Python sklearn.linear_model.RandomizedLogisticRegression() Examples

The following are 6 code examples of sklearn.linear_model.RandomizedLogisticRegression(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module sklearn.linear_model , or try the search function .
Example #1
Source File: create_ngrams.py    From rasa_lookup_demo with Apache License 2.0 8 votes vote down vote up 
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
Example #2
Source File: PipeTasks.py    From ProFET with GNU General Public License v3.0 6 votes vote down vote up 
def GetKFeatures(filename, method='RFE',kbest=30,alpha=0.01, reduceMatrix = True):
    '''
    Gets best features using chosen method
    (K-best, RFE, RFECV,'L1' (RandomizedLogisticRegression),'Tree' (ExtraTreesClassifier), mrmr),
    then prints top K features' names (from featNames).
    If reduceMatrix =  True, then also returns X reduced to the K best features.

    Available methods' names are: 'RFE','RFECV','RandomizedLogisticRegression','K-best','ExtraTreesClassifier'..
    Note, that effectiveyl, Any scikit learn method could be used, if correctly imported..
    '''
    #est = method()
    '''
    Gets the K-best features (filtered by FDR, then select best ranked by t-test , more advanced options can be implemented).
    Save the data/matrix with the resulting/kept features to a new output file, "REDUCED_Feat.csv"
    '''
    features, labels, lb_encoder,featureNames = load_data(filename)
    X, y = features, labels

    # change the names as ints back to strings
    class_names=lb_encoder.inverse_transform(y)
    print("Data and labels imported. PreFilter Feature matrix shape:")
    print(X.shape)

    selectK = SelectKBest(k=kbest)
    selectK.fit(X,y)
    selectK_mask=selectK.get_support()
    K_featnames = featureNames[selectK_mask]
    print('X After K filter:',X.shape)
    print("K_featnames: %s" %(K_featnames))
    if reduceMatrix ==True :
        Reduced_df = pd.read_csv(filename, index_col=0)
        Reduced_df = Reduced_df[Reduced_df.columns[selectK_mask]]
        Reduced_df.to_csv('REDUCED_Feat.csv')
        print('Saved to REDUCED_Feat.csv')
        return Reduced_df

#WORKS! But unreadable with too many features!
Example #3
Source File: create_ngrams.py    From rasa_lookup_demo with Apache License 2.0 5 votes vote down vote up 
def get_features(X_train, y_train, names, selection_threshold=0.2):
    print("\ngetting features with randomized logistic regression...")
    print("using a selection threshold of {}".format(selection_threshold))
    randomized_logistic = RandomizedLogisticRegression(
        selection_threshold=selection_threshold
    )
    randomized_logistic.fit(X_train, y_train)
    mask = randomized_logistic.get_support()
    features = np.array(names)[mask]
    print("found {} ngrams:".format(len([f for f in features])))
    print([f for f in features])
    return features
Example #4
Source File: ngram_featurizer.py    From rasa_nlu with Apache License 2.0 5 votes vote down vote up 
def _rank_ngrams_using_cv(self, examples, labels, list_of_ngrams):
        from sklearn import linear_model

        X = np.array(self._ngrams_in_sentences(examples, list_of_ngrams))
        y = self.encode_labels(labels)

        clf = linear_model.RandomizedLogisticRegression(C=1)
        clf.fit(X, y)

        # sort the ngrams according to the classification score
        scores = clf.scores_
        sorted_idxs = sorted(enumerate(scores), key=lambda x: -1 * x[1])
        sorted_ngrams = [list_of_ngrams[i[0]] for i in sorted_idxs]

        return sorted_ngrams
Example #5
Source File: ngram_featurizer.py    From Rasa_NLU_Chi with Apache License 2.0 5 votes vote down vote up 
def _rank_ngrams_using_cv(self, examples, labels, list_of_ngrams):
        from sklearn import linear_model

        X = np.array(self._ngrams_in_sentences(examples, list_of_ngrams))
        y = self.encode_labels(labels)

        clf = linear_model.RandomizedLogisticRegression(C=1)
        clf.fit(X, y)

        # sort the ngrams according to the classification score
        scores = clf.scores_
        sorted_idxs = sorted(enumerate(scores), key=lambda x: -1 * x[1])
        sorted_ngrams = [list_of_ngrams[i[0]] for i in sorted_idxs]

        return sorted_ngrams
Example #6
Source File: test_linear_model.py    From pandas-ml with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
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)