Python logistic.LogisticRegression类代码示例

    def test_regularization_path(self):
        # Check results using logistic path
        num_samples = 10
        num_feat = 5

        X, y = make_classification(n_samples=num_samples, n_features=num_feat, n_informative=3,
                                       n_classes=2, random_state=0, weights=[0.5, 0.5])
        matrix = np.zeros((num_samples, num_feat + 2))
        matrix[:,:-2] = X
        matrix[:, -2] = np.ones(num_samples)
        matrix[:, -1] = y

        # Betas to test
        logitfitL1 = LogisticRegressionL1()
        lambda_grid = np.exp(-1 * np.linspace(1, 17, 200))
        path = logitfitL1.fit(matrix, lambda_grid)

        # Sklearn
        cs = l1_min_c(X, y, loss='log') * np.logspace(0, 3)

        # Computing regularization path using sklearn
        clf = LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
        coefs_ = []
        for c in cs:
            clf.set_params(C=c)
            clf.fit(X, y)
            coefs_.append(clf.coef_.ravel().copy())

        skbetas = np.append(clf.intercept_[0], clf.coef_)
        np.testing.assert_almost_equal(skbetas, logitfitL1.coef_, 1)

class LogReg:
    def __init__(self):
        self.load_data()
        self.clf = LogisticRegression(class_weight = 'balanced')
        self.train()
        self.predict()

    def load_data(self):
        train_csv = './data/train.csv'
        test_csv = './data/test.csv'
        df_train = pd.read_csv(train_csv, header=0)
        df_test = pd.read_csv(test_csv, header=0)
        arr_train = df_train.values
        arr_test = df_test.values
        self.train_X = arr_train[0::,1::]
        self.train_Y = arr_train[0::, 0]
        self.test_X = arr_test[0::, 1::]
        self.test_ID = arr_test[0::,0]

    def train(self):
        self.clf.fit(self.train_X, self.train_Y)

    def predict(self):
        self.test_Y = self.clf.predict_proba(self.test_X)

    def get_training_accuracy(self):
        return (self.clf.score(self.train_X, self.train_Y))

    def store_result(self):
        df_out = pd.DataFrame()
        df_out['Id'] = self.test_ID
        df_out['Action'] = self.test_Y[0::,1]
        df_out.to_csv('./data/results/c1_result.csv',index=False)

def predictWithThreshold(datadir, threshold, penalty_type='l2'):
	maxent = LogisticRegression(penalty=penalty_type)
	scores = defaultdict(list)
	for dir in sorted(os.listdir(datadir), reverse=True):
		trainfeatures, trainlabels, vec = feats_and_classify.collect_features(datadir+dir+'/train.conll')
		TrainIndices=np.array(range(len(trainfeatures)))
		features, labels,  vec = feats_and_classify.collect_features(datadir+dir+'/all.conll')
		TestIndices=np.array(range(len(trainfeatures),len(features)))
#		print('\r'+dir, end="")
#		print(dir)
		TrainX_i = features[TrainIndices]
		Trainy_i = labels[TrainIndices]

		TestX_i = features[TestIndices]
		Testy_i =  labels[TestIndices]

		maxent.fit(TrainX_i,Trainy_i)
#		print('Finished fitting')
		ypred_i, score=pred_for_threshold(maxent,TestX_i,Testy_i, threshold)
#		print('Predicting')

		scores["F1"].append(score[0])
		scores["Recall"].append(score[1])
		scores["Accuracy"].append(score[2])
		scores["Precision"].append(score[3])

	
	#scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
	print("\n--")

	for key in sorted(scores.keys()):
		currentmetric = np.array(scores[key])
		print("%s : %0.2f (+/- %0.2f)" % (key,currentmetric.mean(), currentmetric.std()))
	print("--")

def cvWithThreshold(X, y_current_tr, y_current_te, threshold, regularization='l2'):
    out_dict = {}
    scores = defaultdict(list)
    fold=1
    maxent = LogisticRegression(penalty=regularization)
    for TrainIndices, TestIndices in cross_validation.StratifiedKFold(y_current_tr, n_folds=10, shuffle=False, random_state=None):
        print('\r'+str(fold), end="")
        fold+=1
        TrainX_i = X[TrainIndices]
        Trainy_i = y_current_tr[TrainIndices]
        TestX_i = X[TestIndices]
        Testy_i =  y_current_te[TestIndices]
     
        maxent.fit(TrainX_i,Trainy_i)
        ypred_i, score=pred_for_threshold(maxent,TestX_i,Testy_i, threshold)

        scores["F1"].append(score[0])
        scores["Recall"].append(score[1])
        scores["Accuracy"].append(score[2])
        scores["Precision"].append(score[3])

