Schemas

lale/lib/sklearn/__init__.py

@@ -24,6 +24,9 @@
 
 * lale.lib.sklearn. `AdaBoostClassifier`_
 * lale.lib.sklearn. `BaggingClassifier`_
+* lale.lib.sklearn. `BernoulliNB`_
+* lale.lib.sklearn. `CalibratedClassifierCV`_
+* lale.lib.sklearn. `ComplementNB`_
 * lale.lib.sklearn. `DecisionTreeClassifier`_
 * lale.lib.sklearn. `DummyClassifier`_
 * lale.lib.sklearn. `ExtraTreesClassifier`_
@@ -44,6 +47,8 @@
 Regressors:
 
 * lale.lib.sklearn. `AdaBoostRegressor`_
+* lale.lib.sklearn. `ARDRegression`_
+* lale.lib.sklearn. `BayesianRidge`_
 * lale.lib.sklearn. `DecisionTreeRegressor`_
 * lale.lib.sklearn. `DummyRegressor`_
 * lale.lib.sklearn. `ExtraTreesRegressor`_
@@ -58,6 +63,11 @@
 
 Transformers:
 
+* lale.lib.sklearn. `AdditiveChi2Sampler`_
+* lale.lib.sklearn. `BernoulliRBM`_
+* lale.lib.sklearn. `Binarizer`_
+* lale.lib.sklearn. `Birch`_
+* lale.lib.sklearn. `CCA`_
 * lale.lib.sklearn. `ColumnTransformer`_
 * lale.lib.sklearn. `FeatureAgglomeration`_
 * lale.lib.sklearn. `FunctionTransformer`_
@@ -83,8 +93,18 @@
 
 .. _`AdaBoostClassifier`: lale.lib.sklearn.ada_boost_classifier.html
 .. _`AdaBoostRegressor`: lale.lib.sklearn.ada_boost_regressor.html
+.. _`AdditiveChi2Sampler`: lale.lib.sklearn.additive_chi2_sampler.html
+.. _`ARDRegression`: lale.lib.sklearn.ard_regression.html
 .. _`BaggingClassifier`: lale.lib.sklearn.bagging_classifier.html
+.. _`BayesianRidge`: lale.lib.sklearn.bayesian_ridge.html
+.. _`BernoulliNB`: lale.lib.sklearn.bernoulli_nb.html
+.. _`BernoulliRBM`: lale.lib.sklearn.bernoulli_rbm.html
+.. _`Binarizer`: lale.lib.sklearn.binarizer.html
+.. _`Birch`: lale.lib.sklearn.birch.html
+.. _`CCA`: lale.lib.sklearn.cca.html
+.. _`CalibratedClassifierCV`: lale.lib.sklearn.calibrated_classifier_cv.html
 .. _`ColumnTransformer`: lale.lib.sklearn.column_transformer.html
+.. _`ComplementNB`: lale.lib.sklearn.complement_nb.html
 .. _`DecisionTreeClassifier`: lale.lib.sklearn.decision_tree_classifier.html
 .. _`DecisionTreeRegressor`: lale.lib.sklearn.decision_tree_regressor.html
 .. _`DummyClassifier`: lale.lib.sklearn.dummy_classifier.html
@@ -137,8 +157,18 @@
 
 from .ada_boost_classifier import AdaBoostClassifier
 from .ada_boost_regressor import AdaBoostRegressor
+from .additive_chi2_sampler import AdditiveChi2Sampler
+from .ard_regression import ARDRegression
 from .bagging_classifier import BaggingClassifier
+from .bayesian_ridge import BayesianRidge
+from .bernoulli_nb import BernoulliNB
+from .bernoulli_rbm import BernoulliRBM
+from .binarizer import Binarizer
+from .birch import Birch
+from .calibrated_classifier_cv import CalibratedClassifierCV
+from .cca import CCA
 from .column_transformer import ColumnTransformer
+from .complement_nb import ComplementNB
 from .decision_tree_classifier import DecisionTreeClassifier
 from .decision_tree_regressor import DecisionTreeRegressor
 from .dummy_classifier import DummyClassifier

