def main():
X_train, y_train = load_features(sys.argv[1])
X_dev, y_dev = load_features(sys.argv[2])
X_test, y_test = load_features(sys.argv[3])
C_list = [0.001, 0.01, 0.1, 1.0, 10., 100.]
train_accuracies = list()
dev_accuracies = list()
test_accuracies = list()
for C in C_list:
model = train(X_train, y_train, C)
train_accuracy = model.score(X_train, y_train)
dev_accuracy = model.score(X_dev, y_dev)
test_accuracy = model.score(X_test, y_test)
train_accuracies.append(train_accuracy)
dev_accuracies.append(dev_accuracy)
test_accuracies.append(test_accuracy)
plt.ylim(.7, 1.)
plt.xscale('log')
plt.grid(True)
plt.plot(C_list, train_accuracies, label='train')
plt.plot(C_list, dev_accuracies, label='dev')
plt.plot(C_list, test_accuracies, label='test')
plt.legend()
plt.show()
def main():
X_train, y_train = load_features(sys.argv[1])
X_test, y_test = load_features(sys.argv[2])
model = train(X_train, y_train)
pred = model.predict(X_test)
print(classification_report(y_test, pred))
def main():
X_train, y_train = load_features(sys.argv[1])
X_test, y_test = load_features(sys.argv[2])
model = train(X_train, y_train)
train_score = model.score(X_train, y_train)
test_score = model.score(X_test, y_test)
print('train score = ' + str(train_score))
print('test score = ' + str(test_score))
def main():
X_train, y_train = load_features(sys.argv[1])
X_test, y_test = load_features(sys.argv[2])
model = train(X_train, y_train)
train_prob = model.predict_proba(X_train)
test_prob = model.predict_proba(X_test)
print('train[:5] =')
print(train_prob[:5])
print('test[:5] =')
print(test_prob[:5])
def main():
X_train, y_train = load_features(sys.argv[1])
X_test, y_test = load_features(sys.argv[2])
model = train(X_train, y_train)
coef = model.coef_.tolist()
for i,c in enumerate(coef):
print('class ' + class_names[i])
order = [y[1] for y in sorted([(x, j) for j,x in enumerate(c)])]
print('best 10 = {}'.format(order[:10]))
print('worst 10 = {}'.format(order[:10][::-1]))
def main():
X_train, y_train = load_features(sys.argv[1])
X_dev, y_dev = load_features(sys.argv[2])
X_test, y_test = load_features(sys.argv[3])
params = list()
# LogisticRegression
for penalty in ('l1', 'l2'):
for C in (0.01, 0.1, 1., 10.):
for solver in ('newton-cg', 'liblinear') if penalty == 'l2' else (
'liblinear', ):
args = {
'penalty': penalty,
'C': C,
'solver': solver,
'multi_class': 'auto',
'random_state': 0
}
param = train(X_train, y_train, X_dev, y_dev,
'logistic regression', LogisticRegression, args)
params.append(param)
# KNeighborsClassifier
for n_neighbors in (2, 3, 5, 10):
args = {'n_neighbors': n_neighbors}
param = train(X_train, y_train, X_dev, y_dev, 'k neighbors',
KNeighborsClassifier, args)
params.append(param)
# DecisionTreeClassifier
for max_depth in (1, 3, 5, 10, None):
args = {'max_depth': max_depth, 'random_state': 0}
param = train(X_train, y_train, X_dev, y_dev, 'decision tree',
DecisionTreeClassifier, args)
params.append(param)
# LinearSVC
for C in (0.01, 0.1, 1., 10.):
args = {'C': C, 'random_state': 0}
param = train(X_train, y_train, X_dev, y_dev, 'SVM', LinearSVC, args)
params.append(param)
bestparam = sorted(params, key=lambda x: x[-1], reverse=True)[0]
name, args, model, dev_accuracy = bestparam
accuracy = model.score(X_test, y_test)
print('name = {}'.format(name))
print('args = {}'.format(args))
print('dev accuracy = {}'.format(dev_accuracy))
print('test accuracy = {}'.format(accuracy))
def main():
X_train, y_train = load_features(sys.argv[1])
X_test, y_test = load_features(sys.argv[2])
model = train(X_train, y_train)
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
c_train_matrix = confusion_matrix(y_train, y_train_pred)
c_test_matrix = confusion_matrix(y_test, y_test_pred)
print('train =')
print(c_train_matrix)
print('test =')
print(c_test_matrix)