Python MinMaxScaler.astype方法代码示例

# 需要导入模块: from sklearn.preprocessing import MinMaxScaler [as 别名]
# 或者: from sklearn.preprocessing.MinMaxScaler import astype [as 别名]
def cuml_like(arr1, arr2):
    arr1=MinMaxScaler().fit_transform(arr1.astype(float).reshape(-1,1))
    arr2=MinMaxScaler().fit_transform(arr2.astype(float).reshape(-1,1))
    if arr1.size!=arr2.size:
        raise Exception('must be equal-sized arrays arr1 and arr2')
    new = np.zeros_like(arr1)
    for n in range(new.size):
        new[n] = arr1[:n+1].sum()+arr2[n+1:].sum()
    return new

# 需要导入模块: from sklearn.preprocessing import MinMaxScaler [as 别名]
# 或者: from sklearn.preprocessing.MinMaxScaler import astype [as 别名]
def make_data(n_samples=1000, n_features=1, n_targets=1, informative_prop=1.0,
              noise=0.0, test_prop=0.1, valid_prop=0.3, method='linear'):
    if method == 'linear':
        params = dict(n_features=n_features,
                      n_informative=int(n_features*informative_prop),
                      noise=noise,
                      n_targets=n_targets,
                      n_samples=n_samples,
                      shuffle=False,
                      bias=0.0)
        X, Y = make_regression(**params)
    elif method == 'boston':
        boston = load_boston()
        X = boston.data
        Y = boston.target
    else:
        params = dict(n_samples=n_samples,
                      n_features=n_features)
        X, Y = make_friedman3(n_samples=n_samples, n_features=n_features,
                                 noise=noise)

    X = MinMaxScaler(feature_range=(0.0,1.0)).fit_transform(X)
    X = X.astype(theano.config.floatX)
    Y = MinMaxScaler(feature_range=(0.0,1.0)).fit_transform(Y)
    Y = Y.astype(theano.config.floatX)
    if len(X.shape) > 1:
        n_features = X.shape[1]
    else:
        X = X.reshape(X.shape[0], -1)
        n_features = 1
    if len(Y.shape) > 1:
        n_targets = Y.shape[1]
    else:
        Y = Y.reshape(Y.shape[0], -1)
        n_targets = 1

    X_train, Y_train, X_valid, Y_valid, X_test, Y_test = \
        train_valid_test_split(X, Y,
                               test_prop=valid_prop, valid_prop=valid_prop)
    return dict(
        X_train=theano.shared(X_train),
        Y_train=theano.shared(Y_train),
        X_valid=theano.shared(X_valid),
        Y_valid=theano.shared(Y_valid),
        X_test=theano.shared(X_test),
        Y_test=theano.shared(Y_test),
        num_examples_train=X_train.shape[0],
        num_examples_valid=X_valid.shape[0],
        num_examples_test=X_test.shape[0],
        input_dim=n_features,
        output_dim=n_targets)

# 需要导入模块: from sklearn.preprocessing import MinMaxScaler [as 别名]
# 或者: from sklearn.preprocessing.MinMaxScaler import astype [as 别名]
def build_dataset(X, y, labels, test_prop=0.2, valid_prop=0.2,
                  register='both', test=False):
    if register in ['IDS', 'ADS']:
        sel_ixs = np.in1d(y, np.nonzero(labels[:, 1]==register))
        X = X[sel_ixs]
        y = y[sel_ixs]
    elif register == 'both': # merge IDS and ADS labels per phone
        ix2phone = dict(enumerate(labels[:, 0]))
        phones = sorted(set(ix2phone.values()))
        phone2newix = {p:ix for ix, p in enumerate(phones)}
        y = np.array([phone2newix[ix2phone[i]] for i in y])
    else:
        raise ValueError('invalid option for register: {0}'.format(register))

    oldix2newix = {old_ix:new_ix for new_ix, old_ix in enumerate(np.unique(y))}
    y = np.array([oldix2newix[i] for i in y])

    # X = StandardScaler().fit_transform(X)
    X = MinMaxScaler(feature_range=(0,1)).fit_transform(X)
    X = X.astype(theano.config.floatX)
    y = y.astype('int32')
    nclasses = np.unique(y).shape[0]
    nfeatures = X.shape[1]

    X_train, y_train, X_valid, y_valid, X_test, y_test = \
        train_valid_test_split(X, y,
                               test_prop=test_prop, valid_prop=valid_prop)

    if test:
        X = X_train[100:200]
        y = y_train[100:200]
        X_train = X_train[:100]
        y_train = y_train[:100]
        X_valid = X_valid[:10]
        y_valid = y_valid[:10]
        X_test = X_test[:50]
        y_test = y_test[:50]

    return dict(
        X_train=theano.shared(X_train),
        y_train=theano.shared(y_train),
        X_valid=theano.shared(X_valid),
        y_valid=theano.shared(y_valid),
        X_test=theano.shared(X_test),
        y_test=theano.shared(y_test),
        num_examples_train=X_train.shape[0],
        num_examples_valid=X_valid.shape[0],
        num_examples_test=X_test.shape[0],
        input_dim=nfeatures,
        output_dim=nclasses,
        labels=labels
    )

# 需要导入模块: from sklearn.preprocessing import MinMaxScaler [as 别名]
# 或者: from sklearn.preprocessing.MinMaxScaler import astype [as 别名]
import numpy as np
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.cross_validation import train_test_split
import theanets
import climate

climate.enable_default_logging()

X_orig = np.load('/Users/bzamecnik/Documents/music-processing/music-processing-experiments/c-scale-piano_spectrogram_2048_hamming.npy')
sample_count, feature_count = X_orig.shape
X = MinMaxScaler().fit_transform(X_orig)
X = X.astype(np.float32)

X_train, X_test = train_test_split(X, test_size=0.4, random_state=42)
X_val, X_test = train_test_split(X_test, test_size=0.5, random_state=42)

# (np.maximum(0, 44100/512*np.arange(13)-2)).astype('int')
#blocks = [0, 84, 170, 256, 342, 428, 514, 600, 687, 773, 859, 945, 1031, 1205]
blocks = [0, 48, 98, 148, 198, 248, 298, 348, 398, 448, 498, 548, 598, 700]

def make_labels(blocks):
    label_count = len(blocks) - 1
    labels = np.zeros(blocks[-1])
    for i in range(label_count):
        labels[blocks[i]:blocks[i+1]] = i
    return labels

y = make_labels(blocks)

def score(exp, Xs):
    X_train, X_val, X_test = Xs