線形回帰モデル ～ボストン住宅価格～
単回帰分析
# 必要なモジュールのimport
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model, datasets
from pandas import DataFrame
import seaborn as sns
%matplotlib inline
# ボストンデータを"boston"というインスタンスにインポート
boston = datasets.load_boston()
# インポートしたデータを確認(data / target / feature_names / DESCR)
print(boston)
{'data': array([[6.3200e-03, 1.8000e+01, 2.3100e+00, ..., 1.5300e+01, 3.9690e+02,
4.9800e+00],
[2.7310e-02, 0.0000e+00, 7.0700e+00, ..., 1.7800e+01, 3.9690e+02,
9.1400e+00],
[2.7290e-02, 0.0000e+00, 7.0700e+00, ..., 1.7800e+01, 3.9283e+02,
4.0300e+00],
...,
[6.0760e-02, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 3.9690e+02,
5.6400e+00],
[1.0959e-01, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 3.9345e+02,
6.4800e+00],
[4.7410e-02, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 3.9690e+02,
7.8800e+00]]), 'target': array([24. , 21.6, 34.7, 33.4, 36.2, 28.7, 22.9, 27.1, 16.5, 18.9, 15. ,
18.9, 21.7, 20.4, 18.2, 19.9, 23.1, 17.5, 20.2, 18.2, 13.6, 19.6,
15.2, 14.5, 15.6, 13.9, 16.6, 14.8, 18.4, 21. , 12.7, 14.5, 13.2,
13.1, 13.5, 18.9, 20. , 21. , 24.7, 30.8, 34.9, 26.6, 25.3, 24.7,
21.2, 19.3, 20. , 16.6, 14.4, 19.4, 19.7, 20.5, 25. , 23.4, 18.9,
35.4, 24.7, 31.6, 23.3, 19.6, 18.7, 16. , 22.2, 25. , 33. , 23.5,
19.4, 22. , 17.4, 20.9, 24.2, 21.7, 22.8, 23.4, 24.1, 21.4, 20. ,
20.8, 21.2, 20.3, 28. , 23.9, 24.8, 22.9, 23.9, 26.6, 22.5, 22.2,
23.6, 28.7, 22.6, 22. , 22.9, 25. , 20.6, 28.4, 21.4, 38.7, 43.8,
33.2, 27.5, 26.5, 18.6, 19.3, 20.1, 19.5, 19.5, 20.4, 19.8, 19.4,
21.7, 22.8, 18.8, 18.7, 18.5, 18.3, 21.2, 19.2, 20.4, 19.3, 22. ,
20.3, 20.5, 17.3, 18.8, 21.4, 15.7, 16.2, 18. , 14.3, 19.2, 19.6,
23. , 18.4, 15.6, 18.1, 17.4, 17.1, 13.3, 17.8, 14. , 14.4, 13.4,
15.6, 11.8, 13.8, 15.6, 14.6, 17.8, 15.4, 21.5, 19.6, 15.3, 19.4,
17. , 15.6, 13.1, 41.3, 24.3, 23.3, 27. , 50. , 50. , 50. , 22.7,
25. , 50. , 23.8, 23.8, 22.3, 17.4, 19.1, 23.1, 23.6, 22.6, 29.4,
23.2, 24.6, 29.9, 37.2, 39.8, 36.2, 37.9, 32.5, 26.4, 29.6, 50. ,
32. , 29.8, 34.9, 37. , 30.5, 36.4, 31.1, 29.1, 50. , 33.3, 30.3,
34.6, 34.9, 32.9, 24.1, 42.3, 48.5, 50. , 22.6, 24.4, 22.5, 24.4,
20. , 21.7, 19.3, 22.4, 28.1, 23.7, 25. , 23.3, 28.7, 21.5, 23. ,
26.7, 21.7, 27.5, 30.1, 44.8, 50. , 37.6, 31.6, 46.7, 31.5, 24.3,
31.7, 41.7, 48.3, 29. , 24. , 25.1, 31.5, 23.7, 23.3, 22. , 20.1,
22.2, 23.7, 17.6, 18.5, 24.3, 20.5, 24.5, 26.2, 24.4, 24.8, 29.6,
42.8, 21.9, 20.9, 44. , 50. , 36. , 30.1, 33.8, 43.1, 48.8, 31. ,
36.5, 22.8, 30.7, 50. , 43.5, 20.7, 21.1, 25.2, 24.4, 35.2, 32.4,
32. , 33.2, 33.1, 29.1, 35.1, 45.4, 35.4, 46. , 50. , 32.2, 22. ,
20.1, 23.2, 22.3, 24.8, 28.5, 37.3, 27.9, 23.9, 21.7, 28.6, 27.1,
20.3, 22.5, 29. , 24.8, 22. , 26.4, 33.1, 36.1, 28.4, 33.4, 28.2,
22.8, 20.3, 16.1, 22.1, 19.4, 21.6, 23.8, 16.2, 17.8, 19.8, 23.1,
21. , 23.8, 23.1, 20.4, 18.5, 25. , 24.6, 23. , 22.2, 19.3, 22.6,
