AI-sklearn 学习笔记（二）数据集
from sklearn import datasets
from sklearn.linear_model import LinearRegression
loaded_data = datasets.load_boston()
data_X = loaded_data.data
data_y = loaded_data.target
model = LinearRegression()
#train and prediect
model.fit(data_X, data_y)
Out[9]: LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
data_X.min
Out[10]: <function ndarray.min>
data_X.min()
Out[11]: 0.0
data_X.max()
Out[12]: 711.0
model.predict(data_X[:4,:])
Out[13]: array([30.00821269, 25.0298606 , 30.5702317 , 28.60814055])
data_y[:4]
Out[14]: array([24. , 21.6, 34.7, 33.4])
#参数和分数
model.coef_
Out[16]:
array([-1.07170557e-01, 4.63952195e-02, 2.08602395e-02, 2.68856140e+00,
-1.77957587e+01, 3.80475246e+00, 7.51061703e-04, -1.47575880e+00,
3.05655038e-01, -1.23293463e-02, -9.53463555e-01, 9.39251272e-03,
-5.25466633e-01])
model.intercept_
Out[17]: 36.49110328036133
model.get_params
Out[18]: <bound method BaseEstimator.get_params of LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)>
#model score 可以对模型的经确定进行打分
model.score(data_X, data_y)
Out[20]: 0.7406077428649428
import matplotlib.pyplot as plt
Backend TkAgg is interactive backend. Turning interactive mode on.
import pandas as pd
import numpy as np
loaded_data.keys
Out[24]: <function Bunch.keys>
loaded_data.keys()
Out[25]: dict_keys(['data', 'target', 'feature_names', 'DESCR'])
loaded_data
Out[26]:
{'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 House Prices dataset\n===========================\n\nNotes\n------\nData Set Characteristics: \n\n :Number of Instances: 506 \n\n :Number of Attributes: 13 numeric/categorical predictive\n \n :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.\nhttp://archive.ics.uci.edu/ml/datasets/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**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 - many more! (see http://archive.ics.uci.edu/ml/datasets/Housing)\n"}
loaded_data.DESCR
Out[27]: "Boston House Prices dataset\n===========================\n\nNotes\n------\nData Set Characteristics: \n\n :Number of Instances: 506 \n\n :Number of Attributes: 13 numeric/categorical predictive\n \n :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.\nhttp://archive.ics.uci.edu/ml/datasets/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**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 - many more! (see http://archive.ics.uci.edu/ml/datasets/Housing)\n"
X = loaded_data.data[:, :2]
#切片操作取loaded_data data部分506行， 13列中的前两行
X
Out[34]:
array([[6.3200e-03, 1.8000e+01],
[2.7310e-02, 0.0000e+00],
[2.7290e-02, 0.0000e+00],
...,
[6.0760e-02, 0.0000e+00],
[1.0959e-01, 0.0000e+00],
[4.7410e-02, 0.0000e+00]])
X.shape
Out[35]: (506, 2)
plt.scatter(X[:,0], X[:, 1])
Out[36]: <matplotlib.collections.PathCollection at 0x1330f550>
plt.hist(X[:,0])
Out[37]:
(array([440., 43., 14., 1., 3., 2., 0., 1., 1., 1.]),
array([6.3200000e-03, 8.9033080e+00, 1.7800296e+01, 2.6697284e+01,
3.5594272e+01, 4.4491260e+01, 5.3388248e+01, 6.2285236e+01,
7.1182224e+01, 8.0079212e+01, 8.8976200e+01]),
<a list of 10 Patch objects>) #了解一下两维数组的切片操作
plt.scatter(X[:,0], loaded_data.target[:,0]) plt.scatter(X[:,0], loaded_data.target[:])
Out[42]: <matplotlib.collections.PathCollection at 0x131fb438>
plt.plot(X[:,0], model.coef_[0][0]*X[:,0] + model.intercept_[0], '-r') plt.scatter(data_X[:,0], data_y[:])
Out[51]: <matplotlib.collections.PathCollection at 0x13a00fd0>
plt.scatter(data_y[:], data_X[:, 0])
Out[52]: <matplotlib.collections.PathCollection at 0x13a00c50>
plt.scatter(data_y[:], data_X[:, 0])
Out[53]: <matplotlib.collections.PathCollection at 0x13a16978>
plt.plot(X[:,0], model.coef_[0]*X[:,0] + model.intercept_, '-r')
Out[54]: [<matplotlib.lines.Line2D at 0x13a564a8>]
AI-sklearn 学习笔记（二）数据集的更多相关文章
- WPF的Binding学习笔记(二)
原文: http://www.cnblogs.com/pasoraku/archive/2012/10/25/2738428.htmlWPF的Binding学习笔记(二) 上次学了点点Binding的 ...
