datachain 0.1.11__py3-none-any.whl → 0.1.13__py3-none-any.whl

datachain/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.11'
-__version_tuple__ = version_tuple = (0, 1, 11)
+__version__ = version = '0.1.13'
+__version_tuple__ = version_tuple = (0, 1, 13)

datachain/lib/dc.py

@@ -492,16 +492,43 @@ class DataChain(DatasetQuery):
         chain.signals_schema = new_schema
         return chain
 
-    def get_values(self) -> Iterator[list]:
-        """Iterate over rows, getting feature values and applying reader calls."""
-        for features in self.iterate():
-            yield [fr.get_value() if isinstance(fr, Feature) else fr for fr in features]
+    def get_values(self, *cols: str) -> Iterator[list]:
+        """Iterate over rows, getting feature values and applying reader calls.
+        If columns are specified - limit them to specified columns.
+        """
+        for features in self.iterate(*cols):
+            yield [fr.get_value() if isinstance(fr, Feature) else fr for fr in features]  # type: ignore[union-attr,call-arg]
+
+    def get_one_value(self, col: str) -> Iterator:
+        for item in self.get_values(col):
+            yield item[0]
 
-    def iterate(self) -> Iterator[Sequence[Feature]]:
-        db_signals = self.signals_schema.db_signals()
+    def iterate(self, *cols: str) -> Iterator[list[FeatureType]]:
+        """Iterate over rows. If columns are specified - limit them to specified
+        columns.
+        """
+        chain = self.select(*cols) if cols else self
+
+        db_signals = chain.signals_schema.db_signals()
         with super().select(*db_signals).as_iterable() as rows_iter:
             for row in rows_iter:
-                yield self.signals_schema.row_to_features(row, self.session.catalog)
+                yield chain.signals_schema.row_to_features(row, chain.session.catalog)
+
+    def iterate_one(self, col: str) -> Iterator[FeatureType]:
+        for item in self.iterate(col):
+            yield item[0]
+
+    def collect(self, *cols: str) -> list[list[FeatureType]]:
+        return list(self.iterate(*cols))
+
+    def collect_one(self, col: str) -> list[FeatureType]:
+        return list(self.iterate_one(col))
+
+    def collect_values(self, *cols: str) -> list[list]:
+        return list(self.get_values(*cols))
+
+    def collect_one_value(self, col: str) -> list:
+        return list(self.get_one_value(col))
 
     def to_pytorch(self, **kwargs):
         """Convert to pytorch dataset format."""

{datachain-0.1.11.dist-info → datachain-0.1.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.1.11
+Version: 0.1.13
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.1.11.dist-info → datachain-0.1.13.dist-info}/RECORD

@@ -1,6 +1,6 @@
 datachain/__init__.py,sha256=9a0qX6tqyA9KC3ahLmGarqlRTZJXhM7HijAWpfUaOnQ,102
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
-datachain/_version.py,sha256=HreDwlLXV189L3kiBj3huM_kqWD1usijlC8LN1YXcCM,413
+datachain/_version.py,sha256=S22EPqqZRb53L2H7sobVA3TUXv9skvkYd-YtLuHuV6M,413
 datachain/asyn.py,sha256=opARBVZJxTKU3EGYd-8gcpNXoshuCfVz_b0ut3oxC50,7641
 datachain/cache.py,sha256=FaPWrqWznPffmskTb1pdPkt2jAMMf__9FC2zEnP0vDU,4022
 datachain/cli.py,sha256=1mBozBJS9Nq-EeahxwyKH8ef64E2v93o0CAEzxjcbkY,32209
@@ -40,7 +40,7 @@ datachain/data_storage/warehouse.py,sha256=sQLOrv6DH8UcWH1aqlg3YJKmaHr696XkVafBx
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/cached_stream.py,sha256=BQI6gpJ2y7_-jqQo_0VB9ntbkOVISvj9wlDwGDQbqw8,3537
 datachain/lib/claude.py,sha256=iAauA1zNVNONpLzUo1t0QN5PZ5Ot6cZkfib7Ka_c638,1969
-datachain/lib/dc.py,sha256=kyuSg-l7HciqFaunqPx41WKyAeuJ2H2tpWJplCXhZJc,26086
+datachain/lib/dc.py,sha256=MAy1Bsxknaz2aduZ28ffuq88x8Ja8QHA59CsyyiUlZE,27048
 datachain/lib/feature.py,sha256=C5lxQ_Ef4rL0-mef4A4EeoqB0rcNZ0ExRE26ehx20RM,14196
 datachain/lib/feature_registry.py,sha256=hg_S_9JPEYaQ-8PI64mU0sEhSJ-rcrKtwQk5TPBotEw,1570
 datachain/lib/feature_utils.py,sha256=6wbKZ2xq08b751EFBRJy1OZLqWYd_gxq9A_Em_aMFk4,4713
@@ -92,9 +92,9 @@ datachain/sql/sqlite/__init__.py,sha256=TAdJX0Bg28XdqPO-QwUVKy8rg78cgMileHvMNot7
 datachain/sql/sqlite/base.py,sha256=XVxn4pB-N4pPfiby5uVvfH7feNzRKlBNzsc5eyKPvhI,10965
 datachain/sql/sqlite/types.py,sha256=oP93nLfTBaYnN0z_4Dsv-HZm8j9rrUf1esMM-z3JLbg,1754
 datachain/sql/sqlite/vector.py,sha256=stBeEW6fbVbILmAtV4khjXdJIGT13HkRWJeCoqIOk50,315
-datachain-0.1.11.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.1.11.dist-info/METADATA,sha256=BFTmlt8_vtCHF80AHQcIQkE9YMCigp7k1jcAZV1D7j4,13972
-datachain-0.1.11.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
-datachain-0.1.11.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.1.11.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.1.11.dist-info/RECORD,,
+datachain-0.1.13.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.1.13.dist-info/METADATA,sha256=aqjqnY-YxqDJZhpkKaPQ35QZkehWOcsGIdqNzdLRw-0,13972
+datachain-0.1.13.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
+datachain-0.1.13.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.1.13.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.1.13.dist-info/RECORD,,