AI - TensorFlow - 示例03:基本回归

基本回归

回归(Regression):https://www.tensorflow.org/tutorials/keras/basic_regressionpython

主要步骤:
数据部分git

  1.   获取数据(Get the data)
  2.   清洗数据(Clean the data)
  3.   划分训练集和测试集(Split the data into train and test)
  4.   检查数据(Inspect the data)
  5.   分离标签(Split features from labels)
  6.   规范化数据(Normalize the data)

模型部分github

  1.   构建模型(Build the model)
  2.   检查模型(Inspect the model)
  3.   训练模型(Train the model)
  4.   作出预测(Make predictions)

Auto MPG Data Set (汽车MPG数据集)

Attribute Information:api

  • 1. mpg: continuous
  • 2. cylinders: multi-valued discrete
  • 3. displacement: continuous
  • 4. horsepower: continuous
  • 5. weight: continuous
  • 6. acceleration: continuous
  • 7. model year: multi-valued discrete
  • 8. origin: multi-valued discrete
  • 9. car name: string (unique for each instance)

一些知识点

验证集

  • - 一般指定训练集的必定比例数据做为验证集。
  • - 验证集将不参与训练,并在每一个epoch结束后测试的模型的指标,如损失函数、精确度等。
  • - 若是数据自己是有序的,须要先手工打乱再指定,不然可能会出现验证集样本不均匀。

回调函数(Callbacks)

回调函数是一个函数的合集,在训练的阶段中,用来查看训练模型的内在状态和统计。
在训练时,相应的回调函数的方法就会被在各自的阶段被调用。
通常是在model.fit函数中调用callbacks(参数为callbacks,必须输入list类型的数据)。
简而言之,Callbacks用于指定在每一个epoch开始和结束的时候进行哪一种特定操做。网络

EarlyStopping

EarlyStopping是Callbacks的一种,可用来加快学习的速度,提升调参效率。
使用一个EarlyStopping回调来测试每个迭代的训练条件,若是某个迭代事后没有显示改进,自动中止训练。dom

结论(conclusion)

  • - 均方偏差(MSE)是一种常见的损失函数,可用于回归问题。
  • - 用于回归和分类问题的损失函数不一样,评价指标也不一样,常见的回归指标是平均绝对偏差(MAE)。
  • - 当输入的数据特性包含不一样范围的数值,每一个特性都应该独立为相同的范围。
  • - 若是没有太多的训练数据时,有一个技巧就是采用包含少许隐藏层的小型网络,更适合来避免过拟合。
  • - EarlyStopping是一个防止过分拟合的实用技巧。

示例

脚本内容

GitHub:https://github.com/anliven/Hello-AI/blob/master/Google-Learn-and-use-ML/3_basic_regression.py函数

 

  1 # coding=utf-8
  2 import tensorflow as tf
  3 from tensorflow import keras
  4 from tensorflow.python.keras import layers
  5 import matplotlib.pyplot as plt
  6 import pandas as pd
  7 import seaborn as sns
  8 import pathlib
  9 import os
 10 
 11 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 12 print("# TensorFlow version: {}  - tf.keras version: {}".format(tf.VERSION, tf.keras.__version__))  # 查看版本
 13 
 14 # ### 数据部分
 15 # 获取数据(Get the data)
 16 ds_path = str(pathlib.Path.cwd()) + "\\datasets\\auto-mpg\\"
 17 ds_file = keras.utils.get_file(fname=ds_path + "auto-mpg.data", origin="file:///" + ds_path)  # 得到文件路径
 18 column_names = ['MPG', 'Cylinders', 'Displacement', 'Horsepower', 'Weight', 'Acceleration', 'Model Year', 'Origin']
 19 raw_dataset = pd.read_csv(filepath_or_buffer=ds_file,  # 数据的路径
 20                           names=column_names,  # 用于结果的列名列表
 21                           na_values="?",  # 用于替换NA/NaN的值
 22                           comment='\t',  # 标识着多余的行不被解析(若是该字符出如今行首,这一行将被所有忽略)
 23                           sep=" ",  # 分隔符
 24                           skipinitialspace=True  # 忽略分隔符后的空白(默认为False,即不忽略)
 25                           )  # 经过pandas导入数据
 26 data_set = raw_dataset.copy()
 27 print("# Data set tail:\n{}".format(data_set.tail()))  # 显示尾部数据
 28 
 29 # 清洗数据(Clean the data)
 30 print("# Summary of NaN:\n{}".format(data_set.isna().sum()))  # 统计NaN值个数(NaN表明缺失值,可用isna()和notna()来检测)
 31 data_set = data_set.dropna()  # 方法dropna()对缺失的数据进行过滤
 32 origin = data_set.pop('Origin')  # Origin"列是分类不是数值,转换为独热编码(one-hot encoding)
 33 data_set['USA'] = (origin == 1) * 1.0
 34 data_set['Europe'] = (origin == 2) * 1.0
 35 data_set['Japan'] = (origin == 3) * 1.0
 36 data_set.tail()
 37 print("# Data set tail:\n{}".format(data_set.tail()))  # 显示尾部数据
 38 
 39 # 划分训练集和测试集(Split the data into train and test)
 40 train_dataset = data_set.sample(frac=0.8, random_state=0)
 41 test_dataset = data_set.drop(train_dataset.index)  # 测试做为模型的最终评估
 42 
 43 # 检查数据(Inspect the data)
 44 sns.pairplot(train_dataset[["MPG", "Cylinders", "Displacement", "Weight"]], diag_kind="kde")
 45 plt.figure(num=1)
 46 plt.savefig("./outputs/sample-3-figure-1.png", dpi=200, format='png')
 47 plt.show()
 48 plt.close()
 49 train_stats = train_dataset.describe()  # 整体统计数据
 50 train_stats.pop("MPG")
 51 train_stats = train_stats.transpose()  # 经过transpose()得到矩阵的转置
 52 print("# Train statistics:\n{}".format(train_stats))
 53 
 54 # 分离标签(Split features from labels)
 55 train_labels = train_dataset.pop('MPG')  # 将要预测的值
 56 test_labels = test_dataset.pop('MPG')
 57 
 58 
 59 # 规范化数据(Normalize the data)
 60 def norm(x):
 61     return (x - train_stats['mean']) / train_stats['std']
 62 
 63 
 64 normed_train_data = norm(train_dataset)
 65 normed_test_data = norm(test_dataset)
 66 
 67 
 68 # ### 模型部分
 69 # 构建模型(Build the model)
 70 def build_model():  # 模型被包装在此函数中
 71     model = keras.Sequential([  # 使用Sequential模型
 72         layers.Dense(64, activation=tf.nn.relu, input_shape=[len(train_dataset.keys())]),  # 包含64个单元的全链接隐藏层
 73         layers.Dense(64, activation=tf.nn.relu),  # 包含64个单元的全链接隐藏层
 74         layers.Dense(1)]  # 一个输出层,返回单个连续的值
 75     )
 76     optimizer = tf.keras.optimizers.RMSprop(0.001)
 77     model.compile(loss='mean_squared_error',  # 损失函数
 78                   optimizer=optimizer,  # 优化器
 79                   metrics=['mean_absolute_error', 'mean_squared_error']  # 在训练和测试期间的模型评估标准
 80                   )
 81     return model
 82 
 83 
 84 # 检查模型(Inspect the model)
