Python sklearn.linear_model.LogisticRegression() Examples

def run_logreg(X_train, y_train, selection_threshold=0.2):
    print("\nrunning logistic regression...")
    print("using a selection threshold of {}".format(selection_threshold))
    pipe = Pipeline(
        [
            (
                "feature_selection",
                RandomizedLogisticRegression(selection_threshold=selection_threshold),
            ),
            ("classification", LogisticRegression()),
        ]
    )
    pipe.fit(X_train, y_train)
    print("training accuracy : {}".format(pipe.score(X_train, y_train)))
    print("testing accuracy : {}".format(pipe.score(X_test, y_test)))
    return pipe 

def _build_model(self,model_name,params=None):
        if params==None:
            if model_name=='xgb':
                self.model=XGBClassifier(n_estimators=100,learning_rate=0.02)
            elif model_name=='svm':
                kernel_function=chi2_kernel if not (self.model_kernel=='linear' or self.model_kernel=='rbf') else self.model_kernel
                self.model=SVC(C=1,kernel=kernel_function,gamma=1,probability=True)
            elif model_name=='lr':
                self.model=LR(C=1,penalty='l1',tol=1e-6)
        else:
            if model_name=='xgb':
                self.model=XGBClassifier(n_estimators=1000,learning_rate=0.02,**params)
            elif model_name=='svm':
                self.model=SVC(C=1,kernel=kernel_function,gamma=1,probability=True)
            elif model_name=='lr':
                self.model=LR(C=1,penalty='l1',tol=1e-6)

        log.l.info('=======> built the model {} done'.format(self.model_name)) 

def _check_autograd_supported(base_algorithm):
    supported = ['LogisticRegression', 'SGDClassifier', 'RidgeClassifier', 'StochasticLogisticRegression', 'LinearRegression']
    if not base_algorithm.__class__.__name__ in supported:
        raise ValueError("Automatic gradients only implemented for the following classes: " + ", ".join(supported))
    if base_algorithm.__class__.__name__ == 'LogisticRegression':
        if base_algorithm.penalty != 'l2':
            raise ValueError("Automatic gradients only defined for LogisticRegression with l2 regularization.")
        if base_algorithm.intercept_scaling != 1:
            raise ValueError("Automatic gradients for LogisticRegression not implemented with 'intercept_scaling'.")

    if base_algorithm.__class__.__name__ == 'RidgeClassifier':
        if base_algorithm.normalize:
            raise ValueError("Automatic gradients for LogisticRegression only implemented without 'normalize'.")

    if base_algorithm.__class__.__name__ == 'SGDClassifier':
        if base_algorithm.loss != 'log':
            raise ValueError("Automatic gradients for LogisticRegression only implemented with logistic loss.")
        if base_algorithm.penalty != 'l2':
            raise ValueError("Automatic gradients only defined for LogisticRegression with l2 regularization.")
    
    try:
        if base_algorithm.class_weight is not None:
            raise ValueError("Automatic gradients for LogisticRegression not supported with 'class_weight'.")
    except:
        pass 

def __init__(self, lambda_=1., fit_intercept=True, alpha=0.95,
                 m=1.0, ts=False, ts_from_ci=True, sample_unique=False, random_state=1):
        self.conf_coef = alpha
        self.m = m
        self.fit_intercept = fit_intercept
        self.lambda_ = lambda_
        self.ts = ts
        self.ts_from_ci = ts_from_ci
        self.warm_start = True
        self.sample_unique = bool(sample_unique)
        self.random_state = _check_random_state(random_state)
        self.is_fitted = False
        self.model = LogisticRegression(C=1./lambda_, penalty="l2",
                                        fit_intercept=fit_intercept,
                                        solver='lbfgs', max_iter=15000,
                                        warm_start=True)
        self.Sigma = np.empty((0,0), dtype=np.float64) 

def test_bad_params(self):
        X = [[1]]
        y = [0]

