Tensorflow2.0学习-回归问题 (三)

分类和回归是两种问题，就看下回归。
就是将模型最后输出换一下，以及损失函数换一下就好了

文章目录

回归

引包

seaborn 是绘制矩阵图的包

import pathlib

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers

print(tf.__version__)

数据准备

# 下载数据
dataset_path = keras.utils.get_file("auto-mpg.data", "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")

column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight',
                'Acceleration', 'Model Year', 'Origin']
raw_dataset = pd.read_csv(dataset_path, names=column_names,
                      na_values = "?", comment='\t',
                      sep=" ", skipinitialspace=True)

dataset = raw_dataset.copy()
# 清洗数据
dataset = dataset.dropna()
origin = dataset.pop('Origin')
dataset['USA'] = (origin == 1)*1.0
dataset['Europe'] = (origin == 2)*1.0
dataset['Japan'] = (origin == 3)*1.0

# 拆分数据集
train_dataset = dataset.sample(frac=0.8,random_state=0)
test_dataset = dataset.drop(train_dataset.index)

# 分离标签
train_labels = train_dataset.pop('MPG')
test_labels = test_dataset.pop('MPG')

# 数据规范
def norm(x):
  return (x - train_stats['mean']) / train_stats['std']
normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)

模型准备

def build_model():
    model = keras.Sequential([
        layers.Dense(64, activation='relu', input_shape=[len(train_dataset.keys())]),
        layers.Dense(64, activation='relu'),
        layers.Dense(1)
    ])

    optimizer = tf.keras.optimizers.RMSprop(0.001)

    model.compile(loss='mse',
                  optimizer=optimizer,
                  metrics=['mae', 'mse'])
    return model
model = build_model()
# 打印模型
model.summary()

# 检查下是否可以工作
example_batch = normed_train_data[:10]
example_result = model.predict(example_batch)
print(example_result)

跑起来

# 通过为每个完成的时期打印一个点来显示训练进度
class PrintDot(keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs):
    if epoch % 100 == 0: print('')
    print('.', end='')

EPOCHS = 1000

history = model.fit(
  normed_train_data, train_labels,
  epochs=EPOCHS, validation_split = 0.2, verbose=0,
  callbacks=[PrintDot()])

# 用history把训练信息提取出来
hist = pd.DataFrame(history.history)
hist['epoch'] = history.epoch
print(hist.tail())

# 用图的形式看下效果
def plot_history(history):
    hist = pd.DataFrame(history.history)
    hist['epoch'] = history.epoch

    plt.figure()
    plt.xlabel('Epoch')
    plt.ylabel('Mean Abs Error [MPG]')
    plt.plot(hist['epoch'], hist['mae'],
             label='Train Error')
    plt.plot(hist['epoch'], hist['val_mae'],
             label='Val Error')
    plt.ylim([0, 5])
    plt.legend()

    plt.figure()
    plt.xlabel('Epoch')
    plt.ylabel('Mean Square Error [$MPG^2$]')
    plt.plot(hist['epoch'], hist['mse'],
             label='Train Error')
    plt.plot(hist['epoch'], hist['val_mse'],
             label='Val Error')
    plt.ylim([0, 20])
    plt.legend()
    plt.show()


plot_history(history)
# 结果有些过拟合，调整下
# patience 值用来检查改进 epochs 的数量
early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)

history = model.fit(normed_train_data, train_labels, epochs=EPOCHS,
                    validation_split = 0.2, verbose=0, callbacks=[early_stop, PrintDot()])

plot_history(history)

# 最后在测试集上试试
loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)

print("Testing set Mean Abs Error: {:5.2f} MPG".format(mae))

做预测

test_predictions = model.predict(normed_test_data).flatten()

plt.scatter(test_labels, test_predictions)
plt.xlabel('True Values [MPG]')
plt.ylabel('Predictions [MPG]')
plt.axis('equal')
plt.axis('square')
plt.xlim([0,plt.xlim()[1]])
plt.ylim([0,plt.ylim()[1]])
_ = plt.plot([-100, 100], [-100, 100])

error = test_predictions - test_labels
plt.hist(error, bins = 25)
plt.xlabel("Prediction Error [MPG]")
_ = plt.ylabel("Count")

