wedata-feature-engineering 0.1.5__py3-none-any.whl → 0.1.7__py3-none-any.whl

wedata/feature_store/utils/utils.py

@@ -1,252 +0,0 @@
-import os
-from datetime import datetime, timezone
-from functools import wraps
-from typing import Any, Dict, List, Optional
-from urllib.parse import urlparse
-
-import mlflow
-from mlflow.exceptions import RestException
-from mlflow.store.artifact.artifact_repository_registry import get_artifact_repository
-from mlflow.utils import databricks_utils
-
-
-
-def enable_if(condition):
-    """
-    A decorator that conditionally enables a function based on a condition.
-    If the condition is not truthy, calling the function raises a NotImplementedError.
-
-    :param condition: A callable that returns a truthy or falsy value.
-    """
-
-    def decorator(func):
-        @wraps(func)
-        def wrapper(*args, **kwargs):
-            if not condition():
-                raise NotImplementedError
-            return func(*args, **kwargs)
-
-        return wrapper
-
-    return decorator
-
-
-def as_list(obj, default=None):
-    if not obj:
-        return default
-    elif isinstance(obj, list):
-        return obj
-    else:
-        return [obj]
-
-
-def as_directory(path):
-    if path.endswith("/"):
-        return path
-    return f"{path}/"
-
-
-def is_empty(target: str):
-    return target is None or len(target.strip()) == 0
-
-
-class _NoDbutilsError(Exception):
-    pass
-
-
-def _get_dbutils():
-    try:
-        import IPython
-
-        ip_shell = IPython.get_ipython()
-        if ip_shell is None:
-            raise _NoDbutilsError
-        return ip_shell.ns_table["user_global"]["dbutils"]
-    except ImportError:
-        raise _NoDbutilsError
-    except KeyError:
-        raise _NoDbutilsError
-
-
-
-def utc_timestamp_ms_from_iso_datetime_string(date_string: str) -> int:
-    # Python uses seconds for its time granularity, so we multiply by 1000 to convert to milliseconds.
-    # The Feature Store backend returns timestamps in milliseconds, so this allows for direct comparisons.
-    dt = datetime.fromisoformat(date_string)
-    utc_dt = dt.replace(tzinfo=timezone.utc)
-    return 1000 * utc_dt.timestamp()
-
-
-def pip_depependency_pinned_major_version(pip_package_name, major_version):
-    """
-    Generate a pip dependency string that is pinned to a major version, for example: "databricks-feature-lookup==0.*"
-    """
-    return f"{pip_package_name}=={major_version}.*"
-
-
-def add_mlflow_pip_depependency(conda_env, pip_package_name):
-    """
-    Add a new pip dependency to the conda environment taken from the raw MLflow model.  This method should only be
-    called for conda environments created by MLflow rather than for generic conda environments, because it assumes
-    the conda environment already contains pip as a dependency.  In the case of MLflow models, this is a safe
-    assumption because MLflow always needs to add "mlflow" to the conda environment's pip dependencies.
-
-    This is idempotent and will not add a pip package that is already present in the list of pip packages.
-    """
-    if pip_package_name is None or len(pip_package_name) == 0:
-        raise ValueError(
-            "Unexpected input: missing or empty pip_package_name parameter"
-        )
-
-    found_pip_dependency = False
-    if conda_env is not None:
-        for dep in conda_env["dependencies"]:
-            if isinstance(dep, dict) and "pip" in dep:
-                found_pip_dependency = True
-                pip_deps = dep["pip"]
-                if pip_package_name not in pip_deps:
-                    pip_deps.append(pip_package_name)
-        # Fail early rather than at model inference time
-        if "dependencies" in conda_env and not found_pip_dependency:
-            raise ValueError(
-                "Unexpected input: mlflow conda_env did not contain pip as a dependency"
-            )
-
-
-def download_model_artifacts(model_uri, dir):
-    """
-    Downloads model artifacts from model_uri to dir. Intended for use only with Feature Store packaged models.
