Question

我目前正在研究并尝试改进python脚本，其目的是预测股市走势（非常简单）。

问题：我得到了相同的输出值，我不明白为什么，因为它假设更像是这个图表（红线是我应该得到的预测和蓝线是真实的数据）：https://i.stack.imgur.com/dvQvY.png

以下是代码：

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from pandas import datetime
import math, time
import itertools
from sklearn import preprocessing
import datetime
from operator import itemgetter
from sklearn.metrics import mean_squared_error
from math import sqrt
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.recurrent import LSTM

def get_stock_data(stock_name, normalized=0):
    url = 'http://chart.finance.yahoo.com/table.csv?s=%s&a=11&b=15&c=2011&d=29&e=10&f=2016&g=d&ignore=.csv' % stock_name

    col_names = ['Date','Open','High','Low','Close','Volume','Adj Close']
    stocks = pd.read_csv(url, header=0, names=col_names) 
    df = pd.DataFrame(stocks)
    date_split = df['Date'].str.split('-').str
    df['Year'], df['Month'], df['Day'] = date_split
    df["Volume"] = df["Volume"] / 10000
    df.drop(df.columns[[0,3,5,6, 7,8,9]], axis=1, inplace=True) 
    return df

stock_name = 'GOOGL'
df = get_stock_data(stock_name,0)
df.head()

today = datetime.date.today()
file_name = stock_name+'_stock_%s.csv' % today
df.to_csv(file_name)

df['High'] = df['High'] / 100
df['Open'] = df['Open'] / 100
df['Close'] = df['Close'] / 100
df.head(5)

def load_data(stock, seq_len):
    amount_of_features = len(stock.columns)
    data = stock.as_matrix() #pd.DataFrame(stock)
    sequence_length = seq_len + 1
    result = []
    for index in range(len(data) - sequence_length):
        result.append(data[index: index + sequence_length])

    result = np.array(result)
    row = round(0.9 * result.shape[0])
    train = result[:int(row), :]
    x_train = train[:, :-1]
    y_train = train[:, -1][:,-1]
    x_test = result[int(row):, :-1]
    y_test = result[int(row):, -1][:,-1]

    x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], amount_of_features))
    x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], amount_of_features))  

    return [x_train, y_train, x_test, y_test]

def build_model2(layers):
        d = 0.2
        model = Sequential()
        model.add(LSTM(128, input_shape=(layers[1], layers[0]), return_sequences=True))
        model.add(Dropout(d))
        model.add(LSTM(64, input_shape=(layers[1], layers[0]), return_sequences=False))
        model.add(Dropout(d))
        model.add(Dense(16,init='uniform',activation='relu'))        
        model.add(Dense(1,init='uniform',activation='linear'))
        model.compile(loss='mse',optimizer='adam',metrics=['accuracy'])
        return model

window = 22
X_train, y_train, X_test, y_test = load_data(df[::-1], window)
print("X_train", X_train.shape)
print("y_train", y_train.shape)
print("X_test", X_test.shape)
print("y_test", y_test.shape)

model = build_model2([3,window,1])

model.fit(
    X_train,
    y_train,
    batch_size=512,
    nb_epoch=500,
    validation_split=0.1,
    verbose=1)

trainScore = model.evaluate(X_train, y_train, verbose=0)
print('Train Score: %.2f MSE (%.2f RMSE)' % (trainScore[0], math.sqrt(trainScore[0])))

testScore = model.evaluate(X_test, y_test, verbose=0)
print('Test Score: %.2f MSE (%.2f RMSE)' % (testScore[0],math.sqrt(testScore[0])))

# print(X_test[-1])
diff=[]
ratio=[]
p = model.predict(X_test)
for u in range(len(y_test)):
    pr = p[u][0]
    ratio.append((y_test[u]/pr)-1)
    diff.append(abs(y_test[u]- pr))
    #print(u, y_test[u], pr, (y_test[u]/pr)-1, abs(y_test[u]- pr))

import matplotlib.pyplot as plt2

plt2.plot(p,color='red', label='prediction')
plt2.plot(y_test,color='blue', label='y_test')
plt2.legend(loc='upper left')
plt2.show()

我得到的输出：https://i.stack.imgur.com/6TVRb.png

（我已经尝试更改批量大小和时期数量）

我目前正在使用（在macosx sierra上）：

Python 3.6.0（默认，2017年1月2日，18：14：29） [dclwin上的[GCC 4.2.1兼容的Apple LLVM 8.0.0（clang-800.0.42.1）] 输入＆＃34; copyright＆＃34;，＆＃34; credit＆＃34;或＆＃34; license（）＆＃34;欲获得更多信息。警告：正在使用的Tcl / Tk（8.5.9）版本可能不稳定。

上一代码中使用的每个模块都是最新的（2017年4月24日）

我可能已经忘记了一些信息，不要犹豫问我。

由于

Answer 1

将nb_epoch=500更改为nb_epoch=2 你会发现LSTM会正常工作。

lstm神经网络异常输出相同的值

1 个答案: