Learn：Build Meachine Learning Model——以预测Melbourne房子价格为例

预测Melbourne房子价格

有监督模型
采用的决策树回归模型

导入数据，初步分析

import pandas as pd

melbourne_file_path =r'G:\kaggle\melb_data.csv'
melbourne_data = pd.read_csv(melbourne_file_path) 
melbourne_data.columns

Index([u'Suburb', u'Address', u'Rooms', u'Type', u'Price', u'Method',
       u'SellerG', u'Date', u'Distance', u'Postcode', u'Bedroom2', u'Bathroom',
       u'Car', u'Landsize', u'BuildingArea', u'YearBuilt', u'CouncilArea',
       u'Lattitude', u'Longtitude', u'Regionname', u'Propertycount'],
      dtype='object')

melbourne_data.head()

	Suburb	Address	Rooms	Type	Price	Method	SellerG	Date	Distance	Postcode	...	Bathroom	Car	Landsize	BuildingArea	YearBuilt	CouncilArea	Lattitude	Longtitude	Regionname	Propertycount
0	Abbotsford	85 Turner St	2	h	1480000.0	S	Biggin	3/12/2016	2.5	3067.0	...	1.0	1.0	202.0	NaN	NaN	Yarra	-37.7996	144.9984	Northern Metropolitan	4019.0
1	Abbotsford	25 Bloomburg St	2	h	1035000.0	S	Biggin	4/02/2016	2.5	3067.0	...	1.0	0.0	156.0	79.0	1900.0	Yarra	-37.8079	144.9934	Northern Metropolitan	4019.0
2	Abbotsford	5 Charles St	3	h	1465000.0	SP	Biggin	4/03/2017	2.5	3067.0	...	2.0	0.0	134.0	150.0	1900.0	Yarra	-37.8093	144.9944	Northern Metropolitan	4019.0
3	Abbotsford	40 Federation La	3	h	850000.0	PI	Biggin	4/03/2017	2.5	3067.0	...	2.0	1.0	94.0	NaN	NaN	Yarra	-37.7969	144.9969	Northern Metropolitan	4019.0
4	Abbotsford	55a Park St	4	h	1600000.0	VB	Nelson	4/06/2016	2.5	3067.0	...	1.0	2.0	120.0	142.0	2014.0	Yarra	-37.8072	144.9941	Northern Metropolitan	4019.0

5 rows × 21 columns

#多少条记录
len(melbourne_data)

13580

melbourne_data.describe()
#从count看出，有很多缺失值,比如BuildingArea有6452个NaN

	Rooms	Price	Distance	Postcode	Bedroom2	Bathroom	Car	Landsize	BuildingArea	YearBuilt	Lattitude	Longtitude	Propertycount
count	13580.000000	1.358000e+04	13580.000000	13580.000000	13580.000000	13580.000000	13518.000000	13580.000000	7130.000000	8205.000000	13580.000000	13580.000000	13580.000000
mean	2.937997	1.075684e+06	10.137776	3105.301915	2.914728	1.534242	1.610075	558.416127	151.967650	1964.684217	-37.809203	144.995216	7454.417378
std	0.955748	6.393107e+05	5.868725	90.676964	0.965921	0.691712	0.962634	3990.669241	541.014538	37.273762	0.079260	0.103916	4378.581772
min	1.000000	8.500000e+04	0.000000	3000.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1196.000000	-38.182550	144.431810	249.000000
25%	2.000000	6.500000e+05	6.100000	3044.000000	2.000000	1.000000	1.000000	177.000000	93.000000	1940.000000	-37.856822	144.929600	4380.000000
50%	3.000000	9.030000e+05	9.200000	3084.000000	3.000000	1.000000	2.000000	440.000000	126.000000	1970.000000	-37.802355	145.000100	6555.000000
75%	3.000000	1.330000e+06	13.000000	3148.000000	3.000000	2.000000	2.000000	651.000000	174.000000	1999.000000	-37.756400	145.058305	10331.000000
max	10.000000	9.000000e+06	48.100000	3977.000000	20.000000	8.000000	10.000000	433014.000000	44515.000000	2018.000000	-37.408530	145.526350	21650.000000

处理缺失值

BuildingArea YearBuilt CouncilArea
48%缺失值 40%缺失值 10%缺失值

#选择删除，删除含有缺失值的记录（行）
#dropna()
melbourne_data=melbourne_data.dropna(axis=0)#默认为删除行 默认how='any' 还有一个how='all'，该条记录所有值为Na值时候才删除

melbourne_data.head()
#可以看到index为0、3、5....的有NaN值的记录都被删了

	Suburb	Address	Rooms	Type	Price	Method	SellerG	Date	Distance	Postcode	...	Bathroom	Car	Landsize	BuildingArea	YearBuilt	CouncilArea	Lattitude	Longtitude	Regionname	Propertycount
1	Abbotsford	25 Bloomburg St	2	h	1035000.0	S	Biggin	4/02/2016	2.5	3067.0	...	1.0	0.0	156.0	79.0	1900.0	Yarra	-37.8079	144.9934	Northern Metropolitan	4019.0
2	Abbotsford	5 Charles St	3	h	1465000.0	SP	Biggin	4/03/2017	2.5	3067.0	...	2.0	0.0	134.0	150.0	1900.0	Yarra	-37.8093	144.9944	Northern Metropolitan	4019.0
4	Abbotsford	55a Park St	4	h	1600000.0	VB	Nelson	4/06/2016	2.5	3067.0	...	1.0	2.0	120.0	142.0	2014.0	Yarra	-37.8072	144.9941	Northern Metropolitan	4019.0
6	Abbotsford	124 Yarra St	3	h	1876000.0	S	Nelson	7/05/2016	2.5	3067.0	...	2.0	0.0	245.0	210.0	1910.0	Yarra	-37.8024	144.9993	Northern Metropolitan	4019.0
7	Abbotsford	98 Charles St	2	h	1636000.0	S	Nelson	8/10/2016	2.5	3067.0	...	1.0	2.0	256.0	107.0	1890.0	Yarra	-37.8060	144.9954	Northern Metropolitan	4019.0

