Credits: Content forked from Parallel Machine Learning with scikit-learn and IPython by Olivier Grisel
%matplotlib inline
import pandas as pd
import numpy as np
import pylab as plt
import seaborn
# Set the global default size of matplotlib figures
plt.rc('figure', figsize=(10, 5))
# Set seaborn aesthetic parameters to defaults
seaborn.set()
x = np.linspace(0, 2, 10)
plt.plot(x, x, 'o-', label='linear')
plt.plot(x, x ** 2, 'x-', label='quadratic')
plt.legend(loc='best')
plt.title('Linear vs Quadratic progression')
plt.xlabel('Input')
plt.ylabel('Output');
plt.show()
# Gaussian, mean 1, stddev .5, 1000 elements
samples = np.random.normal(loc=1.0, scale=0.5, size=1000)
print(samples.shape)
print(samples.dtype)
print(samples[:30])
plt.hist(samples, bins=50);
plt.show()
(1000,) float64 [ 0.6806888 0.72202042 1.40490113 1.13979846 0.5729488 1.32584077 0.61635621 0.60340336 1.29453467 0.69841457 0.6975998 0.72315991 0.66912189 1.03420801 0.62283168 0.38582511 0.89488414 1.4802518 1.43819256 0.98605861 0.60402232 1.03820507 0.35598796 1.32901087 1.03194436 1.3374366 1.82526334 1.26614489 1.20061661 0.86344001]
samples_1 = np.random.normal(loc=1, scale=.5, size=10000)
samples_2 = np.random.standard_t(df=10, size=10000)
bins = np.linspace(-3, 3, 50)
# Set an alpha and use the same bins since we are plotting two hists
plt.hist(samples_1, bins=bins, alpha=0.5, label='samples 1')
plt.hist(samples_2, bins=bins, alpha=0.5, label='samples 2')
plt.legend(loc='upper left');
plt.show()
plt.scatter(samples_1, samples_2, alpha=0.1);
plt.show()