看到一个不错的深度学习做预测,在这里分享给大家。
配置环境 deepin 15.3 Anaconda 2.7 pip 清华镜像 tensorflow
%%time
from __future__ import division
from __future__ import print_function
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
%matplotlib inline
import seaborn as sns
import tensorflow as tf
fac = np.load('/home/big/Quotes/TensorFlow deal with Uqer/fac16.npy').astype(np.float32)
ret = np.load('/home/big/Quotes/TensorFlow deal with Uqer/ret16.npy').astype(np.float32)
#fac = np.load('/home/big/Quotes/TensorFlow deal with Uqer/fac16.npy')
#ret = np.load('/home/big/Quotes/TensorFlow deal with Uqer/ret16.npy')
# Parameters
learning_rate = 0.001 # 学习速率,
training_iters = 20 # 训练次数
batch_size = 1024 # 每次计算数量 批次大小
display_step = 10 # 显示步长
# Network Parameters
n_input = 40*17 # 40 天×17 多因子
n_classes = 7 # 根据涨跌幅度分成 7 类别
# 这里注意要使用 one-hot 格式,也就是如果分类如 3 类 -1,0,1 则需要 3 列来表达这个分类结果, 3 类是-1 0 1 然后是哪类,哪类那一行为 1 否则为 0
dropout = 0.8 # Dropout, probability to keep units
# tensorflow 图 Graph 输入 input ,这里的占位符均为输入
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
2 层
# 2 层 CNN
def CNN_Net_two(x,weights,biases,dropout=0.8,m=1):
# 将输入张量调整成图片格式
# CNN 图像识别,这里将前 40 天的多因子数据假设成图片数据
x = tf.reshape(x, shape=[-1,40,17,1])
# 卷积层 1
x = tf.nn.conv2d(x, weights['wc1'], strides=[1,m,m,1],padding='SAME')
# x*W + b
x = tf.nn.bias_add(x,biases['bc1'])
# 激活函数
x = tf.nn.relu(x)
# 卷积层 2 感受野 5 5 16 64 移动步长 1
x = tf.nn.conv2d(x, weights['wc2'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc2'])
x = tf.nn.relu(x)
# 全连接层
x = tf.reshape(x,[-1,weights['wd1'].get_shape().as_list()[0]])
x = tf.add(tf.matmul(x,weights['wd1']),biases['bd1'])
x = tf.nn.relu(x)
# Apply Dropout
x = tf.nn.dropout(x,dropout)
# Output, class prediction
x = tf.add(tf.matmul(x,weights['out']),biases['out'])
return x
# Store layers weight & bias
weights = {
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 16])),
'wc2': tf.Variable(tf.random_normal([5, 5, 16, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([40*17*64, 1024])),
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([16])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
3 层
def CNN_Net_three(x,weights,biases,dropout=0.8,m=1):
x = tf.reshape(x, shape=[-1,40,17,1])
# 卷积层 1
x = tf.nn.conv2d(x, weights['wc1'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc1'])
x = tf.nn.relu(x)
# 卷积层 2
x = tf.nn.conv2d(x, weights['wc2'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc2'])
x = tf.nn.relu(x)
# 卷积层 3
x = tf.nn.conv2d(x, weights['wc3'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc3'])
x = tf.nn.relu(x)
# 全连接层
x = tf.reshape(x,[-1,weights['wd1'].get_shape().as_list()[0]])
x = tf.add(tf.matmul(x,weights['wd1']),biases['bd1'])
x = tf.nn.relu(x)
# Apply Dropout
x = tf.nn.dropout(x,dropout)
# Output, class prediction
x = tf.add(tf.matmul(x,weights['out']),biases['out'])
return x
# Store layers weight & bias
weights = {
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 16])),
'wc2': tf.Variable(tf.random_normal([5, 5, 16, 32])),
'wc3': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([40*17*64, 1024])),
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([16])),
'bc2': tf.Variable(tf.random_normal([32])),
'bc3': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
%%time
# 模型优化
pred = CNN_Net_two(x,weights,biases,dropout=keep_prob)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred,y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct_pred = tf.equal(tf.argmax(pred,1),tf.arg_max(y,1))
# tf.argmax(input,axis=None) 由于标签的数据格式是 -1 0 1 3 列,该语句是表示返回值最大也就是 1 的索引,两个索引相同则是预测正确。
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# 更改数据格式,降低均值
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
# for step in range(300):
for step in range(1):
for i in range(int(len(fac)/batch_size)):
batch_x = fac[i*batch_size:(i+1)*batch_size]
batch_y = ret[i*batch_size:(i+1)*batch_size]
sess.run(optimizer,feed_dict={x:batch_x,y:batch_y,keep_prob:dropout})
if i % 10 ==0:
print(i,'----',(int(len(fac)/batch_size)))
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,y: batch_y,keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
print("Optimization Finished!")
