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

7.6.0a3 (#131)

Browse Source 
* Updating test matrix for 7.6 + removing oss for now.

* Resolving 7.6.0 docs issues

* Updating ML docs

* Bumping version following doc fixes

* Change ExternalMLModel to ImportedMLModel
This commit is contained in:
stevedodson 2020-02-15 20:29:03 +01:00 committed by GitHub
parent fa930b6cea
commit 1a90e9232e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 49 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
docs/source/examples/demo_notebook.ipynb
View File

@ -753,7 +753,7 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"<eland.index.Index at 0x11631ffd0>" "<eland.index.Index at 0x116b3efd0>"
] ]
}, },
"execution_count": 17, "execution_count": 17,
@ -2704,15 +2704,15 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>25%</th>\n", " <th>25%</th>\n",
" <td>410.011039</td>\n", " <td>410.008918</td>\n",
" <td>2470.545974</td>\n", " <td>2470.545974</td>\n",
" <td>...</td>\n", " <td>...</td>\n",
" <td>251.773003</td>\n", " <td>251.938710</td>\n",
" <td>1.000000</td>\n", " <td>1.000000</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>50%</th>\n", " <th>50%</th>\n",
" <td>640.387285</td>\n", " <td>640.362667</td>\n",
" <td>7612.072403</td>\n", " <td>7612.072403</td>\n",
" <td>...</td>\n", " <td>...</td>\n",
" <td>503.148975</td>\n", " <td>503.148975</td>\n",
@ -2720,11 +2720,11 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>75%</th>\n", " <th>75%</th>\n",
" <td>842.213490</td>\n", " <td>840.617448</td>\n",
" <td>9734.960478</td>\n", " <td>9738.206675</td>\n",
" <td>...</td>\n", " <td>...</td>\n",
" <td>720.505705</td>\n", " <td>720.026320</td>\n",
" <td>4.172535</td>\n", " <td>4.160448</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>max</th>\n", " <th>max</th>\n",
@ -2745,9 +2745,9 @@
"mean 628.253689 7092.142457 ... 511.127842 2.835975\n", "mean 628.253689 7092.142457 ... 511.127842 2.835975\n",
"std 266.386661 4578.263193 ... 334.741135 1.939365\n", "std 266.386661 4578.263193 ... 334.741135 1.939365\n",
"min 100.020531 0.000000 ... 0.000000 0.000000\n", "min 100.020531 0.000000 ... 0.000000 0.000000\n",
"25% 410.011039 2470.545974 ... 251.773003 1.000000\n", "25% 410.008918 2470.545974 ... 251.938710 1.000000\n",
"50% 640.387285 7612.072403 ... 503.148975 3.000000\n", "50% 640.362667 7612.072403 ... 503.148975 3.000000\n",
"75% 842.213490 9734.960478 ... 720.505705 4.172535\n", "75% 840.617448 9738.206675 ... 720.026320 4.160448\n",
"max 1199.729004 19881.482422 ... 1902.901978 6.000000\n", "max 1199.729004 19881.482422 ... 1902.901978 6.000000\n",
"\n", "\n",
"[8 rows x 7 columns]" "[8 rows x 7 columns]"

18
docs/source/examples/online_retail_analysis.ipynb
View File

@ -1023,21 +1023,21 @@
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>25%</th>\n", " <th>25%</th>\n",
" <td>14217.474239</td>\n", " <td>14227.934845</td>\n",
" <td>1.000000</td>\n", " <td>1.000000</td>\n",
" <td>1.250068</td>\n", " <td>1.250000</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>50%</th>\n", " <th>50%</th>\n",
" <td>15662.024630</td>\n", " <td>15669.138235</td>\n",
" <td>2.000000</td>\n", " <td>2.000000</td>\n",
" <td>2.510000</td>\n", " <td>2.510000</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>75%</th>\n", " <th>75%</th>\n",
" <td>17212.723881</td>\n", " <td>17212.690092</td>\n",
" <td>6.671951</td>\n", " <td>6.610262</td>\n",
" <td>4.210000</td>\n", " <td>4.211297</td>\n",
" </tr>\n", " </tr>\n",
" <tr>\n", " <tr>\n",
" <th>max</th>\n", " <th>max</th>\n",
@ -1055,9 +1055,9 @@
"mean 15590.776680 7.464000 4.103233\n", "mean 15590.776680 7.464000 4.103233\n",
"std 1764.025160 85.924387 20.104873\n", "std 1764.025160 85.924387 20.104873\n",
"min 12347.000000 -9360.000000 0.000000\n", "min 12347.000000 -9360.000000 0.000000\n",
"25% 14217.474239 1.000000 1.250068\n", "25% 14227.934845 1.000000 1.250000\n",
"50% 15662.024630 2.000000 2.510000\n", "50% 15669.138235 2.000000 2.510000\n",
"75% 17212.723881 6.671951 4.210000\n", "75% 17212.690092 6.610262 4.211297\n",
"max 18239.000000 2880.000000 950.990000" "max 18239.000000 2880.000000 950.990000"
] ]
}, },

