【Keras学习笔记】2：多元线性回归预测Kaggle房价

多元线性回归

训练模型

多元线性回归也就相当于NN的一层，y=wx+b，其中w和x是>1维的同维向量，也就是用输入的特征x1,x2,…去使用参数w和b预测y值。

import pandas as pd
import matplotlib as plt
%matplotlib inline

# Kaggle房价的train数据
df = pd.read_csv("./data/hp_train.csv")
df.head()

	Id	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	...	PoolArea	PoolQC	Fence	MiscFeature	MiscVal	MoSold	YrSold	SaleType	SaleCondition	SalePrice
0	1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	...	0	NaN	NaN	NaN	0	2	2008	WD	Normal	208500
1	2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	...	0	NaN	NaN	NaN	0	5	2007	WD	Normal	181500
2	3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	...	0	NaN	NaN	NaN	0	9	2008	WD	Normal	223500
3	4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	...	0	NaN	NaN	NaN	0	2	2006	WD	Abnorml	140000
4	5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	...	0	NaN	NaN	NaN	0	12	2008	WD	Normal	250000

5 rows × 81 columns

import numpy as np
# 处理极端值
train = df[df['GarageArea'] < 1200]
# 处理缺失值:对于数值形式的数据,先用默认interpolate()进行插值,再删除那些有NaN的行
train = train.select_dtypes(include=[np.number]).interpolate().dropna()
train.head()

	Id	MSSubClass	LotFrontage	LotArea	OverallQual	OverallCond	YearBuilt	YearRemodAdd	MasVnrArea	BsmtFinSF1	...	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	MiscVal	MoSold	YrSold	SalePrice
0	1	60	65.0	8450	7	5	2003	2003	196.0	706	...	0	61	0	0	0	0	0	2	2008	208500
1	2	20	80.0	9600	6	8	1976	1976	0.0	978	...	298	0	0	0	0	0	0	5	2007	181500
2	3	60	68.0	11250	7	5	2001	2002	162.0	486	...	0	42	0	0	0	0	0	9	2008	223500
3	4	70	60.0	9550	7	5	1915	1970	0.0	216	...	0	35	272	0	0	0	0	2	2006	140000
4	5	60	84.0	14260	8	5	2000	2000	350.0	655	...	192	84	0	0	0	0	0	12	2008	250000

5 rows × 38 columns

# 取出特征和预测值
x = train.iloc[:,1:37]
y = train.iloc[:,-1]

import keras
# 初始化model
model = keras.Sequential()

Using TensorFlow backend.

# 添加全连接层(输出维度是1,输入维度是36)
from keras import layers
model.add(layers.Dense(1, input_dim=36))

WARNING:tensorflow:From E:\MyProgram\Anaconda\envs\krs\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.

model.summary()

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 1)                 37        
=================================================================
Total params: 37
Trainable params: 37
Non-trainable params: 0
_________________________________________________________________

# 编译model,指明优化器和优化目标
model.compile(
    optimizer='adam',
    loss='mse'
)

# 训练模型
model.fit(x, y, epochs=3000, verbose=0)

WARNING:tensorflow:From E:\MyProgram\Anaconda\envs\krs\lib\site-packages\tensorflow\python\ops\math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.

model.predict(x)

array([[200142.2 ],
       [188487.61],
       [205551.75],
       ...,
       [218197.34],
       [115874.6 ],
       [191411.95]], dtype=float32)

y.head()

0    208500
1    181500
2    223500
3    140000
4    250000
Name: SalePrice, dtype: int64

生成预测值以提交到Kaggle

# Kaggle房价的test数据
df = pd.read_csv("./data/hp_test.csv")
# 取数字列,删除id列,进行插值(和训练集相同的预处理)
test = df.select_dtypes(include=np.number).drop(["Id"], axis=1).interpolate()
test.head()

	MSSubClass	LotFrontage	LotArea	OverallQual	OverallCond	YearBuilt	YearRemodAdd	MasVnrArea	BsmtFinSF1	BsmtFinSF2	...	GarageArea	WoodDeckSF	OpenPorchSF	EnclosedPorch	3SsnPorch	ScreenPorch	PoolArea	MiscVal	MoSold	YrSold
0	20	80.0	11622	5	6	1961	1961	0.0	468.0	144.0	...	730.0	140	0	0	0	120	0	0	6	2010
1	20	81.0	14267	6	6	1958	1958	108.0	923.0	0.0	...	312.0	393	36	0	0	0	0	12500	6	2010
2	60	74.0	13830	5	5	1997	1998	0.0	791.0	0.0	...	482.0	212	34	0	0	0	0	0	3	2010
3	60	78.0	9978	6	6	1998	1998	20.0	602.0	0.0	...	470.0	360	36	0	0	0	0	0	6	2010
4	120	43.0	5005	8	5	1992	1992	0.0	263.0	0.0	...	506.0	0	82	0	0	144	0	0	1	2010

5 rows × 36 columns

# 计算预测值
predictions = model.predict(test)

# 生成提交csv
submissions = pd.DataFrame()
submissions["Id"] = df.Id
submissions["SalePrice"] = predictions
submissions.to_csv("./data/hp_upload.csv", index=False)