Python dbn.DBN类代码示例

def train_model(data_set_path='/home/devin.fisher/Kingdoms/treadstone/_samples/still_data/still_training_data.pkl'):
    # data_set = None
    with open(data_set_path, 'rb') as f:
        data_set = pickle.load(f)

    # with open('/home/devin.fisher/Kingdoms/lol/still_training_data2.pkl', 'rb') as f:
    #     data_set = pickle.load(f)

    # (train_x, test_x, train_y, test_y) = train_test_split(data_set['data'], data_set['target'], test_size=0.1)

    train_x = data_set['data']
    test_x = data_set['data']
    train_y = data_set['target']
    test_y = data_set['target']

    dbn = DBN(
        [-1, 300, -1],
        learn_rates=0.3,
        learn_rate_decays=0.9,
        epochs=60,
        verbose=1)
    dbn.fit(train_x, train_y)

    joblib.dump(dbn, 'digit_model.pkl', compress=9)

    # dbn = joblib.load('digit_model.pkl')

    # compute the predictions for the test data and show a classification report
    preds = dbn.predict(test_x)
    print classification_report(test_y, preds)

def benchmark(k, epochs):
  print("*" * 80)
  print("k: %d, epochs: %d\n" % (k, epochs))

  #select = SelectKBest(score_func=chi2, k=k)
  select = TruncatedSVD(n_components=k)
  X_train_trunc = select.fit_transform(X_train, Y_train)
  X_test_trunc = select.transform(X_test)

  print('done truncating')

  clf = DBN([X_train_trunc.shape[1], k, 4], learn_rates=0.3, learn_rate_decays=0.9, epochs=epochs, verbose=1)
  clf.fit(X_train_trunc, Y_train)
  pred = clf.predict(X_test_trunc)

  if CREATE_SUBMISSION:
    X_submit_trunc = select.transform(X_submit)
    pred_submit = clf.predict(X_submit_trunc)
    dump_csv(pred_submit, k, epochs)

  score = metrics.f1_score(Y_test, pred)
  print("f1-score:   %0.3f" % score)

  print("classification report:")
  print(metrics.classification_report(Y_test, pred))

  print("confusion matrix:")
  print(metrics.confusion_matrix(Y_test, pred))

def training_dbn(train_dataset, n_targets=2, learn_rates=0.3, learn_rate_decays=0.9, epochs=1000, n_hidden_layers=5, n_hidden_layer_nodes=100, 
                 verbose=True):
    layers = np.ones(n_hidden_layers, dtype=int) * n_hidden_layer_nodes
    print(layers.tolist())
    X_train, y_train = train_dataset
    ff = [X_train.shape[1]]
    ff.extend(layers.tolist())
    ff.append(n_targets)
    # Create the dbn
    clf = DBN(
              ff,
              learn_rates=learn_rates,
              learn_rate_decays=learn_rate_decays,
              epochs=epochs,
              dropouts=0.1,
              verbose=verbose)

    # Counting time for training
    start = time.time()
    clf.fit(X_train, y_train) # training
    end = time.time()

    exec_time = end - start
    print('Exec time was {} secs'.format(exec_time))
    return clf, exec_time

def main():
  data_id = 'B'
  data_path = '/broad/compbio/maxwshen/data/1-MAKETRAINTEST/complete/golf/'
  
  print 'train...', datetime.datetime.now()
  train_set = readin(data_id, 'train', data_path)
  print 'valid...', datetime.datetime.now()
  valid_set = readin(data_id, 'valid', data_path)
  print 'test...', datetime.datetime.now()
  test_set = readin(data_id, 'test', data_path)

  # Input to 300 node RBM to 2 node output
  dbn = DBN( \
    [xtrain.shape[1], 300, 2], \
    learn_rates = 5, \
    learn_rate_decays = 0.9, \
    epochs = 31, \
    verbose = 1)
  dbn.fit(dat_train, y_train)

  preds = dbn.predict(dat_test)
  print classification_report(y_test, preds)

  out_fn = 'dbn.pickle'
  with open(out_fn, 'w') as f:
    pickle.dump(dbn, out_fn)

  return

def train(X, Y, alphabet):
    model = DBN([13, 1000, len(alphabet)],
    learn_rates=0.3,
    learn_rate_decays=0.9,
    epochs=10,
    verbose=1,)

    model.fit(X, Y)
    return model

def run():
    X_train, Y_train = load_training_data()

    X_train, Y_train = rotate_dataset(X_train, Y_train, 8)
    X_train, Y_train = nudge_dataset(X_train, Y_train)

    n_features = X_train.shape[1]
    n_classes = 10
    classifier = DBN([n_features, 8000, n_classes], 
        learn_rates=0.4, learn_rate_decays=0.9 ,epochs=75, verbose=1)

    classifier.fit(X_train, Y_train)

    test_data = get_test_data_set()
    predictions = classifier.predict(test_data)
    write_predictions_to_csv(predictions)

    def __init__(self):
        # images_train=data_train[:,1:]
        # trainX, _trainX, trainY, _trainY = train_test_split(images_train/255.,values_train,test_size=0.5)

        # #load test.csv
        # test = pd.read_csv("data/test.csv")
        # data_test=test.as_matrix()
        # testX, _testX = train_test_split(data_test/255.,test_size=0.99)
        
        # Random Forest
        # self.clf = RandomForestClassifier()
        
        # Stochastic Gradient Descent
        # self.clf = SGDClassifier()
        
        # Support Vector Machine
        # self.clf = LinearSVC()
        
        # Nearest Neighbors
        # self.clf = KNeighborsClassifier(n_neighbors=13)
        
        
        train = pd.read_csv("data/train.csv")
        data_train=train.as_matrix()
        values_train=data_train[:,0]
        images_train=data_train[:,1:]
        trainX, _trainX, trainY, _trainY = train_test_split(images_train/255.,values_train,test_size=0.995)
        
        # Neural Network
        self.clf = DBN([trainX.shape[1], 300, 10],learn_rates=0.3,learn_rate_decays=0.9,epochs=10,verbose = 1)
        
        #Training
        self.clf.fit(trainX, trainY)
        
        pass

def train_clf(dim, X, y, classificator):
    print("Training for {} classes".format(dim[2]))
    if classificator == "DBN":
        clf = DBN(dim,
                  learn_rates=dbn_learn_rates,
                  learn_rate_decays=dbn_learn_rate_decays,
                  epochs=dbn_epochs,
                  minibatch_size=dbn_minibatch_size,
                  verbose=dbn_verbose,
                  dropouts=dbn_dropouts
              )
    elif classificator == "GaussianNB":
        clf = GaussianNB()

    clf.fit(X, y)

    return clf

def train_dbn_dataset(dataset, x_test, y_test, alpha, nhidden, epochs, batch_size, noises=[]):
    from nolearn.dbn import DBN
    num_classes = len(set(y_test))
    print "Number of classes", num_classes
    x_train, y_train = dataset
    dbn_model = DBN([x_train.shape[1], nhidden, num_classes],
                    learn_rates = alpha,
                    learn_rate_decays = 0.9,
                    epochs = epochs,
                    verbose = 1,
                    nesterov=False,
                    minibatch_size=batch_size,
                    noises = noises)

    dbn_model.fit(x_train, y_train)
    from sklearn.metrics import classification_report, accuracy_score
    y_true, y_pred = y_test, dbn_model.predict(x_test) # Get our predictions
    print(classification_report(y_true, y_pred)) # Classification on each digit
    print(roc_auc_score(y_true, y_pred)) # Classification on each digit
    return y_pred, roc_auc_score(y_true, y_pred)

def dbn_clf(X, y, hidden_sizes=[300], num_epochs=10):
    """ deep belief network """
    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, test_size=0.25, random_state=0)
    output_categories = np.load(os.path.join(loaddir,'submit_col_name.npy'))

    print('Start training Neural Network...')

    dbn = DBN(
        [Xtrain.shape[1]] + hidden_sizes + [len(output_categories)],
        learn_rates = 0.3,
        learn_rate_decays = 0.9,
        epochs = num_epochs,
        verbose = 1)
    dbn.fit(Xtrain, ytrain)
    
    ypred = dbn.predict_proba(Xtest)
    score = log_loss(ytest, ypred)
    print('Log loss = {}'.format(score))

    return dbn, score

	 def test(self):
                 #iris = datasets.load_iris()
                 #X, y = iris.data, iris.target
                 X, y = self.dataMat,self.labelMat
                 X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.6, random_state=12)
                 #clf = RandomForestClassifier(max_depth=6,min_samples_split=9,min_samples_leaf=15,n_estimators=5)
                 #clf = DBN([X.shape[1], 24, 2],scales=0.5,learn_rates=0.02,learn_rate_decays = 0.95, learn_rate_minimums =0.001,epochs=500,l2_costs = 0.02*0.031, dropouts=0.2,verbose=0)
                 #cvnum = ShuffleSplit(2013,n_iter=10,test_size=0.6,train_size=0.4,random_state=0)
                 for scal in arange(4.5, 5.0, 0.5):
                     print "**************************************************************"
                     print "DBN scal=",scal
                     clf = DBN([X.shape[1], 24,48, 2],scales=0.5,learn_rates=0.01,learn_rate_decays = 0.95, learn_rate_minimums =0.001,epochs=50,l2_costs = 0.02*0.001, dropouts=0.0,verbose=0)
                     clf.fit(X_train, y_train);
                     scores = cross_val_score(clf,X,y,cv=3,scoring='roc_auc')
                     y_pred = clf.predict(X_test);
                     y_predprob = clf.predict_proba(X_test);
                     prf=precision_recall_fscore_support(y_test, y_pred, average='binary')
                     print ("Accuracy: %0.5f (+/- %0.5f)" % (scores.mean(), scores.std() * 2))
                     print  classification_report(y_test,y_pred)
                     print 'The accuracy is: ', accuracy_score(y_test,y_pred)
                     print 'The log loss is:', log_loss(y_test, y_predprob)
                     print 'The ROC score is:', roc_auc_score(y_test,y_predprob[:,1])

def main():
    data_fn = "/home/ec2-user/Kellis/data/bravo.formatted/dat.all.txt"
    blacklist_fn = "/home/ec2-user/Kellis/data/bravo.formatted/dat.blacklist.txt"
    y_fn = "/home/ec2-user/Kellis/data/bravo.formatted/dat.y.txt"

    data = read_delimited_txt(data_fn, "\t")
    blacklist = read_delimited_txt(blacklist_fn, "\t")
    y = read_delimited_txt(y_fn, "\t")

    # Get names and remove the first element of each row which is the row number
    names = data[0]
    data = data[1:]
    for i in range(len(data)):
        data[i] = data[i][1:]

    y = y[1:]
    for i in range(len(y)):
        y[i] = y[i][-1]
    y = convert_y_binary(y)

    # Normalizes column-wise so all values are between 0 and 1
    data = normalize_0_1(data)

    # Split into training, testing
    xtrain, xtest, ytrain, ytest = train_test_split(data, y, test_size=0.2, random_state=1)

