# tensorflow深度学习之RNN实现四个数字预测下一个数字

## 不使用csv时

import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, SimpleRNN, Embedding
import matplotlib.pyplot as plt
import os

x_train=[[0,1,2,3],[1,2,3,4],[2,3,4,5],[3,4,5,6],[4,5,6,7],[5,6,7,8],[6,7,8,9],[7,8,9,10],[8,9,10,11],[9,10,11,12],
[10,11,12,13],[11,12,13,14],[12,13,14,15],[13,14,15,16],[14,15,16,17],[15,16,17,18],[16,17,18,19],[17,18,19,20],
[18,19,20,21],[19,20,21,22],[20,21,22,23],[21,22,23,24]]

y_train = [ 4,5 , 6,  7  ,8 , 9 ,10 ,11, 12 ,13, 14 ,15, 16, 17, 18, 19 ,20 ,21 ,22 ,23 ,24, 25]

x_train = np.reshape(x_train, (len(x_train), 4))
y_train = np.array(y_train)

model = tf.keras.Sequential([
Embedding(26, 2),
SimpleRNN(10),
Dense(26, activation='softmax') #26大于最大标签数值25+1
])

loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "./checkpoint/rnn_embedding_4pre1.ckpt"

if os.path.exists(checkpoint_save_path + '.index'):

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
save_weights_only=True,
save_best_only=True,
monitor='loss')  # 由于fit没有给出测试集，不计算测试集准确率，根据loss，保存最优模型

history = model.fit(x_train, y_train, batch_size=32, epochs=100, callbacks=[cp_callback])

model.summary()

file = open('./weights.txt', 'w')  # 参数提取
for v in model.trainable_variables:
file.write(str(v.name) + '\n')
file.write(str(v.shape) + '\n')
file.write(str(v.numpy()) + '\n')
file.close()

###############################################    show   ###############################################

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
loss = history.history['loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.title('Training Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.title('Training Loss')
plt.legend()
plt.show()

## 使用csv时

cpp
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, SimpleRNN, Embedding
import matplotlib.pyplot as plt
import os
import pandas as pd
from sklearn.model_selection import train_test_split

#x_train=[[0,1,2,3],[1,2,3,4],[2,3,4,5],[3,4,5,6],[4,5,6,7],[5,6,7,8],[6,7,8,9],[7,8,9,10],[8,9,10,11],[9,10,11,12],
#        [10,11,12,13],[11,12,13,14],[12,13,14,15],[13,14,15,16],[14,15,16,17],[15,16,17,18],[16,17,18,19],[17,18,19,20],
#       [18,19,20,21],[19,20,21,22],[20,21,22,23],[21,22,23,24]]

# all_inputs = iris_data[['Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width']].values
x_train = iris_data[['1', '2', '3', '4']].values
y_train = iris_data['Species'].values

# y_train = [ 4,5 , 6,  7  ,8 , 9 ,10 ,11, 12 ,13, 14 ,15, 16, 17, 18, 19 ,20 ,21 ,22 ,23 ,24, 25]

x_train = np.reshape(x_train, (len(x_train), 4))
y_train = np.array(y_train)

model = tf.keras.Sequential([
Embedding(26, 2),
SimpleRNN(10),
Dense(26, activation='softmax') #26大于最大标签数值25+1
])

loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "./checkpoint/rnn_embedding_4pre1.ckpt"

if os.path.exists(checkpoint_save_path + '.index'):

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
save_weights_only=True,
save_best_only=True,
monitor='loss')  # 由于fit没有给出测试集，不计算测试集准确率，根据loss，保存最优模型

history = model.fit(x_train, y_train, batch_size=32, epochs=100, callbacks=[cp_callback])

model.summary()

file = open('./weights.txt', 'w')  # 参数提取
for v in model.trainable_variables:
file.write(str(v.name) + '\n')
file.write(str(v.shape) + '\n')
file.write(str(v.numpy()) + '\n')
file.close()

###############################################    show   ###############################################

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
loss = history.history['loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.title('Training Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.title('Training Loss')
plt.legend()
plt.show()

result = model.predict(x_train[0:2])
pred = tf.argmax(result, axis=1)
tf.print(pred)


csv文件下载

01-13
12-23 6万+

03-23 3377
10-19 2399
01-13 4031
07-26 4413
07-29 385
09-08 4022
09-27 4785
05-28 11万+
05-23 55
09-16 2172