def init(self, context):
# super(GrahamDefender, self).init(context)
# context.pool = list(stock_pool_dao.get_list()['code'].values)
context.pool = list(stock_pool_dao.get_list()['code'].values)
self.context = context
def predict_k_data():
df = stock_pool_dao.get_list()
df_index = index_k_data_dao.get_rel_price()
for code in df['code'].values:
try:
logger.debug('begin predict, code:%s' % code)
data, features = k_data_dao.get_k_predict_data_with_features(
code, df_index)
lr = LogisticRegressionClassifier()
svc = SupportVectorClassifier()
rf = RandomForestClassifierModel()
xgb = XGBoostClassier()
#ann = SequantialNeuralClassifier()
lr_pred = lr.predict(code, data[features])
svc_pred = svc.predict(code, data[features])
rf_pred = rf.predict(code, data[features])
xgb_pred = xgb.predict(code, data[features])
#ann_pred = ann.predict(code, data[features])
k_data_predict_log_dao.insert(code,
logistic_regression=lr_pred,
support_vector_classifier=svc_pred,
random_forest_classifier=rf_pred,
xgb_classifier=xgb_pred,
sequantial_neural=0)
logger.debug('predict end, code:%s' % code)
except Exception as e:
logger.error("predict k data error, code:%s, error:%s" %
(code, repr(e)))
def training_k_data(start, end):
df = stock_pool_dao.get_list()
codes = df['code'].values[start:end]
for code in codes:
try:
logger.debug('begin training mode, code:%s' % code)
data, features = k_data_dao.get_k_data_with_features(
code, '2015-01-01',
datetime.now().strftime("%Y-%m-%d"))
pca = PCAModel('k_data')
lr = LogisticRegressionClassifier()
svc = SupportVectorClassifier()
rf = RandomForestClassifierModel()
xgb = XGBoostClassier()
#ann = SequantialNeuralClassifier()
pca.training_model(code, data, features)
lr.training_model(code, data, features)
svc.training_model(code, data, features)
rf.training_model(code, data, features)
xgb.training_model(code, data, features)
#ann.training_model(code, data, features)
logger.debug('training mode end, code:%s' % code)
except Exception as e:
logger.error("training k data error, code:%s, error:%s" %
(code, repr(e)))
def code_muning():
code_list = stock_pool_dao.get_list().values.tolist()
# code_list = ['a', 'b', 'c', 'd', 'e']
lenth = len(code_list) - 1
pair_sets = []
for i in range(0, lenth, 1):
for j in range(lenth, 0, -1):
if i == j or j < i:
continue
code1 = code_list[i][0]
code2 = code_list[j][0]
pair_sets.append((code1, code2))
# print(pair_sets)
# print(len(pair_sets))
return pair_sets
def cal_stock_pool():
df_poll = stock_pool_dao.get_list()
code_list = list(df_poll['code'].values)
w_data_list = k_data_weekly_dao.get_multiple_k_data(code_list,
start='2013-01-01',
end=get_current_date())
k_data_list = k_data_dao.get_multiple_k_data(code_list=code_list,
start=get_next_date(-720),
end=get_current_date())
# k_data_list = k_data_list.set_index('code', inplace=True)
# k_data_list = k_data_dao.get_market_snapshot(code_list=code_list, futu_quote_ctx=futu_quote_ctx)
matched = []
for code in code_list:
rs = cal_single_stock(code, k_data_list, w_data_list)
if rs is True:
matched.append(code)
print("matched:%s" % matched)
def test_get_list(self):
df = stock_pool_dao.get_list()
print(df)
ma10 = data['ma10'].values[-1]
ma5 = data['ma5'].values[-1]
if price < ma5:
return None, None, None
if price < 4:
return None, None, None
label, k, d = cal_signal(data)
return label, k, d
if __name__ == '__main__':
df_pool = stock_pool_dao.get_list()
data = pd.DataFrame(columns=[
'code', 'date', 'name', 'bk_code', 'bk_name', 'k', 'd', 'label'
])
list = []
for index, row in df_pool.iterrows():
code = row['code']
logger.debug("execute code:%s" % code)
try:
label, k, d = cal_single_stock(code)
if label is None:
continue
def init(self, context):
super(KDJStrategy, self).init(context)
context.pool = stock_pool_dao.get_list()['code'].values
self.context = context
