Python preprocessing.normalize函数代码示例

  def __init__(self, hps, example_list, dqn_batch_size, use_state_prime = False, max_art_oovs = 0):
    """
      Args:
       hps: seq2seq model parameters
       example_list: list of experiences
       dqn_batch_size: DDQN batch size
       use_state_prime: whether to use the next decoder state to make the batch or the current one
       max_art_oovs: number of OOV tokens in current batch

      Properties:
        _x: The input to DDQN model for training, this is basically the decoder output (dqn_batch_size, dqn_input_feature_len)
        _y: The Q-estimation (dqn_batch_size, vocab_size)
        _y_extended: The Q-estimation (dqn_batch_size, vocab_size + max_art_oovs)
    """
    self._x = np.zeros((dqn_batch_size, hps.dqn_input_feature_len))
    self._y = np.zeros((dqn_batch_size, hps.vocab_size))
    self._y_extended = np.zeros((dqn_batch_size, hps.vocab_size + max_art_oovs))
    for i,e in enumerate(example_list):
      if use_state_prime:
        self._x[i,:]=e.state_prime
      else:
        self._x[i,:]=e.state
        self._y[i,:]=normalize([e.q_value[0:hps.vocab_size]], axis=1, norm='l1')
      if max_art_oovs == 0:
        self._y_extended[i,:] = normalize([e.q_value[0:hps.vocab_size]], axis=1, norm='l1')
      else:
        self._y_extended[i,:] = e.q_value

def split_and_build_class(X, y):
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
    print X_train.shape
    print X_test.shape

    # Normalize the input data.
    imp = preprocessing.Imputer(missing_values='NaN', strategy='mean', axis=0)
    fixed_X_train = X_train[:, 1:]
    imp.fit(fixed_X_train)
    fixed_X_train = imp.transform(fixed_X_train)
    preprocessing.normalize(fixed_X_train, copy=False)
    X_train[:, 1:] = fixed_X_train

    fixed_X_test = X_test[:, 1:]
    imp.fit(fixed_X_test)
    fixed_X_test = imp.transform(fixed_X_test)
    preprocessing.normalize(fixed_X_test, copy=False)
    X_test[:, 1:] = fixed_X_test

    train_data = read_dataset.microData()
    train_data.get_data(X_train)
    y_train = train_data.set_output(y_train)
    test_data = read_dataset.microData()
    test_data.get_data(X_test)
    y_test = test_data.set_output(y_test)

    return [X_train, X_test, y_train, y_test, train_data, test_data]

def func(A, B):  # comparematrices(A,B):
    colA = A.shape[1]
    colB = B.shape[1]

    # method 1 - n is small dim, m is larger, matnew is new comparison matrix
    if colA == colB and colA != 1:
        Aprime = normalize(A, axis=1, norm='l2')
        Bprime = normalize(B, axis=1, norm='l2')
        if colA == 1:
            dist = np.linalg.norm(Aprime - Bprime)  # L2 norm (vectors)
        else:
            dist = np.linalg.norm(Aprime - Bprime, 2)  # Frobenius norm (matrices)
    else:
        if colA < colB:
            n = colA
            m = colB
            big = B
            small = A
        else:
            n = colB
            m = colA
            big = A
            small = B
        matnew = np.identity(m)
        matnew[0:n, 0:n] = small
        bigprime = normalize(big, axis=1, norm='l2')
        matnewprime = normalize(matnew, axis=1, norm='l2')
    dist = np.linalg.norm(matnewprime - bigprime, 2)

    print dist

 def normalize(self):
     """
     impute
     """
     print('Normalization')
     self.tr = normalize(self.tr)
     self.te = normalize(self.te)

def read_dataset(train_size, scale=False, normalize=False):
    logging.info('fetching the dataset')
    #
    d = sklearn.datasets.load_diabetes() # 糖尿病
    #d = sklearn.datasets.load_boston() # ボストン住宅価格
    #
    data = d['data'].astype(np.float32)
    target = d['target'].astype(np.float32).reshape(len(d['target']), 1)
    #"Chainerのmnist.pyだと下記ののような書き方になっているが、ミニバッチの数が2以上だと動かない"らしい 
    #target = diabetes['target'].astype(np.float32) 
    # 本来訓練データで標準化・正規化して、そのパラメータをテストデータに適用すべき
    if normalize and scale:
        raise Exception('both normalize and scale can not be True')
    if normalize:
        data = preprocessing.normalize(data)
        target = preprocessing.normalize(target)
    if scale:
        data = preprocessing.scale(data)
        target = preprocessing.scale(target)
    # 分割
    x_train, x_test = np.split(data, [train_size])
    y_train, y_test = np.split(target, [train_size])
    assert len(x_train)==len(y_train)
    assert len(x_test)==len(y_test)
    return  ((x_train, y_train), (x_test, y_test), 
        {"SHAPE_TRAIN_X":x_train.shape,
          "SHAPE_TRAIN_Y":y_train.shape,
          "SHAPE_TEST_X":x_test.shape,
          "SHAPE_TEST_Y":y_test.shape,
          })

