utils.py

#
# Utility functions
#
#
from itertools import cycle, islice
from math import sqrt
from numpy import array
from pandas.tools.plotting import parallel_coordinates
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

# Function that creates a DataFrame with Cluster Number
def pd_centers(featuresUsed, centers):
	colNames = list(featuresUsed)
	colNames.append('prediction')

	# Zip with a column called 'prediction' (index)
	Z = [np.append(A, index) for index, A in enumerate(centers)]

	# Convert to pandas for plotting
	P = pd.DataFrame(Z, columns=colNames)
	P['prediction'] = P['prediction'].astype(int)
	return P

# Function that creates Parallel Plot
def parallel_plot(data):
	my_colors = list(islice(cycle(['b', 'r', 'g', 'y', 'k']), None, len(data)))
	plt.figure(figsize=(15,8)).gca().axes.set_ylim([-3,+3])
	parallel_coordinates(data, 'prediction', color = my_colors, marker='o')