import numpy as np
from sklearn.decomposition import PCA
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import scale
%matplotlib inline

#Load data set
data = pd.read_csv('data.csv')

#convert it to numpy arrays
X=data.values[:,1:7]
print 'Raw data:\n', X, '\n'

#Scaling the values
X = scale(X)

pca = PCA(n_components=2)

pca.fit(X)
print 'Components:\n', pca.components_, '\n'

newCoords = pca.transform(X)
print 'Transformed Coordinates:\n', newCoords, '\n'


#The amount of variance that each PC explains
var = pca.explained_variance_ratio_

#Cumulative Variance explains
var1 = np.cumsum(np.round(pca.explained_variance_ratio_, decimals=4)*100)

plt.plot(var1)