dagster-pandas 0.19.5__tar.gz → 0.27.9__tar.gz

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2023 Elementl, Inc.
+   Copyright 2025 Dagster Labs, Inc.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

{dagster-pandas-0.19.5/dagster_pandas.egg-info → dagster_pandas-0.27.9}/PKG-INFO

@@ -1,22 +1,36 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dagster-pandas
-Version: 0.19.5
+Version: 0.27.9
 Summary: Utilities and examples for working with pandas and dagster, an opinionated framework for expressing data pipelines
 Home-page: https://github.com/dagster-io/dagster
-Author: Elementl
-Author-email: hello@elementl.com
+Author: Dagster Labs
+Author-email: hello@dagsterlabs.com
 License: Apache-2.0
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: dagster==1.11.9
+Requires-Dist: pandas
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # dagster-pandas
 
 The docs for `dagster-pandas` can be found
-[here](https://docs.dagster.io/_apidocs/libraries/dagster-pandas).
+[here](https://docs.dagster.io/api/python-api/libraries/dagster-pandas).

dagster_pandas-0.27.9/README.md

@@ -0,0 +1,4 @@
+# dagster-pandas
+
+The docs for `dagster-pandas` can be found
+[here](https://docs.dagster.io/api/python-api/libraries/dagster-pandas).

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/__init__.py

@@ -1,6 +1,6 @@
-from dagster._core.libraries import DagsterLibraryRegistry
+from dagster_shared.libraries import DagsterLibraryRegistry
 
-from .constraints import (
+from dagster_pandas.constraints import (
     ColumnWithMetadataException,
     ConstraintWithMetadata,
     ConstraintWithMetadataException,
@@ -17,34 +17,34 @@ from .constraints import (
     non_null_validation,
     nonnull,
 )
-from .data_frame import (
+from dagster_pandas.data_frame import (
     DataFrame,
     create_dagster_pandas_dataframe_type,
     create_structured_dataframe_type,
 )
-from .validation import PandasColumn
-from .version import __version__
+from dagster_pandas.validation import PandasColumn
+from dagster_pandas.version import __version__
 
 DagsterLibraryRegistry.register("dagster-pandas", __version__)
 
 __all__ = [
-    "DataFrame",
-    "create_dagster_pandas_dataframe_type",
-    "create_structured_dataframe_type",
-    "PandasColumn",
     "ColumnWithMetadataException",
+    "ConstraintWithMetadata",
     "ConstraintWithMetadataException",
+    "DataFrame",
     "MultiAggregateConstraintWithMetadata",
     "MultiColumnConstraintWithMetadata",
-    "ConstraintWithMetadata",
     "MultiConstraintWithMetadata",
+    "PandasColumn",
     "RowCountConstraint",
     "StrictColumnsConstraint",
     "StrictColumnsWithMetadata",
     "all_unique_validator",
+    "categorical_column_validator_factory",
     "column_range_validation_factory",
+    "create_dagster_pandas_dataframe_type",
+    "create_structured_dataframe_type",
     "dtype_in_set_validation_factory",
-    "nonnull",
     "non_null_validation",
-    "categorical_column_validator_factory",
+    "nonnull",
 ]

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/constraints.py

@@ -2,6 +2,7 @@ import sys
 from collections import defaultdict
 from datetime import datetime
 from functools import wraps
+from typing import Final
 
 import pandas as pd
 from dagster import (
@@ -9,9 +10,8 @@ from dagster import (
     TypeCheck,
     _check as check,
 )
-from dagster._utils.backcompat import experimental_class_warning
+from dagster._annotations import beta
 from pandas import DataFrame
-from typing_extensions import Final
 
 CONSTRAINT_METADATA_KEY: Final = "constraint_metadata"
 
@@ -20,6 +20,7 @@ class ConstraintViolationException(Exception):
     """Indicates that a constraint has been violated."""
 
 
+@beta
 class ConstraintWithMetadataException(Exception):
     """This class defines the response generated when a pandas DF fails validation -- it can be used to generate either a
     failed typecheck or an exception.
@@ -45,14 +46,8 @@ class ConstraintWithMetadataException(Exception):
         self.expectation = check.opt_inst_param(expectation, "expectation", (dict, list, str, set))
         self.offending = check.opt_inst_param(offending, "offending", (dict, list, str, set))
         self.actual = check.opt_inst_param(actual, "actual", (dict, list, str, set))
-        super(ConstraintWithMetadataException, self).__init__(
-            "Violated {} - {}, {} was/were expected, but we received {} which was/were {}".format(
-                constraint_name,
-                constraint_description,
-                expectation,
-                offending,
-                actual,
-            )
+        super().__init__(
+            f"Violated {constraint_name} - {constraint_description}, {expectation} was/were expected, but we received {offending} which was/were {actual}"
         )
 
     def normalize_metadata_json_value(self, val):
@@ -82,16 +77,12 @@ class DataFrameConstraintViolationException(ConstraintViolationException):
     """Indicates a dataframe level constraint has been violated."""
 