        with self.assertRaises(ValueError):
            LogisticRegression(data_norm=1, C=-1).fit(X, y)

        with self.assertRaises(ValueError):
            LogisticRegression(data_norm=1, C=1.2).fit(X, y)

        with self.assertRaises(ValueError):
            LogisticRegression(data_norm=1, max_iter=-1).fit(X, y)

        with self.assertRaises(ValueError):
            LogisticRegression(data_norm=1, max_iter="100").fit(X, y)

        with self.assertRaises(ValueError):
            LogisticRegression(data_norm=1, tol=-1).fit(X, y)

        with self.assertRaises(ValueError):
            LogisticRegression(data_norm=1, tol="1").fit(X, y) 

def test_same_results(self):
        from sklearn import datasets
        from sklearn.model_selection import train_test_split
        from sklearn import linear_model

        dataset = datasets.load_iris()
        X_train, X_test, y_train, y_test = train_test_split(dataset.data, dataset.target, test_size=0.2)

        clf = LogisticRegression(data_norm=12, epsilon=float("inf"))
        clf.fit(X_train, y_train)

        predict1 = clf.predict(X_test)

        clf = linear_model.LogisticRegression(solver="lbfgs", multi_class="ovr")
        clf.fit(X_train, y_train)

        predict2 = clf.predict(X_test)

        self.assertTrue(np.all(predict1 == predict2)) 

def test_accountant(self):
        from diffprivlib.accountant import BudgetAccountant
        acc = BudgetAccountant()

        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]
        X -= 3.0
        X /= 2.5

        clf = LogisticRegression(epsilon=2, data_norm=1.0, accountant=acc)
        clf.fit(X, y)
        self.assertEqual((2, 0), acc.total())

        with BudgetAccountant(3, 0) as acc2:
            clf = LogisticRegression(epsilon=2, data_norm=1.0)
            clf.fit(X, y)
            self.assertEqual((2, 0), acc2.total())

            with self.assertRaises(BudgetError):
                clf.fit(X, y) 

def create_logistic_vectorizer():
    vectorizer = CountVectorizer(lowercase=False, min_df=0.0, binary=True)
    lr = LogisticRegression(random_state=777)
    return Pipeline([("vectorizer", vectorizer), ("lr", lr)]) 

def prepare_fit_model_for_factors(model_type, x_train, y_train):
    """
    Given a model type, train and test data
    
    Args:
        model_type (str): 'classification' or 'regression'
        x_train:
        y_train:

    Returns:
        (sklearn.base.BaseEstimator): A fit model.
    """

    if model_type == 'classification':
        algorithm = LogisticRegression()
    elif model_type == 'regression':
        algorithm = LinearRegression()
    else:
        algorithm = None

    if algorithm is not None:
        algorithm.fit(x_train, y_train)

    return algorithm 

def __init__(self, *args, **kwargs):
        super(MaximumLossReductionMaximalConfidence, self).__init__(*args, **kwargs)

        # self.n_labels = len(self.dataset.get_labeled_entries()[0][1])
        self.n_labels = len(self.dataset.get_labeled_entries()[1][0])

        random_state = kwargs.pop('random_state', None)
        self.random_state_ = seed_random_state(random_state)

        self.logreg_param = kwargs.pop('logreg_param',
                                       {'multi_class': 'multinomial',
                                        'solver': 'newton-cg',
                                        'random_state': random_state})
        self.logistic_regression_ = LogisticRegression(**self.logreg_param)

        self.br_base = kwargs.pop('br_base',
              SklearnProbaAdapter(SVC(kernel='linear',
                                      probability=True,
                                      gamma="auto",
                                      random_state=random_state))) 

