用TensorFlow进行回归分析

应用的Python包

• tensorflow
• pandas
• seaborn
• matplotlib

数据集介绍

本次使用的数据集来源于UCI机器学习库。
Auto MPG数据集是一个经典的数据集，本次将使用它来构建预测70年代末到80年代初汽车燃油效率模型。

数据清洗

数据检查

分离特征并规范化数据

构建模型

Model: "sequential"
_________________________________________________________________
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
_________________________________________________________________

训练模型

EPOCHS = 1000
history = md.fit(normed_train_data, train_labels, epochs=EPOCHS, validation_split=0.2, verbose=0)

预测结果

完整代码

# ！/usr/bin/env python
# —*— coding: utf-8 —*—
# @Time:    2020/1/9 8:27
# @Author:  Martin
# @File:    Regression.py
# @Software:PyCharm
from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
from tensorflow import keras
# 下载数据集
data_path = keras.utils.get_file(
    "auto-mpg.data",
    "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")
# 导入数据集
column_names = [
    'MPG',
    'Cylinders',
    'Displacement',
    'Horsepower',
    'Weight',
    'Acceleration',
    'Model Year',
    'Origin']
raw_dataset = pd.read_csv(
    data_path,
    names=column_names,
    na_values='?',
    comment='\t',
    sep=' ',
    skipinitialspace=True)
dataset = raw_dataset.copy()
# 数据清洗
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
# 拆分训练数据集和测试数据集
train_dataset = dataset.sample(frac=0.8, random_state=0)
test_dataset = dataset.drop(train_dataset.index)
# 数据检查
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()
# 分离特征
train_labels = train_dataset.pop('MPG')
test_labels = test_dataset.pop('MPG')
# 数据规范化


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


normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)
# 构建模型


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

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

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


md = build_model()
# 训练模型
EPOCHS = 1000
history = md.fit(normed_train_data, train_labels, epochs=EPOCHS, validation_split=0.2, verbose=0)
# 进行预测
test_predictions = md.predict(normed_test_data).flatten()
# 预测结果可视化
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])
plt.show()
# 误差分布可视化
error = test_predictions - test_labels
plt.hist(error, bins=25)
plt.xlabel('Prediction Error [MPG]')
_ = plt.ylabel('Count')
plt.show()