TF之LSTM/GRU：基于tensorflow框架对boston房价数据集分别利用LSTMGRU算法(batch_size调优对比)实现房价回归预测案例

Posted 2023-03-24 一个处女座的程序猿

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了TF之LSTM/GRU：基于tensorflow框架对boston房价数据集分别利用LSTMGRU算法(batch_size调优对比)实现房价回归预测案例相关的知识，希望对你有一定的参考价值。

TF之LSTM/GRU：基于tensorflow框架对boston房价数据集分别利用LSTM、GRU算法(batch_size调优对比)实现房价回归预测案例

基于tensorflow框架对boston房价数据集分别利用LSTM、GRU算法(batch_size调优对比)实现房价回归预测案例

# 将输入数据重塑为3D张量（样本数、时间步长、特征数）

TF之LSTM：基于tensorflow框架对boston房价数据集利用LSTM算法(随机搜索调参)实现房价回归预测案例
 TF之LSTM：基于tensorflow框架对boston房价数据集利用LSTM算法(随机搜索调参)实现房价回归预测案例实现代码

TF之LSTM：基于tensorflow框架对boston房价数据集利用LSTM算法(网格搜索调参)实现房价回归预测案例实现代码

基于tensorflow框架对boston房价数据集分别利用LSTM、GRU算法(batch_size调优对比)实现房价回归预测案例

# 1、定义数据集

        CRIM    ZN  INDUS  CHAS    NOX  ...    TAX  PTRATIO       B  LSTAT  target
0    0.00632  18.0   2.31   0.0  0.538  ...  296.0     15.3  396.90   4.98    24.0
1    0.02731   0.0   7.07   0.0  0.469  ...  242.0     17.8  396.90   9.14    21.6
2    0.02729   0.0   7.07   0.0  0.469  ...  242.0     17.8  392.83   4.03    34.7
3    0.03237   0.0   2.18   0.0  0.458  ...  222.0     18.7  394.63   2.94    33.4
4    0.06905   0.0   2.18   0.0  0.458  ...  222.0     18.7  396.90   5.33    36.2
..       ...   ...    ...   ...    ...  ...    ...      ...     ...    ...     ...
501  0.06263   0.0  11.93   0.0  0.573  ...  273.0     21.0  391.99   9.67    22.4
502  0.04527   0.0  11.93   0.0  0.573  ...  273.0     21.0  396.90   9.08    20.6
503  0.06076   0.0  11.93   0.0  0.573  ...  273.0     21.0  396.90   5.64    23.9
504  0.10959   0.0  11.93   0.0  0.573  ...  273.0     21.0  393.45   6.48    22.0
505  0.04741   0.0  11.93   0.0  0.573  ...  273.0     21.0  396.90   7.88    11.9

[506 rows x 14 columns]
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 14 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   CRIM     506 non-null    float64
 1   ZN       506 non-null    float64
 2   INDUS    506 non-null    float64
 3   CHAS     506 non-null    float64
 4   NOX      506 non-null    float64
 5   RM       506 non-null    float64
 6   AGE      506 non-null    float64
 7   DIS      506 non-null    float64
 8   RAD      506 non-null    float64
 9   TAX      506 non-null    float64
 10  PTRATIO  506 non-null    float64
 11  B        506 non-null    float64
 12  LSTAT    506 non-null    float64
 13  target   506 non-null    float64
dtypes: float64(14)
memory usage: 55.5 KB

# 2、数据预处理

# 2.1、分离特征和标签

# 3、模型训练与推理

# 3.1、切分数据集

# 3.2、数据再处理

# 将输入数据重塑为3D张量（样本数、时间步长、特征数）

<class 'numpy.ndarray'> (455, 1, 13) X_train 
 [[[6.04700e-02 0.00000e+00 2.46000e+00 ... 1.78000e+01 3.87110e+02
   1.31500e+01]]

 [[6.29760e-01 0.00000e+00 8.14000e+00 ... 2.10000e+01 3.96900e+02
   8.26000e+00]]

 [[7.99248e+00 0.00000e+00 1.81000e+01 ... 2.02000e+01 3.96900e+02
   2.45600e+01]]

 ...

