Using fit transform on a numpy array

Question

This is my code to transform a lists of data to be fed into a Kmeans model. I want to visualize my clusters in a 2d plot using PCA.

import numpy as np
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

#my data is longer than this but this is a sample :
search_terms = ['computer','usb port', 'phone adaptor']
clicks = [3,2,1]
bounce = [0,0,2]
conversion = [4,1,0]

X = np.array([bounce,conversion,clicks]).T
y = np.array(search_term)

num_clusters = 5

pca = PCA(n_components=2, whiten=True).fit_transform(X)
data2D = pca.transform(X)

km = KMeans(n_clusters=num_clusters, init='k-means++',n_init=10, verbose=1)
km.fit(X_pca)

centers2D = pca.transform(km.cluster_centers_)
plt.scatter( data2D[:,0], data2D[:,1], c=label_color)

This is the error i am getting:

data2D = pca.transform(X)
AttributeError: 'numpy.ndarray' object has no attribute 'transform'

I suppose we cant use pca's fit_transform on a numpy array. What can i do instead?

Thanks

maxymoo · Accepted Answer · 2015-07-01 00:30:14Z

1

It looks like you're calling fit_transform twice, is this really what you want to do?

This seems to work for me:

pca = PCA(n_components=2, whiten=True).fit(X)
data2D = pca.transform(X)

data2D
Out[5]: 
array([[-1.29303192,  0.57277158],
       [ 0.15048072, -1.40618467],
       [ 1.14255114,  0.8334131 ]])

edited Jul 1, 2015 at 0:30

answered Jun 30, 2015 at 23:52

maxymoo

36.7k12 gold badges97 silver badges121 bronze badges

Sign up to request clarification or add additional context in comments.

3 Comments

maxymoo Over a year ago

but now you're calling transform on the PCA? what is this line trying to do? you've already tranformed it to 2D.

jxn Over a year ago

Even if i do fit then transform, i get the same error: pca = PCA(n_components=2, whiten=True).fit(X) then data2D = pca.transform(X) i get this error: data2D = X_pca.transform(X) ` X = X - self.mean_` TypeError: unsupported operand type(s) for -: 'numpy.ndarray' and 'numpy.ndarray'

jxn Over a year ago

apologies after fixing that part the error was caused by not changing km.fit(X_pca) . Thanks for your help, ill be deleting this qn.

Collectives™ on Stack Overflow

Using fit transform on a numpy array

1 Answer 1

3 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

3 Comments

Your Answer

Sign up or log in

Post as a guest

Related