19.8, 17.1, 19.4, 22.2, 20.7, 21.1, 19.5, 18.5, 20.6, 19. , 18.7,
32.7, 16.5, 23.9, 31.2, 17.5, 17.2, 23.1, 24.5, 26.6, 22.9, 24.1,
18.6, 30.1, 18.2, 20.6, 17.8, 21.7, 22.7, 22.6, 25. , 19.9, 20.8,
16.8, 21.9, 27.5, 21.9, 23.1, 50. , 50. , 50. , 50. , 50. , 13.8,
13.8, 15. , 13.9, 13.3, 13.1, 10.2, 10.4, 10.9, 11.3, 12.3, 8.8,
7.2, 10.5, 7.4, 10.2, 11.5, 15.1, 23.2, 9.7, 13.8, 12.7, 13.1,
12.5, 8.5, 5. , 6.3, 5.6, 7.2, 12.1, 8.3, 8.5, 5. , 11.9,
27.9, 17.2, 27.5, 15. , 17.2, 17.9, 16.3, 7. , 7.2, 7.5, 10.4,
8.8, 8.4, 16.7, 14.2, 20.8, 13.4, 11.7, 8.3, 10.2, 10.9, 11. ,
9.5, 14.5, 14.1, 16.1, 14.3, 11.7, 13.4, 9.6, 8.7, 8.4, 12.8,
10.5, 17.1, 18.4, 15.4, 10.8, 11.8, 14.9, 12.6, 14.1, 13. , 13.4,
15.2, 16.1, 17.8, 14.9, 14.1, 12.7, 13.5, 14.9, 20. , 16.4, 17.7,
19.5, 20.2, 21.4, 19.9, 19. , 19.1, 19.1, 20.1, 19.9, 19.6, 23.2,
29.8, 13.8, 13.3, 16.7, 12. , 14.6, 21.4, 23. , 23.7, 25. , 21.8,
20.6, 21.2, 19.1, 20.6, 15.2, 7. , 8.1, 13.6, 20.1, 21.8, 24.5,
23.1, 19.7, 18.3, 21.2, 17.5, 16.8, 22.4, 20.6, 23.9, 22. , 11.9]), 'feature_names': array(['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD',
'TAX', 'PTRATIO', 'B', 'LSTAT'], dtype='<U7'), 'DESCR': ".. _boston_dataset:\n\nBoston house prices dataset\n---------------------------\n\n**Data Set Characteristics:** \n\n :Number of Instances: 506 \n\n :Number of Attributes: 13 numeric/categorical predictive. Median Value (attribute 14) is usually the target.\n\n :Attribute Information (in order):\n - CRIM per capita crime rate by town\n - ZN proportion of residential land zoned for lots over 25,000 sq.ft.\n - INDUS proportion of non-retail business acres per town\n - CHAS Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)\n - NOX nitric oxides concentration (parts per 10 million)\n - RM average number of rooms per dwelling\n - AGE proportion of owner-occupied units built prior to 1940\n - DIS weighted distances to five Boston employment centres\n - RAD index of accessibility to radial highways\n - TAX full-value property-tax rate per $10,000\n - PTRATIO pupil-teacher ratio by town\n - B 1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town\n - LSTAT % lower status of the population\n - MEDV Median value of owner-occupied homes in $1000's\n\n :Missing Attribute Values: None\n\n :Creator: Harrison, D. and Rubinfeld, D.L.\n\nThis is a copy of UCI ML housing dataset.\nhttps://archive.ics.uci.edu/ml/machine-learning-databases/housing/\n\n\nThis dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.\n\nThe Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic\nprices and the demand for clean air', J. Environ. Economics & Management,\nvol.5, 81-102, 1978. Used in Belsley, Kuh & Welsch, 'Regression diagnostics\n...', Wiley, 1980. N.B. Various transformations are used in the table on\npages 244-261 of the latter.\n\nThe Boston house-price data has been used in many machine learning papers that address regression\nproblems. \n \n.. topic:: References\n\n - Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.\n - Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.\n", 'filename': 'C:\\Users\\taka0\\Anaconda3\\lib\\site-packages\\sklearn\\datasets\\data\\boston_house_prices.csv'}