def remove_outliers(image,mask):
#taking the mask part to image to check the presence of bee
	im = cv2.bitwise_and(image,image,mask=mask);
	ldp_image,_,_ = ldp.ldp(im);
	test_Y = ldp_image.reshape((ldp_image.shape[0] * ldp_image.shape[1], ldp_image.shape[2]));
	test_rgb = im.reshape((im.shape[0] * im.shape[1], im.shape[2]));
	test = np.concatenate((test_Y,test_rgb),axis=1);
	mask_not = cv2.bitwise_not(mask);
	ret1, mask_not = cv2.threshold (mask_not,np.mean(mask_not), 255, cv2.THRESH_BINARY);		
	im = cv2.bitwise_and(image,image,mask=mask_not);
	ldp_image,_,_ = ldp.ldp(im);	
	data_ldp = ldp_image.reshape((ldp_image.shape[0] * ldp_image.shape[1], ldp_image.shape[2]));
	data_rgb = im.reshape((im.shape[0] * im.shape[1], im.shape[2]));
	data = np.concatenate((data_rgb,data_ldp),axis=1);
	data = data[np.any(data!=0,axis=1)];	
	print data.shape;		
	data = data.astype('float64');		
	data = preprocessing.normalize(data,axis=0);
	ss = StandardScaler();	
	data = ss.fit_transform(data);
	clf = svm.OneClassSVM(nu=0.8, kernel="rbf", gamma=0.1)
	clf.fit(data);
	test = test.astype('float64');		
	test = preprocessing.normalize(test,axis=0);	
	print test.shape;	
	test = ss.fit_transform(test);
	test = clf.predict(test);
	test = test.reshape((image.shape[0] , image.shape[1]));
	test[test==-1] = 0;
	test[test==1] = 255;
	test = test.astype('uint8');
	im = cv2.bitwise_and(image,image,mask=test);	
	im = cv2.bitwise_and(im,im,mask=mask);	
	#print test[:,0],test[:,1];	
	return(im,test);  

def normaliser(x, option):
  # normalize by the norm
    if option == 'norm':
       # print 'normalize by the norm or the row'
        from sklearn.preprocessing import normalize
        x_norma = normalize(x, norm='l2')

#   normalize by the sum of the row, ( normalized matrix sum to 1 )
    elif option == 'sum': # normalize sum to 1:
        #print('normalize by the sum of the row')
        from sklearn.preprocessing import normalize
        x_norma = normalize(x, norm='l1')

#   normalize each row by z-score : (x-mean)/std
    elif option == 'zscore':
        from scipy import stats
        x_norma = stats.zscore(x, axis=1)
        # set the nan to 0
        x_norma[np.isnan(x_norma)] = 0

    elif option == 'none':
       # print ('no normalization')
        x_norma = x

    return x_norma

def getData_NEC():
    reader = JobDBCorpus()
    data = reader.read_sequence_list(target='TODO')
    np.seterr(all='ignore')

    train, test = reader.train_test_data(test_size=0.2)

    print("Reading chunks...")
    chunks_train = ChunkSet(dataset=train)
    chunks_test = ChunkSet(dataset=test)

    print("Building features...")
    idf = featNEC.IDFeatures(dataset=train, chunkset=chunks_train)
    idf.build_features()

    ###############################################################################
    print("Standarizing dataset...")
    X_train, Y_train = getStandart(chunks_train, idf)
    X_test, Y_test = getStandart(chunks_test, idf)

    # sparse representation and normalize
    X_train = sparse.csr_matrix(X_train)
    X_train = normalize(X_train, copy=False)

    X_test = sparse.csr_matrix(X_test)
    X_test = normalize(X_test, copy=False)

    return X_train, Y_train, X_test, Y_test, chunks_train

def rwr(transition,PT,r=0.7):
    """

    :param transition: Get the spare Transition matrix
    :param PT: Intialization Vector
    :param r: restart probability
    :return: Numpy Matrix of predicted scores
    """
    #Stop criteria
    stop = 1e-07
    PO = PT
    Tr  =  transition

    while True:

