def load_features():
# 待预测订单的数据 （原始训练集和测试集）
train = pd.read_csv(Configure.train_data_file, encoding='utf8')
test = pd.read_csv(Configure.test_data_file, encoding='utf8')
train['id'] = np.arange(train.shape[0])
test['id'] = np.arange(test.shape[0])
# 加载特征， 并合并
features_merged_dict = Configure.features
for feature_name in Configure.features:
print 'merge features:', feature_name
train_feature, test_feature = data_utils.load_features(feature_name)
if 'label' in train_feature.columns:
del train_feature['label']
train = pd.merge(train, train_feature,
on=features_merged_dict[feature_name]['on'],
how=features_merged_dict[feature_name]['how'])
test = pd.merge(test, test_feature,
on=features_merged_dict[feature_name]['on'],
how=features_merged_dict[feature_name]['how'])
train.fillna(0, inplace=True)
test.fillna(0, inplace=True)
train.drop(['id', 'q1', 'q2', 'q1_words', 'q1_chars', 'q2_words', 'q2_chars', 'label'], axis=1, inplace=True)
test.drop(['id', 'q1', 'q2', 'q1_words', 'q1_chars', 'q2_words', 'q2_chars',], axis=1, inplace=True)
return train, test
n_classes = 5
classNames = {0: 'Disc', 1: 'Spiral', 2: 'Elliptical', 3: 'Round', 4: 'Other'}
handler = data_utils.data_handler(data_dir_path,
sample_fractions=sample_fractions,
input_size=input_size,
labels_type='classes',
output_size=output_size,
normalize_input=False,
create_samples_bool=False,
preprocess_bool=False,
crp_factor=2,
ds_factor=3)
### Load data
X_train, y_train = data_utils.load_features(handler, 'training')
X_val, y_val = data_utils.load_features(handler, 'validation')
### Train an one vs. all Logistic Regression model
param_grid = {"n_neighbors": np.arange(1, 31, 2)}
knn = KNeighborsClassifier(metric="euclidean")
clf = GridSearchCV(estimator=knn, param_grid=param_grid, cv=10)
t0 = time()
clf = clf.fit(X_train, y_train)
print("done in %0.3fs" % (time() - t0))
print(clf.best_estimator_)
acc_score = [x[1] for x in clf.grid_scores_]
parser.add_argument('--test',
type=float,
help='Percentage (or number) of test instances.',
required=True)
parser.add_argument('--seed',
type=int,
help='PRNG seed (default: 0).',
required=False,
default=0)
parser.add_argument('--out',
type=str,
help='Output file (.json).',
required=True)
args = parser.parse_args()
X, Y, _, Npages, Nloads = load_features(args.features)
log('Seed is {}'.format(args.seed))
n = len(X)
# Get training/test set size
if args.train > 1:
train_size = int(args.train)
else:
train_size = int(args.train * n)
if args.test > 1:
test_size = int(args.test)
else:
test_size = int(args.test * n)
log('Training set size: {}. Test set size: {}.'.format(