 85 mod = build_model()  # 建立模型
 86 mod.summary()  # 打印出关于模型的简单描述
 87 example_batch = normed_train_data[:10]  # 从训练集中截取10个做为示例批次
 88 example_result = mod.predict(example_batch)  # 使用predict()方法进行预测
 89 print("# Example result:\n{}".format(example_result))
 90 
 91 
 92 # 训练模型(Train the model)
 93 class PrintDot(keras.callbacks.Callback):
 94     def on_epoch_end(self, epoch, logs):
 95         if epoch % 100 == 0:
 96             print('')
 97         print('.', end='')  # 每完成一次训练打印一个“.”符号
 98 
 99 
100 EPOCHS = 1000  # 训练次数
101 
102 history = mod.fit(normed_train_data,
103                   train_labels,
104                   epochs=EPOCHS,  # 训练周期(训练模型迭代轮次)
105                   validation_split=0.2,  # 用来指定训练集的必定比例数据做为验证集(0~1之间的浮点数)
106                   verbose=0,  # 日志显示模式:0为安静模式, 1为进度条(默认), 2为每轮一行
107                   callbacks=[PrintDot()]  # 回调函数(在训练过程当中的适当时机被调用)
108                   )  # 返回一个history对象,包含一个字典,其中包括训练期间发生的状况(training and validation accuracy)
109 
110 
111 def plot_history(h, n=1):
112     """可视化模型训练过程"""
113     hist = pd.DataFrame(h.history)
114     hist['epoch'] = h.epoch
115     print("\n# History tail:\n{}".format(hist.tail()))
116 
117     plt.figure(num=n, figsize=(6, 8))
118 
119     plt.subplot(2, 1, 1)
120     plt.xlabel('Epoch')
121     plt.ylabel('Mean Abs Error [MPG]')
122     plt.plot(hist['epoch'], hist['mean_absolute_error'], label='Train Error')
123     plt.plot(hist['epoch'], hist['val_mean_absolute_error'], label='Val Error')
124     plt.ylim([0, 5])
125 
126     plt.subplot(2, 1, 2)
127     plt.xlabel('Epoch')
128     plt.ylabel('Mean Square Error [$MPG^2$]')
129     plt.plot(hist['epoch'], hist['mean_squared_error'], label='Train Error')
130     plt.plot(hist['epoch'], hist['val_mean_squared_error'], label='Val Error')
131     plt.ylim([0, 20])
132 
133     filename = "./outputs/sample-3-figure-" + str(n) + ".png"
134     plt.savefig(filename, dpi=200, format='png')
135     plt.show()
136     plt.close()
137 
138 
139 plot_history(history, 2)  # 可视化
140 
141 # 调试
142 model2 = build_model()
143 early_stop = keras.callbacks.EarlyStopping(monitor='val_loss',
144                                            patience=10)  # 指定提早中止训练的callbacks
145 history2 = model2.fit(normed_train_data,
146                       train_labels,
147                       epochs=EPOCHS,
148                       validation_split=0.2,
149                       verbose=0,
150                       callbacks=[early_stop, PrintDot()])  # 当没有改进时自动中止训练(经过EarlyStopping)
151 plot_history(history2, 3)
152 loss, mae, mse = model2.evaluate(normed_test_data, test_labels, verbose=0)
153 print("# Testing set Mean Abs Error: {:5.2f} MPG".format(mae))  # 测试集上的MAE值
154 
155 # 作出预测(Make predictions)
156 test_predictions = model2.predict(normed_test_data).flatten()  # 使用测试集中数据进行预测
157 plt.figure(num=4, figsize=(6, 8))
158 plt.scatter(test_labels, test_predictions)
159 plt.xlabel('True Values [MPG]')
160 plt.ylabel('Predictions [MPG]')
161 plt.axis('equal')
162 plt.axis('square')
163 plt.xlim([0, plt.xlim()[1]])
164 plt.ylim([0, plt.ylim()[1]])
165 plt.plot([-100, 100], [-100, 100])
166 plt.savefig("./outputs/sample-3-figure-4.png", dpi=200, format='png')
167 plt.show()
168 plt.close()
169 
170 error = test_predictions - test_labels
171 plt.figure(num=5, figsize=(6, 8))
172 plt.hist(error, bins=25)  # 经过直方图来展现错误的分布状况
173 plt.xlabel("Prediction Error [MPG]")
174 plt.ylabel("Count")
175 plt.savefig("./outputs/sample-3-figure-5.png", dpi=200, format='png')
176 plt.show()
177 plt.close()