     def __init__(self, constraint_name, constraint_description):
-        super(DataFrameConstraintViolationException, self).__init__(
-            "Violated {constraint_name} - {constraint_description}".format(
-                constraint_name=constraint_name, constraint_description=constraint_description
-            )
-        )
+        super().__init__(f"Violated {constraint_name} - {constraint_description}")
 
 
 class DataFrameWithMetadataException(ConstraintWithMetadataException):
     def __init__(self, constraint_name, constraint_description, expectation, actual):
-        super(DataFrameWithMetadataException, self).__init__(
+        super().__init__(
             constraint_name, constraint_description, expectation, "a malformed dataframe", actual
         )
 
@@ -104,27 +95,21 @@ class ColumnConstraintViolationException(ConstraintViolationException):
         self.constraint_description = constraint_description
         self.column_name = column_name
         self.offending_rows = offending_rows
-        super(ColumnConstraintViolationException, self).__init__(self.construct_message())
+        super().__init__(self.construct_message())
 
     def construct_message(self):
-        base_message = (
-            'Violated "{constraint_name}" for column "{column_name}" - {constraint_description}'
-            .format(
-                constraint_name=self.constraint_name,
-                constraint_description=self.constraint_description,
-                column_name=self.column_name,
-            )
-        )
+        base_message = f'Violated "{self.constraint_name}" for column "{self.column_name}" - {self.constraint_description}'
         if self.offending_rows is not None:
-            base_message += "The offending (index, row values) are the following: {}".format(
-                self.offending_rows
+            base_message += (
+                f"The offending (index, row values) are the following: {self.offending_rows}"
             )
         return base_message
 
 
+@beta
 class ColumnWithMetadataException(ConstraintWithMetadataException):
     def __init__(self, constraint_name, constraint_description, expectation, offending, actual):
-        super(ColumnWithMetadataException, self).__init__(
+        super().__init__(
             "the column constraint " + constraint_name,
             constraint_description,
             expectation,
@@ -138,7 +123,7 @@ class Constraint:
 
     Args:
         error_description (Optional[str]): The plain string description that is output in the terminal if the constraint fails.
-        markdown_description (Optional[str]): A markdown supported description that is emitted by dagit if the constraint fails.
+        markdown_description (Optional[str]): A markdown supported description that is shown in the Dagster UI if the constraint fails.
     """
 
     def __init__(self, error_description=None, markdown_description=None):
@@ -147,6 +132,7 @@ class Constraint:
         self.error_description = check.str_param(error_description, "error_description")
 
 
+@beta
 class ConstraintWithMetadata:
     """This class defines a base constraint over pandas DFs with organized metadata.
 
@@ -168,7 +154,6 @@ class ConstraintWithMetadata:
     def __init__(
         self, description, validation_fn, resulting_exception, raise_or_typecheck=True, name=None
     ):
-        experimental_class_warning(self.__class__.__name__)
         if name is None:
             self.name = self.__class__.__name__
         else:
@@ -203,14 +188,13 @@ class ConstraintWithMetadata:
             )
         return DagsterType(
             name=self.name,
-            description="A Pandas DataFrame with the following validation: {}".format(
-                self.description
-            ),
-            type_check_fn=lambda x: self.validate(x, *args),
+            description=f"A Pandas DataFrame with the following validation: {self.description}",
+            type_check_fn=lambda x: self.validate(x, *args),  # pyright: ignore[reportArgumentType]
             **kwargs,
         )
 
 
+@beta
 class MultiConstraintWithMetadata(ConstraintWithMetadata):
     """Use this class if you have multiple constraints to check over the entire dataframe.
 
@@ -247,7 +231,7 @@ class MultiConstraintWithMetadata(ConstraintWithMetadata):
                         metadict[key][validation_fn_arr[i].__name__] = dicta[key]
             return (truthparam, metadict)
 
-        super(MultiConstraintWithMetadata, self).__init__(
+        super().__init__(
             description,
             validation_fn,
             resulting_exception,
@@ -256,6 +240,7 @@ class MultiConstraintWithMetadata(ConstraintWithMetadata):
         )
 
 
+@beta
 class StrictColumnsWithMetadata(ConstraintWithMetadata):
     def __init__(self, column_list, enforce_ordering=False, raise_or_typecheck=True, name=None):
         self.enforce_ordering = check.bool_param(enforce_ordering, "enforce_ordering")
@@ -283,7 +268,7 @@ class StrictColumnsWithMetadata(ConstraintWithMetadata):
         basestr = f"ensuring that the right columns, {self.column_list} were present"
         if enforce_ordering:
             basestr += " in the right order"
-        super(StrictColumnsWithMetadata, self).__init__(
+        super().__init__(
             basestr,
             validation_fcn,
             DataFrameWithMetadataException,
@@ -297,11 +282,11 @@ class DataFrameConstraint(Constraint):
 
