def reportBestResult():
C = [16, 32, 64, 128, 256, 512]
bestAUC = 0
bestParam = 0
for c in C:
auc_history = load_np_array("results/ada_auc_" + str(c) + ".bin")
mean_auc = auc_history.mean()
if (mean_auc > bestAUC):
bestAUC = mean_auc
bestParam = c
print bestParam
confusion_matrix_history = load_np_array("results/rfc_folds_confusion_" +
str(c) + ".bin")
print confusion_matrix_history
mean_cm = np.mean(confusion_matrix_history, axis=2)
std_cm = np.std(confusion_matrix_history, axis=2)
# for i in range(0,2):
# for j in range(0,2):
# mean_cm[i][j] = confusion_matrix_history[i][j].mean()
print mean_cm
print std_cm
compute_performance_metrics(mean_cm)
acc_mean = []
recall_mean = []
for c in C:
accuracy_history = load_np_array("results/ada_accuracy_" + str(c) +
".bin")
recall_history = load_np_array("results/ada_recall_" + str(c) + ".bin")
acc_mean.append(accuracy_history.mean())
recall_mean.append(recall_history.mean())
# cost_history = clf.fit(homesite_data, batch_size = 128, \
# max_iterations = 100, save_interval = 10, \
# path = "classifiers_data/ann_weights.bin",
# return_cost = True)
#
# # Save cost and accuracy history
# save_np_array(cost_path, cost_history)
# # Test neural network.
# oversampled_path = "resources/oversampled_normalized_data_ratio_2.bin"
# homesite_data = Data()
# homesite_data.load_sliptted_data(oversampled_path, one_hot = True)
# clf = NeuralNetwork(path = "classifiers_data/ann_weights.bin", \
# lr = 0.005, lamb = 0.)
# prob_predicted_labels = clf.predict(homesite_data.validation_x)
# predicted_labels = np.argmax(prob_predicted_labels, axis = 1)
# validation_labels = np.argmax(homesite_data.validation_y, axis = 1)
#
# # Show final results.
# results = confusion_matrix(validation_labels, predicted_labels)
# accuracy, precision, recall = compute_performance_metrics(results)
# auc = compute_auc(validation_labels, prob_predicted_labels[:, 1])
# Save plot.
non_normalized_cost = load_np_array(
"results/ann_non_normalized_cost_history.bin")
normalized_cost = load_np_array("results/ann_normalized_cost_history.bin")
plot("results/normalization_vs_non_normalization.png", [normalized_cost, non_normalized_cost], \
["com normalizacao", "sem normalizacao"], "iteracoes", "custo", 'center right')
# recall_history.append(recall)
# auc_history.append(auc)
# balancing_rate = np.count_nonzero(homesite.train_y) * 1.0 / len(homesite.train_y)
# balancing_rate_history.append(balancing_rate)
#
# print 'Saving result.', i * 0.1
# save_np_array("../homesite_data/results/random_forest_balancing_accuracy.bin", np.array(accuracy_history))
# save_np_array("../homesite_data/results/random_forest_balancing_precision.bin", np.array(precision_history))
# save_np_array("../homesite_data/results/random_forest_balancing_recall.bin", np.array(recall_history))
# save_np_array("../homesite_data/results/random_forest_balancing_auc.bin", np.array(auc_history))
# save_np_array("../homesite_data/results/random_forest_balancing_rate.bin", np.array(balancing_rate_history))
#
# del homesite
# del clf
accuracy_history = load_np_array(
"../homesite_data/results/random_forest_balancing_accuracy.bin")
precision_history = load_np_array(
"../homesite_data/results/random_forest_balancing_precision.bin")
recall_history = load_np_array(
"../homesite_data/results/random_forest_balancing_recall.bin")
auc_history = load_np_array(
"../homesite_data/results/random_forest_balancing_auc.bin")
balancing_rate_history = load_np_array(
"../homesite_data/results/random_forest_balancing_rate.bin")
# for accuracy, precision, recall, auc, balancing_rate in zip(accuracy_history, precision_history, recall_history, auc_history, balancing_rate_history):
# print accuracy, precision, recall, auc, balancing_rate
plot("../homesite_data/results/random_forest_balacing.png", [recall_history, auc_history], \
["sensitividade ", "AUC"], "taxa de balanceamento", "metricas", 'center right', \
#
# # Plot results.
# accuracy_history = load_np_array("../homesite_data/results/random_forest_grid_search_accuracy.bin")
# precision_history = load_np_array("../homesite_data/results/random_forest_grid_search_precision.bin")
# recall_history = load_np_array("../homesite_data/results/random_forest_grid_search_recall.bin")
# auc_history = load_np_array("../homesite_data/results/random_forest_grid_search_auc.bin")
#
# for accuracy, precision, recall, auc in zip(accuracy_history, precision_history, recall_history, auc_history):
# print accuracy, precision, recall, auc
#
# plot("../homesite_data/results/random_forest_grid_search.png", [recall_history, auc_history], \
# ["sensitividade ", "AUC"], "numero de arvores", "metricas", 'center right', \
# x = np.linspace(1, len(recall_history) * 10, num = len(recall_history), endpoint = True))
#
c = 300
accuracy_history = load_np_array("results/random_forests/rf_accuracy_" + str(c) + ".bin")
precision_history = load_np_array("results/random_forests/rf_precision_" + str(c) + ".bin")
recall_history = load_np_array("results/random_forests/rf_recall_" + str(c) + ".bin")
auc_history = load_np_array("results/random_forests/rf_auc_" + str(c) + ".bin")
confusion_matrix_history = load_np_array("results/random_forests/rf_confusion_matrix_" + str(c) + ".bin")
# Show confusion matrix for best c.
confusion_matrix_mean = np.zeros(4)
confusion_matrix_std = np.zeros(4)
confusion_matrix_mean[0] = np.mean(confusion_matrix_history[0, 0, :] * 100.0 / (confusion_matrix_history[0, 0, :] + confusion_matrix_history[0, 1, :]))
confusion_matrix_mean[1] = np.mean(confusion_matrix_history[0, 1, :] * 100.0 / (confusion_matrix_history[0, 0, :] + confusion_matrix_history[0, 1, :]))
confusion_matrix_mean[2] = np.mean(confusion_matrix_history[1, 0, :] * 100.0 / (confusion_matrix_history[1, 0, :] + confusion_matrix_history[1, 1, :]))
confusion_matrix_mean[3] = np.mean(confusion_matrix_history[1, 1, :] * 100.0 / (confusion_matrix_history[1, 0, :] + confusion_matrix_history[1, 1, :]))
confusion_matrix_std[0] = np.std(confusion_matrix_history[0, 0, :] * 100.0 / (confusion_matrix_history[0, 0, :] + confusion_matrix_history[0, 1, :]))
confusion_matrix_std[1] = np.std(confusion_matrix_history[0, 1, :] * 100.0 / (confusion_matrix_history[0, 0, :] + confusion_matrix_history[0, 1, :]))
confusion_matrix_std[2] = np.std(confusion_matrix_history[1, 0, :] * 100.0 / (confusion_matrix_history[1, 0, :] + confusion_matrix_history[1, 1, :]))
# # Plot results.
# accuracy_history = load_np_array("../homesite_data/results/random_forest_grid_search_accuracy.bin")
# precision_history = load_np_array("../homesite_data/results/random_forest_grid_search_precision.bin")
# recall_history = load_np_array("../homesite_data/results/random_forest_grid_search_recall.bin")
# auc_history = load_np_array("../homesite_data/results/random_forest_grid_search_auc.bin")
#
# for accuracy, precision, recall, auc in zip(accuracy_history, precision_history, recall_history, auc_history):
# print accuracy, precision, recall, auc
#
# plot("../homesite_data/results/random_forest_grid_search.png", [recall_history, auc_history], \
# ["sensitividade ", "AUC"], "numero de arvores", "metricas", 'center right', \
# x = np.linspace(1, len(recall_history) * 10, num = len(recall_history), endpoint = True))
c = 50
accuracy_history = load_np_array("results/ann/ann_accuracy_" + str(c) + ".bin")
precision_history = load_np_array("results/ann/ann_precision_" + str(c) +
".bin")
recall_history = load_np_array("results/ann/ann_recall_" + str(c) + ".bin")
auc_history = load_np_array("results/ann/ann_auc_" + str(c) + ".bin")
confusion_matrix_history = load_np_array("results/ann/ann_confusion_matrix_" +
str(c) + ".bin")
# Show confusion matrix for best c.
confusion_matrix_mean = np.zeros(4)
confusion_matrix_std = np.zeros(4)
confusion_matrix_mean[0] = np.mean(
confusion_matrix_history[0, 0, :] * 100.0 /
(confusion_matrix_history[0, 0, :] + confusion_matrix_history[0, 1, :]))
confusion_matrix_mean[1] = np.mean(
confusion_matrix_history[0, 1, :] * 100.0 /
'''
Created on 30/11/2015
@author: Alexandre Yukio Yamashita
'''
from data.numpy_file import load_np_array
import numpy as np
from data.plot import plot
# Plot grid search.
C = [16, 32, 64, 128, 256, 512]
auc = []
recall = []
for c in C:
recall_history = load_np_array("results/adaboost/ada_recall_" + str(c) + ".bin")
recall_history = recall_history[len(recall_history) - 5:]
accuracy_history = load_np_array("results/adaboost/ada_accuracy_" + str(c) + ".bin")
accuracy_history = recall_history[len(accuracy_history) - 5:]
precision_history = load_np_array("results/adaboost/ada_precision_" + str(c) + ".bin")
precision_history = precision_history[len(precision_history) - 5:]
auc_history = load_np_array("results/adaboost/ada_auc_" + str(c) + ".bin")
auc_history = auc_history[len(auc_history) - 5:]
auc.append(np.mean(auc_history))
recall.append(np.mean(recall_history))
recall = np.array(recall)
auc = np.array(auc)
plot("results/adaboost/adaboost_grid_search.png", [recall, auc], \
["sensitividade ", "AUC"], "numero de estimadores", "metricas", 'center right', \