Statsmodels is a Python package that allows users to explore data, estimate statistical models, and perform statistical tests.StatsmodelsFromWikipedia,thefreeencyclopediaJumptonavigationJumptosearchThisarticlemayrelyexcessivelyonsourcestoocloselyassociatedwiththesubject,potentiallypreventingthearticlefrombeingverifiableandneutral.Pleasehelpimproveitbyreplacingthemwithmoreappropriatecitationstoreliable,independent,third-partysources.(September2019)(Learnhowandwhentoremovethistemplatemessage)StatsmodelsisaPythonpackagethatallowsuserstoexploredata,estimatestatisticalmodels,andperformstatisticaltests.Anextensivelistofdescriptivestatistics,statisticaltests,plottingfunctions,andresultstatisticsareavailablefordifferenttypesofdataandeachestimator.ItcomplementsSciPy'sstatsmodule.[1][2]StatsmodelsispartofthePythonscientificstackthatisorientedtowardsdataanalysis,datascienceandstatistics.StatsmodelsisbuiltontopofthenumericallibrariesNumPyandSciPy,integrateswithPandasfordatahandling,andusesPatsy[3]foranR-likeformulainterface.GraphicalfunctionsarebasedontheMatplotliblibrary.StatsmodelsprovidesthestatisticalbackendforotherPythonlibraries.StatmodelsisfreesoftwarereleasedundertheModifiedBSD(3-clause)license.References[edit]^"StatisticalcomputationsandmodelsforusewithSciPy".^http://www.statsmodels.org/^http://patsy.readthedocs.org/en/latest/index.htmlvteScientificsoftwareinPythonNumPySciPymatplotlibpandasscikit-learnscikit-imagestatsmodelsMayaVimoreRetrievedfrom"https://en.wikipedia.org/w/index.php?title=Statsmodels&oldid=979635404"Categories:FreestatisticalsoftwarePython(programminglanguage)Python(programminglanguage)scientificlibrariesHiddencategories:ArticleslackingreliablereferencesfromSeptember2019AllarticleslackingreliablereferencesNavigationmenuPersonaltoolsNotloggedinTalkContributionsCreateaccountLoginNamespacesArticleTalkVariantsViewsReadEditViewhistoryMoreSearchNavigationMainpageContentsCurrenteventsRandomarticleAboutWikipediaContactusDonateContributeHelpLearntoeditCommunit

<

---

3. 使用python ols 預測值

0使用pythonols預測值pythonolspandaspandas.dataframedataframeh2234499612021-02-2815:33:16‧680瀏覽範例：#-*-coding:utf-8-*-importpandasaspdimportstatsmodels.formula.apiassmimportstatsmodels.regression.linear_modelassmimportstatsmodels.apiassm2TV=[230.1,44.5,17.2,151.5,180.8]Radio=[37.8,39.3,45.9,41.3,10.8]Newspaper=[69.2,45.1,69.3,58.5,58.4]Sales=[22.1,10.4,9.3,18.5,12.9]df=pd.DataFrame({'TV':TV,'Radio':Radio,'Newspaper':Newspaper,'Sales':Sales})Y=df.SalesX=df[['TV','Radio','Newspaper']]X=sm2.add_constant(X)model=sm.OLS(Y,X).fit()new_x=df.loc[df.Sales.notnull(),['TV','Radio','Newspaper']].valuesnew_x=sm2.add_constant(new_x)#sm2=statsmodels.apiy_predict=model.predict(new_x)print(df)print(y_predict)留言追蹤檢舉尚未有邦友留言立即登入留言相關文章[第06天]資料結構（3）DataFrame[第14天]常用屬性或方法（3）DataFrame[第15天]載入資料[第17天]資料角力用tkinter實現選擇路徑打開excel，並用treeview顯示Day03PandasDataFrame,LabelEncodingandOneHotEncoding.Pandas基本資料類型、標籤編碼與獨熱編碼Day25BeautifulSoupTryOut:StepstonePosting美麗的湯爬蟲初體驗：達石職缺Day26StepstonePosting達石職缺[不做怎麼知道系列之Android開發者的30天後端養成故事Day30]-結束是新的開始#學到了什麼?#下一步#後端?iOS?Android?【Day19】批次匯入證交所資料熱門問題電腦開機嗶嗶叫，不是一開機的嗶嗶叫，而是開機運作一段時間後的嗶嗶叫，固定時間，固定次數請推薦好用的前端表格套件電腦螢幕顯示不出畫面關於本機admin密碼的更改gmail拒絕公司信件，下列組織已拒絕您的郵件:gmail-smtp-in.l.google.com。

