#from sklearn.model_selection import train_test_split
#from sklearn.metrics import precision_recall_curve,precision_recall_fscore_support,accuracy_score
from podaci.guosen.data import get_stock_features
col_names = ['b', 'c', 'u', 'l', 'ol', 'cl', 'ac']
for stk in target_universe_list:
try:
start_time = time.time()
label = pd.read_hdf(os.path.join(train_data_path, 'label.h5'),
stk.encode('utf8'))
label.loc[:, 'label'].loc[label['label'] == 2] = 1
# feeatures
features = get_stock_features('20050101', '20180831', [stk])
features = features.sort_values('trade_date', ascending=True)
for i in range(1, 181):
for col in col_names:
features['%s_%s' % (col, i)] = features[col].shift(i)
features.dropna(inplace=True)
features.drop(col_names, axis=1, inplace=True)
# combine and get train&test data
comb = label.join(features.set_index('trade_date').drop('stock_code',
axis=1),
on='trade_date')
comb = comb.drop(['stock_code'], axis=1)
#%% 模型训练
from sklearn.neural_network import MLPClassifier
from sklearn.externals import joblib
from podaci.guosen.data import get_stock_features
col_names = ['b', 'c', 'u', 'l', 'ol', 'cl', 'ac']
for stk in target_universe_list:
try:
start_time = time.time()
label = pd.read_hdf(os.path.join(train_data_path, stk + '.h5'),
'label')
label['label'].loc[label['label'] == 2] = 1
# feeatures
features = get_stock_features('20150801', '20180831', [stk])
features = features.sort_values('trade_date', ascending=True)
for i in range(1, 31):
for col in col_names:
features['%s_%s' % (col, i)] = features[col].shift(i)
features.dropna(inplace=True)
features.drop(col_names, axis=1, inplace=True)
# combine and get train&test data
comb = label.join(features.set_index('trade_date').drop('stock_code',
axis=1),
on='trade_date')
comb = comb.drop(['stock_code'], axis=1)
for i in range(1,30):
for col in col_names:
stock_features['%s_%s'%(col,i)] = stock_features[col].shift(i)
stock_features.dropna(inplace = True)
stock_features = trade_calendar.join(stock_features.set_index('trade_date'),on = 'trade_date',
how = 'left')
stock_features['target_date'] = stock_features['trade_date'].shift(-1)
stock_features.dropna(inplace = True)
target_date_list = stock_features['target_date'].tolist()
X = stock_features.drop(['trade_date','stock_code','target_date'],axis = 1).values
if len(X) < 1:
# 样本数据宽度数量不足扩大取数据的宽度
stock_features = get_stock_features(start_date = '20100101',end_date = today_str,
stock_universe = [stk])
stock_features = stock_features.sort_values('trade_date',ascending = True)
for i in range(1,30):
for col in col_names:
stock_features['%s_%s'%(col,i)] = stock_features[col].shift(i)
stock_features.dropna(inplace = True)
stock_features = trade_calendar.join(stock_features.set_index('trade_date'),on = 'trade_date',
how = 'left')
stock_features['target_date'] = stock_features['trade_date'].shift(-1)
stock_features.dropna(inplace = True)
target_date_list = stock_features['target_date'].tolist()
X = stock_features.drop(['trade_date','stock_code','target_date'],axis = 1).values
if len(X) < 1:
continue # 放弃更新此股票信号