Staging release 0.13.0 (#1165) (#1166)

* refactor: Upgrade the models to use keras 3.0 (#1138) * Replace snappy with cramjam (#1091) * add downloads tile (#1085) * Replace snappy with cramjam * Delete test_no_snappy --------- * pre-commit fix (#1122) * Bug fix for float precision calculation using categorical data with trailing zeros. (#1125) * Revert "Bug fix for float precision calculation using categorical data with t…" (#1133) This reverts commit d3159bd. * refactor: move layers outside of class * refactor: update model to keras 3.0 * fix: manifest * fix: bugs in compile and train * fix: bug in load_from_library * fix: bugs in CharCNN * refactor: loading tf model labeler * fix: bug in data_labeler identification * fix: update model to use proper softmax layer names * fix: formatting * fix: remove unused line * refactor: drop support for 3.8 * fix: comments * fix: comment --------- * Fix Tox (#1143) * tox new * update * update * update * update * update * update * update * update tox.ini * update * update * remove docs * empty retrigger * update (#1146) * Add Python 3.11 to GHA (#1090) * add downloads tile (#1085) * Add Python 3.11 to GHA * Replace snappy with cramjam (#1091) * add downloads tile (#1085) * Replace snappy with cramjam * Delete test_no_snappy --------- * Update dask modules * Install dask dataframe * Update dask modules in precommit * Correct copy/paste error * Try again to clear Unicode * Rolled back pre-commit dask version * Add py311 to tox * Bump dask to 2024.4.1 * Bump python-snappy 0.7.1 * Rewrite labeler test * Correct isort * Satisfy black * And flake8 * Synced with requirements --------- * [Vuln Fix]: Resolve mend vulnerabilities related to requests. (#1162) * resolved check-manifest issue * updating keras version pin to <=3.4.0 * adding comment in requirements.txt to trigger mend check --------- --------- Co-authored-by: JGSweets <[email protected]> Co-authored-by: Gábor Lipták <[email protected]> Co-authored-by: Taylor Turner <[email protected]> Co-authored-by: James Schadt <[email protected]> Co-authored-by: Michael Davis <[email protected]>
capitalone · mhmotamedi · Jan 30, 2025 · Sep 29, 2023 · Oct 4, 2023 · Oct 25, 2023
commit 50da93f0bca6b0add053acdafd34e2f48f61fa1b
@@ -48,14 +48,14 @@ repos:
             # requirements.txt
             h5py>=2.10.0,
             wheel>=0.33.1,
-            numpy>=1.22.0,
+            numpy<2.0.0,
             pandas>=1.1.2,
             python-dateutil>=2.7.5,
             pytz>=2020.1,
             pyarrow>=1.0.1,
             chardet>=3.0.4,
             fastavro>=1.0.0.post1,
-            python-snappy>=0.5.4,
+            python-snappy>=0.7.1,
             charset-normalizer>=1.3.6,
             psutil>=4.0.0,
             scipy>=1.4.1,
@@ -80,7 +80,7 @@ repos:
 
             # requirements-ml.txt
             scikit-learn>=0.23.2,
-            'keras>=2.4.3,<3.0.0',
+            'keras>=2.4.3,<=3.4.0',
             rapidfuzz>=2.6.1,
             "tensorflow>=2.6.4,<2.15.0; sys.platform != 'darwin'",
             "tensorflow>=2.6.4,<2.15.0; sys_platform == 'darwin' and platform_machine != 'arm64'",
@@ -108,7 +108,7 @@ repos:
     rev: "0.48"
     hooks:
       - id: check-manifest
-        additional_dependencies: ['h5py', 'wheel', 'future', 'numpy', 'pandas',
+        additional_dependencies: ['h5py', 'wheel', 'future', 'numpy<2.0.0', 'pandas',
         'python-dateutil', 'pytz', 'pyarrow', 'chardet', 'fastavro',
         'python-snappy', 'charset-normalizer', 'psutil', 'scipy', 'requests',
         'networkx','typing-extensions', 'HLL', 'datasketches', 'boto3']