6
docs/source/reference/api/eland.ml.ExternalMLModel.predict.rst
View File

@ -1,6 +0,0 @@
eland.ml.ExternalMLModel.predict
================================
.. currentmodule:: eland.ml
.. automethod:: ExternalMLModel.predict

6
docs/source/reference/api/eland.ml.ExternalMLModel.rst
View File

@ -1,6 +0,0 @@
eland.ml.ExternalMLModel
========================
.. currentmodule:: eland.ml
.. autoclass:: ExternalMLModel

6
docs/source/reference/api/eland.ml.ImportedMLModel.predict.rst Normal file
View File

@ -0,0 +1,6 @@
eland.ml.ImportedMLModel.predict
================================
.. currentmodule:: eland.ml
.. automethod:: ImportedMLModel.predict

6
docs/source/reference/api/eland.ml.ImportedMLModel.rst Normal file
View File

@ -0,0 +1,6 @@
eland.ml.ImportedMLModel
========================
.. currentmodule:: eland.ml
.. autoclass:: ImportedMLModel

6
docs/source/reference/ml.rst
View File

@ -17,7 +17,7 @@ The fastest way to get started with machine learning features is to start a free
See https://www.elastic.co/guide/en/machine-learning/current/setup.html and other documentation for more detail. See https://www.elastic.co/guide/en/machine-learning/current/setup.html and other documentation for more detail.
ExternalMLModel ImportedMLModel
~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~
.. currentmodule:: eland.ml .. currentmodule:: eland.ml
@ -26,12 +26,12 @@ Constructor
.. autosummary:: .. autosummary::
:toctree: api/ :toctree: api/
ExternalMLModel ImportedMLModel
Learning API Learning API
^^^^^^^^^^^^ ^^^^^^^^^^^^
.. autosummary:: .. autosummary::
:toctree: api/ :toctree: api/
ExternalMLModel.predict ImportedMLModel.predict

2
eland/ml/__init__.py
View File

@ -13,4 +13,4 @@
# limitations under the License. # limitations under the License.
from eland.ml.ml_model import * from eland.ml.ml_model import *
from eland.ml.external_ml_model import * from eland.ml.imported_ml_model import *

10
eland/ml/external_ml_model.py → eland/ml/imported_ml_model.py
View File

@ -28,7 +28,7 @@ from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
from xgboost import XGBRegressor, XGBClassifier from xgboost import XGBRegressor, XGBClassifier
class ExternalMLModel(MLModel): class ImportedMLModel(MLModel):
""" """
Transform and serialize a trained 3rd party model into Elasticsearch. Transform and serialize a trained 3rd party model into Elasticsearch.
This model can then be used for inference in the Elastic Stack. This model can then be used for inference in the Elastic Stack.
@ -67,7 +67,7 @@ class ExternalMLModel(MLModel):
-------- --------
>>> from sklearn import datasets >>> from sklearn import datasets
>>> from sklearn.tree import DecisionTreeClassifier >>> from sklearn.tree import DecisionTreeClassifier
>>> from eland.ml import ExternalMLModel >>> from eland.ml import ImportedMLModel
>>> # Train model >>> # Train model
>>> training_data = datasets.make_classification(n_features=5, random_state=0) >>> training_data = datasets.make_classification(n_features=5, random_state=0)
@ -82,7 +82,7 @@ class ExternalMLModel(MLModel):
>>> # Serialise the model to Elasticsearch >>> # Serialise the model to Elasticsearch
>>> feature_names = ["f0", "f1", "f2", "f3", "f4"] >>> feature_names = ["f0", "f1", "f2", "f3", "f4"]
>>> model_id = "test_decision_tree_classifier" >>> model_id = "test_decision_tree_classifier"
>>> es_model = ExternalMLModel('localhost', model_id, classifier, feature_names, overwrite=True) >>> es_model = ImportedMLModel('localhost', model_id, classifier, feature_names, overwrite=True)
>>> # Get some test results from Elasticsearch model >>> # Get some test results from Elasticsearch model
>>> es_model.predict(test_data) >>> es_model.predict(test_data)
@ -169,7 +169,7 @@ class ExternalMLModel(MLModel):
-------- --------
>>> from sklearn import datasets >>> from sklearn import datasets
>>> from xgboost import XGBRegressor >>> from xgboost import XGBRegressor
>>> from eland.ml import ExternalMLModel >>> from eland.ml import ImportedMLModel
>>> # Train model >>> # Train model
>>> training_data = datasets.make_classification(n_features=6, random_state=0) >>> training_data = datasets.make_classification(n_features=6, random_state=0)
@ -184,7 +184,7 @@ class ExternalMLModel(MLModel):
>>> # Serialise the model to Elasticsearch >>> # Serialise the model to Elasticsearch
>>> feature_names = ["f0", "f1", "f2", "f3", "f4", "f5"] >>> feature_names = ["f0", "f1", "f2", "f3", "f4", "f5"]
>>> model_id = "test_xgb_regressor" >>> model_id = "test_xgb_regressor"
>>> es_model = ExternalMLModel('localhost', model_id, regressor, feature_names, overwrite=True) >>> es_model = ImportedMLModel('localhost', model_id, regressor, feature_names, overwrite=True)
>>> # Get some test results from Elasticsearch model >>> # Get some test results from Elasticsearch model
>>> es_model.predict(test_data) >>> es_model.predict(test_data)