sess.close()
5 层
def CNN_Net_five(x,weights,biases,dropout=0.8,m=1):
x = tf.reshape(x, shape=[-1,40,17,1])
# 卷积层 1
x = tf.nn.conv2d(x, weights['wc1'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc1'])
x = tf.nn.relu(x)
# 卷积层 2
x = tf.nn.conv2d(x, weights['wc2'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc2'])
x = tf.nn.relu(x)
# 卷积层 3
x = tf.nn.conv2d(x, weights['wc3'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc3'])
x = tf.nn.relu(x)
# 卷积层 4
x = tf.nn.conv2d(x, weights['wc4'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc4'])
x = tf.nn.relu(x)
# 卷积层 5
x = tf.nn.conv2d(x, weights['wc5'], strides=[1,m,m,1],padding='SAME')
x = tf.nn.bias_add(x,biases['bc5'])
x = tf.nn.relu(x)
# 全连接层
x = tf.reshape(x,[-1,weights['wd1'].get_shape().as_list()[0]])
x = tf.add(tf.matmul(x,weights['wd1']),biases['bd1'])
x = tf.nn.relu(x)
# Apply Dropout
x = tf.nn.dropout(x,dropout)
# Output, class prediction
x = tf.add(tf.matmul(x,weights['out']),biases['out'])
return x
# Store layers weight & bias
weights = {
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 16])),
'wc2': tf.Variable(tf.random_normal([5, 5, 16, 32])),
'wc3': tf.Variable(tf.random_normal([5, 5, 32, 64])),
'wc4': tf.Variable(tf.random_normal([5, 5, 64, 32])),
'wc5': tf.Variable(tf.random_normal([5, 5, 32, 16])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([40*17*16, 1024])),
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([16])),
'bc2': tf.Variable(tf.random_normal([32])),
'bc3': tf.Variable(tf.random_normal([64])),
'bc4': tf.Variable(tf.random_normal([32])),
'bc5': tf.Variable(tf.random_normal([16])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
%%time
# 模型优化
pred = CNN_Net_five(x,weights,biases,dropout=keep_prob)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred,y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct_pred = tf.equal(tf.argmax(pred,1),tf.arg_max(y,1))
# tf.argmax(input,axis=None) 由于标签的数据格式是 -1 0 1 3 列,该语句是表示返回值最大也就是 1 的索引,两个索引相同则是预测正确。
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# 更改数据格式,降低均值
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for step in range(1):
for i in range(int(len(fac)/batch_size)):
batch_x = fac[i*batch_size:(i+1)*batch_size]
batch_y = ret[i*batch_size:(i+1)*batch_size]
sess.run(optimizer,feed_dict={x:batch_x,y:batch_y,keep_prob:dropout})
print(i,'----',(int(len(fac)/batch_size)))
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,y: batch_y,keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
print("Optimization Finished!")
sess.close()
优化参数之后准确率大概在 94%+
该作者其他有关机器学习,深度学习方面的文章也推荐给大家,希望对大家有帮助:
Tensorflow 笔记 1 CNN : https://uqer.io/community/share/58637c716a5e6d00522939b7
TensorFlow 笔记 2 双向 LSTM : https://uqer.io/community/share/586a4eb889e3ba004defde4b
TensorFlow 笔记 3 多层 LSTM : https://uqer.io/community/share/586bb68423a7d60052a361f6
三个臭皮匠-集成算法框架上手 : https://uqer.io/community/share/58562a9f6a5e6d0052291ebe
1
melovto 2017-02-09 20:12:47 +08:00 via iPhone
顶一下
|
2
liqian123456 2018-03-12 11:12:41 +08:00
请问一下,数据集是什么样的呢
|