        PX = (1-r)* Tr.T * PT + (r * PO)
        delta =  spnorm(PX) - spnorm(PT)

        if delta < stop :
            break

        PT = PX
    #fMat = normalize(PT, norm='l1', axis=0)
    OM = PT[0:5080]
    OM  = normalize(OM, norm='l1', axis=0)
    PP = PT[5080:15078]
    PP = normalize(PP, norm='l1', axis=0)
    CP = PT[15078:16904]
    CP  = normalize(CP, norm='l1', axis=0)
    PAT = PT[16904:19435]
    PAT  = normalize(PAT, norm='l1', axis=0)
    P = np.concatenate((OM,PP,CP,PAT),axis=0)

    return P

def SVM_vary_train(train_images, train_labels, test_images, test_labels, kernel_type, tune1, tune2, tune3, train_amm):
    # reshape the training/testing data into a classifiable form
    train_data_mat = np.reshape(train_images, (train_images.shape[0]*train_images.shape[1],train_images.shape[3]))
    test_data_mat = np.reshape(test_images, (test_images.shape[0]*test_images.shape[1],test_images.shape[3]))

    train_data_mat = 1.0*np.array(np.mat(train_data_mat).transpose())
    test_data_mat = 1.0*np.array(np.mat(test_data_mat).transpose())

    # normalize the data
    train_data_mat = preprocessing.normalize(train_data_mat, norm='l2')
    test_data_mat = preprocessing.normalize(test_data_mat, norm='l2')
     
    
    if kernel_type is "linear": 
        classif_1vr = svm.SVC(kernel=kernel_type, C=tune1)
    elif kernel_type is "rbf": 
        classif_1vr = svm.SVC(kernel=kernel_type, gamma=tune1)
    elif kernel_type is "sigmoid":
        classif_1vr = svm.SVC(kernel=kernel_type, gamma=tune1, coef0=tune2)
    elif kernel_type is "poly":
        classif_1vr = svm.SVC(kernel=kernel_type, gamma=tune1, coef0=tune2, degree=tune3)
    
    # fit the SVM to the training set
    classif_1vr.fit(train_data_mat[0:train_amm,:], train_labels[0][0:train_amm])
    
    targets = test_labels[0]
    
    # make prediction on the test data set
    predict = classif_1vr.predict(test_data_mat)
 
    # calculate the accuracy 
    acc = calc_acc(targets, predict) 

    return "kernel=" + str(kernel_type)  + ", tune1=" + str(tune1)  + ", tune2=" + str(tune2) + ", tune3=" + str(tune3) + ", train_amm=" + str(train_amm) + ", acc: " + str(acc) + "\n"

def classify(data_trn,lbl_trn,data_vld,lbl_vld,data_tst,lbl_tst):

	data_trn = normalize(data_trn,copy=False)
	data_vld = normalize(data_vld,copy=False)
	data_tst = normalize(data_tst,copy=False)

	# accuracy metric
	metric_obj = mean_squared_error
	'''
	Train our model to predict labels for the dataset #1
	'''
	parameters = {'svr__gamma': 1.5, 'svr__probability': False, 'svr__epsilon': 0.4, 'svr__C': 1, 'svr__kernel': 'rbf'}
	cls = Pipeline([
			#('feature_selection',LinearSVC()),
			('svr', SVR())
			])
	cls.set_params(**parameters)

	cls.fit(data_trn, lbl_trn)


        pred_vld = cls.predict(data_vld)
        pred_tst = cls.predict(data_tst)

        print ("Score for vld: %.6f" % (metric_obj(lbl_vld, pred_vld),))
        print ("Score for tst: %.6f" % (metric_obj(lbl_tst, pred_tst),))

	return pred_vld,pred_tst

def PCA_SVM(train_images, train_labels, test_images, test_labels, kernel_type, do_PCA, comps):
    # reshape the training/testing data into a classifiable form
    train_data_mat = np.reshape(train_images, (train_images.shape[0]*train_images.shape[1],train_images.shape[3]))
    test_data_mat = np.reshape(test_images, (test_images.shape[0]*test_images.shape[1],test_images.shape[3]))

    train_data_mat = np.array(np.mat(train_data_mat).transpose())
    test_data_mat = np.array(np.mat(test_data_mat).transpose())

    # normalize the data
    train_data_mat = preprocessing.normalize(train_data_mat, norm='l2')
    test_data_mat = preprocessing.normalize(test_data_mat, norm='l2')
    
