def train_lr(): params = { "offline_model_dir": "weights/lr", } params.update(params_common) X_train, X_valid = load_data("train"), load_data("vali") model = LogisticRegression("ranking", params, logger) model.fit(X_train, validation_data=X_valid) model.save_session()
def train_lr(): params = { "offline_model_dir": "../weights", } params.update(params_common) X_train, X_valid = load_data("train"), load_data("vali") X_test = load_data("test") # print(X_test['label']) model = LogisticRegression("ranking", params, logger) model.fit(X_train, validation_data=X_valid) model.save_session() model.predict(X_test, 'pred.txt')
import numpy as np from model import LogisticRegression # load data x_train = np.load('./data/LR/train_data.npy')[:, 1:] y_train = np.load('./data/LR/train_target.npy') x_test = np.load('./data/LR/test_data.npy')[:, 1:] y_test = np.load('./data/LR/test_target.npy') # create an LR model and fit it lr = LogisticRegression(learning_rate=1, max_iter=10, fit_bias=True, optimizer='Newton', seed=0) lr.fit(x_train, y_train, val_data=(x_test, y_test)) # predict and calculate acc train_acc = lr.score(x_train, y_train, metric='acc') test_acc = lr.score(x_test, y_test, metric='acc') print("train acc = {0}".format(train_acc)) print("test acc = {0}".format(test_acc)) # plot learning curve and decision boundary lr.plot_learning_curve() lr.plot_boundary(x_train, y_train) lr.plot_boundary(x_test, y_test)
from mnist.data_prepration import create_data from model import LogisticRegression import numpy as np import matplotlib.pyplot as plt X_train, Y_train, X_test, Y_test= create_data(1,7) X_train = X_train.T/255 X_test = X_test.T/255 Y_test = Y_test.reshape(1, Y_test.shape[0]) Y_train = Y_train.reshape(1, Y_train.shape[0]) model = LogisticRegression() costs = model.fit(X_train, Y_train, 10000, 0.4) # Plot learning curve (with costs) costs = np.squeeze(costs) plt.plot(costs) plt.ylabel('cross entropy loss') plt.xlabel('iterations ') plt.title("Learning rate =" + str(0.4)) plt.show() accuracy_train,cost_train,prediction = model.evaluate(X_train, Y_train) accuracy_test, cost_test, prediction = model.evaluate(X_test, Y_test) print("accuracy on train set: " + str(accuracy_train)) print("cross entropy loss on train set: " + str(cost_train)) print("accuracy on test set: " + str(accuracy_test)) print("cross entropy loss on test set: " + str(cost_test)) #
print('Done') temp_X_train = np.concatenate((worm_images, noworm_images)) y_train = np.concatenate((worm_label, noworm_label)) print('Shuffling images and labels ...') X_data, y_data = shuffling_files(temp_X_train, y_train) print('spliting data .....') X_train, X_test = data_split(X_data) y_train, y_test = data_split(y_data) print('Done') X_train = X_train / 255 X_test = X_test / 255 model = LogisticRegression(lr=0.02, epochs=500, lamb=8) tic1 = time.time() model.fit(X_train, y_train) toc1 = time.time() tic2 = time.time() y_pred = model.predict(X_test) toc2 = time.time() y_pred = np.argmax(y_pred, axis=1) print('Training Time: {}'.format(toc1 - tic1)) print('Testing Time: {}'.format(toc2 - tic2)) print('acc_test: {}'.format(accuracy_score(y_test, y_pred))) plt.show()
from model import LogisticRegression from Titanic.dataPrepration import create_data train_x, train_y, test_x, test_y = create_data() #reshape train_x = train_x.T train_y = train_y.T test_x = test_x.T test_y = test_y.T model = LogisticRegression() model.fit(train_x, train_y, 20000, 0.2) accuracy_train, cost_train, prediction = model.evaluate(train_x, train_y) accuracy_test, cost_test, prediction = model.evaluate(test_x, test_y) print("accuracy on train set: " + str(accuracy_train)) print("cross entropy loss on train set: " + str(cost_train)) print("accuracy on test set: " + str(accuracy_test)) print("cross entropy loss on test set: " + str(cost_test))