 

运行结果

C:\Users\anliven\AppData\Local\conda\conda\envs\mlcc\python.exe D:/Anliven/Anliven-Code/PycharmProjects/Google-Learn-and-use-ML/3_basic_regression.py
# TensorFlow version: 1.12.0  - tf.keras version: 2.1.6-tf
# Data set tail:
      MPG  Cylinders  Displacement   ...    Acceleration  Model Year  Origin
393  27.0          4         140.0   ...            15.6          82       1
394  44.0          4          97.0   ...            24.6          82       2
395  32.0          4         135.0   ...            11.6          82       1
396  28.0          4         120.0   ...            18.6          82       1
397  31.0          4         119.0   ...            19.4          82       1

[5 rows x 8 columns]
# Summary of NaN:
MPG             0
Cylinders       0
Displacement    0
Horsepower      6
Weight          0
Acceleration    0
Model Year      0
Origin          0
dtype: int64
# Data set tail:
      MPG  Cylinders  Displacement  ...    USA  Europe  Japan
393  27.0          4         140.0  ...    1.0     0.0    0.0
394  44.0          4          97.0  ...    0.0     1.0    0.0
395  32.0          4         135.0  ...    1.0     0.0    0.0
396  28.0          4         120.0  ...    1.0     0.0    0.0
397  31.0          4         119.0  ...    1.0     0.0    0.0

[5 rows x 10 columns]
# Train statistics:
              count         mean         std   ...       50%      75%     max
Cylinders     314.0     5.477707    1.699788   ...       4.0     8.00     8.0
Displacement  314.0   195.318471  104.331589   ...     151.0   265.75   455.0
Horsepower    314.0   104.869427   38.096214   ...      94.5   128.00   225.0
Weight        314.0  2990.251592  843.898596   ...    2822.5  3608.00  5140.0
Acceleration  314.0    15.559236    2.789230   ...      15.5    17.20    24.8
Model Year    314.0    75.898089    3.675642   ...      76.0    79.00    82.0
USA           314.0     0.624204    0.485101   ...       1.0     1.00     1.0
Europe        314.0     0.178344    0.383413   ...       0.0     0.00     1.0
Japan         314.0     0.197452    0.398712   ...       0.0     0.00     1.0

[9 rows x 8 columns]
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                (None, 64)                640       
_________________________________________________________________
dense_1 (Dense)              (None, 64)                4160      
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 65        
=================================================================
Total params: 4,865
Trainable params: 4,865
Non-trainable params: 0
_________________________________________________________________
# Example result:
[[0.3783294 ]
 [0.17875314]
 [0.68095654]
 [0.45696187]
 [1.4998233 ]
 [0.05698915]
 [1.4138494 ]
 [0.7885587 ]
 [0.10802953]
 [1.3029677 ]]

....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
# History tail:
     val_loss  val_mean_absolute_error  ...    mean_squared_error  epoch
995  9.350584                 2.267639  ...              2.541113    995
996  9.191998                 2.195405  ...              2.594836    996
997  9.559576                 2.384058  ...              2.576047    997
998  8.791337                 2.145222  ...              2.782730    998
999  9.088490                 2.227165  ...              2.425531    999

[5 rows x 7 columns]

.........................................................................................
# History tail:
    val_loss  val_mean_absolute_error  ...    mean_squared_error  epoch
84  8.258534                 2.233329  ...              6.221810     84
85  8.328515                 2.208959  ...              6.213853     85
86  8.420452                 2.224991  ...              6.427011     86
87  8.418247                 2.215443  ...              6.178523     87
88  8.437484                 2.193801  ...              6.183405     88

[5 rows x 7 columns]
# Testing set Mean Abs Error:  1.88 MPG

Process finished with exit code 0

 

 

 

 

 

 

 

问题处理

问题1:执行“import tensorflow.keras import layers”失败,提示“Unresolved reference”

问题描述
在Anaconda3建立的运行环境中,执行“import tensorflow.keras import layers”失败,提示“Unresolved reference”
学习

 

处理方法
改写为“from tensorflow.python.keras import layers”
导入包时,须要根据实际的具体位置进行导入。
确认TensorFlow中Keras的实际位置:“D:\DownLoadFiles\anaconda3\envs\mlcc\Lib\site-packages\tensorflow\python\keras\”。
实际上多了一层目录“python”,因此正确的导入方式为“from tensorflow.python.keras import layers”。测试


参考信息
https://stackoverflow.com/questions/47262955/how-to-import-keras-from-tf-keras-in-tensorflowfetch

问题2:执行keras.utils.get_file()报错

问题描述
执行keras.utils.get_file("auto-mpg.data", "https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")报错:

Downloading data from https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data
Traceback (most recent call last):
......
Exception: URL fetch failure on https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data: None -- [WinError 10060] A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond


处理方法“网络”的缘由,致使没法下载。手工下载,而后放置在当前目录,从当前目录地址导入数据文件。

相关文章
相关标签/搜索