def branche_data_test(lr=0.05, batch_size=64, epochs=100):
keys = [(561010, 'Restauranter'), (620100, 'Computerprogrammering')]
feat_train, feat_test, y_train, y_test, cnames = get_branche_data(keys)
c = CountVectorizer()
c.fit(feat_train)
bag_of_words_feat_train = c.transform(feat_train).toarray()
classifier = LogisticRegressionClassifier()
classifier.fit(bag_of_words_feat_train,
y_train,
lr=lr,
batch_size=batch_size,
epochs=epochs)
print('Logistic Regression Industri Codes Classifier')
bag_of_words_feat_test = c.transform(feat_test).toarray()
print_score(classifier, bag_of_words_feat_train, bag_of_words_feat_test,
y_train, y_test)
hist = classifier.history
fig, ax = plt.subplots()
ax.plot(np.array(range(1, 1 + len(hist))), hist, 'b-x')
ax.set_title('Cost as a function of epoch for industry codes data')
ax.set_xlabel('epoch')
ax.set_ylabel('Ein (1/n NLL)')
export_fig(fig, 'logreg_text_cost_per_epoch.png')
plt.show()
fig.savefig("foo.pdf")
def wine_test(epochs=200, batch_size=16, lr=0.1):
print(
'wine test: params - epochs {0}, batch_size: {1}, learning rate: {2}'.
format(epochs, batch_size, lr))
features, target = load_wine(return_X_y=True)
# Make a train/test split using 30% test size
RANDOM_STATE = 42
X_train, X_test, y_train, y_test = train_test_split(
features, target, test_size=0.9, random_state=RANDOM_STATE)
sc = StandardScaler(
) # makes every features zero mean standard deviation 1 - makes learning problem much easier (massages the error function so sgd works better)
sc.fit(X_train)
s = SoftmaxClassifier(num_classes=3)
X_train = sc.transform(X_train)
X_train = np.c_[np.ones(X_train.shape[0]), X_train] # adds bias var
X_test = sc.transform(X_test)
X_test = np.c_[np.ones(X_test.shape[0]), X_test] # adds bias var
s.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, lr=lr)
print('Softmax Wine Classifier')
print_score(s, X_train, X_test, y_train, y_test)
hist = s.history
fig, ax = plt.subplots()
ax.plot(np.array(range(1, 1 + len(hist))), hist, 'b-x')
ax.set_title('Cost as a function of epoch for wine data')
ax.set_xlabel('epoch')
ax.set_ylabel('Ein (1/n NLL)')
export_fig(fig, 'softmax_wine_cost_per_epoch.png')
plt.show()
def branche_data_test():
keys = [(561010, 'Restauranter'), (620100, 'Computerprogrammering')]
feat_train, feat_test, y_train, y_test, cnames = get_branche_data(keys)
c = CountVectorizer()
c.fit(feat_train)
bag_of_words_feat_train = c.transform(feat_train).toarray()
classifier = LogisticRegressionClassifier()
classifier.fit(bag_of_words_feat_train,
y_train,
lr=0.1,
batch_size=16,
epochs=50)
print('Logistic Regression Industri Codes Classifier')
bag_of_words_feat_test = c.transform(feat_test).toarray()
print_score(classifier, bag_of_words_feat_train, bag_of_words_feat_test,
y_train, y_test)
def digits_test(epochs=10, batch_size=32, lr=0.05):
print(
'digits test: params - epochs {0}, batch_size: {1}, learning rate: {2}'
.format(epochs, batch_size, lr))
sc = SoftmaxClassifier(num_classes=10)
X_train, y_train = load_digits_train_data()
X_test, y_test = load_digits_test_data()
sc.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, lr=lr)
print_score(sc, X_train, X_test, y_train, y_test)
fig, ax = plt.subplots()
hist = sc.history
ax.plot(np.array(range(1, 1 + len(hist))), hist, 'b-x')
ax.set_xlabel('epoch')
ax.set_ylabel('Ein (1/n NLL)')
ax.set_title('softmax cost on digits as function of epoch')
export_fig(fig, 'softmax_cost_per_epoch.png')
plt.show()