third_codes/eland
1
0
Fork 0
mirror of https://github.com/elastic/eland.git synced 2025-07-11 00:02:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove deprecated options and aliases

Browse Source
This commit is contained in:
P. Sai Vinay 2021-01-04 20:20:45 +01:00 committed by GitHub
parent f89d79b1b4
commit 27717eead1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
11 changed files with 21 additions and 198 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -153,7 +153,7 @@ to be serialized and used as an inference model in Elasticsearch
```python
>>> from xgboost import XGBClassifier
>>> from eland.ml import ImportedMLModel
>>> from eland.ml import MLModel
# Train and exercise an XGBoost ML model locally
>>> xgb_model = XGBClassifier(booster="gbtree")
@ -163,7 +163,7 @@ to be serialized and used as an inference model in Elasticsearch
[0 1 1 0 1 0 0 0 1 0]
# Import the model into Elasticsearch
>>> es_model = ImportedMLModel(
>>> es_model = MLModel(
es_client="localhost:9200",
model_id="xgb-classifier",
model=xgb_model,

4
docs/sphinx/reference/api/eland.DataFrame.es_info.rst
View File

@ -3,8 +3,4 @@ eland.DataFrame.es_info
.. currentmodule:: eland
.. warning::
Previously this method was named ``info_es()``.
DataFrame.info_es() is deprecated, use DataFrame.es_info() instead.
.. automethod:: DataFrame.es_info

4
docs/sphinx/reference/api/eland.Series.es_info.rst
View File

@ -3,8 +3,4 @@ eland.Series.es_info
.. currentmodule:: eland
.. warning::
Previously this method was named ``info_es()``.
Series.info_es() is deprecated, use Series.es_info() instead.
.. automethod:: Series.es_info

4
eland/__init__.py
View File

@ -27,7 +27,7 @@ from ._version import ( # noqa: F401
)
from .common import SortOrder
from .dataframe import DataFrame
from .etl import csv_to_eland, eland_to_pandas, pandas_to_eland, read_csv, read_es
from .etl import csv_to_eland, eland_to_pandas, pandas_to_eland
from .index import Index
from .ndframe import NDFrame
from .series import Series
@ -40,7 +40,5 @@ __all__ = [
"pandas_to_eland",
"eland_to_pandas",
"csv_to_eland",
"read_csv",
"read_es",
"SortOrder",
]

6
eland/dataframe.py
View File

@ -39,7 +39,7 @@ from eland.filter import BooleanFilter
from eland.groupby import DataFrameGroupBy
from eland.ndframe import NDFrame
from eland.series import Series
from eland.utils import deprecated_api, is_valid_attr_name
from eland.utils import is_valid_attr_name
class DataFrame(NDFrame):
@ -628,10 +628,6 @@ class DataFrame(NDFrame):
return buf.getvalue()
@deprecated_api("eland.DataFrame.es_info()")
def info_es(self):
return self.es_info()
def es_match(
self,
text: str,

36
eland/etl.py
View File

@ -27,37 +27,6 @@ from pandas.io.parsers import _c_parser_defaults # type: ignore
from eland import DataFrame
from eland.common import DEFAULT_CHUNK_SIZE, ensure_es_client
from eland.field_mappings import FieldMappings, verify_mapping_compatibility
from eland.utils import deprecated_api
@deprecated_api("eland.DataFrame()")
def read_es(
es_client: Union[str, List[str], Tuple[str, ...], Elasticsearch],
es_index_pattern: str,
) -> DataFrame:
"""
Utility method to create an eland.Dataframe from an Elasticsearch index_pattern.
