{"id":467,"date":"2019-04-27T20:12:00","date_gmt":"2019-04-27T12:12:00","guid":{"rendered":"http:\/\/note.systw.net\/note\/?p=467"},"modified":"2023-11-02T20:17:01","modified_gmt":"2023-11-02T12:17:01","slug":"sklearn-linear-regression","status":"publish","type":"post","link":"https:\/\/systw.net\/note\/archives\/467","title":{"rendered":"SKLearn Linear Regression"},"content":{"rendered":"\n

\u4f7f\u7528OLS( Ordinary least squares ) \u7684Linear Regression<\/p>\n\n\n\n

…<\/p>\n\n\n\n

\u8f09\u5165\u6a21\u7d44<\/strong>
from sklearn import linear_model<\/p>\n\n\n\n

\u5efa\u7acb\u521d\u59cbmodel<\/strong>
< model>=linear_model.LinearRegression(fit_intercept=True, normalize=False, copy_X=True,n_jobs=1)<\/p>\n\n\n\n

\u8b93model\u5b78\u7fd2<\/strong>
< model>.fit(input, output)<\/p>\n\n\n\n

\u6aa2\u8996model\u5b78\u7fd2\u72c0\u6cc1<\/strong>
< model>.score(input, output)
\u8d8a\u63a5\u8fd11\u8868\u793a\u8d8a\u597d<\/p>\n\n\n\n

\u6839\u64dainput\u9810\u6e2coutput<\/strong>
< model>.predict(input)<\/p>\n\n\n\n

\u5217\u51falinear model\u6a21\u578bAX+b<\/strong>
< model>.coef_
A, Estimated coefficients for the linear regression problem
< model>.intercept_
b, Independent term in the linear model.<\/p>\n\n\n\n

refer
LinearRegression (Ordinary Least Squares)
http:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.linear_model.LinearRegression.html#sklearn.linear_model.LinearRegression
LinearRegression
http:\/\/scikit-learn.org\/stable\/auto_examples\/linear_model\/plot_ols.html#sphx-glr-auto-examples-linear-model-plot-ols-py<\/p>\n\n\n\n

……………………………………………….<\/p>\n\n\n\n

Example in simple dataset<\/strong><\/h2>\n\n\n\n

#vi datatrain.txt<\/strong>
traffic,packet
10,100
20,200
40,400
50,500<\/p>\n\n\n\n

#vi datatest.txt<\/strong>
traffic,packet
30,300
60,600<\/p>\n\n\n\n

#vi lm.py<\/strong>
from sklearn import linear_model
import numpy as np
import sys
import os<\/p>\n\n\n\n

###reload train data and training
filepath=sys.argv[1]
f = open(filepath)
dataset = np.loadtxt(f,delimiter=’,’,skiprows=1)
target=dataset[:,0]
data_train=dataset[:,1:]
f.seek(0)
listhead=f.readlines()[0].strip().split(‘,’)[1:]<\/p>\n\n\n\n

regr = linear_model.LinearRegression()
regr.fit(data_train,target)<\/p>\n\n\n\n


###reload test data and predicting
filepath=sys.argv[2]
f = open(filepath)
dataset2 = np.loadtxt(f,delimiter=’,’,skiprows=1)
data_test=dataset2[:,1:]<\/p>\n\n\n\n

result=regr.predict(data_test) #when packet is 300 and 600 ,predict what is value of traffic
print result<\/p>\n\n\n\n


#python lm.py datatrain.txt datatest.txt<\/strong>
[ 30. 60.]
\u7576packet=300,\u9810\u6e2ctraffic\u70ba30
\u7576traffic=600,\u9810\u6e2ctraffic\u70ba60<\/p>\n\n\n\n