    # Input to 300 node RBM to 2 node output
    dbn = DBN([xtrain.shape[1], 300, 2], learn_rates=5, learn_rate_decays=0.9, epochs=501, verbose=1)
    dbn.fit(xtrain, ytrain)

    preds = dbn.predict(xtest)
    print classification_report(ytest, preds)

    out_fn = "dbn.pickle"
    with open(out_fn, "w") as f:
        pickle.dump(dbn, out_fn)

    return

def runOfflineML(y, X, classifiers, savemodel=False):
    X_train, X_test, y_train, y_test = train_test_split(X, y.astype("int0"), test_size=0.20, random_state=0)
    data = dict(x_train=X_train, x_test=X_test, y_train=y_train, y_test=y_test)
    cls_stats = initClsStats(classifiers)
    for cls_name, cls in classifiers.items():
        cls_stats[cls_name]["n_train"] = data["x_train"].shape[0]
        cls_stats[cls_name]["n_test"] = data["x_test"].shape[0]
        cls_stats[cls_name]["n_features"] = data["x_train"].shape[1]
        tick = time.time()
        if cls_name == "DBN":
            data = dataNormalise(data)
            clf = DBN([data["x_train"].shape[1], 300, 2], learn_rates=0.3, learn_rate_decays=0.9, epochs=10, verbose=1)
            clf.fit(data["x_train"], data["y_train"])
        else:
            clf = classifiers[cls_name].fit(data["x_train"], data["y_train"])
        if savemodel:
            pickle.dump(clf, open(cls_name + ".dat", "w"))
            clf = pickle.load(open(cls_name + ".dat", "r"))
        cls_stats[cls_name]["training_time"] += time.time() - tick
        # check the accuracy on the training set
        tick = time.time()
        predicted = clf.predict(data["x_test"])
        cls_stats[cls_name]["testing_time"] += time.time() - tick
        acc = metrics.accuracy_score(data["y_test"], predicted)
        cls_stats[cls_name]["accuracy"] = acc
        print cls_name, "accuracy is: " + str(acc)
        # auc = metrics.roc_auc_score(data['y_test'], probs[:, 1])
        conf_matrix = metrics.confusion_matrix(data["y_test"], predicted)
        cls_stats[cls_name]["conf_matrix"] = conf_matrix
        # print conf_matrix
        precision, recall, fscore, support = metrics.precision_recall_fscore_support(data["y_test"], predicted)
        cls_stats[cls_name]["precision"] = precision
        cls_stats[cls_name]["recall"] = recall
        cls_stats[cls_name]["fscore"] = fscore
        cls_stats[cls_name]["support"] = support
    return cls_stats

    def fit(self, X, y, X_pretrain=None):
        from nolearn.dbn import DBN

        if y.ndim == 2:
            n_outputs = y.shape[1]
        else:
            y = y[:, np.newaxis]
            n_outputs = 1

        params = dict(self.__dict__)
        from gdbn.activationFunctions import Linear
        params['output_act_funct'] = Linear()

        n_units = params.pop('n_units')
        n_hidden_layers = params.pop('n_hidden_layers')
        if isinstance(n_units, int):
            units = [n_units] * n_hidden_layers
        else:
            units = n_units
        units = [X.shape[1]] + units + [n_outputs]
        self.dbn = DBN(units, **params)
        print X.shape
        self.dbn.fit(X, y, X_pretrain=X_pretrain)

"""
Train the network with 3200 inputs (64x50 values in file)
6 output units (for the different defects)
Lets start with 2 hidden units
"""

# Numbers from example used here
(trainX, testX, trainY, testY) = train_test_split(
    dataset / 255.0, dataset.target.astype("int0"), test_size=0.33)

dbn = DBN(
    # [[numNodes input layer], numNodes hidden layer, numNodes output layer ]
    [trainX.shape[1], 2, 6],
    # Learning rate of algorithm
    learn_rates=0.3,
    # Decay of learn rate
    learn_rate_decays=0.9,
    # Iterations of training data (epochs)
    epochs=10,
    # Verbosity level
    verbose=1)
dbn.fit(trainX,trainY) 

print "trained yo!"

# Evaluate network
#-----------------
preds = dbn.predict(testX)
print classification_report(testY, preds) # Table of accuracies