    
    #scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
    print("\n--")

    for key in sorted(scores.keys()):
        currentmetric = np.array(scores[key])
        out_dict[key] = (currentmetric.mean(),currentmetric.std())
        print("%s : %0.2f (+/- %0.2f)" % (key,currentmetric.mean(), currentmetric.std()))
    print("--")
    return out_dict

def main():
    scriptdir = os.path.dirname(os.path.realpath(__file__))
    parser = argparse.ArgumentParser(description="Skeleton for features and classifier for CWI-2016--optimisation of threshhold")
    parser.add_argument('--threshold',type=float,default=0.5)
    parser.add_argument('--annotator',type=str,default="03")
    parser.add_argument('--penalty',type=str,choices=["l1","l2"],default="l1")


    args = parser.parse_args()
    current_single_ann = scriptdir+"/../data/cwi_training/cwi_training_"+args.annotator+".lbl.conll"
    testfile = scriptdir+"/../data/cwi_testing/cwi_testing.txt.lbl.conll"
    X__dict_train, y_train, v_train = feats_and_classify.collect_features(current_single_ann,vectorize=False)
    X_dict_test, y_test, v_test = feats_and_classify.collect_features(testfile,vectorize=False)
    featdicts = list([x for x in X__dict_train + X_dict_test])
    vect = DictVectorizer()
    X = vect.fit_transform(featdicts).toarray()
    X_train=X[:len(y_train)]
    X_test=X[len(y_train):]

    maxent = LogisticRegression(penalty=args.penalty)
    maxent.fit(X_train,y_train)
    y_pred_proba = maxent.predict_proba(X_test)
    ypred_i=["1" if pair[1]>=args.threshold else "0" for pair in y_pred_proba]
    fout = open(args.annotator+".pred",mode="w")
    print("\n".join(ypred_i),file=fout)
    fout.close()
    sys.exit(0)

def main():
    classes = [
        'chimp',
        'corvette',
        'tokyo',
        'goldengatebridge'
        ]
    
    images, labels = get_labels(classes)
    std_features = get_standard_features(images)
    
    k = 256
    surf_features = get_visual_words(images, k)
    tas_features = get_tas_features(images)
    
    feature_dict = {
        'Std': std_features,
        'SURF': surf_features,
        'TAS': tas_features
        #'Zernike': zernike_features
        }
        
    best_features = log_classify(feature_dict, labels)
    classifier = LogisticRegression() 
    classifier.fit(best_features, labels)

def mlogistic():
	X = []

	# 前三行作为输入样本
	X.append("fuck you")
	X.append("fuck you all")
	X.append("hello everyone")

	# 后两句作为测试样本
	X.append("fuck me")
	X.append("hello boy")

	# y为样本标注
	y = [1,1,0]

	vectorizer = TfidfVectorizer()

	# 取X的前三句作为输入做tfidf转换
	X_train = vectorizer.fit_transform(X[:-2])
	print X_train
	# 取X的后两句用“上句生成”的tfidf做转换
	X_test = vectorizer.transform(X[-2:])
	print X_test

	# 用逻辑回归模型做训练
	classifier = LogisticRegression()
	classifier.fit(X_train, y)

	# 做测试样例的预测
	predictions = classifier.predict(X_test)
	print predictions

def test_logreg_cv_penalty():
    # Test that the correct penalty is passed to the final fit.
    X, y = make_classification(n_samples=50, n_features=20, random_state=0)
    lr_cv = LogisticRegressionCV(penalty="l1", Cs=[1.0], solver='liblinear')
    lr_cv.fit(X, y)
    lr = LogisticRegression(penalty="l1", C=1.0, solver='liblinear')
    lr.fit(X, y)
    assert_equal(np.count_nonzero(lr_cv.coef_), np.count_nonzero(lr.coef_))

def main():
    scriptdir = os.path.dirname(os.path.realpath(__file__))
    default_pool = scriptdir+"/../data/cwi_training/cwi_training.txt.lbl.conll"
    parser = argparse.ArgumentParser(description="Skeleton for features and classifier for CWI-2016--optimisation of threshhold")
    parser.add_argument('--iterations',type=int,default=5)

    args = parser.parse_args()


    all_feats = []
    all_labels = defaultdict(list)
    scores = defaultdict(list)




    for idx in "01 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 17 18 19 20".split(" "):
#    for idx in "01".split(" "):
        current_single_ann = scriptdir+"/../data/cwi_training/cwi_training_"+idx+".lbl.conll"
        f_current, labels_current, v_current = feats_and_classify.collect_features(current_single_ann,vectorize=False,generateFeatures=False)
        for instance_index,l in enumerate(labels_current):
            all_labels[instance_index].append(l)
    current_single_ann = scriptdir+"/../data/cwi_training/cwi_training_01.lbl.conll"
    feats, labels_current, v_current = feats_and_classify.collect_features(current_single_ann,vectorize=True,generateFeatures=True)

    for it in range(args.iterations):
        for TrainIndices, TestIndices in cross_validation.KFold(n=feats.shape[0], n_folds=10, shuffle=True, random_state=None):
            maxent = LogisticRegression(penalty='l2')

            TrainX_i = feats[TrainIndices]
            Trainy_i = [all_labels[x][random.randrange(0,20)] for x in TrainIndices]

            TestX_i = feats[TestIndices]
            Testy_i =  [all_labels[x][random.randrange(0,20)] for x in TestIndices]

            maxent.fit(TrainX_i,Trainy_i)
            ypred_i = maxent.predict(TestX_i)

            acc = accuracy_score(ypred_i, Testy_i)
            pre = precision_score(ypred_i, Testy_i)
            rec = recall_score(ypred_i, Testy_i)
            # shared task uses f1 of *accuracy* and recall!
            f1 = 2 * acc * rec / (acc + rec)

            scores["Accuracy"].append(acc)
            scores["F1"].append(f1)
            scores["Precision"].append(pre)
            scores["Recall"].append(rec)
        #scores = cross_validation.cross_val_score(maxent, features, labels, cv=10)
        print("--")

    for key in sorted(scores.keys()):
        currentmetric = np.array(scores[key])
        print("%s : %0.2f (+/- %0.2f)" % (key,currentmetric.mean(), currentmetric.std()))
    print("--")

    sys.exit(0)

def classify_logistic(train_features, train_labels, test_features):
    global SAVE
    clf = LogisticRegression()
    clf.fit(train_features, train_labels)

    if not TEST and SAVE:
        save_pickle("logistic", clf)

    return clf.predict(test_features)

def my_module(rt, params, inputs, outputs):
    # TODO : Fill your code here
    X = pickle.load(open(inputs.X, 'r'))
    Y = pickle.load(open(inputs.Y, 'r'))

    model = LogisticRegression()
    model.fit(X, Y)
    pickle.dump(model, open(outputs.MODEL, 'w'))
    
    print "Done"

def test_dtype_match():
    # Test that np.float32 input data is not cast to np.float64 when possible

    X_32 = np.array(X).astype(np.float32)
    y_32 = np.array(Y1).astype(np.float32)
    X_64 = np.array(X).astype(np.float64)
    y_64 = np.array(Y1).astype(np.float64)
    X_sparse_32 = sp.csr_matrix(X, dtype=np.float32)

    for solver in ['newton-cg']:
        for multi_class in ['ovr', 'multinomial']:

            # Check type consistency
            lr_32 = LogisticRegression(solver=solver, multi_class=multi_class)
            lr_32.fit(X_32, y_32)
            assert_equal(lr_32.coef_.dtype, X_32.dtype)

            # check consistency with sparsity
            lr_32_sparse = LogisticRegression(solver=solver,
                                              multi_class=multi_class)
            lr_32_sparse.fit(X_sparse_32, y_32)
            assert_equal(lr_32_sparse.coef_.dtype, X_sparse_32.dtype)

            # Check accuracy consistency
            lr_64 = LogisticRegression(solver=solver, multi_class=multi_class)
            lr_64.fit(X_64, y_64)
            assert_equal(lr_64.coef_.dtype, X_64.dtype)
            assert_almost_equal(lr_32.coef_, lr_64.coef_.astype(np.float32))

def test_dtype_match():
    # Disabled to unblock the 0.19.2 release. See:
    # https://github.com/scikit-learn/scikit-learn/issues/11438
    # Test that np.float32 input data is not cast to np.float64 when possible
    raise SkipTest()
    X_32 = np.array(X).astype(np.float32)
    y_32 = np.array(Y1).astype(np.float32)
    X_64 = np.array(X).astype(np.float64)
    y_64 = np.array(Y1).astype(np.float64)
    X_sparse_32 = sp.csr_matrix(X, dtype=np.float32)

    for solver in ['newton-cg']:
        for multi_class in ['ovr', 'multinomial']:

            # Check type consistency
            lr_32 = LogisticRegression(solver=solver, multi_class=multi_class)
            lr_32.fit(X_32, y_32)
            assert_equal(lr_32.coef_.dtype, X_32.dtype)

            # check consistency with sparsity
            lr_32_sparse = LogisticRegression(solver=solver,
                                              multi_class=multi_class)
            lr_32_sparse.fit(X_sparse_32, y_32)
            assert_equal(lr_32_sparse.coef_.dtype, X_sparse_32.dtype)

            # Check accuracy consistency
            lr_64 = LogisticRegression(solver=solver, multi_class=multi_class)
            lr_64.fit(X_64, y_64)
            assert_equal(lr_64.coef_.dtype, X_64.dtype)
            assert_almost_equal(lr_32.coef_, lr_64.coef_.astype(np.float32))

def test_logreg_l1_sparse_data():
    # Because liblinear penalizes the intercept and saga does not, we do not
    # fit the intercept to make it possible to compare the coefficients of
    # the two models at convergence.
    rng = np.random.RandomState(42)
    n_samples = 50
    X, y = make_classification(n_samples=n_samples, n_features=20,
                               random_state=0)
    X_noise = rng.normal(scale=0.1, size=(n_samples, 3))
    X_constant = np.zeros(shape=(n_samples, 2))
    X = np.concatenate((X, X_noise, X_constant), axis=1)
    X[X < 1] = 0
    X = sparse.csr_matrix(X)

    lr_liblinear = LogisticRegression(penalty="l1", C=1.0, solver='liblinear',
                                      fit_intercept=False,
                                      tol=1e-10)
    lr_liblinear.fit(X, y)

    lr_saga = LogisticRegression(penalty="l1", C=1.0, solver='saga',
                                 fit_intercept=False,
                                 max_iter=1000, tol=1e-10)
    lr_saga.fit(X, y)
    assert_array_almost_equal(lr_saga.coef_, lr_liblinear.coef_)
    # Noise and constant features should be regularized to zero by the l1
    # penalty
    assert_array_almost_equal(lr_liblinear.coef_[0, -5:], np.zeros(5))
    assert_array_almost_equal(lr_saga.coef_[0, -5:], np.zeros(5))

    # Check that solving on the sparse and dense data yield the same results
    lr_saga_dense = LogisticRegression(penalty="l1", C=1.0, solver='saga',
                                       fit_intercept=False,
                                       max_iter=1000, tol=1e-10)
    lr_saga_dense.fit(X.toarray(), y)
    assert_array_almost_equal(lr_saga.coef_, lr_saga_dense.coef_)

def test_nnet(n_samples=200, n_features=7, distance=0.8, complete=False):
    """
    :param complete: if True, all possible combinations will be checked, and quality is printed
    """
    X, y = generate_sample(n_samples=n_samples, n_features=n_features, distance=distance)

    nn_types = [
        nnet.SimpleNeuralNetwork,
        nnet.MLPClassifier,
        nnet.SoftmaxNeuralNetwork,
        nnet.RBFNeuralNetwork,
        nnet.PairwiseNeuralNetwork,
        nnet.PairwiseSoftplusNeuralNetwork,
    ]

    if complete:
        # checking all possible combinations
        for loss in nnet.losses:
            for NNType in nn_types:
                for trainer in nnet.trainers:
                    nn = NNType(layers=[5], loss=loss, trainer=trainer, random_state=42, epochs=100)
                    nn.fit(X, y )
                    print(roc_auc_score(y, nn.predict_proba(X)[:, 1]), nn)

        lr = LogisticRegression().fit(X, y)
        print(lr, roc_auc_score(y, lr.predict_proba(X)[:, 1]))

        assert 0 == 1, "Let's see and compare results"
    else:
        # checking combinations of losses, nn_types, trainers, most of them are used once during tests.
        attempts = max(len(nnet.losses), len(nnet.trainers), len(nn_types))
        losses_shift = numpy.random.randint(10)
        trainers_shift = numpy.random.randint(10)
        for attempt in range(attempts):
            # each combination is tried 3 times. before raising exception
            retry_attempts = 3
            for retry_attempt in range(retry_attempts):
                loss = list(nnet.losses.keys())[(attempt + losses_shift) % len(nnet.losses)]
                trainer = list(nnet.trainers.keys())[(attempt + trainers_shift) % len(nnet.trainers)]

                nn_type = nn_types[attempt % len(nn_types)]

                nn = nn_type(layers=[5], loss=loss, trainer=trainer, random_state=42 + retry_attempt, epochs=200)
                print(nn)
                nn.fit(X, y)
                quality = roc_auc_score(y, nn.predict_proba(X)[:, 1])
                computed_loss = nn.compute_loss(X, y)
                if quality > 0.8:
                    break
                else:
                    print('attempt {} : {}'.format(retry_attempt, quality))
                    if retry_attempt == retry_attempts - 1:
                        raise RuntimeError('quality of model is too low: {} {}'.format(quality, nn))