-
-    :param model_uri: The location, in URI format, of a model. Must be either in the model registry
-      (``models:/<model_name>/<model_version>``, ``models:/<model_name>/<stage>``) or the MLflow
-      artifact store (``runs:/<mlflow_run_id>/run-relative/path/to/model``).
-    :param dir: Location to place downloaded model artifacts.
-    """
-    if not is_artifact_uri(model_uri):
-        raise ValueError(
-            f"Invalid model URI '{model_uri}'."
-            f"Use ``models:/model_name>/<version_number>`` or "
-            f"``runs:/<mlflow_run_id>/run-relative/path/to/model``."
-        )
-
-    try:
-        repo = get_artifact_repository(model_uri)
-    except RestException as e:
-        raise ValueError(f"The model at '{model_uri}' does not exist.", e)
-
-    artifact_path = os.path.join(mlflow.pyfunc.DATA, MODEL_DATA_PATH_ROOT)
-    if len(repo.list_artifacts(artifact_path)) == 0:
-        raise ValueError(
-            f"No suitable model found at '{model_uri}'. Either no model exists in this "
-            f"artifact location or an existing model was not packaged with Feature Store metadata. "
-            f"Only models logged by FeatureStoreClient.log_model can be used in inference."
-        )
-
-    return repo.download_artifacts(artifact_path="", dst_path=dir)
-
-
-def validate_params_non_empty(params: Dict[str, Any], expected_params: List[str]):
-    """
-    Validate that none of the expected parameters are empty, otherwise raise a Value error
-    for the first encountered empty parameter.
-
-    Tested with the following param types:
-
-    - str
-    - Dict
-    - List
-
-    :param params: A dictionary of param names -> param values, for example as returned by locals()
-    :param expected_params: List of params to check as non_empty
-    """
-    for expected_param in expected_params:
-        if expected_param not in params:
-            raise ValueError(
-                f'Internal error: expected parameter "{expected_param}" not found in params dictionary'
-            )
-        param_value = params[expected_param]
-        if not param_value:
-            raise ValueError(f'Parameter "{expected_param}" cannot be empty')
-
-
-def is_in_databricks_job():
-    """
-    Overrides the behavior of the mlflow databricks_utils.is_in_databricks_job() to account for the fact that
-    some jobs have job_id but no run_id, for example one-time job runs.
-    """
-    try:
-        return databricks_utils.get_job_id() is not None
-    except Exception:
-        return False
-
-
-def get_workspace_url() -> Optional[str]:
-    """
-    Overrides the behavior of the mlflow.utils.databricks_utils.get_workspace_url(),
-    as get_workspace_url does not always return URLs with defined schemes.
-
-    TODO (ML-32050): Refactor this implementation to mlflow, and bump minimum required mlflow version.
-    """
-    workspace_url = databricks_utils.get_workspace_url()
-    if workspace_url and not urlparse(workspace_url).scheme:
-        workspace_url = "https://" + workspace_url
-    return workspace_url
-
-
-def is_in_databricks_env():
-    """
-    Determine if we are running in a Databricks environment (DBR, MLR, DLT, DCS, Mlflow Projects, Run Cmd 1.2 API, etc)
-
-    If any invoked methods raise an exception, swallow the exception and return False out of an abundance of caution.
-    """
-    try:
-        return (
-            is_in_databricks_job()
-            or databricks_utils.is_in_databricks_notebook()
-            or databricks_utils.is_in_databricks_runtime()
-        )
-    except Exception:
-        return False
-
-
-def sanitize_identifier(identifier: str):
-    """
-    Sanitize and wrap an identifier with backquotes. For example, "a`b" becomes "`a``b`".
-    Use this function to sanitize identifiers such as column names in SQL and PySpark.
-    """
-    return f"`{identifier.replace('`', '``')}`"
-
-
-def sanitize_identifiers(identifiers: List[str]):
-    """
-    Sanitize and wrap the identifiers in a list with backquotes.
-    """
-    return [sanitize_identifier(i) for i in identifiers]
-
-
-def sanitize_multi_level_name(multi_level_name: str):
-    """
-    Sanitize a multi-level name (such as an Unity Catalog table name) by sanitizing each segment
-    and joining the results. For example, "ca+t.fo`o.ba$r" becomes "`ca+t`.`fo``o`.`ba$r`".