[Python]找出最接近二千萬的質數?Fortigatepolicy順序觀念讀研究所的先後，以及是否必要?新手機應該換成甚麼本機最高權限的管制IT邦幫忙熱門tag看更多12th鐵人賽11th鐵人賽鐵人賽2019鐵人賽2018鐵人賽javascript2017鐵人賽windowsphpwindowsserverlinuxpython程式設計c#資訊安全csssql分享mysql專案管理熱門回答電腦螢幕顯示不出畫面電腦開機嗶嗶叫，不是一開機的嗶嗶叫，而是開機運作一段時間後的嗶嗶叫，固定時間，固定次數讀研究所的先後，以及是否必要?gmail拒絕公司信件，下列組織已拒絕您的郵件:gmail-smtp-in.l.google.com。

Fortigatepolicy順序觀念HP5130不同網段設定為甚麼照片傳到雲端硬碟之後畫質會變低?如何列印檔案夾doc，指定範圍想請問如何用注音輸入法打到六十字以上，或是用簡單易學的輸入法java初學遇到system.out.printIn的問題熱門文章乳房大軍的鑑識與情資蒐索理解React的setState到底是同步還是非同步(上)各家筆電還原的快速鍵《賴田捕手：番外篇》第40天：用Netlify整合前後端服務Day23參加職訓(機器學習與資料分析工程師培訓班)，Django大型企業筆電使用者訪問(19~54歲男女車馬費1200元)寫在VSCodeExtension系列文之後-12th鐵人賽頒獎典禮得獎致詞GetReadytoPassScrumStudySMCExamTestGuide–2021PDFQ&A筆記-常見演算法時間複雜度使用證書對代碼進行簽章，以防止其被篡改並向用戶驗證您的身份-使用您的私鑰對代碼進行散列並加密結果一週點數排行更多點數排行海綿寶寶(antijava)japhenchen(japhenchen)國際IT人

---

4. Ordinary Least Squares in Python

SkiptocontentPlatform#OverviewTourtheAIPlatformWhat’sNewGettingStartedSeeDataRobotTryDataRobotCreateAIDataPreparationZeplNotebooksAutomatedMachineLearningAutomatedTimeSeriesOperationalizeAIMLOpsConsumeAIAIAppsProductHighlightsVisualAIFeatureDiscoveryComposableMLEureqaModelsTrustedAIModelGraderContinuousAIBiasandFairnessNo-CodeAIAppBuilderDeploymentOptionsManagedAICloudPrivateAICloudHybridAICloudOn-PremiseAIClusterSolutions#SolutionsByIndustry/UseBankingCasinosandGamingConsumerPackagedGoodsFinancialMarketsFintechHealthcareInsuranceManufacturing MarketingOilandGasPublicSectorRetailTelecommunicationsRoboticProcessAutomationSportsAllUseCasesByroleBusinessAnalystsDataScientistsExecutivesandAnalyticsLeadersITOperationsSoftwareEngineersSuccess#SuccessOverviewCustomersAIHeroesMoreIntelligentTomorrowKeystoAISuccessin2021TheDataRobotAIAdoptionPathProfessionalServicesResources#ResourceLibraryBlogWebinarsMoreIntelligentTomorrowAI+MLin20MinutesAIExperienceRecordingsEventsDataRobotCommunityDocumentationWikiPartners#PartnersOverviewTechnologyAlliancesValueAddedResellersSolutionPartnersConsultingFirmsPartnerPortalEducation#OverviewDataRobotUniversityAcademicSupportProgram10xAcademyCompany#OurCultureAIForGoodNewsroomOpenPositionsSupportPortalBlogEventsMoreIntelligentTomorrowPathfinderDocsCommunityCareersRequestaDemoFreeTrialBlogAI&MLExpertiseOrdinaryLeastSquaresinPythonOrdinaryLeastSquaresinPythonFebruary8,2014byPeterPrettenhofer· 8min readLinearregression,alsocalledOrdinaryLeast-Squares(OLS)Regression,isprobablythemostcommonlyusedtechniqueinStatisticalLearning.Itisalsotheoldest,datingbacktotheeighteenthcenturyandtheworkofCarlFriedrichGaussandAdrien-MarieLegendre.Itisalsooneoftheeasierandmoreintuitivetechniquestounderstand,anditprovidesagoodbasisforlearningmoreadvancedconceptsandtechniques.ThispostexplainshowtoperformlinearregressionusingthestatsmodelsPythonpackage.Wewilldiscussthesinglevariablecaseanddefermultipleregressiontoafuturepost.Thisispartofaseriesofblogpoststoshowhowtodoco

---

5. OLS estimation

SkiptocontentExamplesstatsmodelsv0.12.2statsmodelsInstallingstatsmodelsGettingstartedUserGuideExamplesLinearRegressionModelsOrdinaryLeastSquaresOrdinaryLeastSquaresContentsOrdinaryLeastSquaresOLSestimationOLSnon-linearcurvebutlinearinparametersOLSwithdummyvariablesJointhypothesistestFtestSmallgroupeffectsMulticollinearityConditionnumberDroppinganobservationShowSourceGeneralizedLeastSquaresQuantileregressionRecursiveleastsquaresExample2:QuantitytheoryofmoneyExample3:LinearrestrictionsandformulasRollingRegressionRegressiondiagnosticsWeightedLeastSquaresLinearMixedEffectsModelsComparingRlmertostatsmodelsMixedLMVarianceComponentAnalysisPlottingDiscreteChoiceModelsNonparametricStatisticsGeneralizedLinearModelsRobustRegressionGeneralizedEstimatingEquationsStatisticsTimeSeriesAnalysisStatespacemodelsStatespacemodels-TechnicalnotesForecastingMultivariateMethodsUserNotesAPIReferenceAboutstatsmodelsDeveloperPageReleaseNotesContentsOrdinaryLeastSquaresOLSestimationOLSnon-linearcurvebutlinearinparametersOLSwithdummyvariablesJointhypothesistestFtestSmallgroupeffectsMulticollinearityConditionnumberDroppinganobservationShowSourceOrdinaryLeastSquares¶[1]:%matplotlibinline[2]:importnumpyasnpimportpandasaspdimportmatplotlib.pyplotaspltimportstatsmodels.apiassmfromstatsmodels.sandbox.regression.predstdimportwls_prediction_stdnp.random.seed(9876789)OLSestimation¶Artificialdata:[3]:nsample=100x=np.linspace(0,10,100)X=np.column_stack((x,x**2))beta=np.array([1,0.1,10])e=np.random.normal(size=nsample)Ourmodelneedsaninterceptsoweaddacolumnof1s:[4]:X=sm.add_constant(X)y=np.dot(X,beta)+eFitandsummary:[5]:model=sm.OLS(y,X)results=model.fit()print(results.summary())OLSRegressionResults==============================================================================Dep.Variable:yR-squared:1.000Model:OLSAdj.R-squared:1.000Method:LeastSquaresF-statistic:4.020e+06Date:Tue,02Feb2021Prob(F-statistic):2.83e-239Time:06:52:01Log-Likelihood:-146.51No.Observations:100AIC:299.0DfResiduals:97BIC:306.8DfModel:2

