def generate_sample_data():
dates = pd.date_range(start="2008-01-01", end="2008-01-30")
for index, date in enumerate(dates):
stock = Stock()
stock.code = "T9999"
stock.date = date
stock.open = index
stock.high = index + 1
stock.low = index - 0.5
stock.close = index + 1
stock.volume = 100
stock.save_if_need()
for index, date in enumerate(dates[::-1]):
stock = Stock()
stock.code = "T9998"
stock.date = date
stock.open = index
stock.high = index + 1
stock.low = index - 0.5
stock.close = index + 1
stock.volume = 100
stock.save_if_need()
def crawl(self):
stock_frame = ts.get_k_data(code=self.code,
start=self.start,
end=self.end,
retry_count=30)
for index in stock_frame.index:
stock_series = stock_frame.loc[index]
stock_dict = stock_series.to_dict()
stock = Stock(**stock_dict)
stock.save_if_need()
logging.warning("Finish crawling code: {}, items count: {}".format(
self.code, stock_frame.shape[0]))
def crawl(self):
stock_frame = ts.get_k_data(code=self.code,
start=self.start,
end=self.end,
retry_count=30)
for index in stock_frame.index: # stock_index是从0到length(stock_frame)的整数
stock_series = stock_frame.loc[index] # 某一行的数据
stock_dict = stock_series.to_dict(
) # pandas提供的字典化方法, 返回{"date":"2018-08-01","open":5234,"close":5272,"high":5298,"volume":7665600,"code":"sh"}
stock = Stock(**stock_dict) # 将字典的键和Stock类中各个字段对应起来进行组装
stock.save_if_need() # 储存进数据库
logging.warning("Finish crawling code: {}, items count: {}".format(
self.code, stock_frame.shape[0]))
class LSTMAlgorithm(BaseAlgorithm):
def __init__(self, params):
super(LSTMAlgorithm, self).__init__(params)
def init_model(self):
self.model.add(LSTM(10, input_dim=self.params.get('input_dim'), return_sequences=True))
self.model.add(TimeDistributed(Dense(1)))
self.model.compile(loss="mse", optimizer="adam")
self.model.summary()
return self.model
def run(self, x, y):
return self.model.fit(x, y, epochs=1000, batch_size=128)
def to_scale(data):
scale = MinMaxScaler()
scale.fit(data)
return scale.transform(data)
if __name__ == '__main__':
doc_class = Stock()
data_docs = doc_class.get_k_data('600036', '2017-01-01', '2018-01-01')
data_dicts = [row.to_dict() for row in data_docs]
data = [row[2:] for row in data_dicts]
x = to_scale(data)
y = x[4][2:]
algorithm = LSTMAlgorithm({'input_dim': 5})