def extra_material():
X, y = make_moons(n_samples=1000, noise=0.4, random_state=42)
# plt.plot(X[:, 0][y==0], X[:, 1][y==0], "bs")
# plt.plot(X[:, 0][y==1], X[:, 1][y==1], "g^")
# plt.savefig(PNG_PATH + "extra_moons", dpi=300)
# plt.close()
# tol = 0.1
# tols = []
# times = []
# for i in range(10):
# svm_clf = SVC(kernel="poly", gamma=3, C=10, tol=tol, verbose=1)
# t1 = time.time()
# svm_clf.fit(X, y)
# t2 = time.time()
# times.append(t2-t1)
# tols.append(tol)
# print(i, tol, t2-t1)
# tol /= 10
# plt.semilogx(tols, times)
# plt.savefig(PNG_PATH + "learning_time", dpi=300)
# plt.close()
# Training set
iris = datasets.load_iris()
X = iris["data"][:, (2, 3)] # petal length, petal width
y = (iris["target"] == 2).astype(np.float64).reshape(-1,
1) # Iris-Virginica
C = 2
svm_clf = MyLinearSVC(C=C,
eta0=10,
eta_d=1000,
n_epochs=60000,
random_state=2)
pdb.set_trace()
svm_clf.fit(X, y)
svm_clf.predict(np.array([[5, 2], [4, 1]]))
plt.plot(range(svm_clf.n_epochs), svm_clf.Js)
plt.axis([0, svm_clf.n_epochs, 0, 100])
plt.savefig(PNG_PATH + "svm_cost_vs_epochs", dpi=300)
plt.close()
print(svm_clf.intercept_, svm_clf.coef_)
svm_clf2 = SVC(kernel="linear", C=C)
svm_clf2.fit(X, y.ravel())
print(svm_clf2.intercept_, svm_clf2.coef_)
yr = y.ravel()
plt.figure(figsize=(12, 3.2))
plt.subplot(121)
plt.plot(X[:, 0][yr == 1], X[:, 1][yr == 1], "g^", label="Iris-Virginica")
plt.plot(X[:, 0][yr == 0],
X[:, 1][yr == 0],
"bs",
label="Not Iris-Virginica")
plot_svc_decision_boundary(svm_clf, 4, 6)
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
plt.title("MyLinearSVC", fontsize=14)
plt.axis([4, 6, 0.8, 2.8])
plt.subplot(122)
plt.plot(X[:, 0][yr == 1], X[:, 1][yr == 1], "g^")
plt.plot(X[:, 0][yr == 0], X[:, 1][yr == 0], "bs")
plot_svc_decision_boundary(svm_clf2, 4, 6)
plt.xlabel("Petal length", fontsize=14)
plt.title("SVC", fontsize=14)
plt.axis([4, 6, 0.8, 2.8])
plt.savefig(PNG_PATH + "mine_vs_theirs", dpi=300)
plt.close()
sgd_clf = SGDClassifier(loss="hinge",
alpha=0.017,
max_iter=50,
random_state=42)
sgd_clf.fit(X, y.ravel())
m = len(X)
t = y * 2 - 1 # -1 if t==0, +1 if t==1
X_b = np.c_[np.ones((m, 1)), X] # Add bias input x0=1
X_b_t = X_b * t
sgd_theta = np.r_[sgd_clf.intercept_[0], sgd_clf.coef_[0]]
print(sgd_theta)
support_vectors_idx = (X_b_t.dot(sgd_theta) < 1).ravel()
sgd_clf.support_vectors_ = X[support_vectors_idx]
sgd_clf.C = C
plt.figure(figsize=(5.5, 3.2))
plt.plot(X[:, 0][yr == 1], X[:, 1][yr == 1], "g^")
plt.plot(X[:, 0][yr == 0], X[:, 1][yr == 0], "bs")
plot_svc_decision_boundary(sgd_clf, 4, 6)
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
plt.title("SGDClassifier", fontsize=14)
plt.axis([4, 6, 0.8, 2.8])
plt.savefig(PNG_PATH + "sgd_clssifier", dpi=300)
plt.close()
def mySVC_vs_scikit():
from sklearn.svm import SVC
from sklearn.linear_model import SGDClassifier
from sklearn.datasets import load_iris
iris = load_iris()
X = iris["data"][:, (2, 3)]
y = (iris["target"] == 2).astype(np.float64).reshape(-1, 1)
C = 2
my_clf = MyBinaryLinearSVC(C=C,
eta0=10,
eta_d=1000,
n_epochs=60000,
random_state=42)
my_clf.fit(X, y)
scikit_svc = SVC(kernel="linear", C=C)
scikit_svc.fit(X, y.ravel())
scikit_SGD = SGDClassifier(loss="hinge",
