# Load Matlab data file and extract variables of interest
mat_data = loadmat('../Data/synth7.mat')
X = np.matrix(mat_data['X'])
y = np.matrix(mat_data['y'])
attributeNames = [name[0] for name in mat_data['attributeNames'].squeeze()]
classNames = [name[0][0] for name in mat_data['classNames']]
N, M = X.shape
C = len(classNames)
# Number of rounds of bagging
L = 100
# Fit model using random tree classifier:
rf_classifier = RandomForestClassifier(L)
rf_classifier.fit(X.A, y.A.ravel())
y_est = rf_classifier.predict(X).T
y_est_prob = rf_classifier.predict_proba(X).T
# Compute classification error
ErrorRate = (y != np.mat(y_est).T).sum(dtype=float) / N
print('Error rate: {:.2f}%'.format(ErrorRate * 100))
# Plot decision boundaries
figure(1)
dbprobplot(rf_classifier, X, y, 'auto', resolution=400)
figure(2)
dbplot(rf_classifier, X, y, 'auto', resolution=400)
show()
# For each round of bagging
for l in range(L):
# Extract training set by random sampling with replacement from X and y
X_train, y_train = bootstrap(X, y, N, weights)
# Fit logistic regression model to training data and save result
logit_classifier = LogisticRegression()
logit_classifier.fit(X_train, y_train)
logits[l] = logit_classifier
y_est = logit_classifier.predict(X).T
votes = votes + y_est
ErrorRate = (y!=y_est).sum(dtype=float)/N
print('Error rate: {:2.2f}%'.format(ErrorRate*100))
# Estimated value of class labels (using 0.5 as threshold) by majority voting
y_est_ensemble = votes>(L/2)
# Compute error rate
ErrorRate = (y!=y_est_ensemble).sum(dtype=float)/N
print('Error rate: {:3.2f}%'.format(ErrorRate*100))
ce = BinClassifierEnsemble(logits)
figure(1); dbprobplot(ce, X, y, 'auto', resolution=200)
figure(2); dbplot(ce, X, y, 'auto', resolution=200)
show()
print('Ran Exercise 9.2.1')
from sklearn.ensemble import RandomForestClassifier
# Load Matlab data file and extract variables of interest
mat_data = loadmat('../Data/synth7.mat')
X = np.matrix(mat_data['X'])
y = np.matrix(mat_data['y'])
attributeNames = [name[0] for name in mat_data['attributeNames'].squeeze()]
classNames = [name[0][0] for name in mat_data['classNames']]
N, M = X.shape
C = len(classNames)
# Number of rounds of bagging
L = 100
# Fit model using random tree classifier:
rf_classifier = RandomForestClassifier(L)
rf_classifier.fit(X.A, y.A.ravel())
y_est = rf_classifier.predict(X).T
y_est_prob = rf_classifier.predict_proba(X).T
# Compute classification error
ErrorRate = (y!=np.mat(y_est).T).sum(dtype=float)/N
print('Error rate: {:.2f}%'.format(ErrorRate*100))
# Plot decision boundaries
figure(1); dbprobplot(rf_classifier, X, y, 'auto', resolution=400)
figure(2); dbplot(rf_classifier, X, y, 'auto', resolution=400)
show()
# For each round of bagging
for l in range(L):
# Extract training set by random sampling with replacement from X and y
X_train, y_train = bootstrap(X, y, N, weights)
# Fit logistic regression model to training data and save result
logit_classifier = LogisticRegression()
logit_classifier.fit(X_train, y_train.A.ravel())
logits[l] = logit_classifier
y_est = np.mat(logit_classifier.predict(X)).T
votes = votes + y_est
ErrorRate = (y != y_est).sum(dtype=float) / N
print('Error rate: {0}%'.format(ErrorRate * 100))
# Estimated value of class labels (using 0.5 as threshold) by majority voting
y_est_ensemble = votes > (L / 2)
# Compute error rate
ErrorRate = (y != y_est_ensemble).sum(dtype=float) / N
print('Error rate: {:.1f}%'.format(ErrorRate * 100))
ce = BinClassifierEnsemble(logits)
figure(1)
dbprobplot(ce, X, y, 'auto', resolution=200)
figure(2)
dbplot(ce, X, y, 'auto', resolution=200)
show()
logits = [0]*L
votes = np.zeros((N,1))
# For each round of bagging
for l in range(L):
# Extract training set by random sampling with replacement from X and y
X_train, y_train = bootstrap(X, y, N, weights)
# Fit logistic regression model to training data and save result
logit_classifier = LogisticRegression()
logit_classifier.fit(X_train, y_train.A.ravel())
logits[l] = logit_classifier
y_est = np.mat(logit_classifier.predict(X)).T
votes = votes + y_est
ErrorRate = (y!=y_est).sum(dtype=float)/N
print('Error rate: {0}%'.format(ErrorRate*100))
# Estimated value of class labels (using 0.5 as threshold) by majority voting
y_est_ensemble = votes>(L/2)
# Compute error rate
ErrorRate = (y!=y_est_ensemble).sum(dtype=float)/N
print('Error rate: {:.1f}%'.format(ErrorRate*100))
ce = BinClassifierEnsemble(logits)
figure(1); dbprobplot(ce, X, y, 'auto', resolution=200)
figure(2); dbplot(ce, X, y, 'auto', resolution=200)
show()
from sklearn.ensemble import RandomForestClassifier
# Load Matlab data file and extract variables of interest
mat_data = loadmat('../Data/synth7.mat')
X = np.matrix(mat_data['X'])
y = np.matrix(mat_data['y'])
attributeNames = [name[0] for name in mat_data['attributeNames'].squeeze()]
classNames = [name[0][0] for name in mat_data['classNames']]
N, M = X.shape
C = len(classNames)
# Number of rounds of bagging
L = 100
# Fit model using random tree classifier:
rf_classifier = RandomForestClassifier(L)
rf_classifier.fit(X.A, y.A.ravel())
y_est = rf_classifier.predict(X).T
y_est_prob = rf_classifier.predict_proba(X).T
# Compute classification error
ErrorRate = (y!=np.mat(y_est).T).sum(dtype=float)/N
print('Error rate: {:.2f}%'.format(ErrorRate*100))
# Plot decision boundaries
figure(1); dbprobplot(rf_classifier, X, y, 'auto', resolution=400)
figure(2); dbplot(rf_classifier, X, y, 'auto', resolution=400)
show()