 [[3.51140e-01 0.00000e+00 7.38000e+00 ... 1.96000e+01 3.96900e+02
   7.70000e+00]]

 [[9.18702e+00 0.00000e+00 1.81000e+01 ... 2.02000e+01 3.96900e+02
   2.36000e+01]]

 [[4.55587e+00 0.00000e+00 1.81000e+01 ... 2.02000e+01 3.54700e+02
   7.12000e+00]]]

# 3.3、模型建立和训练

Epoch 1/800
15/15 [==============================] - 2s 22ms/step - loss: 367.5489 - val_loss: 189.7880
Epoch 2/800
15/15 [==============================] - 0s 3ms/step - loss: 95.0314 - val_loss: 133.7617
Epoch 3/800
15/15 [==============================] - 0s 3ms/step - loss: 63.8908 - val_loss: 110.7545
Epoch 4/800
15/15 [==============================] - 0s 3ms/step - loss: 54.9615 - val_loss: 108.7314
Epoch 5/800
15/15 [==============================] - 0s 3ms/step - loss: 53.5053 - val_loss: 104.1971
Epoch 6/800
15/15 [==============================] - 0s 3ms/step - loss: 50.4742 - val_loss: 111.0977
Epoch 7/800
15/15 [==============================] - 0s 4ms/step - loss: 46.4744 - val_loss: 100.7286
Epoch 8/800
15/15 [==============================] - 0s 3ms/step - loss: 46.6553 - val_loss: 99.4326
Epoch 9/800
15/15 [==============================] - 0s 3ms/step - loss: 48.1464 - val_loss: 96.9524
Epoch 10/800
15/15 [==============================] - 0s 3ms/step - loss: 46.4484 - val_loss: 96.3056
Epoch 11/800
15/15 [==============================] - 0s 3ms/step - loss: 41.9167 - val_loss: 92.1237
Epoch 12/800
15/15 [==============================] - 0s 3ms/step - loss: 40.4515 - val_loss: 89.9320
Epoch 13/800
15/15 [==============================] - 0s 3ms/step - loss: 46.7765 - val_loss: 91.3324
Epoch 14/800
15/15 [==============================] - 0s 3ms/step - loss: 45.2451 - val_loss: 83.1068
Epoch 15/800
15/15 [==============================] - 0s 4ms/step - loss: 44.0281 - val_loss: 77.3420
Epoch 16/800
15/15 [==============================] - 0s 3ms/step - loss: 42.0810 - val_loss: 85.3165
Epoch 17/800
15/15 [==============================] - 0s 4ms/step - loss: 37.4590 - val_loss: 70.4207
……
Epoch 757/800
15/15 [==============================] - 0s 3ms/step - loss: 4.9589 - val_loss: 37.6601
Epoch 758/800
15/15 [==============================] - 0s 3ms/step - loss: 4.6070 - val_loss: 36.7595
Epoch 759/800
15/15 [==============================] - 0s 3ms/step - loss: 5.8827 - val_loss: 41.7672
Epoch 760/800
15/15 [==============================] - 0s 3ms/step - loss: 5.3787 - val_loss: 42.0669
Epoch 761/800
15/15 [==============================] - 0s 3ms/step - loss: 5.2201 - val_loss: 47.2067
Epoch 762/800
15/15 [==============================] - 0s 3ms/step - loss: 4.5653 - val_loss: 46.1523
Epoch 763/800
15/15 [==============================] - 0s 3ms/step - loss: 5.7319 - val_loss: 43.6643
Epoch 764/800
15/15 [==============================] - 0s 3ms/step - loss: 4.3259 - val_loss: 41.5630
Epoch 765/800
15/15 [==============================] - 0s 3ms/step - loss: 4.2562 - val_loss: 40.0810
Epoch 766/800
15/15 [==============================] - 0s 3ms/step - loss: 5.4430 - val_loss: 37.8770
Epoch 767/800
15/15 [==============================] - 0s 3ms/step - loss: 5.2480 - val_loss: 46.7311
Epoch 768/800
15/15 [==============================] - 0s 3ms/step - loss: 4.7596 - val_loss: 40.3361
Epoch 769/800
15/15 [==============================] - 0s 3ms/step - loss: 4.8908 - val_loss: 42.5085
Epoch 770/800
15/15 [==============================] - 0s 3ms/step - loss: 4.7232 - val_loss: 39.5460
Epoch 771/800
15/15 [==============================] - 0s 3ms/step - loss: 4.6950 - val_loss: 41.4992
Epoch 772/800
15/15 [==============================] - 0s 3ms/step - loss: 4.9918 - val_loss: 42.5983
Epoch 773/800
15/15 [==============================] - 0s 3ms/step - loss: 5.0848 - val_loss: 50.5700
Epoch 774/800
15/15 [==============================] - 0s 3ms/step - loss: 7.3065 - val_loss: 30.6110
Epoch 775/800
15/15 [==============================] - 0s 3ms/step - loss: 8.4268 - val_loss: 42.6159
Epoch 776/800
15/15 [==============================] - 0s 3ms/step - loss: 9.8120 - val_loss: 45.9334
Epoch 777/800
15/15 [==============================] - 0s 3ms/step - loss: 5.8191 - val_loss: 47.6144
Epoch 778/800
15/15 [==============================] - 0s 3ms/step - loss: 7.1561 - val_loss: 50.9774
Epoch 779/800
15/15 [==============================] - 0s 3ms/step - loss: 5.4377 - val_loss: 32.8492
Epoch 780/800
15/15 [==============================] - 0s 3ms/step - loss: 6.8226 - val_loss: 25.2842
Epoch 781/800
15/15 [==============================] - 0s 4ms/step - loss: 6.6671 - val_loss: 32.6189
Epoch 782/800
15/15 [==============================] - 0s 3ms/step - loss: 5.4168 - val_loss: 48.3716
Epoch 783/800
15/15 [==============================] - 0s 3ms/step - loss: 6.1797 - val_loss: 26.0899
Epoch 784/800
15/15 [==============================] - 0s 3ms/step - loss: 7.9516 - val_loss: 23.3273
Epoch 785/800
15/15 [==============================] - 0s 3ms/step - loss: 7.4502 - val_loss: 29.4346
Epoch 786/800
15/15 [==============================] - 0s 3ms/step - loss: 6.0257 - val_loss: 40.4242
Epoch 787/800
15/15 [==============================] - 0s 3ms/step - loss: 5.0951 - val_loss: 49.2547
Epoch 788/800
15/15 [==============================] - 0s 3ms/step - loss: 4.8296 - val_loss: 37.7677
Epoch 789/800
15/15 [==============================] - 0s 3ms/step - loss: 6.2584 - val_loss: 40.6493
Epoch 790/800
15/15 [==============================] - 0s 4ms/step - loss: 6.6211 - val_loss: 31.1713
Epoch 791/800
15/15 [==============================] - 0s 4ms/step - loss: 5.2383 - val_loss: 55.5448
Epoch 792/800
15/15 [==============================] - 0s 3ms/step - loss: 5.4096 - val_loss: 43.4175
Epoch 793/800
15/15 [==============================] - 0s 3ms/step - loss: 5.0846 - val_loss: 39.2757
Epoch 794/800
15/15 [==============================] - 0s 4ms/step - loss: 4.5122 - val_loss: 41.4339
Epoch 795/800
15/15 [==============================] - 0s 3ms/step - loss: 4.8337 - val_loss: 47.6556
Epoch 796/800
15/15 [==============================] - 0s 3ms/step - loss: 5.1507 - val_loss: 44.6231
Epoch 797/800
15/15 [==============================] - 0s 3ms/step - loss: 5.2973 - val_loss: 44.1294
Epoch 798/800
15/15 [==============================] - 0s 3ms/step - loss: 4.5970 - val_loss: 46.2830
Epoch 799/800
15/15 [==============================] - 0s 3ms/step - loss: 4.4145 - val_loss: 45.5006
Epoch 800/800
15/15 [==============================] - 0s 4ms/step - loss: 4.1411 - val_loss: 46.0986

# 3.4、模型训练

测试集均方误差: 46.099
boston_val_MAE: 3.6606673203262625
boston_val_MSE： 46.098603197697834
boston_val_RMSE： 6.7895952160418105
boston_val_R2: 0.5967941831772676

# 绘制训练集和测试集的loss曲线

# 3.5、模型评估

boston_LSTM_8_val_MAE: 3.642160939235313
boston_LSTM_8_val_MSE： 45.455696025386075
boston_LSTM_8_val_RMSE： 6.742083952709732
boston_LSTM_8_val_R2: 0.6024174319000424
model_name： boston_LSTM_8_0.6024

boston_GRU_8_val_MAE: 2.9867677613800647
boston_GRU_8_val_MSE： 27.82258275867772
boston_GRU_8_val_RMSE： 5.2747116280113095
boston_GRU_8_val_R2: 0.7566471339875444
model_name： boston_GRU_8_0.7566



boston_LSTM_16_val_MAE: 3.33460968615962
boston_LSTM_16_val_MSE： 31.442621036483846
boston_LSTM_16_val_RMSE： 5.607372025867719
boston_LSTM_16_val_R2: 0.7249841249268865
model_name： boston_LSTM_16_0.7250

boston_GRU_16_val_MAE: 3.244604744630701
boston_GRU_16_val_MSE： 31.916550943083372
boston_GRU_16_val_RMSE： 5.649473510255922
boston_GRU_16_val_R2: 0.7208388519283171
model_name： boston_GRU_16_0.7208


boston_LSTM_32_val_MAE: 3.289968232547536
boston_LSTM_32_val_MSE： 32.27946842476036
boston_LSTM_32_val_RMSE： 5.6815023035074415
boston_LSTM_32_val_R2: 0.7176645596615586
model_name： boston_LSTM_32_0.7177

boston_GRU_32_val_MAE: 3.6742190005732516
boston_GRU_32_val_MSE： 38.03228366757621
boston_GRU_32_val_RMSE： 6.167031998261093
boston_GRU_32_val_R2: 0.6673470140504223
model_name： boston_GRU_32_0.6673


boston_LSTM_64_val_MAE: 3.2653301463407627
boston_LSTM_64_val_MSE： 31.565284368449653
boston_LSTM_64_val_RMSE： 5.618299063635688
boston_LSTM_64_val_R2: 0.7239112384286261
model_name： boston_LSTM_64_0.7239



boston_GRU_64_val_MAE: 3.738212989358341
boston_GRU_64_val_MSE： 35.85519371644912
boston_GRU_64_val_RMSE： 5.987920650480358
boston_GRU_64_val_R2: 0.6863891383481191
model_name： boston_GRU_64_0.6864

# 绘制预测结果

DL之LSTM/GRU/CNN：基于tensorflow框架分别利用LSTM/GRUCNN算法对上海最高气温实现回归预测案例

DL之LSTM/GRU/CNN：基于tensorflow框架分别利用LSTM/GRU、CNN算法对上海最高气温实现回归预测案例

基于tensorflow框架分别利用LSTM/GRU、CNN算法对上海最高气温实现回归预测案例

# 1、定义数据集

# 2、特征工程

# 2.1、挑选入模特征

# 2.2、对数据切分并统一进行归一化处理

# 3、模型训练与验证

# 3.1、切分数据集将训练集和测试集，并转换为LSTM模型所需的数据格式

# 3.2、将数据转换为LSTM/GRU、CNN所需要的3D格式

# 3.3、构建LSTM/GRU、CNN模型

# 3.4、编译并训练模型

# 3.5、模型预测并将预测结果反归一化为原始值

基于tensorflow框架分别利用LSTM/GRU、CNN算法对上海最高气温实现回归预测案例

# 1、定义数据集

date	week	max_temperature	min_temperature	weather	wind_direction	wind_level	air_quality_index	air_quality_level
2021/1/1	周五	4	-1	晴~多云	西北风	2级	52	良
2021/1/2	周六	7	1	晴~多云	东北风	2级	69	良
2021/1/3	周日	10	6	阴	东北风	2级	66	良
2021/1/4	周一	13	7	阴	东风	2级	44	优
2021/1/5	周二	8	2	阴~多云	东北风	3级	49	优
2021/1/6	周三	5	-4	阴	北风	3级	46	优
2021/1/7	周四	-3	-6	阴	西北风	4级	67	良
2021/1/8	周五	-1	-5	阴~晴	西北风	3级	50	优
2021/1/9	周六	3	-1	晴~多云	西北风	3级	57	良
2021/1/10	周日	5	-1	阴~多云	西北风	2级	73	良

<class 'pandas.core.frame.DataFrame'>
DatetimeIndex: 805 entries, 2021-01-01 to 2023-03-16
Data columns (total 8 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   week               805 non-null    object 
 1   max_temperature    805 non-null    int64  
 2   min_temperature    805 non-null    int64  
 3   weather            805 non-null    object 
 4   wind_direction     805 non-null    object 
 5   wind_level         805 non-null    object 
 6   air_quality_index  667 non-null    float64
 7   air_quality_level  775 non-null    object 
dtypes: float64(1), int64(2), object(5)
memory usage: 56.6+ KB
None
           week  max_temperature  ...  air_quality_index air_quality_level
date                              ...                                     
2021-01-01   周五                4  ...               52.0                 良
2021-01-02   周六                7  ...               69.0                 良
2021-01-03   周日               10  ...               66.0                 良
2021-01-04   周一               13  ...               44.0                 优
2021-01-05   周二                8  ...               49.0                 优
...         ...              ...  ...                ...               ...
2023-03-12   周日               12  ...               68.0                 良
2023-03-13   周一               14  ...               52.0                 良
2023-03-14   周二               20  ...               55.0                 良
2023-03-15   周三               23  ...               52.0                 良
2023-03-16   周四               15  ...               69.0                 良