     Args:
         error_description (Optional[str]): The plain string description that is output in the terminal if the constraint fails.
-        markdown_description (Optional[str]): A markdown supported description that is emitted by dagit if the constraint fails.
+        markdown_description (Optional[str]): A markdown supported description that is shown in the Dagster UI if the constraint fails.
     """
 
     def __init__(self, error_description=None, markdown_description=None):
-        super(DataFrameConstraint, self).__init__(
+        super().__init__(
             error_description=error_description, markdown_description=markdown_description
         )
 
@@ -309,6 +294,7 @@ class DataFrameConstraint(Constraint):
         raise NotImplementedError()
 
 
+@beta
 class StrictColumnsConstraint(DataFrameConstraint):
     """A dataframe constraint that validates column existence and ordering.
 
@@ -326,9 +312,7 @@ class StrictColumnsConstraint(DataFrameConstraint):
         description = f"No columns outside of {self.strict_column_list} allowed. "
         if enforce_ordering:
             description += "Columns must be in that order."
-        super(StrictColumnsConstraint, self).__init__(
-            error_description=description, markdown_description=description
-        )
+        super().__init__(error_description=description, markdown_description=description)
 
     def validate(self, dataframe):
         check.inst_param(dataframe, "dataframe", DataFrame)
@@ -338,22 +322,19 @@ class StrictColumnsConstraint(DataFrameConstraint):
                 raise DataFrameConstraintViolationException(
                     constraint_name=self.name,
                     constraint_description=(
-                        "Expected the following ordering of columns {expected}. Received:"
-                        " {received}".format(
-                            expected=self.strict_column_list, received=columns_received
-                        )
+                        f"Expected the following ordering of columns {self.strict_column_list}. Received:"
+                        f" {columns_received}"
                     ),
                 )
         for column in columns_received:
             if column not in self.strict_column_list:
                 raise DataFrameConstraintViolationException(
                     constraint_name=self.name,
-                    constraint_description="Expected {}. Recevied {}.".format(
-                        self.strict_column_list, columns_received
-                    ),
+                    constraint_description=f"Expected {self.strict_column_list}. Recevied {columns_received}.",
                 )
 
 
+@beta
 class RowCountConstraint(DataFrameConstraint):
     """A dataframe constraint that validates the expected count of rows.
 
@@ -367,12 +348,8 @@ class RowCountConstraint(DataFrameConstraint):
         self.error_tolerance = abs(check.int_param(error_tolerance, "error_tolerance"))
         if self.error_tolerance > self.num_allowed_rows:
             raise ValueError("Tolerance can't be greater than the number of rows you expect.")
-        description = "Dataframe must have {} +- {} rows.".format(
-            self.num_allowed_rows, self.error_tolerance
-        )
-        super(RowCountConstraint, self).__init__(
-            error_description=description, markdown_description=description
-        )
+        description = f"Dataframe must have {self.num_allowed_rows} +- {self.error_tolerance} rows."
+        super().__init__(error_description=description, markdown_description=description)
 
     def validate(self, dataframe):
         check.inst_param(dataframe, "dataframe", DataFrame)
@@ -385,11 +362,7 @@ class RowCountConstraint(DataFrameConstraint):
             raise DataFrameConstraintViolationException(
                 constraint_name=self.name,
                 constraint_description=(
-                    "Expected {expected} +- {tolerance} rows. Got {received}".format(
-                        expected=self.num_allowed_rows,
-                        tolerance=self.error_tolerance,
-                        received=len(dataframe),
-                    )
+                    f"Expected {self.num_allowed_rows} +- {self.error_tolerance} rows. Got {len(dataframe)}"
                 ),
             )
 
@@ -503,6 +476,7 @@ class ColumnConstraintWithMetadata(ConstraintWithMetadata):
                 return exc.return_as_typecheck()
 
 
+@beta
 class MultiColumnConstraintWithMetadata(ColumnConstraintWithMetadata):
     """This class is useful for constructing more complicated relationships between columns
     and expectations -- i.e. you want some validations on column A, others on column B, etc.
@@ -551,10 +525,10 @@ class MultiColumnConstraintWithMetadata(ColumnConstraintWithMetadata):
                     result = new_validator.validate(
                         DataFrame(data[column]), column, *args, **kwargs
                     )
-                    result_val = result.success
+                    result_val = result.success  # pyright: ignore[reportOptionalMemberAccess]
                     if result_val:
                         continue
-                    result_dict = result.metadata[CONSTRAINT_METADATA_KEY].data
+                    result_dict = result.metadata[CONSTRAINT_METADATA_KEY].data  # pyright: ignore[reportAttributeAccessIssue,reportOptionalMemberAccess]
                     truthparam = truthparam and result_val
                     for key in result_dict.keys():
                         if "constraint" not in key:
@@ -573,7 +547,7 @@ class MultiColumnConstraintWithMetadata(ColumnConstraintWithMetadata):
                                     metadict[key][column][fn.__name__] = "a violation"
             return truthparam, metadict
 
-        super(MultiColumnConstraintWithMetadata, self).__init__(
+        super().__init__(
             description,
             validation_fn,
             resulting_exception,
@@ -585,6 +559,7 @@ class MultiColumnConstraintWithMetadata(ColumnConstraintWithMetadata):
         return ConstraintWithMetadata.validate(self, data, *args, **kwargs)
 
 
+@beta
 class MultiAggregateConstraintWithMetadata(MultiColumnConstraintWithMetadata):
     """This class is similar to multicolumn, but takes in functions that operate on the whole column at once
     rather than ones that operate on each value --
@@ -612,16 +587,17 @@ class MultiAggregateConstraintWithMetadata(MultiColumnConstraintWithMetadata):
         raise_or_typecheck=True,
         name=None,
     ):
-        super(MultiAggregateConstraintWithMetadata, self).__init__(
+        super().__init__(
             description,
             fn_and_columns_dict,
             resulting_exception,
             raise_or_typecheck=raise_or_typecheck,
-            type_for_internal=ColumnAggregateConstraintWithMetadata,
+            type_for_internal=ColumnAggregateConstraintWithMetadata,  # pyright: ignore[reportArgumentType]
             name=name,
         )
 
 
+@beta
 def non_null_validation(x):
     """Validates that a particular value in a column is not null.
 
@@ -635,6 +611,7 @@ def non_null_validation(x):
     return not pd.isnull(x), {}
 
 
+@beta
 def all_unique_validator(column, ignore_missing_vals=False):
     """Validates that all values in an iterable are unique.
 
@@ -673,6 +650,7 @@ def all_unique_validator(column, ignore_missing_vals=False):
     return not duplicated.any(), {"actual": column[duplicated]}
 
 
+@beta
 def nonnull(func):
     """Decorator for column validation functions to make them error on nulls.
 
@@ -691,11 +669,12 @@ def nonnull(func):
         nval = non_null_validation(val)
         return origval[0] and nval[0], {}
 
-    nvalidator.__doc__ += " and ensures no values are null"
+    nvalidator.__doc__ += " and ensures no values are null"  # pyright: ignore[reportOperatorIssue]
 
     return nvalidator
 
 
+@beta
 def column_range_validation_factory(minim=None, maxim=None, ignore_missing_vals=False):
     """Factory for validators testing if column values are within a range.
 
@@ -749,15 +728,14 @@ def column_range_validation_factory(minim=None, maxim=None, ignore_missing_vals=
             return True, {}
         return (isinstance(x, (type(minim), type(maxim)))) and (x <= maxim) and (x >= minim), {}
 
-    in_range_validation_fn.__doc__ = "checks whether values are between {} and {}".format(
-        minim, maxim
-    )
+    in_range_validation_fn.__doc__ = f"checks whether values are between {minim} and {maxim}"
     if ignore_missing_vals:
         in_range_validation_fn.__doc__ += ", ignoring nulls"
 
     return in_range_validation_fn
 
 
+@beta
 def categorical_column_validator_factory(categories, ignore_missing_vals=False):
     """Factory for validators testing if all values are in some set.
 
@@ -812,6 +790,7 @@ def categorical_column_validator_factory(categories, ignore_missing_vals=False):
     return categorical_validation_fn
 
 
+@beta
 def dtype_in_set_validation_factory(datatypes, ignore_missing_vals=False):
     """Factory for testing if the dtype of a val falls within some allowed set.
 
@@ -856,9 +835,7 @@ def dtype_in_set_validation_factory(datatypes, ignore_missing_vals=False):
             return True, {}
         return isinstance(x, datatypes), {}
 
-    dtype_in_set_validation_fn.__doc__ = "checks whether values are this type/types: {}".format(
-        datatypes
-    )
+    dtype_in_set_validation_fn.__doc__ = f"checks whether values are this type/types: {datatypes}"
     if ignore_missing_vals:
         dtype_in_set_validation_fn.__doc__ += ", ignoring nulls"
 
@@ -870,7 +847,7 @@ class ColumnRangeConstraintWithMetadata(ColumnConstraintWithMetadata):
         self.name = self.__class__.__name__
 
         description = f"Confirms values are between {minim} and {maxim}"
-        super(ColumnRangeConstraintWithMetadata, self).__init__(
+        super().__init__(
             description=description,
             validation_fn=column_range_validation_factory(minim=minim, maxim=maxim),
             resulting_exception=ColumnWithMetadataException,
@@ -882,9 +859,7 @@ class ColumnRangeConstraintWithMetadata(ColumnConstraintWithMetadata):
         if self.columns is None:
             self.columns = list(data.columns)
         self.columns.extend(args)
-        return super(ColumnRangeConstraintWithMetadata, self).validate(
-            data, *self.columns, **kwargs
-        )
+        return super().validate(data, *self.columns, **kwargs)
 
 
 class ColumnConstraint(Constraint):
@@ -892,11 +867,11 @@ class ColumnConstraint(Constraint):
 
