I use Ipython Notebook and when I input the code:
import numpy as np
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
pca.fit(data)
I receive a notice that the kernel has died and has restarted. What is going on?
Also my data is in this format:
array([[ 0.00000000e+00, 3.13000000e+02, 3.10000000e+02, ...,
9.00000000e+00, 6.00000000e+00, 2.00000000e+01],
[ 3.00000000e+00, 2.06900000e+03, 2.06700000e+03, ...,
1.90000000e+01, 7.00000000e+00, 3.20000000e+01],
[ 4.00000000e+00, 2.54200000e+03, 2.54000000e+03, ...,
1.10000000e+01, 1.10000000e+01, 1.10000000e+01],
EDIT:
The data itself is not that large (~3 MB). If it helps, I am using ipython notebook.
I tried a simple 3x3 test matrix as input and same problem, so it's probably not something with the data size either:
data = np.array([[1,2,3],[1,4,6],[2,8,11]])
import numpy as np
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
pca.fit(data)
I tried the sklearn's pca in the terminal with python as well:
>>> from sklearn.decomposition import PCA
>>> pca = PCA()
>>> import numpy as np
>>> X = np.array([[1,2,3],[1,5,7],[2,6,10]])
>>> y = np.array[1,2,3]
>>> y = np.array([1,2,3])
>>> pca.fit(X, y)
And got:
Illegal instruction (core dumped)
It seems that sklearn will not run nicely on a 32 bit machine so when I ran this later on a 64 bit server it worked!!!!!
本文收集自互联网，转载请注明来源。
如有侵权，请联系[email protected] 删除。
我来说两句