[805 rows x 8 columns]

# 2、特征工程

# 2.1、挑选入模特征

# 2.2、对数据切分并统一进行归一化处理

(730, 1)
(76, 1)

# 3、模型训练与验证

# 3.1、切分数据集将训练集和测试集，并转换为LSTM模型所需的数据格式

X_train after create_dataset (705, 25) 
            0         1         2   ...        22        23        24
0    0.162791  0.232558  0.302326  ...  0.255814  0.302326  0.418605
1    0.232558  0.302326  0.372093  ...  0.302326  0.418605  0.302326
2    0.302326  0.372093  0.255814  ...  0.418605  0.302326  0.302326
3    0.372093  0.255814  0.186047  ...  0.302326  0.302326  0.302326
4    0.255814  0.186047  0.000000  ...  0.302326  0.302326  0.255814
..        ...       ...       ...  ...       ...       ...       ...
700  0.255814  0.302326  0.302326  ...  0.186047  0.209302  0.232558
701  0.302326  0.302326  0.302326  ...  0.209302  0.232558  0.279070
702  0.302326  0.302326  0.348837  ...  0.232558  0.279070  0.232558
703  0.302326  0.348837  0.372093  ...  0.279070  0.232558  0.209302
704  0.348837  0.372093  0.441860  ...  0.232558  0.209302  0.232558

# 3.2、将数据转换为LSTM/GRU、CNN所需要的3D格式

X_train after reshape (705, 25, 1) 
 [[[0.1627907 ]
  [0.23255814]
  [0.30232558]
  ...
  [0.25581395]
  [0.30232558]
  [0.41860465]]

 [[0.23255814]
  [0.30232558]
  [0.37209302]
  ...
  [0.30232558]
  [0.41860465]
  [0.30232558]]

 [[0.30232558]
  [0.37209302]
  [0.25581395]
  ...
  [0.41860465]
  [0.30232558]
  [0.30232558]]

 ...

 [[0.30232558]
  [0.30232558]
  [0.34883721]
  ...
  [0.23255814]
  [0.27906977]
  [0.23255814]]

 [[0.30232558]
  [0.34883721]
  [0.37209302]
  ...
  [0.27906977]
  [0.23255814]
  [0.20930233]]

 [[0.34883721]
  [0.37209302]
  [0.44186047]
  ...
  [0.23255814]
  [0.20930233]
  [0.23255814]]

# 3.3、构建LSTM/GRU、CNN模型

# 3.4、编译并训练模型

Epoch 1/100
23/23 [==============================] - 3s 9ms/step - loss: 0.0749
Epoch 2/100
23/23 [==============================] - 0s 9ms/step - loss: 0.0135
Epoch 3/100
23/23 [==============================] - 0s 9ms/step - loss: 0.0100
Epoch 4/100
23/23 [==============================] - 0s 9ms/step - loss: 0.0101
Epoch 5/100
23/23 [==============================] - 0s 9ms/step - loss: 0.0097
Epoch 6/100
23/23 [==============================] - 0s 11ms/step - loss: 0.0091
Epoch 7/100
23/23 [==============================] - 0s 10ms/step - loss: 0.0094
Epoch 8/100
23/23 [==============================] - 0s 11ms/step - loss: 0.0097
Epoch 9/100
23/23 [==============================] - 0s 11ms/step - loss: 0.0089
Epoch 10/100
……

Epoch 97/100
23/23 [==============================] - 0s 13ms/step - loss: 0.0059
Epoch 98/100
23/23 [==============================] - 0s 14ms/step - loss: 0.0055
Epoch 99/100
23/23 [==============================] - 0s 13ms/step - loss: 0.0053
Epoch 100/100
23/23 [==============================] - 0s 13ms/step - loss: 0.0053
2/2 [==============================] - 1s 4ms/step
LSTM_val_RMSE： 7.681726490151304
LSTM_val_MSE: 14.169289610796568
LSTM_val_R2: 0.5862969525651983

