Created
November 17, 2020 20:23
-
-
Save accessnash/92690829b0295ffb43c97cc2091595c3 to your computer and use it in GitHub Desktop.
Non-parametric density estimation for a bimodal sample
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Created on Tue Nov 17 20:58:21 2020 | |
@author: Localuser | |
""" | |
import matplotlib.pyplot as plt | |
import numpy as np | |
from sklearn.neighbors import KernelDensity | |
import math | |
#creating and plotting a bimodal data sample | |
sample1 = np.random.normal(loc = 20, scale = 5, size = 300) | |
sample2 = np.random.normal(loc = 40, scale = 5, size = 700) | |
sample = np.hstack((sample1, sample2)) | |
plt.hist(sample, bins = 50) | |
plt.show() | |
# fitting the density | |
model = KernelDensity(bandwidth = 2, kernel = 'gaussian') | |
sample = sample.reshape((len(sample), 1)) | |
model.fit(sample) | |
# sample probabilities for a range of outcomes | |
values = np.asarray([value for value in range(1, 60)]) | |
values = values.reshape((len(values), 1)) | |
probabilities = model.score_samples(values) | |
probabilities = math.exp(probabilities) | |
# plot the histogram and pdf | |
plt.hist(sample, bins=50, density=True) | |
plt.plot(values[:], probabilities) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment