]
-    ) -> StepResult:
-        query = query_generator.select()
-        grouped_query = query.group_by(*self.cols)
+        subquery = query.subquery()
 
-        def q(*columns):
-            return grouped_query.with_only_columns(*columns)
+        cols = [
+            subquery.c[str(c)] if isinstance(c, (str, C)) else c
+            for c in [*self.group_by, *self.cols]
+        ]
 
-        return step_result(q, grouped_query.selected_columns)
+        return sqlalchemy.select(*cols).select_from(subquery).group_by(*self.group_by)
 
 
 def _validate_columns(
@@ -1130,25 +1114,14 @@ class DatasetQuery:
             query.steps = query.steps[-1:] + query.steps[:-1]
 
         result = query.starting_step.apply()
-        group_by = None
         self.dependencies.update(result.dependencies)
 
         for step in query.steps:
-            if isinstance(step, GroupBy):
-                if group_by is not None:
-                    raise TypeError("only one group_by allowed")
-                group_by = step
-                continue
-
             result = step.apply(
                 result.query_generator, self.temp_table_names
             )  # a chain of steps linked by results
             self.dependencies.update(result.dependencies)
 
-        if group_by:
-            result = group_by.apply(result.query_generator, self.temp_table_names)
-            self.dependencies.update(result.dependencies)
-
         return result.query_generator
 
     @staticmethod
@@ -1410,9 +1383,13 @@ class DatasetQuery:
         return query.as_scalar()
 
     @detach
-    def group_by(self, *cols: ColumnElement) -> "Self":
+    def group_by(
+        self,
+        cols: Sequence[ColumnElement],
+        group_by: Sequence[ColumnElement],
+    ) -> "Self":
         query = self.clone()
-        query.steps.append(GroupBy(cols))
+        query.steps.append(SQLGroupBy(cols, group_by))
         return query
 
     @detach
@@ -1591,6 +1568,8 @@ class DatasetQuery:
             )
             version = version or dataset.latest_version
 
+            self.session.add_dataset_version(dataset=dataset, version=version)
+
             dr = self.catalog.warehouse.dataset_rows(dataset)
 
             self.catalog.warehouse.copy_table(dr.get_table(), query.select())

{datachain-0.6.0 → datachain-0.6.1}/src/datachain/query/schema.py

@@ -1,16 +1,13 @@
 import functools
-import json
 from abc import ABC, abstractmethod
-from datetime import datetime, timezone
 from fnmatch import fnmatch
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Optional, Union
+from typing import TYPE_CHECKING, Any, Callable, Optional, Union
 
 import attrs
 import sqlalchemy as sa
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback
 
 from datachain.lib.file import File
-from datachain.sql.types import JSON, Boolean, DateTime, Int64, SQLType, String
 
 if TYPE_CHECKING:
     from datachain.catalog import Catalog
@@ -228,61 +225,4 @@ def normalize_param(param: UDFParamSpec) -> UDFParameter:
     raise TypeError(f"Invalid UDF parameter: {param}")
 
 
-class DatasetRow:
-    schema: ClassVar[dict[str, type[SQLType]]] = {
-        "source": String,
-        "path": String,
-        "size": Int64,
-        "location": JSON,
-        "is_latest": Boolean,
-        "last_modified": DateTime,
-        "version": String,
-        "etag": String,
-    }
-
-    @staticmethod
-    def create(
-        path: str,
-        source: str = "",
-        size: int = 0,
-        location: Optional[dict[str, Any]] = None,
-        is_latest: bool = True,
-        last_modified: Optional[datetime] = None,
-        version: str = "",
-        etag: str = "",
-    ) -> tuple[
-        str,
-        str,
-        int,
-        Optional[str],
-        int,
-        bool,
-        datetime,
-        str,
-        str,
-        int,
-    ]:
-        if location:
-            location = json.dumps([location])  # type: ignore [assignment]
-
-        last_modified = last_modified or datetime.now(timezone.utc)
-
-        return (  # type: ignore [return-value]
-            source,
-            path,
-            size,
-            location,
-            is_latest,
-            last_modified,
-            version,
-            etag,
-        )
-
-    @staticmethod
-    def extend(**columns):
-        cols = {**DatasetRow.schema}
-        cols.update(columns)
-        return cols
-
-
 C = Column