    # do PCA if necessary
    if do_PCA:
        # learn the covariance 
        pca = PCA(n_components=comps, whiten=True)
        pca.fit(train_data_mat)
    
        # use pca to reduce dimensionality of training data
        train_data_mat = pca.transform(train_data_mat)
        test_data_mat = pca.transform(test_data_mat)
    
    # fit svm to pca-reduced
    classif_1vr = svm.SVC(kernel=kernel_type)
    classif_1vr.fit(train_data_mat, train_labels[0])

    targets = test_labels[0]
    
    # make prediction on the test data set
    predict = classif_1vr.predict(test_data_mat)
 
    # calculate the accuracy 
    acc = calc_acc(targets, predict) 

    return "PCA=" + str(do_PCA) + ", num_comps= " + str(comps) + ", kernel=" + str(kernel_type)  + ", acc: " + str(acc) + "\n"

def get_vector_sp(model, x_data, x_test):
    tmp_x = x_data[:, x_data.shape[1]-16:x_data.shape[1]-1]
    tmp_x = tmp_x.reshape(tmp_x.shape[0], tmp_x.shape[1])
    tmp_x = tmp_x/tmp_x[:,0].reshape(tmp_x.shape[0],1)
    #tmp_x[:,1:] = tmp_x[:,1:] / tmp_x[:,0:tmp_x.shape[1]-1]
    tmp_x = preprocessing.normalize(tmp_x, norm='l2')
    preds = model.predict_proba(tmp_x.reshape(x_data.shape[0],15,1))


    test_x = x_test[:, x_test.shape[1]-16:x_test.shape[1]-1]
    test_x = test_x.reshape(test_x.shape[0], test_x.shape[1])
    test_x = test_x/test_x[0][0]
    test_x = preprocessing.normalize(test_x, norm='l2')
    pred_test = model.predict_proba(test_x.reshape(test_x.shape[0],15,1))
    x_result = numpy.hstack((x_data.reshape(x_data.shape[0], x_data.shape[1]), preds))
    x_result_test = numpy.hstack((x_test.reshape(x_test.shape[0], x_test.shape[1]), pred_test))
    test_bdate = x_test[0][1]
    tmp_list = []
    tmp_vec = x_result_test[0][x_result_test.shape[1]-20:]
    i  = 0
    for m in x_result:
        i = i + 1
        dist = numpy.sqrt(numpy.sum(numpy.square(m[m.shape[0]-20:]- pred_test[0])))
        
        tmp_list.append((m[1], dist))
    sort_list = sorted(tmp_list, key = lambda x:x[1], reverse =False)
    return sort_list, test_bdate

def getData_NEC(test=0.2, val=0.2, mode='by_sent',target='TODO'):
    print("Reading data...")
    train,test,val = getData(test=test, val=val, mode=mode,target=target)

    print("Reading chunks...")
    chunks_train = ChunkSet(dataset=train)
    chunks_test = ChunkSet(dataset=test)

    print("Building features...")
    idf = featNEC.IDFeatures(dataset = train, chunkset = chunks_train)
    idf.build_features()

    ###############################################################################
    print("Standarizing dataset...")
    X_train,Y_train = getStandart(chunks_train, idf)
    X_test,Y_test = getStandart(chunks_test, idf)

    # sparse representation and normalize
    X_train = sparse.csr_matrix(X_train)
    X_train = normalize(X_train, copy = False)

    X_test = sparse.csr_matrix(X_test)
    X_test = normalize(X_test, copy = False)

    return X_train,Y_train,X_test,Y_test, chunks_train

def rw_overlap_kernel(C1, C2):
    
    #l = 1.0/np.exp(1.0)
    l = 0.5    
    
    
    k = 0
    c = 0
    
    # reshape rows into kernel matrices
    M1 = np.reshape(C1, (90, 90))
    M2 = np.reshape(C2, (90, 90))
    
    # normalise so rows sum to 1
    M1_norm = normalize(M1, axis=1, norm='l1')
    M2_norm = normalize(M2, axis=1, norm='l1')
    
    for i in range(1, 101) :
        
        M1_exp = np.linalg.matrix_power(M1_norm, i)
        M2_exp = np.linalg.matrix_power(M2_norm, i)
        
        #overlap = np.sum(np.minimum(M1_exp, M2_exp))
        overlap = np.sum(np.sqrt(np.multiply(M1_exp, M2_exp)))
    
        #k = k + ((np.exp(-i) ) * overlap)
        #c = c + ((np.exp(-i)) * 90)
        k = k + ((l ** i) * overlap)
        c = c + ((l ** i) * 90)
    
    return  k/c