chore: 添加Stock-Prediction-Models项目文件

添加了Stock-Prediction-Models项目的多个文件，包括数据集、模型代码、README文档和CSS样式文件。这些文件用于股票预测模型的训练和展示，涵盖了LSTM、GRU等深度学习模型的应用。

5.课程代码/4.Stock-Prediction-Models/使用文档/Stock-Prediction-Models-master/stacking/autoencoder.py

@@ -0,0 +1,41 @@
+import tensorflow as tf
+import numpy as np
+import time
+
+def reducedimension(input_, dimension = 2, learning_rate = 0.01, hidden_layer = 256, epoch = 20):
+    
+    input_size = input_.shape[1]
+    X = tf.placeholder("float", [None, input_size])
+    
+    weights = {
+    'encoder_h1': tf.Variable(tf.random_normal([input_size, hidden_layer])),
+    'encoder_h2': tf.Variable(tf.random_normal([hidden_layer, dimension])),
+    'decoder_h1': tf.Variable(tf.random_normal([dimension, hidden_layer])),
+    'decoder_h2': tf.Variable(tf.random_normal([hidden_layer, input_size])),
+    }
+    
+    biases = {
+    'encoder_b1': tf.Variable(tf.random_normal([hidden_layer])),
+    'encoder_b2': tf.Variable(tf.random_normal([dimension])),
+    'decoder_b1': tf.Variable(tf.random_normal([hidden_layer])),
+    'decoder_b2': tf.Variable(tf.random_normal([input_size])),
+    }
+    
+    first_layer_encoder = tf.nn.sigmoid(tf.add(tf.matmul(X, weights['encoder_h1']), biases['encoder_b1']))
+    second_layer_encoder = tf.nn.sigmoid(tf.add(tf.matmul(first_layer_encoder, weights['encoder_h2']), biases['encoder_b2']))
+    first_layer_decoder = tf.nn.sigmoid(tf.add(tf.matmul(second_layer_encoder, weights['decoder_h1']), biases['decoder_b1']))
+    second_layer_decoder = tf.nn.sigmoid(tf.add(tf.matmul(first_layer_decoder, weights['decoder_h2']), biases['decoder_b2']))
+    cost = tf.reduce_mean(tf.pow(X - second_layer_decoder, 2))
+    optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)
+    sess = tf.InteractiveSession()
+    sess.run(tf.global_variables_initializer())
+    
+    for i in range(epoch):
+        last_time = time.time()
+        _, loss = sess.run([optimizer, cost], feed_dict={X: input_})
+        if (i + 1) % 10 == 0:
+            print('epoch:', i + 1, 'loss:', loss, 'time:', time.time() - last_time)
+        
+    vectors = sess.run(second_layer_encoder, feed_dict={X: input_})
+    tf.reset_default_graph()
+    return vectors

5.课程代码/4.Stock-Prediction-Models/使用文档/Stock-Prediction-Models-master/stacking/model.py

@@ -0,0 +1,19 @@
+import tensorflow as tf
+import numpy as np
+
+class Model:
+    def __init__(self, learning_rate, num_layers, size, size_layer, output_size, forget_bias = 0.1):
+        
+        def lstm_cell(size_layer):
+            return tf.nn.rnn_cell.LSTMCell(size_layer, state_is_tuple = False)
+        rnn_cells = tf.nn.rnn_cell.MultiRNNCell([lstm_cell(size_layer) for _ in range(num_layers)], state_is_tuple = False)
+        self.X = tf.placeholder(tf.float32, (None, None, size))
+        self.Y = tf.placeholder(tf.float32, (None, output_size))
+        drop = tf.contrib.rnn.DropoutWrapper(rnn_cells, output_keep_prob = forget_bias)
+        self.hidden_layer = tf.placeholder(tf.float32, (None, num_layers * 2 * size_layer))
+        self.outputs, self.last_state = tf.nn.dynamic_rnn(drop, self.X, initial_state = self.hidden_layer, dtype = tf.float32)
+        rnn_W = tf.Variable(tf.random_normal((size_layer, output_size)))
+        rnn_B = tf.Variable(tf.random_normal([output_size]))
+        self.logits = tf.matmul(self.outputs[-1], rnn_W) + rnn_B
+        self.cost = tf.reduce_mean(tf.square(self.Y - self.logits))
+        self.optimizer = tf.train.AdamOptimizer(learning_rate).minimize(self.cost)