---

6. Linear Regression — statsmodels

SkiptocontentUserGuidestatsmodelsv0.12.2statsmodelsInstallingstatsmodelsGettingstartedUserGuideBackgroundRegressionandLinearModelsLinearRegressionLinearRegressionContentsLinearRegressionExamplesTechnicalDocumentationReferencesAttributesModuleReferenceModelClassesResultsClassesShowSourceGeneralizedLinearModelsGeneralizedEstimatingEquationsGeneralizedAdditiveModels(GAM)RobustLinearModelsLinearMixedEffectsModelsRegressionwithDiscreteDependentVariableGeneralizedLinearMixedEffectsModelsANOVATimeSeriesAnalysisOtherModelsStatisticsandToolsDataSetsSandboxExamplesAPIReferenceAboutstatsmodelsDeveloperPageReleaseNotesContentsLinearRegressionExamplesTechnicalDocumentationReferencesAttributesModuleReferenceModelClassesResultsClassesShowSourceLinearRegression¶Linearmodelswithindependentlyandidenticallydistributederrors,andforerrorswithheteroscedasticityorautocorrelation.Thismoduleallowsestimationbyordinaryleastsquares(OLS),weightedleastsquares(WLS),generalizedleastsquares(GLS),andfeasiblegeneralizedleastsquareswithautocorrelatedAR(p)errors.SeeModuleReferenceforcommandsandarguments.Examples¶#LoadmodulesanddataIn[1]:importnumpyasnpIn[2]:importstatsmodels.apiassmIn[3]:spector_data=sm.datasets.spector.load(as_pandas=False)In[4]:spector_data.exog=sm.add_constant(spector_data.exog,prepend=False)#FitandsummarizeOLSmodelIn[5]:mod=sm.OLS(spector_data.endog,spector_data.exog)In[6]:res=mod.fit()In[7]:print(res.summary())OLSRegressionResults==============================================================================Dep.Variable:yR-squared:0.416Model:OLSAdj.R-squared:0.353Method:LeastSquaresF-statistic:6.646Date:Tue,02Feb2021Prob(F-statistic):0.00157Time:07:07:13Log-Likelihood:-12.978No.Observations:32AIC:33.96DfResiduals:28BIC:39.82DfModel:3CovarianceType:nonrobust==============================================================================coefstderrtP>|t|[0.0250.975]------------------------------------------------------------------------------x10.46390.1622.8640.0080.1320.796x20.01050.01

---

7. statsmodels.regression.linear

SkiptocontentUserGuideLinearRegressionstatsmodelsv0.12.2statsmodelsInstallingstatsmodelsGettingstartedUserGuideBackgroundRegressionandLinearModelsLinearRegressionGeneralizedLinearModelsGeneralizedEstimatingEquationsGeneralizedAdditiveModels(GAM)RobustLinearModelsLinearMixedEffectsModelsRegressionwithDiscreteDependentVariableGeneralizedLinearMixedEffectsModelsANOVATimeSeriesAnalysisOtherModelsStatisticsandToolsDataSetsSandboxExamplesAPIReferenceAboutstatsmodelsDeveloperPageReleaseNotesShowSourcestatsmodels.regression.linear_model.OLS¶classstatsmodels.regression.linear_model.OLS(endog,exog=None,missing='none',hasconst=None,**kwargs)[source]¶OrdinaryLeastSquaresParametersendogarray_likeA1-dendogenousresponsevariable.Thedependentvariable.exogarray_likeAnobsxkarraywherenobsisthenumberofobservationsandkisthenumberofregressors.Aninterceptisnotincludedbydefaultandshouldbeaddedbytheuser.Seestatsmodels.tools.add_constant.missingstrAvailableoptionsare‘none’,‘drop’,and‘raise’.If‘none’,nonancheckingisdone.If‘drop’,anyobservationswithnansaredropped.If‘raise’,anerrorisraised.Defaultis‘none’.hasconstNoneorboolIndicateswhethertheRHSincludesauser-suppliedconstant.IfTrue,aconstantisnotcheckedforandk_constantissetto1andallresultstatisticsarecalculatedasifaconstantispresent.IfFalse,aconstantisnotcheckedforandk_constantissetto0.**kwargsExtraargumentsthatareusedtosetmodelpropertieswhenusingtheformulainterface.SeealsoWLSFitalinearmodelusingWeightedLeastSquares.GLSFitalinearmodelusingGeneralizedLeastSquares.NotesNoconstantisaddedbythemodelunlessyouareusingformulas.Examples>>>importstatsmodels.apiassm>>>importnumpyasnp>>>duncan_prestige=sm.datasets.get_rdataset("Duncan","carData")>>>Y=duncan_prestige.data['income']>>>X=duncan_prestige.data['education']>>>X=sm.add_constant(X)>>>model=sm.OLS(Y,X)>>>results=model.fit()>>>results.paramsconst10.603498education0.594859dtype:float64>>>results.tvaluesconst2.039813education6.892802dtype:float64>>>print(results.t_test([1,0]))TestforConstraints========