5 rows × 21 columns

melbourne_data.describe()

	Rooms	Price	Distance	Postcode	Bedroom2	Bathroom	Car	Landsize	BuildingArea	YearBuilt	Lattitude	Longtitude	Propertycount
count	6196.000000	6.196000e+03	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000
mean	2.931407	1.068828e+06	9.751097	3101.947708	2.902034	1.576340	1.573596	471.006940	141.568645	1964.081988	-37.807904	144.990201	7435.489509
std	0.971079	6.751564e+05	5.612065	86.421604	0.970055	0.711362	0.929947	897.449881	90.834824	38.105673	0.075850	0.099165	4337.698917
min	1.000000	1.310000e+05	0.000000	3000.000000	0.000000	1.000000	0.000000	0.000000	0.000000	1196.000000	-38.164920	144.542370	389.000000
25%	2.000000	6.200000e+05	5.900000	3044.000000	2.000000	1.000000	1.000000	152.000000	91.000000	1940.000000	-37.855438	144.926198	4383.750000
50%	3.000000	8.800000e+05	9.000000	3081.000000	3.000000	1.000000	1.000000	373.000000	124.000000	1970.000000	-37.802250	144.995800	6567.000000
75%	4.000000	1.325000e+06	12.400000	3147.000000	3.000000	2.000000	2.000000	628.000000	170.000000	2000.000000	-37.758200	145.052700	10175.000000
max	8.000000	9.000000e+06	47.400000	3977.000000	9.000000	8.000000	10.000000	37000.000000	3112.000000	2018.000000	-37.457090	145.526350	21650.000000

Selecting The Prediction Target选择预测目标

以房价为预测目标

#以[Price]作为真实的y
y= melbourne_data.Price

Choosing “Features” 选择特征

作为模型的输入的那些columns叫做“特征”
哪些列影响着房价呢？
有时候，把除了target那一列外的所有columns作为特征
有时候，可能选更少的一些比较好

melbourne_data.columns

Index([u'Suburb', u'Address', u'Rooms', u'Type', u'Price', u'Method',
       u'SellerG', u'Date', u'Distance', u'Postcode', u'Bedroom2', u'Bathroom',
       u'Car', u'Landsize', u'BuildingArea', u'YearBuilt', u'CouncilArea',
       u'Lattitude', u'Longtitude', u'Regionname', u'Propertycount'],
      dtype='object')

#an example:选取这些列作为特征
melbourne_features=['Rooms', 'Bathroom',  'Landsize', 'Lattitude', 'Longtitude']

#By convention，this data is called X
X= melbourne_data[melbourne_features]
print(X.head()) #6189*5
print(y.head()) #6169*1

   Rooms  Bathroom  Landsize  Lattitude  Longtitude
1      2       1.0     156.0   -37.8079    144.9934
2      3       2.0     134.0   -37.8093    144.9944
4      4       1.0     120.0   -37.8072    144.9941
6      3       2.0     245.0   -37.8024    144.9993
7      2       1.0     256.0   -37.8060    144.9954
1    1035000.0
2    1465000.0
4    1600000.0
6    1876000.0
7    1636000.0
Name: Price, dtype: float64

X.describe()

	Rooms	Bathroom	Landsize	Lattitude	Longtitude
count	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000
mean	2.931407	1.576340	471.006940	-37.807904	144.990201
std	0.971079	0.711362	897.449881	0.075850	0.099165
min	1.000000	1.000000	0.000000	-38.164920	144.542370
25%	2.000000	1.000000	152.000000	-37.855438	144.926198
50%	3.000000	1.000000	373.000000	-37.802250	144.995800
75%	4.000000	2.000000	628.000000	-37.758200	145.052700
max	8.000000	8.000000	37000.000000	-37.457090	145.526350

Building Model: 定义model、训练fit、预测、评估

使用机器学习库scikit-learn, 简称sklearn
**Steps:

• define: 用哪种模型 决策树？其他？
• fit: 从数据中获取模式，即用数据训练模型 建模的核心
• predict: 预测新样本
• evaluate: 模型预测的准确程度

#用决策树做回归： DecisionTreeRegressor类
# from sklearn import tree
# clf= tree.DecisionTreeRegressor(random_state=1)
# clf.fit(X, y)
# clf.predict([[3,1.0,122.0, -37.8072,144.9941]])

from sklearn.tree import DecisionTreeRegressor

#Define model
melbourne_model= DecisionTreeRegressor(random_state=1)#random_state=1：确保每次运行是同一个结果
#Fit model
melbourne_model.fit( X, y)
#use model to Predict
melbourne_model.predict([[3,1.0,122.0, -37.8072,144.9941]])

array([1200000.])

melbourne_model.predict(X.head())

array([1035000., 1465000., 1600000., 1876000., 1636000.])