- AJax 学习笔记二(onreadystatechange的作用)
AJax 学习笔记二(onreadystatechange的作用) 当发送一个请求后,客户端无法确定什么时候会完成这个请求,所以需要用事件机制来捕获请求的状态XMLHttpRequest对象提供了on ...
- [Firefly引擎][学习笔记二][已完结]卡牌游戏开发模型的设计
源地址:http://bbs.9miao.com/thread-44603-1-1.html 在此补充一下Socket的验证机制:socket登陆验证.会采用session会话超时的机制做心跳接口验证 ...
- JMX学习笔记(二)-Notification
Notification通知,也可理解为消息,有通知,必然有发送通知的广播,JMX这里采用了一种订阅的方式,类似于观察者模式,注册一个观察者到广播里,当有通知时,广播通过调用观察者,逐一通知. 这里写 ...
- java之jvm学习笔记二(类装载器的体系结构)
java的class只在需要的时候才内转载入内存,并由java虚拟机的执行引擎来执行,而执行引擎从总的来说主要的执行方式分为四种, 第一种,一次性解释代码,也就是当字节码转载到内存后,每次需要都会重新 ...
- Java IO学习笔记二
Java IO学习笔记二 流的概念 在程序中所有的数据都是以流的方式进行传输或保存的,程序需要数据的时候要使用输入流读取数据,而当程序需要将一些数据保存起来的时候,就要使用输出流完成. 程序中的输入输 ...
- 《SQL必知必会》学习笔记二)
<SQL必知必会>学习笔记(二) 咱们接着上一篇的内容继续.这一篇主要回顾子查询,联合查询,复制表这三类内容. 上一部分基本上都是简单的Select查询,即从单个数据库表中检索数据的单条语 ...
- NumPy学习笔记 二
NumPy学习笔记 二 <NumPy学习笔记>系列将记录学习NumPy过程中的动手笔记,前期的参考书是<Python数据分析基础教程 NumPy学习指南>第二版.<数学分 ...
- Learning ROS for Robotics Programming Second Edition学习笔记(二) indigo tools
中文译著已经出版,详情请参考:http://blog.csdn.net/ZhangRelay/article/category/6506865 Learning ROS for Robotics Pr ...
- Redis学习笔记二 （BitMap算法分析与BitCount语法）
Redis学习笔记二 一.BitMap是什么 就是通过一个bit位来表示某个元素对应的值或者状态,其中的key就是对应元素本身.我们知道8个bit可以组成一个Byte,所以bitmap本身会极大的节省 ...
随机推荐
- 完美解决linux不能编辑sshd_cofig和实现xshell远程连接的问题
第一步:我们使用命令行vim /etc/ssh/sshd_config 执行修改,强制保持 :wq! 系统不让我们修改这个文件 "/etc/ssh/sshd_config" ...
- Comet OJ - Contest #6 C 一道树题 数学 + 推导
Code: #include <bits/stdc++.h> #define setIO(s) freopen(s".in","r",stdin) ...
- （22）Python练习项目集
文本操作 逆转字符串——输入一个字符串,将其逆转并输出. 拉丁猪文字游戏——这是一个英语语言游戏.基本规则是将一个英语单词的第一个辅音音素的字母移动到词尾并且加上后缀-ay(譬如“banana”会变成 ...
- 拆系数$FFT$（$4$遍$DFT$）
#include <iostream> #include <cstdio> #include <cstdlib> #include <cstring> ...
- border、outline、boxshadow那些事
border 边框是我们美化网页.增强样式最常用的手段之一.例如: <div class="text"></div> .text { width: 254p ...
- 语法检查程序LanguageTool学习和使用笔记
这是LanguageTool的官方语法规则说明,一定要仔细研究,学会这个语法,就可以自己编写语法检查规则了,这篇文档上说,编写这份语法检查文档,你甚至都不需要是一名程序员: http://wiki.l ...
- 用 MuGo 搭建 Go Engine 在 KGS 对战
MuGo 是一个开源的 Go Engine,下棋能力大概在 10k - 2k 左右. 用 MuGo 搭建 Go Engine 并在 KGS 对战的步骤如下: 1. 安装 TensorFlow 因为 M ...
- 快速入门分布式消息队列之 RabbitMQ（1）
目录 目录 前言 简介 安装 RabbitMQ 基本对象概念 Message 消息 Producer 生产者 Consumer 消费者 Queue 队列 Exchange 交换机 Binding 绑定 ...
- windows10下安装docker报错：error during connect
详细报错信息如下: C:\Users\zig>docker info error during connect: Get http://%2F%2F.%2Fpipe%2Fdocker_engin ...
- Jmeter之用户参数和用户定义的变量
在调试脚本的时候,可以使用前置处理器中的用户参数组件进行数据的提供,在该数据中可以使用固定值也可以使用变量值. 如果是固定不变的一些配置项,不需要多个值的时候,也可以使用用户已定义的变量组件. 一.界 ...