     Args:
         error_description (Optional[str]): The plain string description that is output in the terminal if the constraint fails.
-        markdown_description (Optional[str]): A markdown supported description that is emitted by dagit if the constraint fails.
+        markdown_description (Optional[str]): A markdown supported description that is shown in the Dagster UI if the constraint fails.
     """
 
     def __init__(self, error_description=None, markdown_description=None):
-        super(ColumnConstraint, self).__init__(
+        super().__init__(
             error_description=error_description, markdown_description=markdown_description
         )
 
@@ -919,9 +894,7 @@ class ColumnDTypeFnConstraint(ColumnConstraint):
     def __init__(self, type_fn):
         self.type_fn = check.callable_param(type_fn, "type_fn")
         description = f'Dtype must satisfy "{self.type_fn.__name__}"'
-        super(ColumnDTypeFnConstraint, self).__init__(
-            error_description=description, markdown_description=description
-        )
+        super().__init__(error_description=description, markdown_description=description)
 
     def validate(self, dataframe, column_name):
         column_dtype = dataframe[column_name].dtype
@@ -942,12 +915,8 @@ class ColumnDTypeInSetConstraint(ColumnConstraint):
 
     def __init__(self, expected_dtype_set):
         self.expected_dtype_set = check.set_param(expected_dtype_set, "expected_dtype_set")
-        description = "Column dtype must be in the following set {}.".format(
-            self.expected_dtype_set
-        )
-        super(ColumnDTypeInSetConstraint, self).__init__(
-            error_description=description, markdown_description=description
-        )
+        description = f"Column dtype must be in the following set {self.expected_dtype_set}."
+        super().__init__(error_description=description, markdown_description=description)
 
     def validate(self, dataframe, column_name):
         received_dtypes = dataframe[column_name].dtype
@@ -955,9 +924,7 @@ class ColumnDTypeInSetConstraint(ColumnConstraint):
             raise ColumnConstraintViolationException(
                 constraint_name=self.name,
                 constraint_description=(
-                    "{base_error_message}. DTypes received: {received_dtypes}".format(
-                        base_error_message=self.error_description, received_dtypes=received_dtypes
-                    )
+                    f"{self.error_description}. DTypes received: {received_dtypes}"
                 ),
                 column_name=column_name,
             )
@@ -968,9 +935,7 @@ class NonNullableColumnConstraint(ColumnConstraint):
 
     def __init__(self):
         description = "No Null values allowed."
-        super(NonNullableColumnConstraint, self).__init__(
-            error_description=description, markdown_description=description
-        )
+        super().__init__(error_description=description, markdown_description=description)
 
     def validate(self, dataframe, column_name):
         rows_with_null_columns = dataframe[dataframe[column_name].isna()]
@@ -993,9 +958,7 @@ class UniqueColumnConstraint(ColumnConstraint):
     def __init__(self, ignore_missing_vals):
         description = "Column must be unique."
         self.ignore_missing_vals = check.bool_param(ignore_missing_vals, "ignore_missing_vals")
-        super(UniqueColumnConstraint, self).__init__(
-            error_description=description, markdown_description=description
-        )
+        super().__init__(error_description=description, markdown_description=description)
 
     def validate(self, dataframe, column_name):
         invalid = dataframe[column_name].duplicated()
@@ -1022,7 +985,7 @@ class CategoricalColumnConstraint(ColumnConstraint):
     def __init__(self, categories, ignore_missing_vals):
         self.categories = list(check.set_param(categories, "categories", of_type=str))
         self.ignore_missing_vals = check.bool_param(ignore_missing_vals, "ignore_missing_vals")
-        super(CategoricalColumnConstraint, self).__init__(
+        super().__init__(
             error_description=f"Expected Categories are {self.categories}",
             markdown_description=f"Category examples are {self.categories[:5]}...",
         )
@@ -1053,7 +1016,7 @@ class MinValueColumnConstraint(ColumnConstraint):
     def __init__(self, min_value, ignore_missing_vals):
         self.min_value = check.inst_param(min_value, "min_value", (int, float, datetime))
         self.ignore_missing_vals = check.bool_param(ignore_missing_vals, "ignore_missing_vals")
-        super(MinValueColumnConstraint, self).__init__(
+        super().__init__(
             markdown_description=f"values > {self.min_value}",
             error_description=f"Column must have values > {self.min_value}",
         )
@@ -1084,7 +1047,7 @@ class MaxValueColumnConstraint(ColumnConstraint):
     def __init__(self, max_value, ignore_missing_vals):
         self.max_value = check.inst_param(max_value, "max_value", (int, float, datetime))
         self.ignore_missing_vals = check.bool_param(ignore_missing_vals, "ignore_missing_vals")
-        super(MaxValueColumnConstraint, self).__init__(
+        super().__init__(
             markdown_description=f"values < {self.max_value}",
             error_description=f"Column must have values < {self.max_value}",
         )
@@ -1118,11 +1081,9 @@ class InRangeColumnConstraint(ColumnConstraint):
         self.min_value = check.inst_param(min_value, "min_value", (int, float, datetime))
         self.max_value = check.inst_param(max_value, "max_value", (int, float, datetime))
         self.ignore_missing_vals = check.bool_param(ignore_missing_vals, "ignore_missing_vals")
-        super(InRangeColumnConstraint, self).__init__(
+        super().__init__(
             markdown_description=f"{self.min_value} < values < {self.max_value}",
-            error_description="Column must have values between {} and {} inclusive.".format(
-                self.min_value, self.max_value
-            ),
+            error_description=f"Column must have values between {self.min_value} and {self.max_value} inclusive.",
         )
 
     def validate(self, dataframe, column_name):

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/data_frame.py

@@ -12,11 +12,10 @@ from dagster import (
     _check as check,
     dagster_type_loader,
 )
-from dagster._annotations import experimental
+from dagster._annotations import beta
 from dagster._config import Selector
 from dagster._core.definitions.metadata import normalize_metadata
 from dagster._utils import dict_without_keys
-from dagster._utils.backcompat import canonicalize_backcompat_args
 
 from dagster_pandas.constraints import (
     CONSTRAINT_METADATA_KEY,
@@ -43,7 +42,7 @@ CONSTRAINT_BLACKLIST = {ColumnDTypeFnConstraint, ColumnDTypeInSetConstraint}
     )
 )
 def dataframe_loader(_context, config):
-    file_type, file_options = list(config.items())[0]
+    file_type, file_options = next(iter(config.items()))
 
     if file_type == "csv":
         path = file_options["path"]
@@ -84,9 +83,7 @@ DataFrame = DagsterType(
 
 def _construct_constraint_list(constraints):
     def add_bullet(constraint_list, constraint_description):
-        return constraint_list + "+ {constraint_description}\n".format(
-            constraint_description=constraint_description
-        )
+        return constraint_list + f"+ {constraint_description}\n"
 
     constraint_list = ""
     for constraint in constraints:
@@ -100,13 +97,9 @@ def _build_column_header(column_name, constraints):
     for constraint in constraints:
         if isinstance(constraint, ColumnDTypeInSetConstraint):
             dtypes_tuple = tuple(constraint.expected_dtype_set)
-            return header + ": `{expected_dtypes}`".format(
-                expected_dtypes=dtypes_tuple if len(dtypes_tuple) > 1 else dtypes_tuple[0]
-            )
+            return header + f": `{dtypes_tuple if len(dtypes_tuple) > 1 else dtypes_tuple[0]}`"  # pyright: ignore[reportGeneralTypeIssues]
         elif isinstance(constraint, ColumnDTypeFnConstraint):
-            return header + ": Validator `{expected_dtype_fn}`".format(
-                expected_dtype_fn=constraint.type_fn.__name__
-            )
+            return header + f": Validator `{constraint.type_fn.__name__}`"
     return header
 
 
@@ -114,10 +107,7 @@ def create_dagster_pandas_dataframe_description(description, columns):
     title = "\n".join([description, "### Columns", ""])
     buildme = title
     for column in columns:
-        buildme += "{}\n{}\n".format(
-            _build_column_header(column.name, column.constraints),
-            _construct_constraint_list(column.constraints),
-        )
+        buildme += f"{_build_column_header(column.name, column.constraints)}\n{_construct_constraint_list(column.constraints)}\n"
     return buildme
 
 
@@ -132,7 +122,9 @@ def create_table_schema_metadata_from_dataframe(
     Returns:
         TableSchemaMetadataValue: returns an object with the TableSchema for the DataFrame.
     """
-    check.inst(pandas_df, pd.DataFrame, "Input must be a pandas DataFrame object")
+    check.inst_param(
+        pandas_df, "pandas_df", pd.DataFrame, "Input must be a pandas DataFrame object"
+    )
     return MetadataValue.table_schema(
         TableSchema(
             columns=[
@@ -143,6 +135,7 @@ def create_table_schema_metadata_from_dataframe(
     )
 
 
+@beta
 def create_dagster_pandas_dataframe_type(
     name,
     description=None,
@@ -150,7 +143,6 @@ def create_dagster_pandas_dataframe_type(
     metadata_fn=None,
     dataframe_constraints=None,
     loader=None,
-    event_metadata_fn=None,
 ):
     """Constructs a custom pandas dataframe dagster type.
 
