In [ ]:

    

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
import datetime

from mpl_toolkits.mplot3d import Axes3D
from plyfile import PlyData, PlyElement
from sklearn.decomposition import PCA


    

In [4]:

    

# Every 100 data samples, we save
# 1. If things run too
# slow, try increasing this number. If things run too fast,
# try decreasing it... =)
reduce_factor = 100


# Look pretty...
matplotlib.style.use('ggplot')


# Load up the scanned armadillo
plyfile = PlyData.read('Datasets/stanford_armadillo.ply')
armadillo = pd.DataFrame({
    'x':plyfile['vertex']['z'][::reduce_factor],
    'y':plyfile['vertex']['x'][::reduce_factor],
    'z':plyfile['vertex']['y'][::reduce_factor]
})


    

In [29]:

    

# Render the Original Armadillo
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.set_title('Armadillo 3D')
ax.set_xlabel('X')
ax.set_ylabel('Y')
ax.set_zlabel('Z')
ax.scatter(armadillo.x, armadillo.y, armadillo.z, c='orange', marker='.', alpha=0.75)

plt.show()


    

In [33]:

    

fpca = PCA(n_components= 2, svd_solver = 'full')


    

In [54]:

    

fpca.fit(armadillo)


    

    
Out[54]:





PCA(copy=True, iterated_power='auto', n_components=2, random_state=None,
  svd_solver='full', tol=0.0, whiten=False)

In [62]:

    

def do_PCA(armadillo):
      
    
      # TODO: Write code to import the libraries required for PCA.
      # Then, train your PCA on the armadillo dataframe. Finally,
      # drop one dimension (reduce it down to 2D) and project the
      # armadillo down to the 2D principal component feature space.
    fpca = PCA(n_components= 2, svd_solver = 'full')
    fpca.fit(armadillo)  
    fullproject = fpca.transform(armadillo)

      # NOTE: Be sure to RETURN your projected armadillo! 
      # (This projection is actually stored in a NumPy NDArray and
      # not a Pandas dataframe, which is something Pandas does for
      # you automatically. =)
    return fullproject

# Time the execution of PCA 5000x
# PCA is ran 5000x in order to help decrease the potential of rogue
# processes altering the speed of execution.
t1 = datetime.datetime.now()
for i in range(5000): 
    pca = do_PCA(armadillo)
time_delta = datetime.datetime.now() - t1
print(time_delta)

# Render the newly transformed PCA armadillo!
if not pca is None:
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.set_title('PCA, build time: ' + str(time_delta))
    ax.scatter(pca[:,0], pca[:,1], c='blue', marker='.', alpha=0.75)
plt.show()


    

    




0:00:03.577542

In [64]:

    

def do_RandomizedPCA(armadillo):
    rpca = PCA(n_components = 2, svd_solver = 'randomized', random_state=1)
  # TODO: Write code to import the libraries required for
  # RandomizedPCA. Then, train your RandomizedPCA on the armadillo
  # dataframe. Finally, drop one dimension (reduce it down to 2D)
  # and project the armadillo down to the 2D principal component
  # feature space.
    rpca.fit(armadillo)
   

  # NOTE: Be sure to RETURN your projected armadillo! 
  # (This projection is actually stored in a NumPy NDArray and
  # not a Pandas dataframe, which is something Pandas does for
  # you automatically. =)
  #
  # NOTE: SKLearn deprecated the RandomizedPCA method, but still
  # has instructions on how to use randomized (truncated) method
  # for the SVD solver. To find out how to use it, set `svd_solver`
  # to 'randomized' and check out the full docs here
  #
  # http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html
  #
  # Deprecated Method: http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.RandomizedPCA.html
    rproject = rpca.transform(armadillo)
    return rproject



# Time the execution of rPCA 5000x
t1 = datetime.datetime.now()
for i in range(5000): rpca = do_RandomizedPCA(armadillo)
time_delta = datetime.datetime.now() - t1
print(time_delta)

# Render the newly transformed RandomizedPCA armadillo!
if not rpca is None:
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.set_title('RandomizedPCA, build time: ' + str(time_delta))
    ax.scatter(rpca[:,0], rpca[:,1], c='red', marker='.', alpha=0.75)


plt.show()


    

    




0:00:10.383377

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [46]:

    

print(__doc__)


# Code source: Gaël Varoquaux
# License: BSD 3 clause

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D


from sklearn import decomposition
from sklearn import datasets

np.random.seed(5)

centers = [[1, 1], [-1, -1], [1, -1]]
iris = datasets.load_iris()


    

    




Automatically created module for IPython interactive environment

In [47]:

    

X = iris.data
y = iris.target


    

In [53]:

    

plyfile.data


    

    




---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-53-cf1d4cdc7691> in <module>()
----> 1 plyfile.data

