Merge branch 'master' into 4310-read-csv-glob-lists-of-lists-of-ints

.github/workflows/ci.yml

@@ -115,6 +115,7 @@ jobs:
             modin/experimental/core/execution/native/implementations/omnisci_on_native/expr.py \
             modin/experimental/core/execution/native/implementations/omnisci_on_native/omnisci_worker.py \
       - run: python scripts/doc_checker.py modin/experimental/core/storage_formats/omnisci
+      - run: python scripts/doc_checker.py modin/experimental/core/execution/native/implementations/omnisci_on_native/exchange/dataframe_protocol
 
   lint-flake8:
     name: lint (flake8)
@@ -339,6 +340,8 @@ jobs:
       - run: MODIN_BENCHMARK_MODE=True pytest modin/pandas/test/internals/test_benchmark_mode.py
       - run: pytest modin/experimental/core/execution/native/implementations/omnisci_on_native/test/test_dataframe.py
       - run: pytest modin/pandas/test/test_io.py::TestCsv --verbose
+      - run: pytest modin/test/exchange/dataframe_protocol/test_general.py
+      - run: pytest modin/test/exchange/dataframe_protocol/omnisci
       - uses: codecov/codecov-action@v2
 
   test-asv-benchmarks:
@@ -480,6 +483,7 @@ jobs:
       - run: python -m pytest modin/experimental/pandas/test/test_io_exp.py
       - run: pip install "dfsql>=0.4.2" "pyparsing<=2.4.7" && pytest modin/experimental/sql/test/test_sql.py
       - run: pytest modin/test/exchange/dataframe_protocol/test_general.py
+      - run: pytest modin/test/exchange/dataframe_protocol/pandas/test_protocol.py
       - uses: codecov/codecov-action@v2
 
   test-experimental:

.github/workflows/push.yml

@@ -110,6 +110,8 @@ jobs:
       - run: pytest modin/test/storage_formats/omnisci/test_internals.py
       - run: pytest modin/experimental/core/execution/native/implementations/omnisci_on_native/test/test_dataframe.py
       - run: pytest modin/pandas/test/test_io.py::TestCsv
+      - run: pytest modin/test/exchange/dataframe_protocol/test_general.py
+      - run: pytest modin/test/exchange/dataframe_protocol/omnisci
       - uses: codecov/codecov-action@v2
 
   test-all:
@@ -182,6 +184,7 @@ jobs:
       - run: python -m pytest modin/pandas/test/test_io.py
       - run: python -m pytest modin/experimental/pandas/test/test_io_exp.py
       - run: pytest modin/test/exchange/dataframe_protocol/test_general.py
+      - run: pytest modin/test/exchange/dataframe_protocol/pandas/test_protocol.py
       - uses: codecov/codecov-action@v2
 
   test-windows:

