Keras, Sequential: нейронка предсказывает не будущее, а настоящее

import numpy as np
import matplotlib.pyplot as plt
import pandas
import math
import datetime as dt
from datetime import datetime
from getDataFromPoloniex import get_data_from_poloniex
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
np.random.seed(7)
 
data3 = pandas.read_csv('data/mydata.csv')[::-1]
data3.columns = ['date','high','low','open','close','volume','quoteVolume','weightedAverage']
 
def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back), 0]
        dataX.append(a)
        dataY.append(dataset[i + look_back, 0])
    return np.array(dataX), np.array(dataY)
 
dataset = pandas.DataFrame(data3.close.ewm(span=14).mean())[::-1]
 
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
 
train_size = int(len(dataset))
train = dataset[0:train_size,:]
 
look_back = 3
trainX, trainY = create_dataset(train, look_back)
 
trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
trainXX = trainX[3740:len(trainX)]
 
model = Sequential()
model.add(LSTM(100, activation='relu', return_sequences=True, input_shape=(look_back, 1)))
model.add(LSTM(100, activation='relu'))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=20, batch_size=1, verbose=2)
 
trainPredict = model.predict(trainXX)