如何用 AI 预测以太坊价格？

本篇仅为教育目的，教大家写一个有意思的深度学习算法和应用。真正实现可工业化的预测股票和加密货币市场的 AI 模型还需要太多的数据和更好的模型。

导入 dependencies

import pandas as pd
import numpy as np
from numpy import newaxis
import matplotlib.pyplot as plt
%matplotlib inline

import warnings
warnings.filterwarnings('ignore')

通过 Quandl 获取以太坊历史价格

import quandl
eth_data = quandl.get("BITFINEX/ETHUSD"); eth_data.head()

eth_price = eth_data['Last']

eth_price.plot()

eth_price.to_csv('eth_price.csv',header = None, index=None)

导入深度学习集成框架 Keras

from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential

训练窗口期标准化

def normalise_windows(window_data):
    normalised_data = []
    for window in window_data:
        normalised_window = [((float(p) / float(window[0])) - 1) for p in window]
        normalised_data.append(normalised_window)
    return normalised_data

导入以太价格数据，并在切分窗口后，选取训练组和测试组

def load_data(filename, seq_len, normalise_window):
    with open(filename, 'r') as f:
        data = f.read().split('\n')
        
        sequence_length = seq_len + 1
        result = []
        for index in range(len(data) - sequence_length):
            result.append(data[index:index+sequence_length])
            
        if normalise_window:
            result = normalise_windows(result)
        
        result = np.array(result)
        
        row = round(0.8 * result.shape[0])
        train = result[:int(row),:]
        np.random.shuffle(train)
        x_train = train[:,:-1]
        y_train = train[:,-1]
        x_test = result[-150:,:-1]
        y_test = result[-150:,-1]
        
        x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
        x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))
        
        return [x_train, y_train, x_test, y_test]

X_train, y_train, X_test, y_test = load_data('eth_price.csv', 50, True)

X_train.shape

(658, 50, 1)

建立深度学习模型

model = Sequential()

model.add(LSTM(
    input_dim = 1,
    output_dim = 50,
    return_sequences = True))
model.add(Dropout(0.2))

model.add(LSTM(
    output_dim = 100,
    return_sequences = False))
model.add(Dropout(0.2))

model.add(Dense(
output_dim = 1))
model.add(Activation('linear'))

训练模型

model.fit(X_train, y_train, nb_epoch = 10, validation_split = 0.05)

预测结果

根据选定区预测下一天的价格

def predict_point_by_point(model, data):
    predicted = model.predict(data)
    predicted = np.reshape(predicted, (predicted.size,))
    return predicted

predictions1 = predict_point_by_point(model, X_test)

def plot_results_single(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()

plot_results_single(predictions1, y_test)

根据选定区预测整个测试数据的价格

def predict_sequence_full(model, data, window_size):
    curr_frame = data[0]
    predicted = []
    for i in xrange(len(data)):
        predicted.append(model.predict(curr_frame[newaxis,:,:])[0,0])
        curr_frame = curr_frame[1:]
        curr_frame = np.insert(curr_frame, [window_size-1], predicted[-1], axis=0)
    return predicted

predictions2 = predict_sequence_full(model, X_test, 50)

plot_results_single(predictions2, y_test)

根据每个所选区预测下之后20天的价格

def predict_sequences_multiple(model, data, window_size, prediction_len):
    prediction_seqs = []
    for i in xrange(len(data)/prediction_len):
        curr_frame = data[i*prediction_len]
        predicted = []
        for j in xrange(prediction_len):
            predicted.append(model.predict(curr_frame[newaxis,:,:])[0,0])
            curr_frame = curr_frame[1:]
            curr_frame = np.insert(curr_frame,[window_size - 1], predicted[-1], axis = 0)
        prediction_seqs.append(predicted)
    return prediction_seqs

predictions3 = predict_sequences_multiple(model, X_test, 50, 20)

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')
    for i, data in enumerate(predicted_data):
        padding = [None for p in xrange(i * prediction_len)]
        plt.plot(padding + data, label='Prediction')
    plt.show()

plot_results_multiple(predictions3,y_test, 20)

TIME TO MAKE MONEY?