How to plot 3D PCA with different colors?

Question

Let's take data following :

 import numpy as np
from sklearn.datasets import load_breast_cancer
import pandas as pd
from sklearn.decomposition import PCA
from sklearn import datasets
from sklearn.preprocessing import StandardScaler

Let's consider data

data = load_breast_cancer()
X = data.data
y = data.target
sc = StandardScaler()

I want to plot 3D plot of PCA with 3 components, however I'm only capable to do it for first two.

My work so far

scaler=StandardScaler()
scaler.fit(X) 
X_scaled=scaler.transform(X)
pca=PCA(n_components=3)
pca.fit(X_scaled) 
X_pca=pca.transform(X_scaled) 
ex_variance=np.var(X_pca,axis=0)
ex_variance_ratio = ex_variance/np.sum(ex_variance)
ex_variance_ratio


Xax=X_pca[:,0]
Yax=X_pca[:,1]
cdict={0:'red',1:'green'}
labl={0:'Malignant',1:'Benign'}
marker={0:'*',1:'o'}
alpha={0:.3, 1:.5}
fig,ax=plt.subplots(figsize=(7,5))
fig.patch.set_facecolor('white')
for l in np.unique(y):
 ix=np.where(y==l)
 ax.scatter(Xax[ix],Yax[ix],c=cdict[l],s=40,
           label=labl[l],marker=marker[l],alpha=alpha[l])
# for loop ends
plt.xlabel("First Principal Component",fontsize=14)
plt.ylabel("Second Principal Component",fontsize=14)
plt.legend()
plt.show()

And in output we get :

Do you know how to perform this for third principial component ? For sure it should be 3D but I'm not sure how to do it...

user_10733051 · Answer

It is quite simple actually-

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from mpl_toolkits.mplot3d import Axes3D
from sklearn.datasets import load_breast_cancer
from sklearn.decomposition import PCA
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
# %matplotlib notebook

data = load_breast_cancer()
X = data.data
y = data.target
sc = StandardScaler()

scaler = StandardScaler()
scaler.fit(X) 
X_scaled = scaler.transform(X)

pca = PCA(n_components=3)
pca.fit(X_scaled) 
X_pca = pca.transform(X_scaled) 

ex_variance=np.var(X_pca,axis=0)
ex_variance_ratio = ex_variance/np.sum(ex_variance)
ex_variance_ratio


Xax = X_pca[:,0]
Yax = X_pca[:,1]
Zax = X_pca[:,2]

cdict = {0:'red',1:'green'}
labl = {0:'Malignant',1:'Benign'}
marker = {0:'*',1:'o'}
alpha = {0:.3, 1:.5}

fig = plt.figure(figsize=(7,5))
ax = fig.add_subplot(111, projection='3d')

fig.patch.set_facecolor('white')
for l in np.unique(y):
 ix=np.where(y==l)
 ax.scatter(Xax[ix], Yax[ix], Zax[ix], c=cdict[l], s=40,
           label=labl[l], marker=marker[l], alpha=alpha[l])
# for loop ends
ax.set_xlabel("First Principal Component", fontsize=14)
ax.set_ylabel("Second Principal Component", fontsize=14)
ax.set_zlabel("Third Principal Component", fontsize=14)

ax.legend()
plt.show()

Is this what you are after?

How to plot 3D PCA with different colors?

1 Answers