def main2():
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(X_train_std, y_train)
pdb.set_trace()
plot_decision_regions(X_combined_std,
y_combined,
classifier=lr,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'logistic_regression.png', dpi=300)
def main3():
# logistic regretion with regularization
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
weights, params = [], []
for c in np.arange(-5, 5):
lr = LogisticRegression(C=10**c, random_state=0)
lr.fit(X_train_std, y_train)
weights.append(lr.coef_[1])
params.append(10**c)
weights = np.array(weights)
plt.plot(params, weights[:, 0], label='petal length')
plt.plot(params, weights[:, 1], linestyle='--', label='petal width')
plt.ylabel('weight coefficient')
plt.xlabel('C')
plt.legend(loc='upper left')
plt.xscale('log')
plt.savefig(PIC_LOC + 'regression_path.png', dpi=300)
def KNN_model():
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined = np.vstack((X_train, X_test))
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=knn,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'k_nearest_neighbors.png', dpi=300)
def build_dec_tree():
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
tree = DecisionTreeClassifier(criterion='entropy',
max_depth=3,
random_state=0)
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined,
y_combined,
classifier=tree,
test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'decision_tree_decision.png', dpi=300)
export_graphviz(tree,
out_file='tree.dot',
feature_names=['petal length', 'petal width'])
def main1():
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0)
ppn.fit(X_train_std, y_train)
y_pred = ppn.predict(X_test_std)
print('Misclassified samples: %d' % (y_test != y_pred).sum())
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined_std,
y=y_combined,
classifier=ppn,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'iris_perceptron_scikit.png', dpi=300)
def linear_svm():
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=svm,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'support_vector_machine_linear.png', dpi=300)
# plt.show()
plt.close()
svm = SVC(kernel='rbf', random_state=0, gamma=100.0, C=10.0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=svm,
test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'svm_linear_highgamma.png', dpi=300)
def random_forests():
X, y = get_data_sklearn()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
forest = RandomForestClassifier(criterion='entropy',
n_estimators=10,
random_state=1,
n_jobs=2)
forest.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined,
y_combined,
classifier=forest,
test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.savefig(PIC_LOC + 'random_forest.png', dpi=300)