@@ -172,9 +164,6 @@ def create_dagster_pandas_dataframe_type(
     # dataframes via configuration their own way if the default configs don't suffice. This is
     # purely optional.
     check.str_param(name, "name")
-    metadata_fn = canonicalize_backcompat_args(
-        metadata_fn, "metadata_fn", event_metadata_fn, "event_metadata_fn", "1.4.0"
-    )
     metadata_fn = check.opt_callable_param(metadata_fn, "metadata_fn")
     description = create_dagster_pandas_dataframe_description(
         check.opt_str_param(description, "description", default=""),
@@ -185,8 +174,8 @@ def create_dagster_pandas_dataframe_type(
         if not isinstance(value, pd.DataFrame):
             return TypeCheck(
                 success=False,
-                description="Must be a pandas.DataFrame. Got value of type. {type_name}".format(
-                    type_name=type(value).__name__
+                description=(
+                    f"Must be a pandas.DataFrame. Got value of type. {type(value).__name__}"
                 ),
             )
 
@@ -201,7 +190,7 @@ def create_dagster_pandas_dataframe_type(
 
         return TypeCheck(
             success=True,
-            metadata=_execute_summary_stats(name, value, metadata_fn) if metadata_fn else None,
+            metadata=_execute_summary_stats(name, value, metadata_fn) if metadata_fn else None,  # pyright: ignore[reportArgumentType]
         )
 
     return DagsterType(
@@ -213,7 +202,7 @@ def create_dagster_pandas_dataframe_type(
     )
 
 
-@experimental
+@beta
 def create_structured_dataframe_type(
     name,
     description=None,
@@ -248,8 +237,8 @@ def create_structured_dataframe_type(
         if not isinstance(value, pd.DataFrame):
             return TypeCheck(
                 success=False,
-                description="Must be a pandas.DataFrame. Got value of type. {type_name}".format(
-                    type_name=type(value).__name__
+                description=(
+                    f"Must be a pandas.DataFrame. Got value of type. {type(value).__name__}"
                 ),
             )
         individual_result_dict = {}

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/__init__.py

@@ -1,13 +1,18 @@
 from dagster import (
+    FilesystemIOManager,
     config_from_files,
     file_relative_path,
-    fs_io_manager,
     graph,
     in_process_executor,
     repository,
 )
 
-from .pandas_hello_world.ops import always_fails_op, papermill_pandas_hello_world, sum_op, sum_sq_op
+from dagster_pandas.examples.pandas_hello_world.ops import (
+    always_fails_op,
+    papermill_pandas_hello_world,
+    sum_op,
+    sum_sq_op,
+)
 
 
 @graph
@@ -51,7 +56,7 @@ def papermill_pandas_hello_world_graph():
 
 
 papermill_pandas_hello_world_test = papermill_pandas_hello_world_graph.to_job(
-    resource_defs={"io_manager": fs_io_manager},
+    resource_defs={"io_manager": FilesystemIOManager()},
     config=config_from_files(
         [
             file_relative_path(
@@ -63,7 +68,7 @@ papermill_pandas_hello_world_test = papermill_pandas_hello_world_graph.to_job(
 )
 
 papermill_pandas_hello_world_prod = papermill_pandas_hello_world_graph.to_job(
-    resource_defs={"io_manager": fs_io_manager},
+    resource_defs={"io_manager": FilesystemIOManager()},
     config=config_from_files(
         [
             file_relative_path(

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/pandas_hello_world/environments/pandas_hello_world_prod.yaml

@@ -3,4 +3,4 @@ ops:
     inputs:
       num:
         csv:
-          path: 'data/num_prod.csv'
+          path: "data/num_prod.csv"

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/pandas_hello_world/environments/pandas_hello_world_test.yaml

@@ -3,4 +3,4 @@ ops:
     inputs:
       num:
         csv:
-          path: 'data/num.csv'
+          path: "data/num.csv"

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/pandas_hello_world/environments/papermill_pandas_hello_world_prod.yaml

@@ -3,4 +3,4 @@ ops:
     inputs:
       df:
         csv:
-          path: 'data/num_prod.csv'
+          path: "data/num_prod.csv"

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/pandas_hello_world/environments/papermill_pandas_hello_world_test.yaml

@@ -3,4 +3,4 @@ ops:
     inputs:
       df:
         csv:
-          path: 'data/num.csv'
+          path: "data/num.csv"

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/pandas_hello_world/ops.py

@@ -2,8 +2,7 @@ import dagstermill
 from dagster import In, Out, file_relative_path, op
 
 import dagster_pandas as dagster_pd
-
-from ...data_frame import DataFrame
+from dagster_pandas.data_frame import DataFrame
 
 
 @op(

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/examples/pandas_hello_world.yaml