lale/lib/sklearn/additive_chi2_sampler.py

@@ -0,0 +1,93 @@
+from sklearn.kernel_approximation import AdditiveChi2Sampler as Op
+
+from lale.docstrings import set_docstrings
+from lale.operators import make_operator
+
+_hyperparams_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Approximate feature map for additive chi2 kernel.",
+    "allOf": [
+        {
+            "type": "object",
+            "required": ["sample_steps", "sample_interval"],
+            "relevantToOptimizer": ["sample_steps"],
+            "additionalProperties": False,
+            "properties": {
+                "sample_steps": {
+                    "type": "integer",
+                    "minimumForOptimizer": 1,
+                    "maximumForOptimizer": 3,
+                    "distribution": "uniform",
+                    "default": 2,
+                    "description": "Gives the number of (complex) sampling points.",
+                },
+                "sample_interval": {
+                    "anyOf": [{"type": "number"}, {"enum": [None]}],
+                    "default": None,
+                    "description": "Sampling interval",
+                },
+            },
+        },
+        {
+            "description": "sample_interval must be specified when sample_steps not in {1,2,3}",
+            "anyOf": [
+                {
+                    "type": "object",
+                    "properties:": {"sample_steps": {"enum": [1, 2, 3]}},
+                },
+                {
+                    "type": "object",
+                    "properties:": {"sample_interval": {"type": "number"}},
+                },
+            ],
+        },
+    ],
+}
+_input_fit_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Set the parameters",
+    "type": "object",
+    "required": ["X"],
+    "properties": {
+        "X": {
+            "type": "array",
+            "items": {"type": "array", "items": {"type": "number"}},
+            "description": "Training data, where n_samples in the number of samples and n_features is the number of features.",
+        }
+    },
+}
+_input_transform_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Apply approximate feature map to X.",
+    "type": "object",
+    "required": ["X"],
+    "properties": {
+        "X": {"type": "array", "items": {"type": "array", "items": {"type": "number"}}}
+    },
+}
+_output_transform_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Whether the return value is an array of sparse matrix depends on the type of the input X.",
+    "laleType": "Any",
+    "XXX TODO XXX": "{array, sparse matrix},                shape = (n_samples, n_features * (2*sample_steps + 1))",
+}
+_combined_schemas = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": """`Approximate feature map for additive chi2 kernel`_ from sklearn
+
+.. _`Approximate feature map for additive chi2 kernel.`: https://scikit-learn.org/stable/modules/generated/sklearn.kernel_approximation.AdditiveChi2Sampler
+""",
+    "documentation_url": "https://lale.readthedocs.io/en/latest/modules/lale.lib.sklearn.additive_chi2_sampler.html",
+    "import_from": "sklearn.kernel_approximation",
+    "type": "object",
+    "tags": {"pre": [], "op": ["transformer"], "post": []},
+    "properties": {
+        "hyperparams": _hyperparams_schema,
+        "input_fit": _input_fit_schema,
+        "input_transform": _input_transform_schema,
+        "output_transform": _output_transform_schema,
+    },
+}
+AdditiveChi2Sampler = make_operator(Op, _combined_schemas)
+
+set_docstrings(AdditiveChi2Sampler)