-    """
-    segments = multi_level_name.split(".")
-    return ".".join(sanitize_identifiers(segments))
-
-
-def unsanitize_identifier(identifier: str):
-    """
-    Unsanitize an identifier. Useful when we get a possibly sanitized identifier from Spark or
-    somewhere else, but we need an unsanitized one.
-    Note: This function does not check the correctness of the identifier passed in. e.g. `foo``
-    is not a valid sanitized identifier. When given such invalid input, this function returns
-    invalid output.
-    """
-    if len(identifier) >= 2 and identifier[0] == "`" and identifier[-1] == "`":
-        return identifier[1:-1].replace("``", "`")
-    else:
-        return identifier
-
-
-# strings containing \ or ' can break sql statements, so escape them.
-def escape_sql_string(input_str: str) -> str:
-    return input_str.replace("\\", "\\\\").replace("'", "\\'")

wedata_feature_engineering-0.1.5.dist-info/RECORD

@@ -1,79 +0,0 @@
-feature_store/__init__.py,sha256=CP3YAMoy3pSTWRYzTza_CYBnGbTv_KzycVEBMQCeiD8,101
-feature_store/client.py,sha256=FG1xK460rD859iSY4VA75XeYhqStJD8Wlr0sRxk25LI,5267
-feature_store/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-feature_store/constants/constants.py,sha256=exW3kiFLDyCmU9cYHFjcvIQhPWEpFtkogLXeB9Arfd8,827
-feature_store/entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-feature_store/entities/column_info.py,sha256=WezowI46YHDym5ZlbhCJDqhKbVcjXjnjt7dQdy3XqYM,4164
-feature_store/entities/data_type.py,sha256=VpHS6Fr3TphQQ8NbAcEnDJ-8eOZV6ivYuWxv3pAM2RM,3394
-feature_store/entities/environment_variables.py,sha256=ZEFml5H9MQuzBKM074mUrFYu-Sga4Knmxqiwpke2WGc,1679
-feature_store/entities/feature.py,sha256=wX8fTBlJq3GYdj9rrBDCY3kFgcVBBAiOOZdxEhnQkNQ,1241
-feature_store/entities/feature_column_info.py,sha256=-TGxRafYUaNKe0YzHus2XbfRaVrMv7pcffMdbtTT4nA,2031
-feature_store/entities/feature_function.py,sha256=R17INrCE-U_Uj9KLbFz69aYlOkTETTwQHMMo470F4lQ,1865
-feature_store/entities/feature_lookup.py,sha256=zUDMdDIboitOffYRZlurf_O_4UeBPmE5YS0PyCS2Fqg,7912
-feature_store/entities/feature_spec.py,sha256=F4MiKEyvKZSBh6Uv7V4vVLbamZ9fRClaC3HCrUeynDE,20079
-feature_store/entities/feature_spec_constants.py,sha256=YWDBfRiNDe6fUJFUBo3V4WYg2xsljoPAE-ZejfFZCgM,785
-feature_store/entities/feature_table.py,sha256=4ghopIvJcoIlyFiSEuTkOcDWn88c1Kt6q5LWM4BYEHI,6073
-feature_store/entities/feature_table_info.py,sha256=2vUaVdW_jw1dRAlmJWvBRueuMeuqWu_NYB9SlxLI7Uw,1126
-feature_store/entities/function_info.py,sha256=l0kmiq2R_QNfSMJ7y0xZohlMiemgYSr1dN5vzV8ijIs,7314
-feature_store/entities/on_demand_column_info.py,sha256=Eh5ieaj1TxC7DG6ipBZzH2ZyY0bwkLrDOkuZjgYr4gY,1297
-feature_store/entities/source_data_column_info.py,sha256=a9jQOJvehwDIrKPwsP6W9YRBSPNK2nZYypE6-p80CwA,542
-feature_store/entities/training_set.py,sha256=9H2uGnUxTAsk93Om50QxRELbeFCocwGMze2VexPVJWI,5569
