我是这个领域的新手，所以我需要你的帮助。我正在处理mnist数据集。我使用了http://g.sweyla.com/blog/2012/mnist-numpy/中的代码，但将“images”更改为二维数组，以便每个图像都是一个特征向量。然后我对数据运行了PCA，接着运行了SVM并检查了得分。一切似乎都正常，但我收到了以下警告，不确定原因。
感谢您的帮助！
"DataConversionWarning: A column-vector y was passed when a 1d array was expected.\
Please change the shape of y to (n_samples, ), for example using ravel()."
我尝试了几个方法，但似乎无法消除此警告。有什么建议吗？这是完整代码（忽略缺少的缩进，看起来好像复制代码时出了点问题）：
import os, struct
from array import array as pyarray
from numpy import append, array, int8, uint8, zeros, arange
from sklearn import svm, decomposition
#from pylab import *
#from matplotlib import pyplot as plt
def load_mnist(dataset="training", digits=arange(10), path="."):
"""
Loads MNIST files into 3D numpy arrays
Adapted from: http://abel.ee.ucla.edu/cvxopt/_downloads/mnist.py
"""
if dataset == "training":
fname_img = os.path.join(path, 'train-images.idx3-ubyte')
fname_lbl = os.path.join(path, 'train-labels.idx1-ubyte')
elif dataset == "testing":
fname_img = os.path.join(path, 't10k-images.idx3-ubyte')
fname_lbl = os.path.join(path, 't10k-labels.idx1-ubyte')
else:
raise ValueError("dataset must be 'testing' or 'training'")
flbl = open(fname_lbl, 'rb')
magic_nr, size = struct.unpack(">II", flbl.read(8))
lbl = pyarray("b", flbl.read())
flbl.close()
fimg = open(fname_img, 'rb')
magic_nr, size, rows, cols = struct.unpack(">IIII", fimg.read(16))
img = pyarray("B", fimg.read())
fimg.close()
ind = [ k for k in range(size) if lbl[k] in digits ]
N = len(ind)
images = zeros((N, rows*cols), dtype=uint8)
labels = zeros((N, 1), dtype=int8)
for i in range(len(ind)):
images[i] = array(img[ ind[i]*rows*cols : (ind[i]+1)*rows*cols ])
labels[i] = lbl[ind[i]]
return images, labels
if __name__ == "__main__":
images, labels = load_mnist('training', arange(10),"path...")
pca = decomposition.PCA()
pca.fit(images)
pca.n_components = 200
images_reduced = pca.fit_transform(images)
lin_classifier = svm.LinearSVC()
lin_classifier.fit(images_reduced, labels)
images2, labels2 = load_mnist('testing', arange(10),"path...")
images2_reduced = pca.transform(images2)
score = lin_classifier.score(images2_reduced,labels2)
print score
感谢您的帮助！