@@ -20,22 +20,6 @@
 from .validators.base_validators import Validator
 from .version import __version__
 
-try:
-    import snappy
-except ImportError:
-    import warnings
-
-    warnings.warn(
-        "Snappy must be installed to use parquet/avro datasets."
-        "\n\n"
-        "For macOS use Homebrew:\n"
-        "\t`brew install snappy`"
-        "\n\n"
-        "For linux use apt-get:\n`"
-        "\tsudo apt-get -y install libsnappy-dev`\n",
-        ImportWarning,
-    )
-
 
 def set_seed(seed=None):
     # also check it's an integer

@@ -56,46 +56,6 @@ def test_data_profiling(self):
             self.assertIsNotNone(profile.profile)
             self.assertIsNotNone(profile.report())
 
-    def test_no_snappy(self):
-        import importlib
-        import sys
-        import types
-
-        orig_import = __import__
-        # necessary for any wrapper around the library to test if snappy caught
-        # as an issue
-
-        def reload_data_profiler():
-            """Recursively reload modules."""
-            sys_modules = sys.modules.copy()
-            for module_name, module in sys_modules.items():
-                # Only reload top level of the dataprofiler
-                if "dataprofiler" in module_name and len(module_name.split(".")) < 3:
-                    if isinstance(module, types.ModuleType):
-                        importlib.reload(module)
-
-        def import_mock(name, *args, **kwargs):
-            if name == "snappy":
-                raise ImportError("test")
-            return orig_import(name, *args, **kwargs)
-
-        with mock.patch("builtins.__import__", side_effect=import_mock):
-            with self.assertWarns(ImportWarning) as w:
-                import dataprofiler
-
-                reload_data_profiler()
-
-        self.assertEqual(
-            str(w.warning),
-            "Snappy must be installed to use parquet/avro datasets."
-            "\n\n"
-            "For macOS use Homebrew:\n"
-            "\t`brew install snappy`"
-            "\n\n"
-            "For linux use apt-get:\n`"
-            "\tsudo apt-get -y install libsnappy-dev`\n",
-        )
-
     def test_no_tensorflow(self):
         import sys
 

diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -1,4 +1,4 @@
-check-manifest>=0.48
+check-manifest>=0.50
 black>=24.3.0
 isort==5.12.0
 pre-commit==2.19.0

diff --git a/requirements-ml.txt b/requirements-ml.txt
@@ -1,5 +1,5 @@
 scikit-learn>=0.23.2
-keras>=3.0.0
+keras<=3.4.0
 rapidfuzz>=2.6.1
 tensorflow>=2.16.0; sys.platform != 'darwin'
 tensorflow>=2.16.0; sys_platform == 'darwin' and platform_machine != 'arm64'

diff --git a/requirements.txt b/requirements.txt
@@ -1,20 +1,21 @@
 h5py>=2.10.0
 wheel>=0.33.1
-numpy>=1.22.0
+numpy<2.0.0
 pandas>=1.1.2
 python-dateutil>=2.7.5
 pytz>=2020.1
 pyarrow>=1.0.1
 chardet>=3.0.4
 fastavro>=1.1.0
-python-snappy>=0.5.4
+python-snappy>=0.7.1
 charset-normalizer>=1.3.6
 psutil>=4.0.0
 scipy>=1.10.0
-requests>=2.28.1
+requests==2.32.*
 networkx>=2.5.1
 typing-extensions>=3.10.0.2
 HLL>=2.0.3
 datasketches>=4.1.0
 packaging>=23.0
 boto3>=1.28.61
+# adding comment to trigger mend check
@@ -1,5 +1,5 @@
 [tox]
-envlist = py39, py310, 311, pypi-description, manifest, precom
+envlist = py39, py310, py311, pypi-description, manifest, precom
 
 
 [testenv]