# DESCR変数の中身を確認
print(boston['DESCR'])
.. _boston_dataset:
Boston house prices dataset
---------------------------
**Data Set Characteristics:**
:Number of Instances: 506
:Number of Attributes: 13 numeric/categorical predictive. Median Value (attribute 14) is usually the target.
:Attribute Information (in order):
- CRIM per capita crime rate by town
- ZN proportion of residential land zoned for lots over 25,000 sq.ft.
- INDUS proportion of non-retail business acres per town
- CHAS Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)
- NOX nitric oxides concentration (parts per 10 million)
- RM average number of rooms per dwelling
- AGE proportion of owner-occupied units built prior to 1940
- DIS weighted distances to five Boston employment centres
- RAD index of accessibility to radial highways
- TAX full-value property-tax rate per $10,000
- PTRATIO pupil-teacher ratio by town
- B 1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town
- LSTAT % lower status of the population
- MEDV Median value of owner-occupied homes in $1000's
:Missing Attribute Values: None
:Creator: Harrison, D. and Rubinfeld, D.L.
This is a copy of UCI ML housing dataset.
https://archive.ics.uci.edu/ml/machine-learning-databases/housing/
This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.
The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic
prices and the demand for clean air', J. Environ. Economics & Management,
vol.5, 81-102, 1978. Used in Belsley, Kuh & Welsch, 'Regression diagnostics
...', Wiley, 1980. N.B. Various transformations are used in the table on
pages 244-261 of the latter.
The Boston house-price data has been used in many machine learning papers that address regression
problems.
.. topic:: References
- Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.
- Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.
# データフレームに変換する
df = DataFrame(data=boston.data, columns = boston.feature_names)
df['PRICE'] = np.array(boston.target)
df.head()
| CRIM | ZN | INDUS | CHAS | NOX | RM | AGE | DIS | RAD | TAX | PTRATIO | B | LSTAT | PRICE | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.00632 | 18.0 | 2.31 | 0.0 | 0.538 | 6.575 | 65.2 | 4.0900 | 1.0 | 296.0 | 15.3 | 396.90 | 4.98 | 24.0 |
| 1 | 0.02731 | 0.0 | 7.07 | 0.0 | 0.469 | 6.421 | 78.9 | 4.9671 | 2.0 | 242.0 | 17.8 | 396.90 | 9.14 | 21.6 |
| 2 | 0.02729 | 0.0 | 7.07 | 0.0 | 0.469 | 7.185 | 61.1 | 4.9671 | 2.0 | 242.0 | 17.8 | 392.83 | 4.03 | 34.7 |
| 3 | 0.03237 | 0.0 | 2.18 | 0.0 | 0.458 | 6.998 | 45.8 | 6.0622 | 3.0 | 222.0 | 18.7 | 394.63 | 2.94 | 33.4 |