整体代码

import pathlib

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers

print(tf.__version__)

dataset_path = keras.utils.get_file("auto-mpg.data",
                                    "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")
print(dataset_path)

column_names = ['MPG', 'Cylinders', 'Displacement', 'Horsepower', 'Weight',
                'Acceleration', 'Model Year', 'Origin']
raw_dataset = pd.read_csv(dataset_path, names=column_names,
                          na_values="?", comment='\t',
                          sep=" ", skipinitialspace=True)

dataset = raw_dataset.copy()
print(dataset.tail())

dataset.isna().sum()
dataset = dataset.dropna()
origin = dataset.pop('Origin')
dataset['USA'] = (origin == 1) * 1.0
dataset['Europe'] = (origin == 2) * 1.0
dataset['Japan'] = (origin == 3) * 1.0
print(dataset.tail())

train_dataset = dataset.sample(frac=0.8, random_state=0)
test_dataset = dataset.drop(train_dataset.index)

sns.pairplot(train_dataset[["MPG", "Cylinders", "Displacement", "Weight"]], diag_kind="kde")
plt.show()
train_stats = train_dataset.describe()
train_stats.pop("MPG")
train_stats = train_stats.transpose()
print(train_stats)

train_labels = train_dataset.pop('MPG')
test_labels = test_dataset.pop('MPG')


def norm(x):
    return (x - train_stats['mean']) / train_stats['std']


normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)


def build_model():
    model = keras.Sequential([
        layers.Dense(64, activation='relu', input_shape=[len(train_dataset.keys())]),
        layers.Dense(64, activation='relu'),
        layers.Dense(1)
    ])

    optimizer = tf.keras.optimizers.RMSprop(0.001)

    model.compile(loss='mse',
                  optimizer=optimizer,
                  metrics=['mae', 'mse'])
    return model


def build_model():
    model = keras.Sequential([
        layers.Dense(64, activation='relu', input_shape=[len(train_dataset.keys())]),
        layers.Dense(64, activation='relu'),
        layers.Dense(1)
    ])

    optimizer = tf.keras.optimizers.RMSprop(0.001)

    model.compile(loss='mse',
                  optimizer=optimizer,
                  metrics=['mae', 'mse'])
    return model


model = build_model()
# 打印模型
model.summary()

# 检查下是否可以工作
example_batch = normed_train_data[:10]
example_result = model.predict(example_batch)
print(example_result)


# 通过为每个完成的时期打印一个点来显示训练进度
class PrintDot(keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs):
        if epoch % 100 == 0: print('')
        print('.', end='')


EPOCHS = 1000

history = model.fit(
    normed_train_data, train_labels,
    epochs=EPOCHS, validation_split=0.2, verbose=0,
    callbacks=[PrintDot()])

# 用history把训练信息提取出来
hist = pd.DataFrame(history.history)
hist['epoch'] = history.epoch
print(hist.tail())


def plot_history(history):
    hist = pd.DataFrame(history.history)
    hist['epoch'] = history.epoch

    plt.figure()
    plt.xlabel('Epoch')
    plt.ylabel('Mean Abs Error [MPG]')
    plt.plot(hist['epoch'], hist['mae'],
             label='Train Error')
    plt.plot(hist['epoch'], hist['val_mae'],
             label='Val Error')
    plt.ylim([0, 5])
    plt.legend()

    plt.figure()
    plt.xlabel('Epoch')
    plt.ylabel('Mean Square Error [$MPG^2$]')
    plt.plot(hist['epoch'], hist['mse'],
             label='Train Error')
    plt.plot(hist['epoch'], hist['val_mse'],
             label='Val Error')
    plt.ylim([0, 20])
    plt.legend()
    plt.show()


plot_history(history)

model = build_model()

# patience 值用来检查改进 epochs 的数量
early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)

history = model.fit(normed_train_data, train_labels, epochs=EPOCHS,
                    validation_split = 0.2, verbose=0, callbacks=[early_stop, PrintDot()])

plot_history(history)

loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)

print("Testing set Mean Abs Error: {:5.2f} MPG".format(mae))
test_predictions = model.predict(normed_test_data).flatten()

plt.scatter(test_labels, test_predictions)
plt.xlabel('True Values [MPG]')
plt.ylabel('Predictions [MPG]')
plt.axis('equal')
plt.axis('square')
plt.xlim([0,plt.xlim()[1]])
plt.ylim([0,plt.ylim()[1]])
_ = plt.plot([-100, 100], [-100, 100])

error = test_predictions - test_labels
plt.hist(error, bins = 25)
plt.xlabel("Prediction Error [MPG]")
_ = plt.ylabel("Count")

总结

我们将使用一个 EarlyStopping callback 来测试每个 epoch 的训练条件。如果经过一定数量的 epochs后没有改进，则自动停止训练。

sns.pairplot的用法

posted @   赫凯  阅读(20)  评论(0)  编辑  收藏  举报
相关博文：
·  Tensorflow2.0学习-快速入门 (一)
·  Tensorflow2.0学习-基础分类 (二)
·  tensorflow2.0的学习
·  [深度学习] tf.keras入门3-回归
·  TensorFlow 2.0 快速入门指南：第二部分
阅读排行：
· 25岁的心里话
· 闲置电脑爆改个人服务器（超详细） #公网映射 #Vmware虚拟网络编辑器
· 基于 Docker 搭建 FRP 内网穿透开源项目（很简单哒）
· 零经验选手，Compose 一天开发一款小游戏！
· 一起来玩mcp_server_sqlite，让AI帮你做增删改查！！
点击右上角即可分享
微信分享提示