docs/release_notes/release_notes-0.14.0.rst

@@ -24,9 +24,9 @@ Key Features and Updates
   * FIX-#4303: Fix the syntax error in reading from postgres (#4304)
   * FIX-#4308: Add proper error handling in df.set_index (#4309)
   * FIX-#4056: Allow an empty parse_date list in `read_csv_glob` (#4074)
-  * FIX-#4312: Fix constructing categorical frame with duplicate column names (#4313).  
-  * FIX-#4314: Allow passing a series of dtypes to astype (#4318)  
-  * FIX-#4310: Handle lists of lists of ints in read_csv_glob (#4319)  
+  * FIX-#4312: Fix constructing categorical frame with duplicate column names (#4313).
+  * FIX-#4314: Allow passing a series of dtypes to astype (#4318)
+  * FIX-#4310: Handle lists of lists of ints in read_csv_glob (#4319)
 * Performance enhancements
   * FIX-#4138, FIX-#4009: remove redundant sorting in the internal '.mask()' flow (#4140)
   * FIX-#4183: Stop shallow copies from creating global shared state. (#4184)
@@ -54,6 +54,9 @@ Key Features and Updates
   *
 * Developer API enhancements
   * FEAT-#4245: Define base interface for dataframe exchange protocol (#4246)
+  * FEAT-#4244: Implement dataframe exchange protocol for OmnisciOnNative execution (#4269)
+  * FEAT-#4144: Implement dataframe exchange protocol for pandas storage format (#4150)
+  * FEAT-#4342: Support `from_dataframe`` for pandas storage format (#4343)
 * Update testing suite
   * TEST-#3628: Report coverage data for `test-internals` CI job (#4198)
   * TEST-#3938: Test tutorial notebooks in CI (#4145)
@@ -74,6 +77,9 @@ Key Features and Updates
   * DOCS-#4280: Change links in jupyter notebooks (#4281)
   * DOCS-#4290: Add changes for OmniSci notebooks (#4291)
   * DOCS-#4241: Update warnings and docs regarding defaulting to pandas (#4242)
+  * DOCS-#3099: Fix `BasePandasDataSet` docstrings warnings (#4333)
+  * DOCS-#4339: Reformat I/O functions docstrings (#4341)
+  * DOCS-#4336: Reformat general utilities docstrings (#4338)
 * Dependencies
   * FIX-#4113, FIX-#4116, FIX-#4115: Apply new `black` formatting, fix pydocstyle check and readthedocs build (#4114)
   * TEST-#3227: Use codecov github action instead of bash form in GA workflows (#3226)

modin/core/dataframe/base/exchange/dataframe_protocol/utils.py

@@ -124,6 +124,16 @@ class ArrowCTypes:
     #   - microseconds -> 'u'
     #   - nanoseconds -> 'n'
     TIMESTAMP = "ts{resolution}:{tz}"
+    TIME = "tt{resolution}"
+
+
+class Endianness:
+    """Enum indicating the byte-order of a data-type."""
+
+    LITTLE = "<"
+    BIG = ">"
+    NATIVE = "="
+    NA = "|"
 
 
 def pandas_dtype_to_arrow_c(dtype) -> str:
@@ -158,3 +168,19 @@ def pandas_dtype_to_arrow_c(dtype) -> str:
     raise NotImplementedError(
         f"Convertion of {dtype} to Arrow C format string is not implemented."
     )
+
+
+def raise_copy_alert(copy_reason=None):
+    """
+    Raise a ``RuntimeError`` mentioning that there's a copy required.
+
+    Parameters
+    ----------
+    copy_reason : str, optional
+        The reason of making a copy. Should fit to the following format:
+        'The copy occured due to {copy_reason}.'.
+    """
+    msg = "Copy required but 'allow_copy=False' is set."
+    if copy_reason:
+        msg += f" The copy occured due to {copy_reason}."
+    raise RuntimeError(msg)

modin/core/dataframe/pandas/dataframe/dataframe.py

@@ -2859,3 +2859,36 @@ def __dataframe__(self, nan_as_null: bool = False, allow_copy: bool = True):
         return PandasProtocolDataframe(
             self, nan_as_null=nan_as_null, allow_copy=allow_copy
         )
+
+    @classmethod
+    def from_dataframe(cls, df: "ProtocolDataframe") -> "PandasDataframe":
+        """
+        Convert a DataFrame implementing the dataframe exchange protocol to a Core Modin Dataframe.
+
+        See more about the protocol in https://data-apis.org/dataframe-protocol/latest/index.html.
+
+        Parameters
+        ----------
+        df : ProtocolDataframe
+            The DataFrame object supporting the dataframe exchange protocol.
+
+        Returns
+        -------
+        PandasDataframe
+            A new Core Modin Dataframe object.
+        """
+        if type(df) == cls:
+            return df
+
+        if not hasattr(df, "__dataframe__"):
+            raise ValueError(
+                "`df` does not support DataFrame exchange protocol, i.e. `__dataframe__` method"
+            )
+
+        from modin.core.dataframe.pandas.exchange.dataframe_protocol.from_dataframe import (
+            from_dataframe_to_pandas,
+        )
+
+        ErrorMessage.default_to_pandas(message="`from_dataframe`")
+        pandas_df = from_dataframe_to_pandas(df)
+        return cls.from_pandas(pandas_df)