(Similar to pandas.read_csv, but source data is an Elasticsearch index rather than
a csv file)
Parameters
----------
es_client: Elasticsearch client argument(s)
- elasticsearch-py parameters or
- elasticsearch-py instance
es_index_pattern: str
Elasticsearch index pattern
Returns
-------
eland.DataFrame
See Also
--------
eland.pandas_to_eland: Create an eland.Dataframe from pandas.DataFrame
eland.eland_to_pandas: Create a pandas.Dataframe from eland.DataFrame
"""
return DataFrame(es_client=es_client, es_index_pattern=es_index_pattern)
def pandas_to_eland(
@ -552,8 +521,3 @@ def csv_to_eland( # type: ignore
# Now create an eland.DataFrame that references the new index
return DataFrame(es_client, es_index_pattern=es_dest_index)
@deprecated_api("eland.csv_to_eland()")
def read_csv(*args, **kwargs) -> DataFrame: # type: ignore
return csv_to_eland(*args, **kwargs)

6
eland/index.py
View File

@ -17,8 +17,6 @@
from typing import TYPE_CHECKING, Optional, TextIO
from eland.utils import deprecated_api
if TYPE_CHECKING:
from .query_compiler import QueryCompiler
@ -95,7 +93,3 @@ class Index:
buf.write("Index:\n")
buf.write(f" es_index_field: {self.es_index_field}\n")
buf.write(f" is_source_field: {self.is_source_field}\n")
@deprecated_api("eland.Index.es_info()")
def info_es(self, buf: TextIO) -> None:
self.es_info(buf)

7
eland/ml/__init__.py
View File

@ -15,9 +15,6 @@
# specific language governing permissions and limitations
# under the License.
from eland.ml.ml_model import ImportedMLModel, MLModel
from eland.ml.ml_model import ImportedMLModel, MLModel # noqa: F401
__all__ = [
"MLModel",
"ImportedMLModel",
]
__all__ = ["MLModel"]

22
eland/ml/ml_model.py
View File

@ -15,7 +15,6 @@
# specific language governing permissions and limitations
# under the License.
import warnings
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union, cast
import elasticsearch
@ -105,7 +104,7 @@ class MLModel:
--------
>>> from sklearn import datasets
>>> from xgboost import XGBRegressor
>>> from eland.ml import ImportedMLModel
>>> from eland.ml import MLModel
>>> # Train model
>>> training_data = datasets.make_classification(n_features=6, random_state=0)
@ -254,7 +253,6 @@ class MLModel:
classification_labels: Optional[List[str]] = None,
classification_weights: Optional[List[float]] = None,
es_if_exists: Optional[str] = None,
overwrite: Optional[bool] = None,
es_compress_model_definition: bool = True,
) -> "MLModel":
"""
@ -318,9 +316,6 @@ class MLModel:
- fail: Raise a Value Error
- replace: Overwrite existing model
overwrite: **DEPRECATED** - bool
Delete and overwrite existing model (if exists)
es_compress_model_definition: bool
If True will use 'compressed_definition' which uses gzipped
JSON instead of raw JSON to reduce the amount of data sent
@ -370,20 +365,7 @@ class MLModel:
serializer = transformer.transform()
model_type = transformer.model_type
# Verify if both parameters are given
if overwrite is not None and es_if_exists is not None:
raise ValueError(
"Using 'overwrite' and 'es_if_exists' together is invalid, use only 'es_if_exists'"
)
if overwrite is not None:
warnings.warn(
"'overwrite' parameter is deprecated, use 'es_if_exists' instead",
DeprecationWarning,
stacklevel=2,
)
es_if_exists = "replace" if overwrite else "fail"
elif es_if_exists is None:
if es_if_exists is None:
es_if_exists = "fail"
ml_model = MLModel(

6
eland/series.py
View File

@ -59,7 +59,7 @@ from eland.filter import (
ScriptFilter,
)
from eland.ndframe import NDFrame
from eland.utils import deprecated_api, to_list
from eland.utils import to_list
if TYPE_CHECKING: # type: ignore
from elasticsearch import Elasticsearch # noqa: F401
@ -712,10 +712,6 @@ class Series(NDFrame):
return buf.getvalue()
@deprecated_api("eland.Series.es_info()")
def info_es(self) -> str:
return self.es_info()
def __add__(self, right):
"""
Return addition of series and right, element-wise (binary operator add).