| 4 | 0.06905 | 0.0 | 2.18 | 0.0 | 0.458 | 7.147 | 54.2 | 6.0622 | 3.0 | 222.0 | 18.7 | 396.90 | 5.33 | 36.2 |
# データ間の相関係数を求める
corr_mat = df.corr(method="pearson")
# ヒートマップで可視化
sns.heatmap(corr_mat, vmax=1, vmin=-1, center=0, annot=True, fmt=".1f")
<matplotlib.axes._subplots.AxesSubplot at 0x22bf70c1ba8>
# RM(部屋の数)と価格のヒストグラムと散布図を表示
sns.pairplot(df[["RM", "PRICE"]])
<seaborn.axisgrid.PairGrid at 0x22bf9447320>
# 説明変数(部屋の数)
data = df.loc[:, ['RM']].values
# 目的変数(価格)
target = df.loc[:, 'PRICE'].values
# オブジェクト生成
model = linear_model.LinearRegression()
model.fit(data, target)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None,
normalize=False)
# 係数の確認
a = model.coef_
b = model.intercept_
a
array([9.10210898])
b
-34.67062077643857
y_pred = model.predict(data)
plt.scatter(data, target)
plt.plot(data, y_pred, "r", lw=3)
plt.ylabel("PRICE")
plt.xlabel("NUMBER OF ROOMS")
Text(0.5, 0, 'NUMBER OF ROOMS')
重回帰分析
# 犯罪率と部屋数を使用
# 説明変数
data2 = df.loc[:, ['CRIM', 'RM']].values
# 目的変数
target2 = df.loc[:, 'PRICE'].values
from sklearn.model_selection import train_test_split
# データを学習用と検証用に分割
X_train, X_test, Y_train, Y_test = train_test_split(data2, target2, train_size = 0.7, test_size = 0.3, random_state = 0)
# オブジェクト生成
model2 = linear_model.LinearRegression(fit_intercept = True, normalize = False, copy_X = True, n_jobs = 1)
model2.fit(X_train, Y_train)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
# 検証データを用いて目的変数を予測
Y_pred = model2.predict(X_test)
# 残差をプロット
plt.scatter(Y_pred, Y_pred - Y_test, color = 'blue')
# x軸に沿った直線をプロット
plt.hlines(y = 0, xmin = -10, xmax = 50, color = 'black')
# 図のタイトル
plt.title('Residual Plot')
# x軸のラベル
plt.xlabel('Predicted Values')
# y軸のラベル
plt.ylabel('Residuals')
plt.grid()
plt.show()
# 重回帰の回帰係数と切片を出力
print(model2.coef_)
print(model2.intercept_)
[-0.29144992 8.65837674]
-30.89648178869284
決定係数
# 学習用データでパラメータ推定
model.fit(X_train, Y_train)
# 作成したモデルから予測（学習用、検証用モデル使用）
Y_train_pred = model.predict(X_train)
Y_test_pred = model.predict(X_test)
# 学習用、検証用それぞれで残差をプロット
plt.scatter(Y_train_pred, Y_train_pred - Y_train, c = 'blue', marker = 'o', label = 'Train Data')
plt.scatter(Y_test_pred, Y_test_pred - Y_test, c = 'lightgreen', marker = 's', label = 'Test Data')
plt.xlabel('Predicted Values')
plt.ylabel('Residuals')
# 凡例を左上に表示
plt.legend(loc = 'upper left')
# y = 0に直線を引く
plt.hlines(y = 0, xmin = -10, xmax = 50, lw = 2, color = 'red')
plt.xlim([10, 50])
plt.show()
# 平均二乗誤差を評価するためのメソッドを呼び出し
from sklearn.metrics import mean_squared_error
# 学習用、検証用データに関して平均二乗誤差を出力
print('MSE Train : %.3f, Test : %.3f' % (mean_squared_error(Y_train, Y_train_pred), mean_squared_error(Y_test, Y_test_pred)))
# 学習用、検証用データに関してR^2を出力
print('R^2 Train : %.3f, Test : %.3f' % (model.score(X_train, Y_train), model.score(X_test, Y_test)))
MSE Train : 36.457, Test : 44.184
R^2 Train : 0.570, Test : 0.469