AttributeError: 'PlyData' object has no attribute 'data'

In [52]:

    

iris.data


    

    
Out[52]:





array([[ 5.1,  3.5,  1.4,  0.2],
       [ 4.9,  3. ,  1.4,  0.2],
       [ 4.7,  3.2,  1.3,  0.2],
       [ 4.6,  3.1,  1.5,  0.2],
       [ 5. ,  3.6,  1.4,  0.2],
       [ 5.4,  3.9,  1.7,  0.4],
       [ 4.6,  3.4,  1.4,  0.3],
       [ 5. ,  3.4,  1.5,  0.2],
       [ 4.4,  2.9,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5.4,  3.7,  1.5,  0.2],
       [ 4.8,  3.4,  1.6,  0.2],
       [ 4.8,  3. ,  1.4,  0.1],
       [ 4.3,  3. ,  1.1,  0.1],
       [ 5.8,  4. ,  1.2,  0.2],
       [ 5.7,  4.4,  1.5,  0.4],
       [ 5.4,  3.9,  1.3,  0.4],
       [ 5.1,  3.5,  1.4,  0.3],
       [ 5.7,  3.8,  1.7,  0.3],
       [ 5.1,  3.8,  1.5,  0.3],
       [ 5.4,  3.4,  1.7,  0.2],
       [ 5.1,  3.7,  1.5,  0.4],
       [ 4.6,  3.6,  1. ,  0.2],
       [ 5.1,  3.3,  1.7,  0.5],
       [ 4.8,  3.4,  1.9,  0.2],
       [ 5. ,  3. ,  1.6,  0.2],
       [ 5. ,  3.4,  1.6,  0.4],
       [ 5.2,  3.5,  1.5,  0.2],
       [ 5.2,  3.4,  1.4,  0.2],
       [ 4.7,  3.2,  1.6,  0.2],
       [ 4.8,  3.1,  1.6,  0.2],
       [ 5.4,  3.4,  1.5,  0.4],
       [ 5.2,  4.1,  1.5,  0.1],
       [ 5.5,  4.2,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5. ,  3.2,  1.2,  0.2],
       [ 5.5,  3.5,  1.3,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 4.4,  3. ,  1.3,  0.2],
       [ 5.1,  3.4,  1.5,  0.2],
       [ 5. ,  3.5,  1.3,  0.3],
       [ 4.5,  2.3,  1.3,  0.3],
       [ 4.4,  3.2,  1.3,  0.2],
       [ 5. ,  3.5,  1.6,  0.6],
       [ 5.1,  3.8,  1.9,  0.4],
       [ 4.8,  3. ,  1.4,  0.3],
       [ 5.1,  3.8,  1.6,  0.2],
       [ 4.6,  3.2,  1.4,  0.2],
       [ 5.3,  3.7,  1.5,  0.2],
       [ 5. ,  3.3,  1.4,  0.2],
       [ 7. ,  3.2,  4.7,  1.4],
       [ 6.4,  3.2,  4.5,  1.5],
       [ 6.9,  3.1,  4.9,  1.5],
       [ 5.5,  2.3,  4. ,  1.3],
       [ 6.5,  2.8,  4.6,  1.5],
       [ 5.7,  2.8,  4.5,  1.3],
       [ 6.3,  3.3,  4.7,  1.6],
       [ 4.9,  2.4,  3.3,  1. ],
       [ 6.6,  2.9,  4.6,  1.3],
       [ 5.2,  2.7,  3.9,  1.4],
       [ 5. ,  2. ,  3.5,  1. ],
       [ 5.9,  3. ,  4.2,  1.5],
       [ 6. ,  2.2,  4. ,  1. ],
       [ 6.1,  2.9,  4.7,  1.4],
       [ 5.6,  2.9,  3.6,  1.3],
       [ 6.7,  3.1,  4.4,  1.4],
       [ 5.6,  3. ,  4.5,  1.5],
       [ 5.8,  2.7,  4.1,  1. ],
       [ 6.2,  2.2,  4.5,  1.5],
       [ 5.6,  2.5,  3.9,  1.1],
       [ 5.9,  3.2,  4.8,  1.8],
       [ 6.1,  2.8,  4. ,  1.3],
       [ 6.3,  2.5,  4.9,  1.5],
       [ 6.1,  2.8,  4.7,  1.2],
       [ 6.4,  2.9,  4.3,  1.3],
       [ 6.6,  3. ,  4.4,  1.4],
       [ 6.8,  2.8,  4.8,  1.4],
       [ 6.7,  3. ,  5. ,  1.7],
       [ 6. ,  2.9,  4.5,  1.5],
       [ 5.7,  2.6,  3.5,  1. ],
       [ 5.5,  2.4,  3.8,  1.1],
       [ 5.5,  2.4,  3.7,  1. ],
       [ 5.8,  2.7,  3.9,  1.2],
       [ 6. ,  2.7,  5.1,  1.6],
       [ 5.4,  3. ,  4.5,  1.5],
       [ 6. ,  3.4,  4.5,  1.6],