def compute_acc(emb, labels, train_nids, val_nids, test_nids):
    """
    Compute the accuracy of prediction given the labels.
    """
    emb = emb.cpu().numpy()
    train_nids = train_nids.cpu().numpy()
    train_labels = labels[train_nids].cpu().numpy()
    val_nids = val_nids.cpu().numpy()
    val_labels = labels[val_nids].cpu().numpy()
    test_nids = test_nids.cpu().numpy()
    test_labels = labels[test_nids].cpu().numpy()

    emb = (emb - emb.mean(0, keepdims=True)) / emb.std(0, keepdims=True)

    lr = lm.LogisticRegression(multi_class='multinomial', max_iter=10000)
    lr.fit(emb[train_nids], labels[train_nids])

    pred = lr.predict(emb)
    f1_micro_eval = skm.f1_score(labels[val_nids], pred[val_nids], average='micro')
    f1_micro_test = skm.f1_score(labels[test_nids], pred[test_nids], average='micro')
    f1_macro_eval = skm.f1_score(labels[val_nids], pred[val_nids], average='macro')
    f1_macro_test = skm.f1_score(labels[test_nids], pred[test_nids], average='macro')
    return f1_micro_eval, f1_micro_test 

def __init__(self, base_estimator=LogisticRegression(penalty='l1'), lambda_name='C',
                 lambda_grid=np.logspace(-5, -2, 25), n_bootstrap_iterations=100,
                 sample_fraction=0.5, threshold=0.6, bootstrap_func=bootstrap_without_replacement,
                 bootstrap_threshold=None, verbose=0, n_jobs=1, pre_dispatch='2*n_jobs',
                 random_state=None):
        self.base_estimator = base_estimator
        self.lambda_name = lambda_name
        self.lambda_grid = lambda_grid
        self.n_bootstrap_iterations = n_bootstrap_iterations
        self.sample_fraction = sample_fraction
        self.threshold = threshold
        self.bootstrap_func = bootstrap_func
        self.bootstrap_threshold = bootstrap_threshold
        self.verbose = verbose
        self.n_jobs = n_jobs
        self.pre_dispatch = pre_dispatch
        self.random_state = random_state 

def test_experiment_sklearn_classifier(tmpdir_name):
    X, y = make_classification_df(n_samples=1024, n_num_features=10, n_cat_features=0,
                                  class_sep=0.98, random_state=0, id_column='user_id')

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)

    params = {
        'C': 0.1
    }

    result = run_experiment(params, X_train, y_train, X_test, tmpdir_name, eval_func=roc_auc_score,
                            algorithm_type=LogisticRegression, with_auto_prep=False)

    assert len(np.unique(result.oof_prediction)) > 5  # making sure prediction is not binarized
    assert len(np.unique(result.test_prediction)) > 5
    assert roc_auc_score(y_train, result.oof_prediction) >= 0.8
    assert roc_auc_score(y_test, result.test_prediction) >= 0.8

    _check_file_exists(tmpdir_name) 

def test_regularization():
    """Test for fitting the model."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = ImportanceWeightedClassifier(loss_function='lr',
                                       l2_regularization=None)
    assert isinstance(clf.clf, LogisticRegressionCV)
    clf = ImportanceWeightedClassifier(loss_function='lr',
                                       l2_regularization=1.0)
    assert isinstance(clf.clf, LogisticRegression) 

def test_not_none(self):
        self.assertIsNotNone(LogisticRegression) 

def test_one_class(self):
        X = [[1]]
        y = [0]

        clf = LogisticRegression(data_norm=1)

        with self.assertRaises(ValueError):
            clf.fit(X, y) 

def test_no_params(self):
        clf = LogisticRegression()