…………………………………….<\/p>\n\n\n\n

Example in diabetes<\/strong><\/p>\n\n\n\n

\u9032\u5165python\u4e92\u52d5\u4ecb\u9762<\/strong>
#python<\/p>\n\n\n\n

\u8f09\u5165\u8cc7\u6599<\/strong>
>>> from sklearn import datasets
>>> diabetes = datasets.load_diabetes()
>>> diabetes_train_data = diabetes.data
>>> diabetes_train_target = diabetes.target
\u5c07\u6700\u5f8c10\u7b46\u7d66validation\u4f7f\u7528
>>> diabetes_test_data = diabetes.data[-10:]
>>> diabetes_test_target = diabetes.target[-10:]<\/p>\n\n\n\n


\u8dd1training<\/strong>
>>> from sklearn import linear_model
>>> regr = linear_model.LinearRegression()
>>> regr.fit(diabetes_train_data,diabetes_train_target)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)<\/p>\n\n\n\n


\u9810\u6e2c\u5df1\u77e5\u8cc7\u6599<\/strong>
>>>regr.predict(diabetes_test_data)
array([ 218.17749233, 60.94590955, 131.09513588, 119.48417359,
52.60848094, 193.01802803, 101.05169913, 121.22505534,
211.8588945 , 53.44819015])<\/p>\n\n\n\n

\u6aa2\u8996\u9810\u6e2c\u7d50\u679c,\u8207\u5be6\u969b\u7d50\u679c\u7684\u72c0\u6cc1<\/strong>
>>> for target_predict,target in zip(regr.predict(diabetes_test_data),diabetes_test_target):
>>> print target_predict, target , target_predict-target
218.177492333 173.0 45.1774923325
60.9459095521 72.0 -11.0540904479
131.095135883 49.0 82.0951358828
119.484173585 64.0 55.4841735855
52.6084809435 48.0 4.60848094354
193.018028027 178.0 15.018028027
101.051699131 104.0 -2.94830086911
121.225055336 132.0 -10.7749446642
211.858894501 220.0 -8.14110549902
53.4481901497 57.0 -3.5518098503<\/p>\n\n\n\n

\u4f30\u7b97\u6b64\u689d\u8ff4\u6b78\u7dda\u7684\u6574\u9ad4\u8aa4\u5dee<\/strong>
\u900f\u904e\u5e73\u65b9\u5e73\u5747\u6578\u4e86\u89e3\u6b64\u8ff4\u6b78\u7dda\u7684\u6574\u9ad4\u8aa4\u5dee\u72c0\u6cc1
>>> np.mean((regr.predict(diabetes_test_data)-diabetes_test_target)**2)
2859.6903987680648<\/p>\n\n\n\n

\u4ee5MAPE\u4f30\u7b97\u7d50\u679c<\/strong>
>>>np.mean(np.abs((diabetes_test_target-regr.predict(diabetes_test_data))\/diabetes_test_target))<\/p>\n\n\n\n


\u770bLinear Regression\u7522\u751f\u7684\u7dda(AX+b)<\/strong>
AX+b\u6703\u8b93\u6240\u6709training set\u7684target value\u8aa4\u5dee\u7e3d\u548c\u70ba\u6700\u5c0f,
\u4ee5\u4e0b\u986f\u793atraining\u5b8c\u7372\u5f97\u7684A(.coef_)\u548cb(.intercept_)
>>> print(regr.coef_)
[ -10.01219782 -239.81908937 519.83978679 324.39042769 -792.18416163
476.74583782 101.04457032 177.06417623 751.27932109 67.62538639]
>>> print(regr.intercept_)
152.133484163<\/p>\n\n\n\n

refer
http:\/\/beancoder.com\/linear-regression-stock-prediction\/<\/p>\n","protected":false},"excerpt":{"rendered":"

\u4f7f\u7528OLS( Ordinary least squares …<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[13],"tags":[],"class_list":["post-467","post","type-post","status-publish","format-standard","hentry","category-dataanalysis"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/467","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/comments?post=467"}],"version-history":[{"count":0,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/467\/revisions"}],"wp:attachment":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/media?parent=467"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/categories?post=467"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/tags?post=467"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}