alpha=0.017,
max_iter=50,
random_state=42)
scikit_SGD.fit(X, y.ravel())
m = len(X)
t = y * 2 - 1
X_b = np.c_[np.ones((m, 1)), X]
X_b_t = X_b * t
sgd_theta = np.r_[scikit_SGD.intercept_[0], scikit_SGD.coef_[0]]
support_vectors_idx = (X_b_t.dot(sgd_theta) < 1).ravel()
scikit_SGD.support_vectors_ = X[support_vectors_idx]
scikit_SGD.C = C
print("Parameters of my SVC model - ")
print("weight : {}, bias : {}".format(np.squeeze(my_clf.coef_, axis=0),
my_clf.intercept_))
print("Parameters of scikit SVC model - ")
print("weight : {}, bias : {}".format(scikit_svc.coef_,
scikit_svc.intercept_))
print("Parameters of scikit SGD model - ")
print("weight : {}, bias : {}".format(scikit_SGD.coef_[0],
scikit_SGD.intercept_[0]))
y_ravel = y.ravel()
plt.figure(figsize=(12, 4.8))
plt.subplot(131)
plt.plot(X[:, 0][y_ravel == 1],
X[:, 1][y_ravel == 1],
"g^",
label="Iris-Virginica")
plt.plot(X[:, 0][y_ravel == 0],
X[:, 1][y_ravel == 0],
"bs",
label="Not Iris-Virginica")
plt.xlabel("Petal Length(cm)", fontsize=14)
plt.ylabel("Petal Width(cm)", fontsize=14)
plot_svc_decision_boundary(my_clf, 4, 6)
plt.title("MyLinearSVM")
plt.axis([4, 6, 0.8, 2.8])
plt.subplot(132)
plt.plot(X[:, 0][y_ravel == 1],
X[:, 1][y_ravel == 1],
"g^",
label="Iris-Virginica")
plt.plot(X[:, 0][y_ravel == 0],
X[:, 1][y_ravel == 0],
"bs",
label="Not Iris-Virginica")
plt.xlabel("Petal Length(cm)", fontsize=14)
plot_svc_decision_boundary(scikit_svc, 4, 6)
plt.title("scikit LinearSVC")
plt.axis([4, 6, 0.8, 2.8])
plt.subplot(133)
plt.plot(X[:, 0][y_ravel == 1],
X[:, 1][y_ravel == 1],
"g^",
label="Iris-Virginica")
plt.plot(X[:, 0][y_ravel == 0],
X[:, 1][y_ravel == 0],
"bs",
label="Not Iris-Virginica")
plt.xlabel("Petal Length(cm)", fontsize=14)
plot_svc_decision_boundary(scikit_SGD, 4, 6)
plt.title("SGDClassifier")
plt.axis([4, 6, 0.8, 2.8])
save_fig("Comparison_mySVM_vs_Scikit")
plt.show()
sgd_clf = SGDClassifier(loss="hinge",
alpha=0.017,
max_iter=50,
random_state=42)
sgd_clf.fit(X, y.ravel())
m = len(X)
t = y * 2 - 1 # -1 if t==0, +1 if t==1
X_b = np.c_[np.ones((m, 1)), X] # Add bias input x0=1
X_b_t = X_b * t
sgd_theta = np.r_[sgd_clf.intercept_[0], sgd_clf.coef_[0]]
print(sgd_theta)
support_vectors_idx = (X_b_t.dot(sgd_theta) < 1).ravel()
sgd_clf.support_vectors_ = X[support_vectors_idx]
sgd_clf.C = C
plt.figure(figsize=(5.5, 3.2))
plt.plot(X[:, 0][yr == 1], X[:, 1][yr == 1], "g^")
plt.plot(X[:, 0][yr == 0], X[:, 1][yr == 0], "bs")
plot_svc_decision_boundary(sgd_clf, 4, 6)
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
plt.title("SGDClassifier", fontsize=14)
plt.axis([4, 6, 0.8, 2.8])
# # Exercise solutions
# ## 1. to 7.
# See appendix A.
# initialize NB classifier
#clf = MultinomialNB()
#clf = BernoulliNB()
#clf.class_prior =[0.041175856307435255,0.9588241436925647]
#clf = svm.SVC()
#clf.cache_size = 4000
#clf.n_jobs = -1
#clf.C = .1
clf = SGDClassifier()
clf.n_jobs = -1
clf.C =1
clf.alpha = .00000001
clf.n_iter = 10000
#clf = DecisionTreeClassifier()
#clf.max_depth = 3
#scores = cross_validation.cross_val_score(clf, feat_vecs, labels, cv=10,scoring='recall')
#print scores
#set_trace()
def mp(t,k=None):
# set_trace()
trainI,testI = t
if k:
ch2 = SelectKBest(chi2, k=k)
