Created
March 11, 2019 19:10
-
-
Save RichardKelley/31321f0e7fa438f0108bbd10b1d51018 to your computer and use it in GitHub Desktop.
ML utilities
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
import numpy as np | |
import matplotlib.pyplot as plt | |
from sklearn import datasets | |
from matplotlib.patches import Ellipse | |
from math import sqrt | |
def build_dataset(n_samples, n_features, n_classes = 1): | |
''' | |
Create a dataset. | |
@arg n_samples - the number of points to generate. | |
@arg n_features - the dimensionality of the points | |
@arg n_classes - the number of classes to generate. | |
Defaults to 1 for "unlabeled" data. | |
returns (x,y), where | |
x is a numpy array with x.shape = (n_samples, n_features). | |
y is a numpy array with y.shape = n_samples. | |
''' | |
return datasets.make_classification(n_samples=n_samples, n_features = n_features, n_classes = n_classes, | |
n_informative = n_features, n_redundant = 0, n_repeated = 0, | |
n_clusters_per_class=1, class_sep=2) | |
def plot_dataset(dataset): | |
if type(dataset) == tuple: | |
plt.scatter(dataset[0][:,0], dataset[0][:,1], c = dataset[1], cmap = 'cool', edgecolors="Black") | |
elif type(dataset) == np.ndarray: | |
plt.scatter(dataset[:,0], dataset[:,1], cmap = "cool", edgecolors="Black") | |
else: | |
print("Argument dataset should be an (x,y) tuple or an ndarray.") | |
def plot_classification(dataset, model): | |
h = 0.05 # mesh size | |
x_min, x_max = dataset[0][:, 0].min() - 1, dataset[0][:,0].max() + 1 | |
y_min, y_max = dataset[0][:, 1].min() - 1, dataset[0][:,1].max() + 1 | |
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h)) | |
Z = [] | |
for pt in np.c_[xx.ravel(), yy.ravel()]: | |
Z.append(model.forward(pt).argmax()) | |
Z = np.asarray(Z) | |
Z = Z.reshape(xx.shape) | |
plt.figure() | |
plt.pcolormesh(xx, yy, Z, cmap='cool') | |
plot_dataset(dataset) | |
def compute_accuracy(model, dataset): | |
correct = 0 | |
for i in range(dataset[0].shape[0]): | |
if model.forward(dataset[0][i]).argmax() == dataset[1][i]: | |
correct += 1 | |
return (correct, dataset[0].shape[0]) | |
def draw_gaussian(mean, cov): | |
ax = plt.gca() | |
plt.scatter(mean[0], mean[1], c="Orange") | |
w, v = np.linalg.eig(cov) | |
idx = w.argsort()[::-1] | |
w = w[idx] | |
v = v[idx] | |
ax.add_patch(Ellipse((mean[0], mean[1]), | |
2.0 * sqrt(5.991 * w[1]), | |
2.0 * sqrt(5.991 * w[0]), | |
np.rad2deg(-np.arctan2(v[1][1], v[1][0])), | |
linewidth=1, | |
fill=False )) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment