mhjensen
66 lines
2.6 KiB
Plaintext
66 lines
2.6 KiB
Plaintext
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.datasets import load_breast_cancer
|
|
from sklearn.svm import SVC
|
|
from sklearn.linear_model import LogisticRegression
|
|
from sklearn.tree import DecisionTreeClassifier
|
|
from sklearn.ensemble import AdaBoostClassifier
|
|
|
|
def plot_decision_boundary(clf, X, y, axes=[-1.5, 2.5, -1, 1.5], alpha=0.5, contour=True):
|
|
x1s = np.linspace(axes[0], axes[1], 100)
|
|
x2s = np.linspace(axes[2], axes[3], 100)
|
|
x1, x2 = np.meshgrid(x1s, x2s)
|
|
X_new = np.c_[x1.ravel(), x2.ravel()]
|
|
y_pred = clf.predict(X_new).reshape(x1.shape)
|
|
custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])
|
|
plt.contourf(x1, x2, y_pred, alpha=0.3, cmap=custom_cmap)
|
|
if contour:
|
|
custom_cmap2 = ListedColormap(['#7d7d58','#4c4c7f','#507d50'])
|
|
plt.contour(x1, x2, y_pred, cmap=custom_cmap2, alpha=0.8)
|
|
plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo", alpha=alpha)
|
|
plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs", alpha=alpha)
|
|
plt.axis(axes)
|
|
plt.xlabel(r"$x_1$", fontsize=18)
|
|
plt.ylabel(r"$x_2$", fontsize=18, rotation=0)
|
|
|
|
# Load the data
|
|
cancer = load_breast_cancer()
|
|
X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)
|
|
#now scale the data
|
|
from sklearn.preprocessing import StandardScaler
|
|
scaler = StandardScaler()
|
|
scaler.fit(X_train)
|
|
X_train_scaled = scaler.transform(X_train)
|
|
X_test_scaled = scaler.transform(X_test)
|
|
|
|
ada_clf = AdaBoostClassifier(
|
|
DecisionTreeClassifier(max_depth=1), n_estimators=200,
|
|
algorithm="SAMME.R", learning_rate=0.5, random_state=42)
|
|
|
|
ada_clf.fit(X_train_scaled, y_train)
|
|
plot_decision_boundary(ada_clf, cancer.data,cancer.target)
|
|
|
|
m = len(X_train_scaled)
|
|
|
|
plt.figure(figsize=(11, 4))
|
|
for subplot, learning_rate in ((121, 1), (122, 0.5)):
|
|
sample_weights = np.ones(m)
|
|
plt.subplot(subplot)
|
|
for i in range(5):
|
|
svm_clf = SVC(kernel="rbf", C=0.05, gamma="auto", random_state=42)
|
|
svm_clf.fit(X_train_scaled, y_train, sample_weight=sample_weights)
|
|
y_pred = svm_clf.predict(X_train_scaled)
|
|
sample_weights[y_pred != y_train] *= (1 + learning_rate)
|
|
plot_decision_boundary(svm_clf, cancer.data,cancer.target, alpha=0.2)
|
|
plt.title("learning_rate = {}".format(learning_rate), fontsize=16)
|
|
if subplot == 121:
|
|
plt.text(-0.7, -0.65, "1", fontsize=14)
|
|
plt.text(-0.6, -0.10, "2", fontsize=14)
|
|
plt.text(-0.5, 0.10, "3", fontsize=14)
|
|
plt.text(-0.4, 0.55, "4", fontsize=14)
|
|
plt.text(-0.3, 0.90, "5", fontsize=14)
|
|
|
|
plt.show()
|
|
|