Created
March 25, 2020 04:47
-
-
Save tonghuikang/c57a4f2f05a1a59bf5a148e12ee8b1c3 to your computer and use it in GitHub Desktop.
SML homework template Q3
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
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 27, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Q1\n", | |
"\n", | |
"import numpy as np\n", | |
"import matplotlib.pyplot as plt\n", | |
"from numpy import linalg as LA\n", | |
"from matplotlib.patches import Ellipse\n", | |
"from sklearn.datasets.samples_generator import make_blobs \n", | |
"from scipy.stats import multivariate_normal\n", | |
"\n", | |
"K = 3\n", | |
"NUMDATAPTS = 150\n", | |
"\n", | |
"X, y = make_blobs(n_samples=NUMDATAPTS, centers=K, shuffle=False, random_state=0, cluster_std=0.6)\n", | |
"\n", | |
"g1 = np.asarray([[2.0, 0], [-0.9, 1]])\n", | |
"g2 = np.asarray([[1.4, 0], [0.5, 0.7]])\n", | |
"\n", | |
"mean1 = np.mean(X[:int(NUMDATAPTS/K)])\n", | |
"mean2 = np.mean(X[int(NUMDATAPTS/K):2*int(NUMDATAPTS/K)])\n", | |
"\n", | |
"X[:int(NUMDATAPTS/K)] = np.einsum('nj,ij->ni', X[:int(NUMDATAPTS/K)] - mean1, g1) + mean1\n", | |
"X[int(NUMDATAPTS/K):2*int(NUMDATAPTS/K)] = np.einsum('nj,ij->ni', X[int(NUMDATAPTS/K):2*int(NUMDATAPTS/K)] - mean2, g2) + mean2\n", | |
"X[:,1] -= 4\n", | |
"\n", | |
"\n", | |
"def E_step():\n", | |
" gamma = np.zeros((NUMDATAPTS, K))\n", | |
" # your steps here\n", | |
" return gamma\n", | |
"\n", | |
"def M_step(gamma): \n", | |
" # your steps here\n", | |
" return None\n", | |
"\n", | |
"\n", | |
"def plot_result(gamma=None):\n", | |
" ax = plt.subplot (111 , aspect='equal')\n", | |
" ax.set_xlim([-5, 5])\n", | |
" ax.set_ylim([-5, 5])\n", | |
" ax.scatter(X[:, 0], X[:, 1], c=gamma, s=50, cmap=None)\n", | |
" for k in range(K):\n", | |
" l, v = LA.eig(cov[k])\n", | |
" theta = np.arctan(v[1,0]/v[0,0])\n", | |
" e = Ellipse((mu[k, 0], mu[k, 1]), 6*l[0], 6*l[1], theta*180 / np.pi)\n", | |
" e.set_alpha(0.5) \n", | |
" ax.add_artist(e)\n", | |
" plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 28, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"## Q4\n", | |
"\n", | |
"import numpy as np\n", | |
"from sklearn import decomposition\n", | |
"from sklearn import datasets\n", | |
"X = datasets.load_diabetes().data" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.7.7" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 4 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment