Python sklearn.linear_model.SGDRegressor() Examples

def test_multi_target_regression_partial_fit():
    X, y = datasets.make_regression(n_targets=3)
    X_train, y_train = X[:50], y[:50]
    X_test, y_test = X[50:], y[50:]

    references = np.zeros_like(y_test)
    half_index = 25
    for n in range(3):
        sgr = SGDRegressor(random_state=0, max_iter=5)
        sgr.partial_fit(X_train[:half_index], y_train[:half_index, n])
        sgr.partial_fit(X_train[half_index:], y_train[half_index:, n])
        references[:, n] = sgr.predict(X_test)

    sgr = MultiOutputRegressor(SGDRegressor(random_state=0, max_iter=5))

    sgr.partial_fit(X_train[:half_index], y_train[:half_index])
    sgr.partial_fit(X_train[half_index:], y_train[half_index:])

    y_pred = sgr.predict(X_test)
    assert_almost_equal(references, y_pred)
    assert not hasattr(MultiOutputRegressor(Lasso), 'partial_fit') 

def test_not_robust_regression(loss, weighting):
    clf = RobustWeightedEstimator(
        SGDRegressor(),
        loss=loss,
        max_iter=100,
        weighting=weighting,
        k=0,
        c=1e7,
        burn_in=0,
        random_state=rng,
    )
    clf_not_rob = SGDRegressor(loss=loss, random_state=rng)
    clf.fit(X_r, y_r)
    clf_not_rob.fit(X_r, y_r)
    pred1 = clf.predict(X_r)
    pred2 = clf_not_rob.predict(X_r)

    assert np.linalg.norm(pred1 - pred2) / np.linalg.norm(
        pred2
    ) < np.linalg.norm(pred1 - y_r) / np.linalg.norm(y_r) 

def test_bagging_regressor_sgd(self):
        model, X = fit_regression_model(
            BaggingRegressor(SGDRegressor()))
        model_onnx = convert_sklearn(
            model,
            "bagging regressor",
            [("input", FloatTensorType([None, X.shape[1]]))],
            dtype=np.float32,
        )
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnBaggingRegressorSGD-Dec4",
            allow_failure="StrictVersion(onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_multi_target_regression_partial_fit():
    X, y = datasets.make_regression(n_targets=3)
    X_train, y_train = X[:50], y[:50]
    X_test, y_test = X[50:], y[50:]

    references = np.zeros_like(y_test)
    half_index = 25
    for n in range(3):
        sgr = SGDRegressor(random_state=0, max_iter=5)
        sgr.partial_fit(X_train[:half_index], y_train[:half_index, n])
        sgr.partial_fit(X_train[half_index:], y_train[half_index:, n])
        references[:, n] = sgr.predict(X_test)

    sgr = MultiOutputRegressor(SGDRegressor(random_state=0, max_iter=5))

    sgr.partial_fit(X_train[:half_index], y_train[:half_index])
    sgr.partial_fit(X_train[half_index:], y_train[half_index:])

    y_pred = sgr.predict(X_test)
    assert_almost_equal(references, y_pred)
    assert_false(hasattr(MultiOutputRegressor(Lasso), 'partial_fit')) 

def set_params(self, r=3, d=8, nbits=16, discrete=True,
                   normalization=True, inner_normalization=True,
                   penalty='elasticnet', loss='squared_loss'):
        """setter."""
        self.r = r
        self.d = d
        self.nbits = nbits
        self.normalization = normalization
        self.inner_normalization = inner_normalization
        self.discrete = discrete
        self.model = SGDRegressor(
            loss=loss, penalty=penalty,
            average=True, shuffle=True,
            max_iter=5, tol=None)
        self.vectorizer = Vectorizer(
            r=self.r, d=self.d,
            normalization=self.normalization,
            inner_normalization=self.inner_normalization,
            discrete=self.discrete,
            nbits=self.nbits)
        return self 

def test_model_sgd_regressor_bool(self):
        model, X = fit_regression_model(
            linear_model.SGDRegressor(), is_bool=True)
        model_onnx = convert_sklearn(
            model, "SGD regression",
            [("input", BooleanTensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnSGDRegressorBool",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_model_sgd_regressor_int(self):
        model, X = fit_regression_model(
            linear_model.SGDRegressor(), is_int=True)
        model_onnx = convert_sklearn(
            model, "SGD regression",
            [("input", Int64TensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnSGDRegressorInt-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_model_sgd_regressor(self):
        model, X = fit_regression_model(linear_model.SGDRegressor())
        model_onnx = convert_sklearn(
            model,
            "scikit-learn SGD regression",
            [("input", FloatTensorType([None, X.shape[1]]))],
        )
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnSGDRegressor-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def __init__(self):
        self.clf = linear_model.SGDRegressor(n_iter=50) 

def fit_ensemble(x,y):
    fit_type = jhkaggle.jhkaggle_config['FIT_TYPE']
    if 1:
        if fit_type == jhkaggle.const.FIT_TYPE_BINARY_CLASSIFICATION:
            blend = SGDClassifier(loss="log", penalty="elasticnet")  # LogisticRegression()
        else:
            # blend = SGDRegressor()
            #blend = LinearRegression()
            #blend = RandomForestRegressor(n_estimators=10, n_jobs=-1, max_depth=5, criterion='mae')
            blend = LassoLarsCV(normalize=True)
            #blend = ElasticNetCV(normalize=True)
            #blend = LinearRegression(normalize=True)
        blend.fit(x, y)
    else:
        blend = LogisticRegression()
        blend.fit(x, y)


    return blend 

def load_default(self, machine_list='basic'):
        """
        Loads 4 different scikit-learn regressors by default. The advanced list adds more machines. 

        Parameters
        ----------
        machine_list: optional, list of strings
            List of default machine names to be loaded.
        Returns
        -------
        self : returns an instance of self.
        """

        if machine_list == 'basic':
            machine_list = ['tree', 'ridge', 'random_forest', 'svm']
        if machine_list == 'advanced':
            machine_list=['lasso', 'tree', 'ridge', 'random_forest', 'svm', 'bayesian_ridge', 'sgd']

        self.estimators_ = {}
        for machine in machine_list:
            try:
                if machine == 'lasso':
                    self.estimators_['lasso'] = linear_model.LassoCV(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'tree':
                    self.estimators_['tree'] = DecisionTreeRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'ridge':
                    self.estimators_['ridge'] = linear_model.RidgeCV().fit(self.X_k_, self.y_k_)
                if machine == 'random_forest':
                    self.estimators_['random_forest'] = RandomForestRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'svm':
                    self.estimators_['svm'] = LinearSVR(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'sgd':
                    self.estimators_['sgd'] = linear_model.SGDRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'bayesian_ridge':
                    self.estimators_['bayesian_ridge'] = linear_model.BayesianRidge().fit(self.X_k_, self.y_k_)
            except ValueError:
                continue
        return self 

def test_sgd_regressor_1(self):
        from lale.lib.sklearn import SGDRegressor

        reg = SGDRegressor(learning_rate='optimal', eta0=0.2)
        reg.fit(self.X_train, self.y_train) 

def load_default(self, machine_list='basic'):
        """
        Loads 4 different scikit-learn regressors by default. The advanced list adds more machines. 
        Parameters
        ----------
        machine_list: optional, list of strings
            List of default machine names to be loaded. 
            Default is basic,
        Returns
        -------
        self : returns an instance of self.
        """
        if machine_list == 'basic':
            machine_list = ['tree', 'ridge', 'random_forest', 'svm']
        if machine_list == 'advanced':
            machine_list=['lasso', 'tree', 'ridge', 'random_forest', 'svm', 'bayesian_ridge', 'sgd']

        self.estimators_ = {}
        for machine in machine_list:
            try:
                if machine == 'lasso':
                    self.estimators_['lasso'] = linear_model.LassoCV(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'tree':
                    self.estimators_['tree'] = DecisionTreeRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'ridge':
                    self.estimators_['ridge'] = linear_model.RidgeCV().fit(self.X_k_, self.y_k_)
                if machine == 'random_forest':
                    self.estimators_['random_forest'] = RandomForestRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'svm':
                    self.estimators_['svm'] = SVR().fit(self.X_k_, self.y_k_)
                if machine == 'sgd':
                    self.estimators_['sgd'] = linear_model.SGDRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'bayesian_ridge':
                    self.estimators_['bayesian_ridge'] = linear_model.BayesianRidge().fit(self.X_k_, self.y_k_)
            except ValueError:
                continue
        return self 

def __init__(self, options):
        self.handle_options(options)

        out_params = convert_params(
            options.get('params', {}),
            bools=['fit_intercept'],
            ints=['random_state', 'n_iter'],
            floats=['l1_ratio', 'alpha', 'eta0', 'power_t'],
            strs=['penalty', 'learning_rate'],
        )

        self.scaler = StandardScaler()
        self.estimator = _SGDRegressor(**out_params)
        self.columns = None 