16
eland/tests/ml/test_external_ml_model_pytest.py → eland/tests/ml/test_imported_ml_model_pytest.py
View File

@ -18,11 +18,11 @@ from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
from xgboost import XGBRegressor, XGBClassifier from xgboost import XGBRegressor, XGBClassifier
from eland.ml import ExternalMLModel from eland.ml import ImportedMLModel
from eland.tests import ES_TEST_CLIENT from eland.tests import ES_TEST_CLIENT
class TestExternalMLModel: class TestImportedMLModel:
def test_decision_tree_classifier(self): def test_decision_tree_classifier(self):
# Train model # Train model
@ -38,7 +38,7 @@ class TestExternalMLModel:
feature_names = ["f0", "f1", "f2", "f3", "f4"] feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_decision_tree_classifier" model_id = "test_decision_tree_classifier"
es_model = ExternalMLModel(ES_TEST_CLIENT, model_id, classifier, feature_names, overwrite=True) es_model = ImportedMLModel(ES_TEST_CLIENT, model_id, classifier, feature_names, overwrite=True)
es_results = es_model.predict(test_data) es_results = es_model.predict(test_data)
np.testing.assert_almost_equal(test_results, es_results, decimal=4) np.testing.assert_almost_equal(test_results, es_results, decimal=4)
@ -60,7 +60,7 @@ class TestExternalMLModel:
feature_names = ["f0", "f1", "f2", "f3", "f4"] feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_decision_tree_regressor" model_id = "test_decision_tree_regressor"
es_model = ExternalMLModel(ES_TEST_CLIENT, model_id, regressor, feature_names, overwrite=True) es_model = ImportedMLModel(ES_TEST_CLIENT, model_id, regressor, feature_names, overwrite=True)
es_results = es_model.predict(test_data) es_results = es_model.predict(test_data)
np.testing.assert_almost_equal(test_results, es_results, decimal=4) np.testing.assert_almost_equal(test_results, es_results, decimal=4)
@ -82,7 +82,7 @@ class TestExternalMLModel:
feature_names = ["f0", "f1", "f2", "f3", "f4"] feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_random_forest_classifier" model_id = "test_random_forest_classifier"
es_model = ExternalMLModel(ES_TEST_CLIENT, model_id, classifier, feature_names, overwrite=True) es_model = ImportedMLModel(ES_TEST_CLIENT, model_id, classifier, feature_names, overwrite=True)
es_results = es_model.predict(test_data) es_results = es_model.predict(test_data)
np.testing.assert_almost_equal(test_results, es_results, decimal=4) np.testing.assert_almost_equal(test_results, es_results, decimal=4)
@ -104,7 +104,7 @@ class TestExternalMLModel:
feature_names = ["f0", "f1", "f2", "f3", "f4"] feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_random_forest_regressor" model_id = "test_random_forest_regressor"
es_model = ExternalMLModel(ES_TEST_CLIENT, model_id, regressor, feature_names, overwrite=True) es_model = ImportedMLModel(ES_TEST_CLIENT, model_id, regressor, feature_names, overwrite=True)
es_results = es_model.predict(test_data) es_results = es_model.predict(test_data)
np.testing.assert_almost_equal(test_results, es_results, decimal=4) np.testing.assert_almost_equal(test_results, es_results, decimal=4)
@ -126,7 +126,7 @@ class TestExternalMLModel:
feature_names = ["f0", "f1", "f2", "f3", "f4"] feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_xgb_classifier" model_id = "test_xgb_classifier"
es_model = ExternalMLModel(ES_TEST_CLIENT, model_id, classifier, feature_names, overwrite=True) es_model = ImportedMLModel(ES_TEST_CLIENT, model_id, classifier, feature_names, overwrite=True)
es_results = es_model.predict(test_data) es_results = es_model.predict(test_data)
np.testing.assert_almost_equal(test_results, es_results, decimal=4) np.testing.assert_almost_equal(test_results, es_results, decimal=4)
@ -148,7 +148,7 @@ class TestExternalMLModel:
feature_names = ["f0", "f1", "f2", "f3", "f4"] feature_names = ["f0", "f1", "f2", "f3", "f4"]
model_id = "test_xgb_regressor" model_id = "test_xgb_regressor"
es_model = ExternalMLModel(ES_TEST_CLIENT, model_id, regressor, feature_names, overwrite=True) es_model = ImportedMLModel(ES_TEST_CLIENT, model_id, regressor, feature_names, overwrite=True)
es_results = es_model.predict(test_data) es_results = es_model.predict(test_data)
np.testing.assert_almost_equal(test_results, es_results, decimal=4) np.testing.assert_almost_equal(test_results, es_results, decimal=4)