@@ -3,4 +3,4 @@ ops:
     inputs:
       num:
         csv:
-          path: 'data/num.csv'
+          path: "data/num.csv"

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/dagster_pandas/validation.py

@@ -2,6 +2,7 @@ from dagster import (
     DagsterInvariantViolationError,
     _check as check,
 )
+from dagster._annotations import beta
 from pandas import DataFrame, Timestamp
 from pandas.core.dtypes.common import (
     is_bool_dtype,
@@ -42,6 +43,7 @@ def _construct_keyword_constraints(non_nullable, unique, ignore_missing_vals):
     return constraints
 
 
+@beta
 class PandasColumn:
     """The main API for expressing column level schemas and constraints for your custom dataframe
     types.
@@ -65,14 +67,11 @@ class PandasColumn:
             # Ignore validation if column is missing from dataframe and is not required
             if self.is_required:
                 raise ConstraintViolationException(
-                    "Required column {column_name} not in dataframe with columns"
-                    " {dataframe_columns}".format(
-                        column_name=self.name, dataframe_columns=dataframe.columns
-                    )
+                    f"Required column {self.name} not in dataframe with columns {dataframe.columns}"
                 )
         else:
             for constraint in self.constraints:
-                constraint.validate(dataframe, self.name)
+                constraint.validate(dataframe, self.name)  # pyright: ignore[reportAttributeAccessIssue]
 
     @staticmethod
     def exists(name, non_nullable=False, unique=False, ignore_missing_vals=False, is_required=None):

dagster_pandas-0.27.9/dagster_pandas/version.py

@@ -0,0 +1 @@
+__version__ = "0.27.9"

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9/dagster_pandas.egg-info}/PKG-INFO

@@ -1,22 +1,36 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dagster-pandas
-Version: 0.19.5
+Version: 0.27.9
 Summary: Utilities and examples for working with pandas and dagster, an opinionated framework for expressing data pipelines
 Home-page: https://github.com/dagster-io/dagster
-Author: Elementl
-Author-email: hello@elementl.com
+Author: Dagster Labs
+Author-email: hello@dagsterlabs.com
 License: Apache-2.0
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: dagster==1.11.9
+Requires-Dist: pandas
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 # dagster-pandas
 
 The docs for `dagster-pandas` can be found
-[here](https://docs.dagster.io/_apidocs/libraries/dagster-pandas).
+[here](https://docs.dagster.io/api/python-api/libraries/dagster-pandas).

dagster_pandas-0.27.9/dagster_pandas.egg-info/requires.txt

@@ -0,0 +1,2 @@
+dagster==1.11.9
+pandas

{dagster-pandas-0.19.5 → dagster_pandas-0.27.9}/setup.py

@@ -1,18 +1,17 @@
 import os
 from pathlib import Path
-from typing import Dict
 
 from setuptools import find_packages, setup
 
 
 def long_description() -> str:
     here = os.path.abspath(os.path.dirname(__file__))
-    with open(os.path.join(here, "README.md"), "r", encoding="utf8") as fh:
+    with open(os.path.join(here, "README.md"), encoding="utf8") as fh:
         return fh.read()
 
 
 def get_version() -> str:
-    version: Dict[str, str] = {}
+    version: dict[str, str] = {}
     with open(Path(__file__).parent / "dagster_pandas/version.py", encoding="utf8") as fp:
         exec(fp.read(), version)
 
@@ -25,8 +24,8 @@ pin = "" if ver == "1!0+dev" else f"=={ver}"
 setup(
     name="dagster-pandas",
     version=ver,
-    author="Elementl",
-    author_email="hello@elementl.com",
+    author="Dagster Labs",
+    author_email="hello@dagsterlabs.com",
     license="Apache-2.0",
     description=(
         "Utilities and examples for working with pandas and dagster, an opinionated "
@@ -36,15 +35,19 @@ setup(
     long_description_content_type="text/markdown",
     url="https://github.com/dagster-io/dagster",
     classifiers=[
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
         "License :: OSI Approved :: Apache Software License",
         "Operating System :: OS Independent",
     ],
     packages=find_packages(exclude=["dagster_pandas_tests*"]),
     include_package_data=True,
-    install_requires=["dagster==1.3.5", "pandas"],
+    python_requires=">=3.9,<3.14",
+    install_requires=[
+        "dagster==1.11.9",
+        "pandas",
+    ],
 )

dagster-pandas-0.19.5/README.md

@@ -1,4 +0,0 @@
-# dagster-pandas
-
-The docs for `dagster-pandas` can be found
-[here](https://docs.dagster.io/_apidocs/libraries/dagster-pandas).

dagster-pandas-0.19.5/dagster_pandas/version.py

@@ -1 +0,0 @@
-__version__ = "0.19.5"

dagster-pandas-0.19.5/dagster_pandas.egg-info/requires.txt

@@ -1,2 +0,0 @@
-dagster==1.3.5
-pandas