Search code examples
pythonnumpypca

Unable to run PCA on a dataset


I am trying to run PCA on the loan dataset - find test here and train.

The code snippet is as follows,

from sklearn.decomposition import PCA
pca = PCA(n_components = 2)
X_train = pca.fit_transform(X_train)
X_test = pca.transform(X_test)
explained_variance = pca.explained_variance_ratio_

However, on running the same, I get the following error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-102-829bdba63de3> in <module>
      3 pca = PCA(n_components = 2)
      4 X_train = pca.fit_transform(X_train)
----> 5 X_test = pca.transform(X_test)
      6 explained_variance = pca.explained_variance_ratio_

C:\Anaconda\lib\site-packages\sklearn\decomposition\base.py in transform(self, X)
    127         X = check_array(X)
    128         if self.mean_ is not None:
--> 129             X = X - self.mean_
    130         X_transformed = np.dot(X, self.components_.T)
    131         if self.whiten:

ValueError: operands could not be broadcast together with shapes (185,112) (2,) 

Can someone help me on this? I don't where I am going wrong.


Solution

  • Doing a PCA only require :

    import numpy as np
    from sklearn.decomposition import PCA
    X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
    pca = PCA(n_components=2)
    pca.fit(X) 
    

    Maybe you should drop labels on train, join test and train then do PCA.