def gen_json(self, home_dir=None, pdbbind_version=2016):
        if not home_dir:
            home_dir = path_join(dirname(__file__), 'PLECscore')

        if isinstance(self.model, SGDRegressor):
            attributes = ['coef_', 'intercept_', 't_']
        elif isinstance(self.model, MLPRegressor):
            attributes = ['loss_', 'coefs_', 'intercepts_', 'n_iter_',
                          'n_layers_', 'n_outputs_', 'out_activation_']

        out = {}
        for attr_name in attributes:
            attr = getattr(self.model, attr_name)
            # convert numpy arrays to list for json
            if isinstance(attr, np.ndarray):
                attr = attr.tolist()
            elif (isinstance(attr, (list, tuple)) and
                  isinstance(attr[0], np.ndarray)):
                attr = [x.tolist() for x in attr]
            out[attr_name] = attr

        json_path = path_join(home_dir, 'plecscore_%s_p%i_l%i_s%i_pdbbind%i.json' %
                              (self.version, self.depth_protein,
                               self.depth_ligand, self.size, pdbbind_version))

        with open(json_path, 'w') as json_f:
            json.dump(out, json_f, indent=2)
        return json_path 

def test_lm(self):
		_checkLM(ElasticNet())
		_checkLM(LinearRegression())
		_checkLM(SGDRegressor()) 

def linear_model_SGD(X_train, y_train, X_val, y_val):
    model = SGDRegressor()
    model.fit(X_train, y_train)
    print_evaluation_metrics(model, "sgd", X_val, y_val.values.ravel())
    print_evaluation_metrics2(model, "sgd", X_train, y_train.values.ravel()) 

def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.linear_model.ARDRegression, lm.ARDRegression)
        self.assertIs(df.linear_model.BayesianRidge, lm.BayesianRidge)
        self.assertIs(df.linear_model.ElasticNet, lm.ElasticNet)
        self.assertIs(df.linear_model.ElasticNetCV, lm.ElasticNetCV)

        self.assertIs(df.linear_model.HuberRegressor, lm.HuberRegressor)

        self.assertIs(df.linear_model.Lars, lm.Lars)
        self.assertIs(df.linear_model.LarsCV, lm.LarsCV)
        self.assertIs(df.linear_model.Lasso, lm.Lasso)
        self.assertIs(df.linear_model.LassoCV, lm.LassoCV)
        self.assertIs(df.linear_model.LassoLars, lm.LassoLars)
        self.assertIs(df.linear_model.LassoLarsCV, lm.LassoLarsCV)
        self.assertIs(df.linear_model.LassoLarsIC, lm.LassoLarsIC)

        self.assertIs(df.linear_model.LinearRegression, lm.LinearRegression)
        self.assertIs(df.linear_model.LogisticRegression, lm.LogisticRegression)
        self.assertIs(df.linear_model.LogisticRegressionCV, lm.LogisticRegressionCV)
        self.assertIs(df.linear_model.MultiTaskLasso, lm.MultiTaskLasso)
        self.assertIs(df.linear_model.MultiTaskElasticNet, lm.MultiTaskElasticNet)
        self.assertIs(df.linear_model.MultiTaskLassoCV, lm.MultiTaskLassoCV)
        self.assertIs(df.linear_model.MultiTaskElasticNetCV, lm.MultiTaskElasticNetCV)

        self.assertIs(df.linear_model.OrthogonalMatchingPursuit, lm.OrthogonalMatchingPursuit)
        self.assertIs(df.linear_model.OrthogonalMatchingPursuitCV, lm.OrthogonalMatchingPursuitCV)
        self.assertIs(df.linear_model.PassiveAggressiveClassifier, lm.PassiveAggressiveClassifier)
        self.assertIs(df.linear_model.PassiveAggressiveRegressor, lm.PassiveAggressiveRegressor)

        self.assertIs(df.linear_model.Perceptron, lm.Perceptron)
        self.assertIs(df.linear_model.RandomizedLasso, lm.RandomizedLasso)
        self.assertIs(df.linear_model.RandomizedLogisticRegression, lm.RandomizedLogisticRegression)
        self.assertIs(df.linear_model.RANSACRegressor, lm.RANSACRegressor)
        self.assertIs(df.linear_model.Ridge, lm.Ridge)
        self.assertIs(df.linear_model.RidgeClassifier, lm.RidgeClassifier)
        self.assertIs(df.linear_model.RidgeClassifierCV, lm.RidgeClassifierCV)
        self.assertIs(df.linear_model.RidgeCV, lm.RidgeCV)
        self.assertIs(df.linear_model.SGDClassifier, lm.SGDClassifier)
        self.assertIs(df.linear_model.SGDRegressor, lm.SGDRegressor)
        self.assertIs(df.linear_model.TheilSenRegressor, lm.TheilSenRegressor) 

def test_multi_target_sample_weight_partial_fit():
    # weighted regressor
    X = [[1, 2, 3], [4, 5, 6]]
    y = [[3.141, 2.718], [2.718, 3.141]]
    w = [2., 1.]
    rgr_w = MultiOutputRegressor(SGDRegressor(random_state=0, max_iter=5))
    rgr_w.partial_fit(X, y, w)

