Pandas please!

I have a function for creating a confusion matrix:

my features have 6 other feature sets in it

```````

def make_confusion(features, labels):

from sklearn.metrics import confusion_matrix

km = KMeans(n_clusters=10)

km.fit(features)

cluster_labels = km.labels_

confusion = confusion_matrix(cluster_labels, labels)

return confusion

```````

I also have a rearrange function for one of the sets!

I need to make a correctly rearranged confusion matrix for my other 5 sets.

ji, ki = scipy.optimize.linear_sum_assignment(conf, maximize=True)

return conf[:, ki]

and a

I also need to use the rearranged confusion matrixes and calculate the fraction of data points that were assigned to the correct cluster center, and make a plot showing how this accuracy measure performs on the different feature sets.