# 3.5、模型预测并将预测结果反归一化为原始值

# 3.6、模型评估

'''
40 0.51478
25 0.586529
20 0.579569
12   0.5689
6   0.5397
'''

LSTM_val_RMSE： 7.666831051805234
LSTM_val_MSE: 14.324265340141883
LSTM_val_R2: 0.5817721010539598


LSTM_val_RMSE： 7.778038916207498
LSTM_val_MSE: 15.424474218238425
LSTM_val_R2: 0.5496491239544908

# 3.7、绘制预测值对比真实值

LSTM，epochs = 100

LSTM_val_RMSE： 7.7114049938862195
LSTM_val_MSE: 14.225878442019523
LSTM_val_R2: 0.5846447192796375

LSTM，epochs = 400

LSTM_val_RMSE： 7.926438561188859
LSTM_val_MSE: 18.42118750026751
LSTM_val_R2: 0.4621536001055656

GRU2，epochs = 100

GRU2，epochs = 400

GRU_val_RMSE： 7.801296944756388
GRU_val_MSE: 15.746488121878885
GRU_val_R2: 0.5402472317699365

GRU3，epochs = 100

GRU3_val_RMSE： 7.748423445714951
GRU3_val_MSE: 15.642613371982792
GRU3_val_R2: 0.5432800796941399

GRU3，epochs = 400

GRU3_val_RMSE： 7.767935199334584
GRU3_val_MSE: 16.609856586892658
GRU3_val_R2: 0.5150393226336065

CNN，epochs = 100

CNN_val_RMSE： 8.157615491942318
CNN_val_MSE: 26.20883236889009
CNN_val_R2: 0.23477646949527275

CNN，epochs = 400

CNN_val_RMSE： 8.045454928215973
CNN_val_MSE: 36.41909143818048
CNN_val_R2: -0.06333412094997337

以上是关于TF之LSTM/GRU：基于tensorflow框架对boston房价数据集分别利用LSTMGRU算法(batch_size调优对比)实现房价回归预测案例的主要内容，如果未能解决你的问题，请参考以下文章

3.5 tensorflow 中LSTM和GRU模块使用意境级讲解

Tensorflow 2 实战（kears）- 双层RNN/LSTM/GRU

中文文本分类之TextRNN

几种常见的循环神经网络结构RNN、LSTM、GRU

RNN - LSTM - GRU

如何在 Pytorch LSTM/GRU/RNN 中指定不同的层大小

TF之LSTM/GRU：基于tensorflow框架对boston房价数据集分别利用LSTMGRU算法(batch_size调优对比)实现房价回归预测案例

基于tensorflow框架对boston房价数据集分别利用LSTM、GRU算法(batch_size调优对比)实现房价回归预测案例

# 1、定义数据集

# 2、数据预处理

# 2.1、分离特征和标签

# 3、模型训练与推理

# 3.1、切分数据集

# 3.2、数据再处理

# 将输入数据重塑为3D张量（样本数、时间步长、特征数）

# 3.3、模型建立和训练

# 3.4、模型训练

# 绘制训练集和测试集的loss曲线

# 3.5、模型评估

# 绘制预测结果​​

DL之LSTM/GRU/CNN：基于tensorflow框架分别利用LSTM/GRUCNN算法对上海最高气温实现回归预测案例

基于tensorflow框架分别利用LSTM/GRU、CNN算法对上海最高气温实现回归预测案例

# 1、定义数据集

# 2、特征工程

# 2.1、挑选入模特征

# 2.2、对数据切分并统一进行归一化处理

# 3、模型训练与验证

# 3.1、切分数据集将训练集和测试集，并转换为LSTM模型所需的数据格式

# 3.2、将数据转换为LSTM/GRU、CNN所需要的3D格式

# 3.3、构建LSTM/GRU、CNN模型

# 3.4、编译并训练模型

# 3.5、模型预测并将预测结果反归一化为原始值

# 3.6、模型评估

# 3.7、绘制预测值对比真实值

LSTM，epochs = 100

LSTM，epochs = 400

GRU2，epochs = 100

GRU2，epochs = 400

GRU3，epochs = 100

GRU3，epochs = 400

CNN，epochs = 100

CNN，epochs = 400

# 绘制预测结果