labels = []
unencoded_data = []
for line in text.splitlines():
splitted = line.split(",")
assert(len(splitted) == 35)
missing_val = False
for attr in splitted:
if attr == '?':
missing_val = True
break
if missing_val:
continue
labels.append(int(splitted[34]))
unencoded_data.append(splitted[:34])
data = enc.fit_transform(unencoded_data).toarray()
print(data.shape)
return (data, np.array(labels))
if __name__ == "__main__":
(data, labels) = parse_dermatology("../data/dermatology/dermatology.data")
print(data[:10])
print(labels[:10])
(train_data, train_labels, test_data, test_labels) = utils.split_train_test(data, labels)
utils.save_protobuf(train_data, train_labels, "dermatology_train")
utils.save_protobuf(test_data, test_labels, "dermatology_test")
dst_host_serror_rate: continuous.
dst_host_srv_serror_rate: continuous.
dst_host_rerror_rate: continuous.
dst_host_srv_rerror_rate: continuous.
"""
def parse_kddcup(fp):
all_cols = []
numeric_cols = []
nominal_cols = []
label_col = ['label']
for line in raw_name.splitlines()[1:]:
col = line.split(":")[0]
col_type = line.split(":")[1][1:-1]
if (col_type == 'continuous'):
numeric_cols.append(col)
elif (col_type == 'symbolic'):
nominal_cols.append(col)
else:
assert(False)
all_cols.append(col)
df = pandas.read_csv(fp, names=all_cols+label_col)
return utils.parse_data_with_pandas(df, [], numeric_cols, label_col, nominal_cols)
if __name__ == "__main__":
data, labels = parse_kddcup("../data/kddcup/kddcup.data_10_percent")
(train_data, train_labels, test_data, test_labels) = utils.split_train_test(data, labels, 0.1)
utils.save_protobuf(train_data, train_labels, "kddcup_train")
utils.save_protobuf(test_data, test_labels, "kddcup_test")
num_correct += torch.sum(torch.eq(preds, genders_batch))
total += preds.size(0)
epoch_end = time.time()
print("Epoch %d took %s" %
(epoch, utils.sec2str(int(epoch_end - epoch_start))))
print("acc: ", float(num_correct) / float(total))
end = time.time()
print(utils.sec2str(int(end - start)))
if __name__ == "__main__":
device = "cuda:0"
with torch.no_grad():
# vgg16 = load_face_model("../../caffemodel2pytorch/gender.caffemodel.pt").to(device)
vgg16 = torchvision.models.vgg16(pretrained=True)
vgg16 = expose_last_fc(vgg16).to(device)
# evaluate_model(128, 10000, device)
data, labels = get_features(128, 1024, vgg16, device)
# normalize each feature to be [0,1)
data = data - data.min(dim=0)[0]
data = data / (data.max(dim=0)[0] + 1e-6)
data = data.to('cpu').numpy()
labels = labels.to('cpu').numpy()
(train_data, train_labels, test_data,
test_labels) = utils.split_train_test(data, labels, 0.1)
utils.save_protobuf(train_data, train_labels, "imdb_train")
utils.save_protobuf(test_data, test_labels, "imdb_test")
'priority': 3,
'spec_prior': 4,
}
def parse_nursery(fp):
with open(fp) as f:
text = f.read()
enc = OneHotEncoder(handle_unknown='error')
unencoded_data = []
labels = []
for line in text.splitlines():
splitted = line.split(",")
assert(len(splitted) == 9)
unencoded_data.append(splitted[:-1])
labels.append(label_map[splitted[8]])
data = enc.fit_transform(unencoded_data).toarray()
assert(data.shape == (len(labels), 3+5+4+4+3+2+3+3))
return (data, np.array(labels))
if __name__ == '__main__':
(data, labels) = parse_nursery('../data/nursery/nursery.data')
print(data[:10])
print(labels[:10])
(train_data, train_labels, test_data, test_labels) = utils.split_train_test(data, labels)
utils.save_protobuf(train_data, train_labels, "nursery_train")
utils.save_protobuf(test_data, test_labels, "nursery_test")
import pandas
import utils
import numpy as np
def parse_creditcard(fp):
df = pandas.read_excel(fp, sheet_name='Data')
df = df[1:]
drop_cols = []
numeric_cols = ["X%d" % i for i in range(1, 24)]
label_col = ["Y"]
return utils.parse_data_with_pandas(df, drop_cols, numeric_cols, label_col,
[])
if __name__ == "__main__":
data, labels = parse_creditcard('../data/creditcard/creditcard.xls')
(train_data, train_labels, test_data,
test_labels) = utils.split_train_test(data, labels)
utils.save_protobuf(train_data, train_labels, "creditcard_train")
utils.save_protobuf(test_data, test_labels, "creditcard_test")
import utils
import numpy as np
import struct
def parse_images(fp):
with open(fp, "rb") as f:
magic, size = struct.unpack(">II", f.read(8))
nrows, ncols = struct.unpack(">II", f.read(8))
data = np.fromfile(f, dtype=np.dtype(np.uint8).newbyteorder(">"))
data = data.reshape((size, nrows * ncols)).astype(float)
return data
def parse_labels(fp):
with open(fp, "rb") as f:
magic, size = struct.unpack(">II", f.read(8))
data = np.fromfile(f, dtype=np.dtype(
np.uint8).newbyteorder(">")).astype(int)
return data
if __name__ == "__main__":
train_data = parse_images("../raw_data/mnist/mnist500k-patterns")
train_labels = parse_labels("../raw_data/mnist/mnist500k-labels")
utils.save_protobuf(train_data, train_labels, "mnist500k_train")
# test_data = parse_images("../data/mnist/test10k-patterns")
# test_labels = parse_labels("../data/mnist/test10k-labels")
# utils.save_protobuf(test_data, test_labels, "mnist60k_test")
df = df.drop(drop_cols, axis=1)
numeric_df = df[numeric_cols]
label_df = df[label_col]
nominal_df = df.drop(numeric_cols + label_col, axis=1)
numeric = np.array(numeric_df.as_matrix())
nominal = OneHotEncoder().fit_transform(nominal_df.as_matrix()).toarray()
labels = np.array(LabelEncoder().fit_transform(label_df.as_matrix().ravel()))
# first 8 columns are numeric, and the rest are nominal for total of 155 columns
# 0: 1-14
# 1: 0-6
# 2: 1-132
# 3: 1-81
# 4: 0-42
# 5: 0-76
# 6: 0-21
# 7: 1-16
data = np.concatenate((numeric, nominal), axis=1)
print("data shape: ", data.shape)
print("labels shape: ", labels.shape)
return data, labels
if __name__ == "__main__":
data, labels = parse_diabetes('../data/diabetes/diabetic_data.csv')
(train_data, train_labels, test_data, test_labels) = utils.split_train_test(data, labels)
utils.save_protobuf(train_data, train_labels, "diabetes_train")
utils.save_protobuf(test_data, test_labels, "diabetes_test")