-feature_store/feature_table_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-feature_store/feature_table_client/feature_table_client.py,sha256=uir33K7oigrSnjTT6VbNOp0Nb22-X3JHd1_92kWjrow,10754
-feature_store/spark_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-feature_store/spark_client/spark_client.py,sha256=vd-NCE9IGC0Ygqr-QSVY0teuWsQSkq_BFV4Mn6xMMNU,11578
-feature_store/training_set_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-feature_store/training_set_client/training_set_client.py,sha256=Aa80xVXVE1KBdgplL9qqR8ftD5A5r2pfBttAhmySrB0,6696
-feature_store/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-feature_store/utils/common_utils.py,sha256=ck8pJYeN6vrcZmTrcnmIOOJWzYZaY3ZjvRSVme4tplo,3314
-feature_store/utils/feature_lookup_utils.py,sha256=iILSP4AFHXrjNTuId6mT7wtMFAsZejyxThr_mZHPRF4,22330
-feature_store/utils/feature_spec_utils.py,sha256=jeWzEhmkVW-bMRySMx_5grepHAlLquMhYxpbbiaJR-g,11582
-feature_store/utils/feature_utils.py,sha256=8KhlkWax3KAi_xRnStVPlhCxeUHO08VW2fmT9jN8QUs,2761
-feature_store/utils/schema_utils.py,sha256=8NhNUsF4Z6UtmzFeaVBnmb7xut0LqZepK3M27PSEpfE,4484
-feature_store/utils/topological_sort.py,sha256=ebzKxmxeCLk9seB1zR0ASCGXsZsa-DjxJeTc4KUadtg,6475
-feature_store/utils/training_set_utils.py,sha256=V5yW-XQ9in7gNOo4xsWy7txnSw_Z9Zxm4mV7MQmrWnk,22466
-feature_store/utils/uc_utils.py,sha256=ets7YlrAtkhW9kKyYajDNo6iZasBIhFyxUT2MOyLuV8,10767
-feature_store/utils/utils.py,sha256=T6dOUX3oOYRsbvXyTIElFZ20kNO92KMYPUCrqY5eomE,8953
-feature_store/utils/validation_utils.py,sha256=FslvrNs3kstqvM6THScLOluEE6O9RWlDrD9xiihTzlw,1735
-wedata/__init__.py,sha256=oXL7D4a-5Twx50aBoB2TqfwODH-UbJy9Ovw1uvfeMf8,101
-wedata/feature_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/client.py,sha256=FG1xK460rD859iSY4VA75XeYhqStJD8Wlr0sRxk25LI,5267
-wedata/feature_store/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/constants/constants.py,sha256=exW3kiFLDyCmU9cYHFjcvIQhPWEpFtkogLXeB9Arfd8,827
-wedata/feature_store/entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/entities/column_info.py,sha256=WezowI46YHDym5ZlbhCJDqhKbVcjXjnjt7dQdy3XqYM,4164
-wedata/feature_store/entities/data_type.py,sha256=VpHS6Fr3TphQQ8NbAcEnDJ-8eOZV6ivYuWxv3pAM2RM,3394
-wedata/feature_store/entities/environment_variables.py,sha256=ZEFml5H9MQuzBKM074mUrFYu-Sga4Knmxqiwpke2WGc,1679
-wedata/feature_store/entities/feature.py,sha256=wX8fTBlJq3GYdj9rrBDCY3kFgcVBBAiOOZdxEhnQkNQ,1241
-wedata/feature_store/entities/feature_column_info.py,sha256=-TGxRafYUaNKe0YzHus2XbfRaVrMv7pcffMdbtTT4nA,2031
-wedata/feature_store/entities/feature_function.py,sha256=R17INrCE-U_Uj9KLbFz69aYlOkTETTwQHMMo470F4lQ,1865
-wedata/feature_store/entities/feature_lookup.py,sha256=zUDMdDIboitOffYRZlurf_O_4UeBPmE5YS0PyCS2Fqg,7912
