LSTM 应用预测股票数据

所用数据集:https://www.kaggle.com/datasets/yuanheqiuye/bank-stock 基于:tensorFlow 2.x

数据处理

import numpy as np

import pandas as pd

from matplotlib import pyplot as plt

from sklearn.model_selection import train_test_split

# 读取数据

data = pd.read_csv('data.csv', index_col=0)

# 将数据分为特征和目标变量

y = np.array(data['open'], dtype='float32').reshape(-1, 1)

X = np.array(data.drop('open', axis=1)).astype('float32')

# 划分数据集为训练集和测试集(95%训练,5%测试)

train_xs, test_xs, train_ys, test_ys = train_test_split(X, y, test_size=0.05, random_state=42)

# y 归一化处理

min_train_ys = train_ys.min()

max_train_ys = train_ys.max()

train_ys = (train_ys - min_train_ys) / (max_train_ys - min_train_ys)

test_ys = (test_ys - min_train_ys) / (max_train_ys - min_train_ys)

# 对x特征进行归一化处理

for dim in range(train_xs.shape[1]):

min_val = train_xs[:, dim].min()

max_val = train_xs[:, dim].max()

train_xs[:, dim] = (train_xs[:, dim] - min_val) / (max_val - min_val)

test_xs[:, dim] = (test_xs[:, dim] - min_val) / (max_val - min_val)

# 重新排列数据以创建时间序列

time_step = 5

input_dim = 13

def create_time_series_data(xs, ys, time_step):

aranged_xs = np.zeros(shape=(xs.shape[0] - time_step + 1, time_step, input_dim))

for idx in range(aranged_xs.shape[0]):

aranged_xs[idx] = xs[idx:idx + time_step]

aranged_ys = ys[time_step - 1:]

return aranged_xs, aranged_ys

aranged_train_xs, aranged_train_ys = create_time_series_data(train_xs, train_ys, time_step)

aranged_test_xs, aranged_test_ys = create_time_series_data(test_xs, test_ys, time_step)

# 保存数据

np.save(r'train_x_batch.npy', aranged_train_xs)

np.save(r'train_y_batch.npy', aranged_train_ys)

np.save(r'test_x_batch.npy', aranged_test_xs)

np.save(r'test_y_batch.npy', aranged_test_ys)

模型训练

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import tensorflow as tf

# Hyperparams

batch_size = 128 # 批量大小,指定每次迭代训练时传入模型的样本数量。较大的批量大小可以加快训练速度,但可能会占用更多的内存资源。

lr = 1e-4 # 控制模型在每次迭代时更新权重的步长。较小的学习率可以使模型收敛得更慢但更稳定,较大的学习率可以加快收敛速度但可能导致不稳定的训练过程。

epochs = 400 # 训练轮数,指定模型要遍历整个训练数据集的次数。每个 epoch 包含多个批次的训练。

num_neurons = [32, 32, 64, 64, 128, 128] # 神经元数量,指定每个隐藏层的神经元数量。这里给出了一个列表,表示了模型中每个隐藏层的神经元数量。通常情况下,增加神经元数量可以增加模型的表达能力,但也可能增加过拟合的风险。

kp = 0.99 # 保持概率(keep probability),用于控制 Dropout 正则化的保留概率。Dropout 是一种正则化技术,通过随机地丢弃一部分神经元的输出来减少过拟合。保持概率 kp 指定了要保留的神经元输出的比例,例如 kp=1.0 表示保留全部输出。

def load_data():

train_x_batch = np.load(r'train_x_batch.npy', allow_pickle=True)

train_y_batch = np.load(r'train_y_batch.npy', allow_pickle=True)

return (train_x_batch, train_y_batch)

# 载入数据

(train_x, train_y) = load_data()

train_data = tf.data.Dataset.from_tensor_slices((train_x, train_y)).shuffle(buffer_size=128).batch(batch_size)

# 定义模型

model = tf.keras.Sequential([

tf.keras.layers.LSTM(num_neurons[0], return_sequences=True, input_shape=(5, 13)),

tf.keras.layers.Dropout(1 - kp),

tf.keras.layers.LSTM(num_neurons[1], return_sequences=True),

tf.keras.layers.Dropout(1 - kp),

tf.keras.layers.LSTM(num_neurons[2], return_sequences=True),

tf.keras.layers.Dropout(1 - kp),

tf.keras.layers.LSTM(num_neurons[3], return_sequences=True),

tf.keras.layers.Dropout(1 - kp),

tf.keras.layers.LSTM(num_neurons[4], return_sequences=True),

tf.keras.layers.Dropout(1 - kp),

tf.keras.layers.LSTM(num_neurons[5]),

tf.keras.layers.Dense(1)

])

# 编译模型

model.compile(optimizer=tf.keras.optimizers.legacy.SGD(learning_rate=lr), loss='mean_squared_error')

# 使用提前停止

early_stopping = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=5)

# 训练模型

history = model.fit(train_data, epochs=epochs, callbacks=[early_stopping])

# 可视化训练过程

plt.plot(history.history['loss'])

plt.ylim(0, 1.2 * max(history.history['loss']))

plt.title('loss trend')

plt.xlabel('Epoch')

plt.ylabel('loss')

plt.show()

# 保存模型

model.save(r'stock_lstm_model.keras')

预测

import numpy as np

import matplotlib.pyplot as plt

import tensorflow as tf

def load_data():

test_x_batch = np.load(r'test_x_batch.npy', allow_pickle=True)

test_y_batch = np.load(r'test_y_batch.npy', allow_pickle=True)

return (test_x_batch, test_y_batch)

# 超参数

num_neurons = [32, 32, 64, 64, 128, 128]

# 定义模型

model = tf.keras.Sequential([

tf.keras.layers.LSTM(num_neurons[0], return_sequences=True, input_shape=(None, 13)),

tf.keras.layers.LSTM(num_neurons[1], return_sequences=True),

tf.keras.layers.LSTM(num_neurons[2], return_sequences=True),

tf.keras.layers.LSTM(num_neurons[3], return_sequences=True),

tf.keras.layers.LSTM(num_neurons[4], return_sequences=True),

tf.keras.layers.LSTM(num_neurons[5]),

tf.keras.layers.Dense(1)

])

# 尝试加载模型权重

model.load_weights(r'stock_lstm_model.keras')

# 载入数据

test_x, test_y = load_data()

# 预测

predicts = model.predict(test_x)

predicts = ((predicts.max() - predicts) / (predicts.max() - predicts.min())) # 数学校准

# 可视化

plt.figure(figsize=(12, 6))

plt.plot(predicts, 'r', label='predict')

plt.plot(test_y, 'g', label='real')

plt.xlabel('days')

plt.ylabel('open')

plt.title('predict trend')

plt.legend()

plt.show()

相关阅读

评论可见,请评论后查看内容,谢谢!!!
 您阅读本篇文章共花了: