虚拟货币(比特币,以太坊)价值预测

缘由:好友开发了一个程序化交易虚拟货币的助手软件。卖的火热(想购买的朋友请加微信: endpang )。出于对土豪的敬意,抽时间做一个时序预测的东西。

财富自由之路开始。。。。

首先得获得实时的价格数据,

火币网的接口:https://github.com/huobiapi/API_Docs/wiki/REST_introduction

websocket 获得实时数据并将价格写入文本文件

from websocket import create_connection
import gzip
import time
import json




if __name__ == '__main__':
    while(1):
        try:
            ws = create_connection("wss://api.huobipro.com/ws")
            break
        except:
            print('connect ws error,retry...')
            time.sleep(5)

    # 订阅 KLine 数据
    tradeStr="""{"sub": "market.ethusdt.kline.1min","id": "id10"}"""

    # 请求 KLine 数据
    # tradeStr="""{"req": "market.ethusdt.kline.1min","id": "id10", "from": 1513391453, "to": 1513392453}"""

    #订阅 Market Depth 数据
    # tradeStr="""{"sub": "market.ethusdt.depth.step5", "id": "id10"}"""

    #请求 Market Depth 数据
    # tradeStr="""{"req": "market.ethusdt.depth.step5", "id": "id10"}"""

    #订阅 Trade Detail 数据
    # tradeStr="""{"sub": "market.ethusdt.trade.detail", "id": "id10"}"""

    #请求 Trade Detail 数据
    # tradeStr="""{"req": "market.ethusdt.trade.detail", "id": "id10"}"""

    #请求 Market Detail 数据
    # tradeStr="""{"req": "market.ethusdt.detail", "id": "id12"}"""

    ws.send(tradeStr)
    old = {"vol": 0,"count":0,"close":0}
    i = 0
    with open('test_csv.csv',"w") as csv:
        #csv.write("lines\n")
        while(1):

            compressData=ws.recv()
            result=gzip.decompress(compressData).decode('utf-8')
            if result[:7] == '{"ping"':

                ts=result[8:21]
                pong='{"pong":'+ts+'}'
                ws.send(pong)
                ws.send(tradeStr)
            elif result[:5] == '{"ch"':
                arr = json.loads(result)
                #print("arr",arr)

                if arr['tick']['count'] < old["count"]:
                    i = i+1
                    csv.write(format(old['close'])+"\n")
                    print('count',old)
                else:
                    delta = arr['tick']['vol'] - old['vol']
                    print("delta:",delta)
                    if delta > 0:
                        deltap = arr['tick']['close'] -  old["close"]

                        print("deltap",deltap)
                old = arr['tick']

基于tensorflow  lstm 的预测模型。

import lstm
import time
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt

def plot_results(predicted_data, true_data):
    fig = plt.figure(facecolor='white')
    ax = fig.add_subplot(111)
    ax.plot(true_data, label='True Data')
    plt.plot(predicted_data, label='Prediction')
    plt.legend()
    plt.show()

def plot_results_multiple(predicted_data, true_data, prediction_len):
    fig = plt.figure(facecolor='white')
    ax = fig.add_subplot(111)
    ax.plot(true_data, label='True Data')
    #Pad the list of predictions to shift it in the graph to it's correct start
    for i, data in enumerate(predicted_data):
        padding = [None for p in range(i * prediction_len)]
        plt.plot(padding + data, label='Prediction')
        plt.legend()
    plt.show()

#Main Run Thread
if __name__=='__main__':
	global_start_time = time.time()
	epochs  = 1
	seq_len = 50

	print('> Loading data... ')

	X_train, y_train, X_test, y_test = lstm.load_data('test_csv.csv', seq_len, True)

	print('> Data Loaded. Compiling...')

	model = lstm.build_model([1, 50, 100, 1])

	model.fit(
	    X_train,
	    y_train,
	    batch_size=512,
	    nb_epoch=epochs,
	    validation_split=0.05)

	predictions = lstm.predict_sequences_multiple(model, X_test, seq_len, 50)
	#predicted = lstm.predict_sequence_full(model, X_test, seq_len)
	#predicted = lstm.predict_point_by_point(model, X_test)        

	print('Training duration (s) : ', time.time() - global_start_time)
	plot_results_multiple(predictions, y_test, 50)

市场有风险,交易需谨慎。不准莫怪我,预测准的,写出来也不会开放代码的。。。 : P

发表评论

您的电子邮箱地址不会被公开。

此站点使用Akismet来减少垃圾评论。了解我们如何处理您的评论数据