-wedata/feature_store/entities/feature_spec.py,sha256=F4MiKEyvKZSBh6Uv7V4vVLbamZ9fRClaC3HCrUeynDE,20079
-wedata/feature_store/entities/feature_spec_constants.py,sha256=YWDBfRiNDe6fUJFUBo3V4WYg2xsljoPAE-ZejfFZCgM,785
-wedata/feature_store/entities/feature_table.py,sha256=4ghopIvJcoIlyFiSEuTkOcDWn88c1Kt6q5LWM4BYEHI,6073
-wedata/feature_store/entities/feature_table_info.py,sha256=2vUaVdW_jw1dRAlmJWvBRueuMeuqWu_NYB9SlxLI7Uw,1126
-wedata/feature_store/entities/function_info.py,sha256=l0kmiq2R_QNfSMJ7y0xZohlMiemgYSr1dN5vzV8ijIs,7314
-wedata/feature_store/entities/on_demand_column_info.py,sha256=Eh5ieaj1TxC7DG6ipBZzH2ZyY0bwkLrDOkuZjgYr4gY,1297
-wedata/feature_store/entities/source_data_column_info.py,sha256=a9jQOJvehwDIrKPwsP6W9YRBSPNK2nZYypE6-p80CwA,542
-wedata/feature_store/entities/training_set.py,sha256=9H2uGnUxTAsk93Om50QxRELbeFCocwGMze2VexPVJWI,5569
-wedata/feature_store/feature_table_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/feature_table_client/feature_table_client.py,sha256=uir33K7oigrSnjTT6VbNOp0Nb22-X3JHd1_92kWjrow,10754
-wedata/feature_store/spark_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/spark_client/spark_client.py,sha256=vd-NCE9IGC0Ygqr-QSVY0teuWsQSkq_BFV4Mn6xMMNU,11578
-wedata/feature_store/training_set_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/training_set_client/training_set_client.py,sha256=Aa80xVXVE1KBdgplL9qqR8ftD5A5r2pfBttAhmySrB0,6696
-wedata/feature_store/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/utils/common_utils.py,sha256=ck8pJYeN6vrcZmTrcnmIOOJWzYZaY3ZjvRSVme4tplo,3314
-wedata/feature_store/utils/feature_lookup_utils.py,sha256=iILSP4AFHXrjNTuId6mT7wtMFAsZejyxThr_mZHPRF4,22330
-wedata/feature_store/utils/feature_spec_utils.py,sha256=jeWzEhmkVW-bMRySMx_5grepHAlLquMhYxpbbiaJR-g,11582
-wedata/feature_store/utils/feature_utils.py,sha256=8KhlkWax3KAi_xRnStVPlhCxeUHO08VW2fmT9jN8QUs,2761
-wedata/feature_store/utils/schema_utils.py,sha256=8NhNUsF4Z6UtmzFeaVBnmb7xut0LqZepK3M27PSEpfE,4484
-wedata/feature_store/utils/topological_sort.py,sha256=ebzKxmxeCLk9seB1zR0ASCGXsZsa-DjxJeTc4KUadtg,6475
-wedata/feature_store/utils/training_set_utils.py,sha256=V5yW-XQ9in7gNOo4xsWy7txnSw_Z9Zxm4mV7MQmrWnk,22466
-wedata/feature_store/utils/uc_utils.py,sha256=ets7YlrAtkhW9kKyYajDNo6iZasBIhFyxUT2MOyLuV8,10767
-wedata/feature_store/utils/utils.py,sha256=T6dOUX3oOYRsbvXyTIElFZ20kNO92KMYPUCrqY5eomE,8953
-wedata/feature_store/utils/validation_utils.py,sha256=FslvrNs3kstqvM6THScLOluEE6O9RWlDrD9xiihTzlw,1735
-wedata_feature_engineering-0.1.5.dist-info/METADATA,sha256=2vR4aNUosgey5HA_HsyCV3XdgEi5xrEUD5gpavj2l7U,493
-wedata_feature_engineering-0.1.5.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-wedata_feature_engineering-0.1.5.dist-info/top_level.txt,sha256=Xa0v1rh__RvfVTVDirW5r5UBKg7ZO_iuTeXfp8MNo2A,7
-wedata_feature_engineering-0.1.5.dist-info/RECORD,,