sgd.py

import matplotlib.pyplot as plt
import numpy as np

from sklearn import datasets
from sklearn.inspection import DecisionBoundaryDisplay
from sklearn.linear_model import SGDClassifier

def setup_sgd():
    # import some data to play with
    iris = datasets.load_iris()

    # we only take the first two features. We could
    # avoid this ugly slicing by using a two-dim dataset
    X = iris.data[:, :2]
    y = iris.target
    colors = ["navy", "turquoise", "darkorange"]

    # shuffle
    idx = np.arange(X.shape[0])
    np.random.seed(13)
    np.random.shuffle(idx)
    X = X[idx]
    y = y[idx]

    # standardize
    mean = X.mean(axis=0)
    std = X.std(axis=0)
    X = (X - mean) / std

    clf = SGDClassifier(alpha=0.001, max_iter=100).fit(X, y)

    # Plot also the training points
    plt.figure()
    for i, color in zip(clf.classes_, colors):
        idx = np.where(y == i)
        plt.scatter(
            X[idx, 0],
            X[idx, 1],
            c=color,
            label=iris.target_names[i],
            # cmap=plt.cm.Paired,
            # edgecolor="black",
            s=20,
        )
    plt.title("Decision surface of multi-class SGD")
    plt.axis("tight")

    # Plot the three one-against-all classifiers
    xmin, xmax = plt.xlim()
    ymin, ymax = plt.ylim()
    coef = clf.coef_
    intercept = clf.intercept_


    # def plot_hyperplane(c, color):
    #     def line(x0):
    #         return (-(x0 * coef[c, 0]) - intercept[c]) / coef[c, 1]

    #     plt.plot([xmin, xmax], [line(xmin), line(xmax)], ls="--", color=color)

    plt.legend()