Python mlp.Regressor类代码示例

def NeuralNet(train, test, features):
    eta = 0.025
    niter = 2000

    regressor = Regressor(
        layers=[Layer("Rectifier", units=100), Layer("Tanh", units=100), Layer("Sigmoid", units=100), Layer("Linear")],
        learning_rate=eta,
        learning_rule="momentum",
        learning_momentum=0.9,
        batch_size=100,
        valid_size=0.01,
        n_stable=100,
        n_iter=niter,
        verbose=True,
    )

    print regressor.__class__.__name__
    start = time.time()
    regressor.fit(np.array(train[list(features)]), train[goal])
    print "  -> Training time:", time.time() - start

    if not os.path.exists("result/"):
        os.makedirs("result/")
    # TODO: fix this shit
    predictions = regressor.predict(np.array(test[features]))
    try:  # try to flatten a list that might be flattenable.
        predictions = list(itertools.chain.from_iterable(predictions))
    except:
        pass
    csvfile = "result/dat-nnet-eta%s-niter%s.csv" % (str(eta), str(niter))
    with open(csvfile, "w") as output:
        writer = csv.writer(output, lineterminator="\n")
        writer.writerow([myid, goal])
        for i in range(0, len(predictions)):
            writer.writerow([i + 1, predictions[i]])

def gamma():
    value_map = {'warm': 1.0, 'neutral': 0.5, 'cold': 0.0}

    X = data["x"][:, [0, 1, 2, 5, 6]]
    X = np.abs(X)
    maxX = np.amax(X, axis=0)
    minX = np.amax(X, axis=0)
    X = (X - minX) / maxX
    Y = data["y"][:, 1]
    Y = np.asarray([value_map[y] for y in Y])

    split_data = cross_validation.train_test_split(X, Y, test_size=0.2)
    X_train = split_data[0]
    X_test = split_data[1]
    Y_train = split_data[2]
    Y_test = split_data[3]

    nn = Regressor(
        layers=[
            Layer("Rectifier", units=3),
            Layer("Linear")],
        learning_rate=1e-3,
        n_iter=100)

    nn.fit(X_train, Y_train)

    print 'inosity accuracy'
    prediction = nn.predict(X_test)
    prediction = [closest(y[0]) for y in prediction]
    Y_test = [closest(y) for y in Y_test]
    print metrics.accuracy_score(prediction, Y_test)

class ClassificationTools():
	def __init__(self, inputVector=[], outputVector=[], filepath=''):
		if filepath == '':
			self.inputVector = numpy.asarray(inputVector)
			self.outputVector = numpy.asarray(outputVector)
			self.model = None
		else:
			self.model = pickle.load(file(filepath, 'r'))

	def setVectors(self, inputVector, outputVector):
		self.inputVector = numpy.asarray(inputVector)
		self.outputVector = numpy.asarray(outputVector)


	def trainMultilayerPerceptron(self, hlunits=10000, learningRate=0.01, iters=1000):
		# trains a simple MLP with a single hidden layer
		self.model = Regressor(
			layers=[
				Layer("Rectifier", units=hlunits),
				Layer("Linear")],
			learning_rate=learningRate,
			n_iter=iters)
		self.model.fit(self.inputVector, self.outputVector)

	def predict(self, toPredict):
		prediction = self.model.predict(numpy.asarray(toPredict))
		return prediction # this will be a 1D numpy array of floats

	def trainDeepNetwork(self):
		# trains a deep network based a multi layer autoencoder
		# which is then fine tuned using an MLP
		pass

	def serializeModel(self, filepath):
		pickle.dump(self.model, file(filepath, 'w'))

 def test_VerboseRegressor(self):
     nn = MLPR(layers=[L("Linear")], verbose=1, n_iter=1)
     a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,4))
     nn.fit(a_in, a_out)
     assert_in("Epoch       Training Error       Validation Error       Time", self.buf.getvalue())
     assert_in("    1       ", self.buf.getvalue())
     assert_in("    N/A     ", self.buf.getvalue())

def neural_net(features,target,test_size_percent=0.2,cv_split=3,n_iter=100,learning_rate=0.01):
    '''Features -> Pandas Dataframe with attributes as columns
        target -> Pandas Dataframe with target column for prediction
        Test_size_percent -> Percentage of data point to be used for testing'''
    scale=preprocessing.MinMaxScaler()
    X_array = scale.fit_transform(features)
    y_array = scale.fit_transform(target)
    mlp = Regressor(layers=[Layer("Rectifier",units=5), # Hidden Layer1
                            Layer("Rectifier",units=3)  # Hidden Layer2
                            ,Layer("Linear")],     # Output Layer
                        n_iter = n_iter, learning_rate=0.01)
    X_train, X_test, y_train, y_test = train_test_split(X_array, y_array.T.squeeze(), test_size=test_size_percent, random_state=4)
    mlp.fit(X_train,y_train)
    test_prediction = mlp.predict(X_test)
    tscv = TimeSeriesSplit(cv_split)
    
    training_score = cross_val_score(mlp,X_train,y_train,cv=tscv.n_splits) 
    testing_score = cross_val_score(mlp,X_test,y_test,cv=tscv.n_splits)
    print"Cross-val Training score:", training_score.mean()
#    print"Cross-val Testing score:", testing_score.mean()
    training_predictions = cross_val_predict(mlp,X_train,y_train,cv=tscv.n_splits)
    testing_predictions = cross_val_predict(mlp,X_test,y_test,cv=tscv.n_splits)
    
    training_accuracy = metrics.r2_score(y_train,training_predictions) 
#    test_accuracy_model = metrics.r2_score(y_test,test_prediction_model)
    test_accuracy = metrics.r2_score(y_test,testing_predictions)
    
#    print"Cross-val predicted accuracy:", training_accuracy
    print"Test-predictions accuracy:",test_accuracy

    plot_model(target,y_train,y_test,training_predictions,testing_predictions)
    return mlp

def CreateNetwork(data, predicates):
    # входная размерность
    dim_in = len(predicates)
    # выходная размерность
    dim_out = len(data[0]) - 1
    # конфигурация сети
    neural_network = Regressor(
        layers=[
            Layer("Rectifier", units=50),
            Layer("Linear")],
        learning_rate=0.001,
        n_iter=5000)
    # формирование обучающей выборки
    x_train = np.array([CalcPredicates(row[0], predicates) for row in data])
    y_train = np.array([apply(float, row[1:]) for row in data])
    # обучение
    logging.info('Start training')
    logging.info('\n'+str(x_train))
    logging.info('\n'+str(y_train))
    try:
        neural_network.fit(x_train, y_train)
    except KeyboardInterrupt:
        logging.info('User break')
        pass
    logging.info('Network created successfully')
    logging.info('score = '+str(neural_network.score(x_train, y_train)))
    # сохранение обученной сети
    pickle.dump(neural_network, open(datetime.datetime.now().isoformat()+'.pkl', 'wb'))
    return neural_network

class NeuralRegLearner(object):

    def __init__(self, verbose = False):
        self.name = "Neural net Regression Learner"
        self.network =  Regressor( layers=[
										Layer("Rectifier", units=100),
										Layer("Linear")],
									learning_rate=0.02,
									n_iter=10)

    def addEvidence(self,dataX,dataY):
        """
        @summary: Add training data to learner
        @param dataX: X values of data to add
        @param dataY: the Y training values
        """
        dataX = np.array(dataX)
        dataY = np.array(dataY)
        self.network.fit(dataX, dataY) 
        
    def query(self,points):
        """
        @summary: Estimate a set of test points given the model we built.
        @param points: should be a numpy array with each row corresponding to a specific query.
        @returns the estimated values according to the saved model.
        """
        return self.network.predict(points)

class TestLinearNetwork(unittest.TestCase):

    def setUp(self):
        self.nn = MLPR(layers=[L("Linear")], n_iter=1)

    def test_LifeCycle(self):
        del self.nn

    def test_PredictNoOutputUnitsAssertion(self):
        a_in = numpy.zeros((8,16))
        assert_raises(AssertionError, self.nn.predict, a_in)

    def test_AutoInitializeWithOutputUnits(self):
        self.nn.layers[-1].units = 4
        a_in = numpy.zeros((8,16))
        self.nn.predict(a_in)

    def test_FitAutoInitialize(self):
        a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,4))
        self.nn.fit(a_in, a_out)
        assert_true(self.nn.is_initialized)

    def test_FitWrongSize(self):
        a_in, a_out = numpy.zeros((7,16)), numpy.zeros((9,4))
        assert_raises(AssertionError, self.nn.fit, a_in, a_out)

    def run_EqualityTest(self, copier, asserter):
        for activation in ["Rectifier", "Sigmoid", "Maxout", "Tanh"]:
            nn1 = MLPR(layers=[L(activation, units=16, pieces=2), L("Linear", units=1)], random_state=1234)
            nn1._initialize(self.a_in, self.a_out)

            nn2 = copier(nn1, activation)
            asserter(numpy.all(nn1.predict(self.a_in) == nn2.predict(self.a_in)))

class TestSerializedNetwork(TestLinearNetwork):

    def setUp(self):
        self.original = MLPR(layers=[L("Linear")])
        a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,4))
        self.original._initialize(a_in, a_out)

        buf = io.BytesIO()
        pickle.dump(self.original, buf)
        buf.seek(0)
        self.nn = pickle.load(buf)

    def test_TypeOfWeightsArray(self):
        for w, b in self.nn._mlp_to_array():
            assert_equal(type(w), numpy.ndarray)
            assert_equal(type(b), numpy.ndarray)

    # Override base class test, you currently can't re-train a network that
    # was serialized and deserialized.
    def test_FitAutoInitialize(self): pass
    def test_ResizeInputFrom4D(self): pass
    def test_ResizeInputFrom3D(self): pass

    def test_PredictNoOutputUnitsAssertion(self):
        # Override base class test, this is not initialized but it
        # should be able to predict without throwing assert.
        assert_true(self.nn.is_initialized)

    def test_PredictAlreadyInitialized(self):
        a_in = numpy.zeros((8,16))
        self.nn.predict(a_in)

class TestDataAugmentation(unittest.TestCase):

    def setUp(self):
        self.called = 0
        self.value = 1.0

        self.nn = MLPR(
                    layers=[L("Linear")],
                    n_iter=1,
                    batch_size=2,
                    mutator=self._mutate_fn)

    def _mutate_fn(self, sample):
        self.called += 1
        sample[sample == 0.0] = self.value

    def test_TestCalledOK(self):
        a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,4))
        self.nn._fit(a_in, a_out)
        assert_equals(a_in.shape[0], self.called)

    def test_DataIsUsed(self):
        self.value = float("nan")
        a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,4))
        assert_raises(RuntimeError, self.nn._fit, a_in, a_out)

 def make(self, activation, seed=1234, train=False, **keywords):
     nn = MLPR(layers=[L(activation, units=16, **keywords), L("Linear", units=1)], random_state=seed, n_iter=1)
     if train:
         nn.fit(self.a_in, self.a_out)
     else:
         nn._initialize(self.a_in, self.a_out)
     return nn

    def test_UnusedParameterWarning(self):
        nn = MLPR(layers=[L("Linear", pieces=2)], n_iter=1)
        a_in = numpy.zeros((8,16))
        nn._initialize(a_in, a_in)

        assert_in('Parameter `pieces` is unused', self.buf.getvalue())
        self.buf = io.StringIO() # clear

    def test_SetParametersConstructor(self):
        weights = numpy.random.uniform(-1.0, +1.0, (16,4))
        biases = numpy.random.uniform(-1.0, +1.0, (4,))
        nn = MLPR(layers=[L("Linear")], parameters=[(weights, biases)])

        a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,4))
        nn._initialize(a_in, a_out)
        assert_in('Reloading parameters for 1 layer weights and biases.', self.buf.getvalue())

    def test_HorizontalKernel(self):
        nn = MLPR(layers=[
                    C("Rectifier", channels=7, kernel_shape=(16,1)),
                    L("Linear", units=5)])

        a_in = numpy.zeros((8,16,16,1))
        nn._create_specs(a_in)
        assert_equal(nn.unit_counts, [256, 16 * 7, 5])