In [5]:

import pandas as pd
from pandas import DataFrame
import numpy as np

from sklearn.decomposition import PCA

Create a DataFrame full of random numbers.

In [9]:

df = pd.DataFrame(data=np.random.normal(0, 1, (50, 8)))
df.head()

Out[9]:

Fit the PCA.

In [10]:

pca = PCA(n_components=4)
pca.fit(df)

Out[10]:

PCA(copy=True, iterated_power='auto', n_components=4, random_state=None,
  svd_solver='auto', tol=0.0, whiten=False)

Apply the transformation and convert the result into a DataFrame.

In [14]:

columns = ['pca_%i' % i for i in range(4)]
df_pca = DataFrame(pca.transform(df), columns=columns, index=df.index)
df_pca.head()

Out[14]:

	pca_0	pca_1	pca_2	pca_3
0	-0.546917	0.506951	-1.042971	0.287119
1	-0.054910	-0.217007	-0.539264	0.457777
2	0.908084	-0.113016	-0.602685	-1.009475
3	-0.168224	-1.419395	-1.216016	0.196382
4	0.678731	-0.605830	-0.057639	-0.428901

Apply PCA to a DataFrame