def grow_decision_tree(df_train, df_test, var_list, output_var):
trees, accuracies = [], []
alpha = 0
root_node_unpruned = grow_unpruned_tree(df_train, var_list, output_var)
cond = True
while cond:
root_node = copy.deepcopy(root_node_unpruned)
prune(root_node, df_train, var_list, output_var, df_test, root_node,
alpha)
acc = test_accuracy(root_node, df_train, var_list, output_var, df_test)
trees.append(root_node)
accuracies.append(acc)
if root_node.left == None and root_node.right == None:
break
alpha += 0.02
final_model = trees[accuracies.index(max(accuracies))]
return final_model
test_result_11_400 = functions.extract_values(
shp=file_test11_shp,
raster='/Volumes/ga87rif/Study Project/Result/New/A_result_09_100.tif')
np.save('/Volumes/ga87rif/Study Project/Samples/A_test_result_11_400.npy',
test_result_11_400)
test_result_11_500 = functions.extract_values(
shp=file_test11_shp,
raster='/Volumes/ga87rif/Study Project/Result/New/A_result_09_100.tif')
np.save('/Volumes/ga87rif/Study Project/Samples/A_test_result_11_500.npy',
test_result_11_500)
#-----------------------------------------------------------------------------------------------
# calculate accuracy
functions.test_accuracy(year=2009,
trees=100,
test_array=test_result_09_100,
gt_test_array=test09)
functions.test_accuracy(year=2009,
trees=200,
test_array=test_result_09_100,
gt_test_array=test09)
functions.test_accuracy(year=2009,
trees=300,
test_array=test_result_09_100,
gt_test_array=test09)
functions.test_accuracy(year=2009,
trees=400,
test_array=test_result_09_100,
gt_test_array=test09)
functions.test_accuracy(year=2009,
trees=500,
model = models.vgg11()
# 5. Build Custom Classifier
from collections import OrderedDict
classifier = nn.Sequential(
OrderedDict([('fc1', nn.Linear(25088, 5000)), ('relu', nn.ReLU()),
('drop', nn.Dropout(p=0.5)), ('fc2', nn.Linear(5000, 3)),
('output', nn.LogSoftmax(dim=1))]))
model.classifier = classifier
# 6. Loss function and gradient descent
criterion = nn.NLLLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
# 7. model training
model = functions.train_classifier(model, train_loader, validate_loader,
optimizer, criterion)
# 8. test accuracy
functions.test_accuracy(model, test_loader)
# 9. model save
model_save_path = r"C:/Users/LG/Desktop/ksb/3. CODE/model/"
filename = 'sepa_image_classifier2.pth'
functions.save_checkpoint(model, training_dataset, model_save_path, filename)
from functions import test_accuracy, convert_csv_to_Q
# load a.i.
file_path = 'pickled_brain3.csv'
Q = convert_csv_to_Q(file_path)
# test
print("Begin testing.")
number_of_games_per_unit_test = 10000
test_accuracy(number_of_games_per_unit_test, Q)
print("Done testing.\n")
