machine_learn/stock/dnn_predict_dmi_everyday.py

# -*- encoding:utf-8 -*-
import numpy as np
from keras.models import load_model
import joblib


holder_stock_list = [
                     '000063.SZ',
                     '002796.SZ',
                     '002373.SZ',
                     '300253.SZ',
                     '300059.SZ',
                    # b账户
                     '002373.SZ',
                     '300422.SZ',
    ]


def read_data(path):
    lines = []
    with open(path) as f:
        for line in f.readlines()[:]:
            line = eval(line.strip())
            if line[-2][0].startswith('0') or line[-2][0].startswith('3'):
                lines.append(line)

    size = len(lines[0])
    train_x=[s[:size - 2] for s in lines]
    train_y=[s[size-1] for s in lines]
    return np.array(train_x),np.array(train_y),lines


import pymongo
from util.mongodb import get_mongo_table_instance
code_table = get_mongo_table_instance('tushare_code')
k_table = get_mongo_table_instance('stock_day_k')
stock_concept_table = get_mongo_table_instance('tushare_concept_detail')
all_concept_code_list = list(get_mongo_table_instance('tushare_concept').find({}))


industry = ['家用电器', '元器件', 'IT设备', '汽车服务',
            '汽车配件', '软件服务',
            '互联网', '纺织',
            '塑料', '半导体',]

A_concept_code_list = [   'TS2', # 5G
                        'TS24', # OLED
                        'TS26', #健康中国
                        'TS43',  #新能源整车
                        'TS59', # 特斯拉
                        'TS65', #汽车整车
                        'TS142', # 物联网
                        'TS153', # 无人驾驶
                        'TS163', # 雄安板块-智慧城市
                        'TS175', # 工业自动化
                        'TS232', # 新能源汽车
                        'TS254', # 人工智能
                        'TS258', # 互联网医疗
                        'TS264', # 工业互联网
                        'TS266', # 半导体
                        'TS269', # 智慧城市
                        'TS271', # 3D玻璃
                        'TS295', # 国产芯片
                        'TS303', # 医疗信息化
                        'TS323', # 充电桩
                        'TS328', # 虹膜识别
                        'TS361', # 病毒
    ]


gainian_map = {}
hangye_map = {}

def predict_today(day, model='10_18d', log=True):
    lines = []
    with open('D:\\data\\quantization\\stock' + model + '_' +  str(day) +'.log') as f:
        for line in f.readlines()[:]:
            line = eval(line.strip())
            # if line[-1][0].startswith('0') or line[-1][0].startswith('3'):
            lines.append(line)

    size = len(lines[0])
    train_x=[s[:size - 1] for s in lines]
    np.array(train_x)

    estimator = joblib.load('km_dmi_18.pkl')

    models = []
    for x in range(0, 12):
        models.append(load_model(model + '_dnn_seq_' + str(x) + '.h5'))

    x = 24 # 每条数据项数
    k = 18 # 周期
    for line in lines:
        # print(line)
        v = line[1:x*k + 1]
        v = np.array(v)
        v = v.reshape(k, x)
        v = v[:,4:8]
        v = v.reshape(1, 4*k)
        # print(v)
        r = estimator.predict(v)

        train_x = np.array([line[:size - 1]])

        result = models[r[0]].predict(train_x)
        # print(result, line[-1])
        stock = code_table.find_one({'ts_code':line[-1][0]})

        if result[0][0] > 0.6 or result[0][1] > 0.6:
            if line[-1][0].startswith('688'):
                continue
            # 去掉ST
            if stock['name'].startswith('ST') or stock['name'].startswith('N') or stock['name'].startswith('*'):
                continue

            if stock['ts_code'] in holder_stock_list:
                print(stock['ts_code'], stock['name'], '维持买入评级')

            # 跌的
            k_table_list = list(k_table.find({'code':line[-1][0], 'tradeDate':{'$lte':day}}).sort("tradeDate", pymongo.DESCENDING).limit(5))
            # if k_table_list[0]['close'] > k_table_list[-1]['close']*1.20:
            #     continue
            # if k_table_list[0]['close'] < k_table_list[-1]['close']*0.90:
            #     continue
            # if k_table_list[-1]['close'] > 80:
            #     continue

            # 指定某几个行业
            # if stock['industry'] in industry:
            concept_code_list = list(stock_concept_table.find({'ts_code':stock['ts_code']}))
            concept_detail_list = []

            # 处理行业
            if stock['industry'] in hangye_map:
                i_c = hangye_map[stock['industry']]
                hangye_map[stock['industry']] = i_c + 1
            else:
                hangye_map[stock['industry']] = 1

            if len(concept_code_list) > 0:
                for concept in concept_code_list:
                    for c in all_concept_code_list:
                        if c['code'] == concept['concept_code']:
                            concept_detail_list.append(c['name'])

                            if c['name'] in gainian_map:
                                g_c = gainian_map[c['name']]
                                gainian_map[c['name']] = g_c + 1
                            else:
                                gainian_map[c['name']] = 1

            print(line[-1], stock['name'], stock['industry'], str(concept_detail_list), 'buy', k_table_list[0]['pct_chg'])

            if log is True:
                with open('D:\\data\\quantization\\predict\\' + str(day) + '.txt', mode='a', encoding="utf-8") as f:
                    f.write(str(line[-1]) + ' ' + stock['name'] + ' ' + stock['industry'] + ' ' + str(concept_detail_list) + ' buy' + '\n')


            # concept_list = list(stock_concept_table.find({'ts_code':stock['ts_code']}))
            # concept_list = [c['concept_code'] for c in concept_list]

        elif result[0][2] > 0.5:
            if stock['ts_code'] in holder_stock_list:
                print(stock['ts_code'], stock['name'], '震荡评级')

        elif result[0][3] > 0.5 or result[0][4] > 0.5:
            if stock['ts_code'] in holder_stock_list:
                print(stock['ts_code'], stock['name'], '赶紧卖出')
        else:
            if stock['ts_code'] in holder_stock_list:
                print(stock['ts_code'], stock['name'], result[0], r[0])

    print(gainian_map)
    print(hangye_map)


def _read_pfile_map(path):
    s_list = []
    with open(path, encoding='utf-8') as f:
        for line in f.readlines()[:]:
            s_list.append(line)
    return s_list


def join_two_day(a, b):
    a_list = _read_pfile_map('D:\\data\\quantization\\predict\\' + str(a) + '.txt')
    b_list = _read_pfile_map('D:\\data\\quantization\\predict\\dmi_' + str(b) + '.txt')
    for a in a_list:
        for b in b_list:
            if a[2:11] == b[2:11]:
                print(a)


if __name__ == '__main__':
    # predict(file_path='D:\\data\\quantization\\stock6_5_test.log', model_path='5d_dnn_seq.h5')
    # predict(file_path='D:\\data\\quantization\\stock6_test.log', model_path='15m_dnn_seq.h5')
    # multi_predict()
    # predict_today(20200303, model='11_18d', log=True)
    join_two_day(20200303, 20200303)