lale/lib/sklearn/ard_regression.py

@@ -0,0 +1,165 @@
+from sklearn.linear_model import ARDRegression as Op
+
+from lale.docstrings import set_docstrings
+from lale.operators import make_operator
+
+_hyperparams_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "ARDRegression Hyperparameter schema.",
+    "allOf": [
+        {
+            "type": "object",
+            "required": [
+                "n_iter",
+                "tol",
+                "alpha_1",
+                "alpha_2",
+                "lambda_1",
+                "lambda_2",
+                "compute_score",
+                "threshold_lambda",
+                "fit_intercept",
+                "normalize",
+                "copy_X",
+                "verbose",
+            ],
+            "relevantToOptimizer": [
+                "n_iter",
+                "tol",
+                "compute_score",
+                "fit_intercept",
+                "normalize",
+            ],
+            "additionalProperties": False,
+            "properties": {
+                "n_iter": {
+                    "type": "integer",
+                    "minimumForOptimizer": 5,
+                    "maximumForOptimizer": 1000,
+                    "distribution": "uniform",
+                    "default": 300,
+                    "description": "Maximum number of iterations",
+                },
+                "tol": {
+                    "type": "number",
+                    "minimumForOptimizer": 1e-08,
+                    "maximumForOptimizer": 0.01,
+                    "distribution": "loguniform",
+                    "default": 0.001,
+                    "description": "Stop the algorithm if w has converged",
+                },
+                "alpha_1": {
+                    "type": "number",
+                    "default": 1e-06,
+                    "description": "Hyper-parameter : shape parameter for the Gamma distribution prior over the alpha parameter",
+                },
+                "alpha_2": {
+                    "type": "number",
+                    "default": 1e-06,
+                    "description": "Hyper-parameter : inverse scale parameter (rate parameter) for the Gamma distribution prior over the alpha parameter",
+                },
+                "lambda_1": {
+                    "type": "number",
+                    "default": 1e-06,
+                    "description": "Hyper-parameter : shape parameter for the Gamma distribution prior over the lambda parameter",
+                },
+                "lambda_2": {
+                    "type": "number",
+                    "default": 1e-06,
+                    "description": "Hyper-parameter : inverse scale parameter (rate parameter) for the Gamma distribution prior over the lambda parameter",
+                },
+                "compute_score": {
+                    "type": "boolean",
+                    "default": False,
+                    "description": "If True, compute the objective function at each step of the model",
+                },
+                "threshold_lambda": {
+                    "type": "number",
+                    "default": 10000.0,
+                    "description": "threshold for removing (pruning) weights with high precision from the computation",
+                },
+                "fit_intercept": {
+                    "type": "boolean",
+                    "default": True,
+                    "description": "whether to calculate the intercept for this model",
+                },
+                "normalize": {
+                    "type": "boolean",
+                    "default": False,
+                    "description": "This parameter is ignored when ``fit_intercept`` is set to False",
+                },
+                "copy_X": {
+                    "type": "boolean",
+                    "default": True,
+                    "description": "If True, X will be copied; else, it may be overwritten.",
+                },
+                "verbose": {
+                    "type": "boolean",
+                    "default": False,
+                    "description": "Verbose mode when fitting the model.",
+                },
+            },
+        }
+    ],
+}
+_input_fit_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Fit the ARDRegression model according to the given training data",
+    "type": "object",
+    "required": ["X", "y"],
+    "properties": {
+        "X": {
+            "type": "array",
+            "items": {"type": "array", "items": {"type": "number"}},
+            "description": "Training vector, where n_samples in the number of samples and n_features is the number of features.",
+        },
+        "y": {
+            "type": "array",
+            "items": {"type": "number"},
+            "description": "Target values (integers)",
+        },
+    },
+}
+_input_predict_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Predict using the linear model.",
+    "type": "object",
+    "required": ["X"],
+    "properties": {
+        "X": {
+            "type": "array",
+            "items": {"type": "array", "items": {"type": "number"}},
+            "description": "Samples.",
+        },
+        "return_std": {
+            "anyOf": [{"type": "boolean"}, {"enum": [None]}],
+            "default": None,
+            "description": "Whether to return the standard deviation of posterior prediction.",
+        },
+    },
+}
+_output_predict_schema = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": "Predict using the linear model.",
+    "laleType": "Any",
+}
+_combined_schemas = {
+    "$schema": "http://json-schema.org/draft-04/schema#",
+    "description": """`ARDRegression`_ Bayesian ARD regression from sklearn.
+
+.. _`ARDRegression`: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.ARDRegression"
+""",
+    "documentation_url": "https://lale.readthedocs.io/en/latest/modules/lale.lib.sklearn.ard_regression.html",
+    "import_from": "sklearn.linear_model",
+    "type": "object",
+    "tags": {"pre": [], "op": ["estimator"], "post": []},
+    "properties": {
+        "hyperparams": _hyperparams_schema,
+        "input_fit": _input_fit_schema,
+        "input_predict": _input_predict_schema,
+        "output_predict": _output_predict_schema,
+    },
+}
+ARDRegression = make_operator(Op, _combined_schemas)
+
+set_docstrings(ARDRegression)