        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]

        with self.assertWarns(PrivacyLeakWarning):
            clf.fit(X, y) 

def test_large_norm(self):
        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]

        clf = LogisticRegression(data_norm=1.0)

        self.assertIsNotNone(clf.fit(X, y)) 

def test_trinomial(self):
        X = np.array(
            [0.50, 0.75, 1.00])
        y = np.array([0, 1, 2])
        X = X[:, np.newaxis]

        clf = LogisticRegression(data_norm=1.0)

        self.assertIsNotNone(clf.fit(X, y)) 

def test_solver_warning(self):
        with self.assertWarns(DiffprivlibCompatibilityWarning):
            LogisticRegression(solver="newton-cg") 

def test_multi_class_warning(self):
        with self.assertWarns(DiffprivlibCompatibilityWarning):
            LogisticRegression(multi_class="multinomial") 

def test_different_results(self):
        from sklearn import datasets
        from sklearn import linear_model
        from sklearn.model_selection import train_test_split

        dataset = datasets.load_iris()
        X_train, X_test, y_train, y_test = train_test_split(dataset.data, dataset.target, test_size=0.2)

        clf = LogisticRegression(data_norm=12)
        clf.fit(X_train, y_train)

        predict1 = clf.predict(X_test)

        clf = LogisticRegression(data_norm=12)
        clf.fit(X_train, y_train)

        predict2 = clf.predict(X_test)

        clf = linear_model.LogisticRegression(solver="lbfgs", multi_class="ovr")
        clf.fit(X_train, y_train)

        predict3 = clf.predict(X_test)

        self.assertFalse(np.all(predict1 == predict2))
        self.assertFalse(np.all(predict3 == predict1) and np.all(predict3 == predict2)) 

def create_sklearn_logistic_regressor(X, y, pipeline=False):
    lin = linear_model.LogisticRegression()
    if pipeline:
        lin = Pipeline([("lin", lin)])
    model = lin.fit(X, y)
    return model 

def train_expert(history_context, history_action):
    n_round = len(history_context)
    history_context = np.array([history_context[t] for t in range(n_round)])
    history_action = np.array([history_action[t] for t in range(n_round)])
    logreg = OneVsRestClassifier(LogisticRegression())
    mnb = OneVsRestClassifier(MultinomialNB())
    logreg.fit(history_context, history_action)
    mnb.fit(history_context, history_action)
    return [logreg, mnb] 

def train_expert(action_context):
    logreg = OneVsRestClassifier(LogisticRegression())
    mnb = OneVsRestClassifier(MultinomialNB(), )
    logreg.fit(action_context.iloc[:, 2:], action_context.iloc[:, 1])
    mnb.fit(action_context.iloc[:, 2:], action_context.iloc[:, 1])
    return [logreg, mnb] 

def __init__(self,
                 coefficients=None,
                 intercept=None,
                 **kwargs):
        super(LogisticRegressionClassifier, self).__init__()

        self.kernel = linear_model.LogisticRegression(**kwargs)

        self.coefficients = coefficients
        self.intercept = intercept 

def make_lr(C):
    cls = sklearn.pipeline.make_pipeline(StandardScaler(), LogisticRegression(C=C))
    name = 'ss-lr-C%.4f' % C
    return (cls, name) 

