def run_forest(n_trees=400, n_features_per_tree=70, n_rows_power=0.5):
start_time = time.time()
forest = RandomForest(trainset, labels, n_trees, n_features_per_tree, n_rows_power)
forest.train()
score = []
for test, (i, bm) in zip(testset, benchmarkset):
result = forest.classify(test)
result = result.most_common(1)[0][0]
print('{:.1f}s -- No.{} should be: <{}> cal: {}'.format(time.time()-start_time, i, bm, result))
if result == bm:
score.append('+')
else:
score.append('-')
with open('result_by_self_train[28000].csv', 'a') as f:
f.write('{},{},<{}>\n'.format(i, result, bm))
# print('classify done {}, {:.1%}'.format(Counter(score), Counter(score)['+'] / len(score)))
return Counter(score)['+'] / len(score)
def run_forest(n_trees=400, n_features_per_tree=70, n_rows_power=0.5):
start_time = time.time()
forest = RandomForest(trainset, labels, n_trees, n_features_per_tree,
n_rows_power)
forest.train()
score = []
for test, (i, bm) in zip(testset, benchmarkset):
result = forest.classify(test)
result = result.most_common(1)[0][0]
print('{:.1f}s -- No.{} should be: <{}> cal: {}'.format(
time.time() - start_time, i, bm, result))
if result == bm:
score.append('+')
else:
score.append('-')
with open('result_by_self_train[28000].csv', 'a') as f:
f.write('{},{},<{}>\n'.format(i, result, bm))
# print('classify done {}, {:.1%}'.format(Counter(score), Counter(score)['+'] / len(score)))
return Counter(score)['+'] / len(score)
def use_random_forest(data):
'''
Trains and predicts using a random forest on a data set.
'''
n_trees = input("How many decision trees would you like to use in your " +\
"random forest?\nUse 1 for a decision tree\n> ")
while not n_trees.isdigit() or int(n_trees) < 1:
print("Please enter an integer greater than 1...")
n_trees = input("> ")
print()
if data == "1": # use cifar
# Get training data
n_files = input(
"How many file batches would you like to use?\nThere are 5.\n> ")
while not n_files.isdigit() or int(n_files) < 1 or int(n_files) > 5:
print("Please enter an integer between 1 and 5...")
n_files = input("> ")
print()
n_files = int(n_files)
n_images = input(
"How many images would you like from each file?\nThere are 10000 images in each file.\n> "
)
while not n_images.isdigit() or int(n_images) < 1 or int(
n_images) > 10000:
print("Please enter an integer between 1 and 10000...")
n_images = input("> ")
print()
n_images = int(n_images)
training_data = aggregate_cifar(n_files=n_files, n_images=n_images)
# Get test data
test_data, test_labels = unpickle("cifar-10-batches-py/test_batch",
n_images=10)
test_full = np.array([np.append(test_data[0], test_labels[0])])
for i in range(1, len(test_labels)):
test_full = np.vstack(
(test_full, np.append(test_data[i], test_labels[i])))
else: # use csgo
n_data = input(
"How many rows of data would you like to use for training and testing? 955466 rows available.\n80% will be used for training, 20% for testing\n> "
)
while not n_data.isdigit() or int(n_data) < 1 or int(n_data) > 955466:
print("Please enter an integer between 1 and 955466...")
n_data = input("> ")
print()
n_data = int(n_data)
full_data = load_csgo(False)
full_data = full_data.values
full_data = full_data[:n_data]
#splits dataset into training and test
training_data = full_data[:int((len(full_data) + 1) * .80)]
test_full = full_data[int(len(full_data) * .80 + 1):]
print("Done unpacking CS:GO data...")
start_time = time.time()
rf = RandomForest(training_data, n_trees) # create and train random forest
print("Training time: " + str(time.time() - start_time) + " seconds")
pass_count = 0
fail_count = 0
print("Classifying test data...")
for row in test_full:
res = rf.classify(row, label=True)
print("Predicted: " + str(res) + "\tActual: " + str(row[-1]))
if res == row[-1]:
pass_count += 1
else:
fail_count += 1
# Report results
print("Correct classifications: " + str(pass_count))
print("Wrong classifications: " + str(fail_count))
print("Accuracy: " +
str(float(pass_count) * 100 / (pass_count + fail_count)) + "%")