    # weighted with different weights
    w = [2., 2.]
    rgr = MultiOutputRegressor(SGDRegressor(random_state=0, max_iter=5))
    rgr.partial_fit(X, y, w)

    assert_not_equal(rgr.predict(X)[0][0], rgr_w.predict(X)[0][0]) 

def test_sgd_regressor_3(self):
        from sklearn.linear_model import SGDRegressor

        reg = SGDRegressor(l1_ratio=0.2, penalty='l1')
        reg.fit(self.X_train, self.y_train) 

def test_sgd_regressor_2(self):
        from lale.lib.sklearn import SGDRegressor

        reg = SGDRegressor(early_stopping=False, validation_fraction=0.2)
        reg.fit(self.X_train, self.y_train) 

def test_sgd_regressor(self):
        from lale.lib.sklearn import SGDRegressor

        reg = SGDRegressor(loss='squared_loss', epsilon=0.2)
        reg.fit(self.X_train, self.y_train) 

def fit(self, X, y, *args):
        sgd = SGDRegressor(penalty='l1', loss='squared_loss', alpha=3.0e-11, power_t=-0.12, eta0=0.019, random_state=0,
                           average=True)
        sgd.fit(X, np.log1p(y))
        coef_cutoff = np.percentile(np.abs(sgd.coef_), self.percentile_cutoff)
        self.features_to_keep = np.where(np.abs(sgd.coef_) >= coef_cutoff)[0]
        return self 

def getModels():
    result = []
    result.append("LinearRegression")
    result.append("BayesianRidge")
    result.append("ARDRegression")
    result.append("ElasticNet")
    result.append("HuberRegressor")
    result.append("Lasso")
    result.append("LassoLars")
    result.append("Rigid")
    result.append("SGDRegressor")
    result.append("SVR")
    result.append("MLPClassifier")
    result.append("KNeighborsClassifier")
    result.append("SVC")
    result.append("GaussianProcessClassifier")
    result.append("DecisionTreeClassifier")
    result.append("RandomForestClassifier")
    result.append("AdaBoostClassifier")
    result.append("GaussianNB")
    result.append("LogisticRegression")
    result.append("QuadraticDiscriminantAnalysis")
    return result 

def __init__(self):
        OutputThing.__init__(self, ports=['train', 'observe', 'predict'])
        self.clf = linear_model.SGDRegressor() 

def decision_function(self, X, *args, **kw):
        X = sp.csr_matrix(X)
        return linear_model.SGDRegressor.decision_function(self, X, *args,
                                                           **kw) 

def partial_fit(self, X, y, *args, **kw):
        X = sp.csr_matrix(X)
        return linear_model.SGDRegressor.partial_fit(self, X, y, *args, **kw) 

def fit(self, X, y, *args, **kw):
        X = sp.csr_matrix(X)
        return linear_model.SGDRegressor.fit(self, X, y, *args, **kw) 

def test_multi_target_sample_weight_partial_fit():
    # weighted regressor
    X = [[1, 2, 3], [4, 5, 6]]
    y = [[3.141, 2.718], [2.718, 3.141]]
    w = [2., 1.]
    rgr_w = MultiOutputRegressor(SGDRegressor(random_state=0, max_iter=5))
    rgr_w.partial_fit(X, y, w)

    # weighted with different weights
    w = [2., 2.]
    rgr = MultiOutputRegressor(SGDRegressor(random_state=0, max_iter=5))
    rgr.partial_fit(X, y, w)

    assert_not_equal(rgr.predict(X)[0][0], rgr_w.predict(X)[0][0]) 

def __init__(self, base_estimator=SGDRegressor(), order=None, random_state=None):
        super().__init__()
        self.base_estimator = base_estimator
        self.order = order
        self.random_state = random_state
        self.chain = None
        self.ensemble = None
        self.L = None
        self._random_state = None   # This is the actual random_state object used internally
        self.__configure()