       [ 6.7,  3.1,  4.7,  1.5],
       [ 6.3,  2.3,  4.4,  1.3],
       [ 5.6,  3. ,  4.1,  1.3],
       [ 5.5,  2.5,  4. ,  1.3],
       [ 5.5,  2.6,  4.4,  1.2],
       [ 6.1,  3. ,  4.6,  1.4],
       [ 5.8,  2.6,  4. ,  1.2],
       [ 5. ,  2.3,  3.3,  1. ],
       [ 5.6,  2.7,  4.2,  1.3],
       [ 5.7,  3. ,  4.2,  1.2],
       [ 5.7,  2.9,  4.2,  1.3],
       [ 6.2,  2.9,  4.3,  1.3],
       [ 5.1,  2.5,  3. ,  1.1],
       [ 5.7,  2.8,  4.1,  1.3],
       [ 6.3,  3.3,  6. ,  2.5],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 7.1,  3. ,  5.9,  2.1],
       [ 6.3,  2.9,  5.6,  1.8],
       [ 6.5,  3. ,  5.8,  2.2],
       [ 7.6,  3. ,  6.6,  2.1],
       [ 4.9,  2.5,  4.5,  1.7],
       [ 7.3,  2.9,  6.3,  1.8],
       [ 6.7,  2.5,  5.8,  1.8],
       [ 7.2,  3.6,  6.1,  2.5],
       [ 6.5,  3.2,  5.1,  2. ],
       [ 6.4,  2.7,  5.3,  1.9],
       [ 6.8,  3. ,  5.5,  2.1],
       [ 5.7,  2.5,  5. ,  2. ],
       [ 5.8,  2.8,  5.1,  2.4],
       [ 6.4,  3.2,  5.3,  2.3],
       [ 6.5,  3. ,  5.5,  1.8],
       [ 7.7,  3.8,  6.7,  2.2],
       [ 7.7,  2.6,  6.9,  2.3],
       [ 6. ,  2.2,  5. ,  1.5],
       [ 6.9,  3.2,  5.7,  2.3],
       [ 5.6,  2.8,  4.9,  2. ],
       [ 7.7,  2.8,  6.7,  2. ],
       [ 6.3,  2.7,  4.9,  1.8],
       [ 6.7,  3.3,  5.7,  2.1],
       [ 7.2,  3.2,  6. ,  1.8],
       [ 6.2,  2.8,  4.8,  1.8],
       [ 6.1,  3. ,  4.9,  1.8],
       [ 6.4,  2.8,  5.6,  2.1],
       [ 7.2,  3. ,  5.8,  1.6],
       [ 7.4,  2.8,  6.1,  1.9],
       [ 7.9,  3.8,  6.4,  2. ],
       [ 6.4,  2.8,  5.6,  2.2],
       [ 6.3,  2.8,  5.1,  1.5],
       [ 6.1,  2.6,  5.6,  1.4],
       [ 7.7,  3. ,  6.1,  2.3],
       [ 6.3,  3.4,  5.6,  2.4],
       [ 6.4,  3.1,  5.5,  1.8],
       [ 6. ,  3. ,  4.8,  1.8],
       [ 6.9,  3.1,  5.4,  2.1],
       [ 6.7,  3.1,  5.6,  2.4],
       [ 6.9,  3.1,  5.1,  2.3],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 6.8,  3.2,  5.9,  2.3],
       [ 6.7,  3.3,  5.7,  2.5],
       [ 6.7,  3. ,  5.2,  2.3],
       [ 6.3,  2.5,  5. ,  1.9],
       [ 6.5,  3. ,  5.2,  2. ],
       [ 6.2,  3.4,  5.4,  2.3],
       [ 5.9,  3. ,  5.1,  1.8]])

In [48]:

    

fig = plt.figure(1, figsize=(4, 3))
plt.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)


    

In [49]:

    

plt.cla()
pca = decomposition.PCA(n_components=3)
pca.fit(X)
X = pca.transform(X)

for name, label in [('Setosa', 0), ('Versicolour', 1), ('Virginica', 2)]:
    ax.text3D(X[y == label, 0].mean(),
              X[y == label, 1].mean() + 1.5,
              X[y == label, 2].mean(), name,
              horizontalalignment='center',
              bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))
# Reorder the labels to have colors matching the cluster results
y = np.choose(y, [1, 2, 0]).astype(np.float)
ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=y, cmap=plt.cm.spectral)

ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])

plt.show()