120
tests/ml/test_imported_ml_model_pytest.py → tests/ml/test_ml_model_pytest.py
View File

@ -80,7 +80,7 @@ def check_prediction_equality(es_model, py_model, test_data):
np.testing.assert_almost_equal(test_results, es_results, decimal=2)
class TestImportedMLModel:
class TestMLModel:
@requires_no_ml_extras
def test_import_ml_model_when_dependencies_are_not_available(self):
from eland.ml import MLModel # noqa: F401
@ -239,6 +239,17 @@ class TestImportedMLModel:
es_model, regressor, random_rows(training_data[0], 20)
)
match = f"Trained machine learning model {model_id} already exists"
with pytest.raises(ValueError, match=match):
MLModel.import_model(
ES_TEST_CLIENT,
model_id,
regressor,
feature_names,
es_if_exists="fail",
es_compress_model_definition=compress_model_definition,
)
# Clean up
es_model.delete_model()
@ -460,110 +471,3 @@ class TestImportedMLModel:
# Clean up
es_model.delete_model()
# If both overwrite and es_if_exists is given.
@requires_sklearn
@pytest.mark.parametrize("compress_model_definition", [True, False])
@pytest.mark.parametrize("es_if_exists", ["fail", "replace"])
@pytest.mark.parametrize("overwrite", [True, False])
def test_imported_mlmodel_bothparams(
self, compress_model_definition, es_if_exists, overwrite
):
# Train model
training_data = datasets.make_regression(n_features=5)
regressor = RandomForestRegressor()
regressor.fit(training_data[0], training_data[1])
feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_random_forest_regressor"
match = "Using 'overwrite' and 'es_if_exists' together is invalid, use only 'es_if_exists'"
with pytest.raises(ValueError, match=match):
MLModel.import_model(
ES_TEST_CLIENT,
model_id,
regressor,
feature_names,
es_if_exists=es_if_exists,
overwrite=overwrite,
es_compress_model_definition=compress_model_definition,
)
# Deprecation warning for overwrite parameter
@requires_sklearn
@pytest.mark.parametrize("compress_model_definition", [True, False])
@pytest.mark.parametrize("overwrite", [True])
def test_imported_mlmodel_overwrite_true(
self, compress_model_definition, overwrite
):
# Train model
training_data = datasets.make_regression(n_features=5)
regressor = RandomForestRegressor()
regressor.fit(training_data[0], training_data[1])
feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_random_forest_regressor"
match = "'overwrite' parameter is deprecated, use 'es_if_exists' instead"
with pytest.warns(DeprecationWarning, match=match):
MLModel.import_model(
ES_TEST_CLIENT,
model_id,
regressor,
feature_names,
overwrite=overwrite,
es_compress_model_definition=compress_model_definition,
)
@requires_sklearn
@pytest.mark.parametrize("compress_model_definition", [True, False])
@pytest.mark.parametrize("overwrite", [False])
def test_imported_mlmodel_overwrite_false(
self, compress_model_definition, overwrite
):
# Train model
training_data = datasets.make_regression(n_features=5)
regressor = RandomForestRegressor()
regressor.fit(training_data[0], training_data[1])
feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_random_forest_regressor"
match_error = f"Trained machine learning model {model_id} already exists"
match_warning = (
"'overwrite' parameter is deprecated, use 'es_if_exists' instead"
)
with pytest.raises(ValueError, match=match_error):
with pytest.warns(DeprecationWarning, match=match_warning):
MLModel.import_model(
ES_TEST_CLIENT,
model_id,
regressor,
feature_names,
overwrite=overwrite,
es_compress_model_definition=compress_model_definition,
)
# Raise ValueError if Model exists when es_if_exists = 'fail'
@requires_sklearn
@pytest.mark.parametrize("compress_model_definition", [True, False])
def test_es_if_exists_fail(self, compress_model_definition):
# Train model
training_data = datasets.make_regression(n_features=5)
regressor = RandomForestRegressor()
regressor.fit(training_data[0], training_data[1])
feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_random_forest_regressor"
# If both overwrite and es_if_exists is given.
match = f"Trained machine learning model {model_id} already exists"
with pytest.raises(ValueError, match=match):
MLModel.import_model(
ES_TEST_CLIENT,
model_id,
regressor,
feature_names,
es_if_exists="fail",
es_compress_model_definition=compress_model_definition,
)