def define_clfs_params(self):
        '''
        Defines all relevant parameters and classes for classfier objects.
        Edit these if you wish to change parameters.
        '''
        # These are the classifiers
        self.clfs = {
            'RF': RandomForestClassifier(n_estimators = 50, n_jobs = -1),
            'ET': ExtraTreesClassifier(n_estimators = 10, n_jobs = -1, criterion = 'entropy'),
            'AB': AdaBoostClassifier(DecisionTreeClassifier(max_depth = [1, 5, 10, 15]), algorithm = "SAMME", n_estimators = 200),
            'LR': LogisticRegression(penalty = 'l1', C = 1e5),
            'SVM': svm.SVC(kernel = 'linear', probability = True, random_state = 0),
            'GB': GradientBoostingClassifier(learning_rate = 0.05, subsample = 0.5, max_depth = 6, n_estimators = 10),
            'NB': GaussianNB(),
            'DT': DecisionTreeClassifier(),
            'SGD': SGDClassifier(loss = 'log', penalty = 'l2'),
            'KNN': KNeighborsClassifier(n_neighbors = 3)
            }
        # These are the parameters which will be run through
        self.params = {
             'RF':{'n_estimators': [1,10,100,1000], 'max_depth': [10, 15,20,30,40,50,60,70,100], 'max_features': ['sqrt','log2'],'min_samples_split': [2,5,10], 'random_state': [1]},
             'LR': {'penalty': ['l1','l2'], 'C': [0.00001,0.0001,0.001,0.01,0.1,1,10], 'random_state': [1]},
             'SGD': {'loss': ['log'], 'penalty': ['l2','l1','elasticnet'], 'random_state': [1]},
             'ET': {'n_estimators': [1,10,100,1000], 'criterion' : ['gini', 'entropy'], 'max_depth': [1,3,5,10,15], 'max_features': ['sqrt','log2'],'min_samples_split': [2,5,10], 'random_state': [1]},
             'AB': {'algorithm': ['SAMME', 'SAMME.R'], 'n_estimators': [1,10,100,1000], 'random_state': [1]},
             'GB': {'n_estimators': [1,10,100,1000], 'learning_rate' : [0.001,0.01,0.05,0.1,0.5],'subsample' : [0.1,0.5,1.0], 'max_depth': [1,3,5,10,20,50,100], 'random_state': [1]},
             'NB': {},
             'DT': {'criterion': ['gini', 'entropy'], 'max_depth': [1,2,15,20,30,40,50], 'max_features': ['sqrt','log2'],'min_samples_split': [2,5,10], 'random_state': [1]},
             'SVM' :{'C' :[0.00001,0.0001,0.001,0.01,0.1,1,10],'kernel':['linear'], 'random_state': [1]},
             'KNN' :{'n_neighbors': [1,5,10,25,50,100],'weights': ['uniform','distance'],'algorithm': ['auto','ball_tree','kd_tree']}
             } 

def setUp(self):
        bl1 = RandomForestClassifier(random_state=8)
        bl2 = LogisticRegression()
        bl3 = RandomForestClassifier(max_depth=10, random_state=10)

        meta_est = LogisticRegression()

        skf = StratifiedKFold(random_state=8).split

        self.stacked_ensemble = stacker.XcessivStackedEnsemble(
            [bl1, bl2, bl3],
            ['predict', 'predict_proba', 'predict_proba'],
            meta_est,
            skf
        ) 

def main():
    # Enable eager execution for DataFrame endpoint
    import tensorflow as tf
    tf.enable_eager_execution()

    # Set up training data
    train_data_dir = get_data_dir("train")
    train_data = os.path.join(train_data_dir, "part-*")
    schema_path = os.path.join(train_data_dir, "_inferred_schema.pb")

    df_train_data = next(Datasets.dataframe.examples_via_schema(train_data,
                                                                schema_path,
                                                                batch_size=1024))

    # the feature keys are ordered alphabetically for determinism
    label_keys = sorted([l for l in set(df_train_data.columns) if l.startswith("class_name")])
    feature_keys = sorted(set(df_train_data.columns).difference(label_keys))

    label = df_train_data[label_keys].apply(transform_labels, axis=1)
    features = df_train_data[feature_keys]

    # Build model
    from sklearn.linear_model import LogisticRegression
    model = LogisticRegression(multi_class="multinomial", solver="newton-cg")
    model.fit(features, label)

    # Set up eval data
    eval_data_dir = get_data_dir("eval")
    eval_data = os.path.join(eval_data_dir, "part-*")
    df_eval_data = next(Datasets.dataframe.examples_via_schema(eval_data,
                                                               schema_path,
                                                               batch_size=1024))

    eval_label = df_eval_data[label_keys].apply(transform_labels, axis=1)
    eval_features = df_eval_data[feature_keys]

    # Evaluate model
    score = model.score(eval_features, eval_label)
    print("Score is %f" % score)