---

8. Python statsmodels.api 模块，OLS 实例源码

---

9. Ordinary Least Squares (OLS) using statsmodels ...

SkiptocontentTutorialsPracticeDS&Algo.DSATopic-wiseDSACompany-wiseAlgorithmsAnalysisofAlgorithmsAsymptoticAnalysisWorst,AverageandBestCasesAsymptoticNotationsLittleoandlittleomeganotationsLowerandUpperBoundTheoryAnalysisofLoopsSolvingRecurrencesAmortizedAnalysisWhatdoes'SpaceComplexity'mean?Pseudo-polynomialAlgorithmsPolynomialTimeApproximationSchemeATimeComplexityQuestionSearchingAlgorithmsSortingAlgorithmsGraphAlgorithmsPatternSearchingGeometricAlgorithmsMathematicalBitwiseAlgorithmsRandomizedAlgorithmsGreedyAlgorithmsDynamicProgrammingDivideandConquerBacktrackingBranchandBoundAllAlgorithmsDataStructuresArraysLinkedListStackQueueBinaryTreeBinarySearchTreeHeapHashingGraphAdvancedDataStructureMatrixStringsAllDataStructuresInterviewCornerCompanyPreparationTopTopicsPracticeCompanyQuestionsInterviewExperiencesExperiencedInterviewsInternshipInterviewsCompetititveProgrammingDesignPatternsSystemDesignTutorialMultipleChoiceQuizzesLanguagesCC++JavaPythonC#JavaScriptjQuerySQLPHPScalaPerlGoLanguageHTMLCSSKotlinISROCSISROCSSolvedPapersISROCSOriginalPapersandOfficialKeysISROCSSyllabusforScientist/EngineerExamGATEGATEComputerScienceNotesLastMinuteNotesGATECSSolvedPapersGATECSOriginalPapersandOfficialKeysGATE2021DatesGATECS2021SyllabusImportantTopicsforGATECSCSSubjectsMathematicsOperatingSystemDBMSComputerNetworksComputerOrganizationandArchitectureTheoryofComputationCompilerDesignDigitalLogicSoftwareEngineeringWebTechnologiesHTMLCSSJavaScriptAngularJSReactJSNodeJSBootstrapjQueryPHPSchoolLearningSchoolProgrammingMathematicsAlgebraTrigonometryStatisticsProbabilityGeometryMensurationCalculusMathsNotes(Class8-11)Class8NotesClass9NotesClass10NotesClass11NotesNCERTSolutionsClass8MathsSolutionClass9MathsSolutionClass10MathsSolutionClass11MathsSolutionClass12MathsSolutionRDSharmaSolutionsClass8MathsSolutionClass9MathsSolutionClass10MathsSolutionClass11MathsSolutionClass12MathsSolutionUGCNETCSUGCNETCSNotesPaperIIUGCNETCSNotesPaperIIIUGCNETCSSolvedPapersStudentCampusAmbassadorProgramSchool

---

10. Implementing ordinary least squares (OLS) using Statsmodels in Python ...

SigninMOBILE+MLLENSSTUDIOMACHINELEARNINGCOMMUNITYCONTRIBUTEALLABOUTFRITZAIImplementingordinaryleastsquares(OLS)usingStatsmodelsinPythonDhirajKFollowOct10,2019·4minreadPhotobyIlzeLuceroonUnsplashAreyoulookingforacomputationallycheap,easy-to-explainlinearestimatorthat’sbasedonsimplemathematics?LooknofurtherthanOLS!OLSstandsforordinaryleastsquares.OLSisheavilyusedineconometrics—abranchofeconomicswherestatisticalmethodsareusedtofindtheinsightsineconomicdata.Asweknow,thesimplestlinearregressionalgorithmassumesthattherelationshipbetweenanindependentvariable(x)anddependentvariable(y)isofthefollowingform:y=mx+c,whichistheequationofaline.Inlinewiththat,OLSisanestimatorinwhichthevaluesofmandc(fromtheaboveequation)arechoseninsuchawayastominimizethesumofthesquaresofthedifferencesbetweentheobserveddependentvariableandpredicteddependentvariable.That’swhyit’snamedordinaryleastsquares.Also,itshouldbenotedthatwhenthesumofthesquaresofthedifferencesisminimum,thelossisalsominimum—hencethepredictionisbetter.PleasefindbelowthevideoonMultipleLinearRegressioninPythonandsklearnJoinmorethan14,000ofyourfellowmachinelearnersanddatascientists.Subscribetothepremiernewsletterforallthingsdeeplearning.AdvantagesofOLSOLSiseasiertoimplementcomparedtoothersimilareconometrictechniques.Thisisbecausethetheoryofleastsquaresiseasiertounderstandforadeveloperthanothercommonapproaches.OLShasasimplemathematicalconceptsoitiseasiertoexplaintonon-technologistsorstakeholdersathighlevel.AssumptionsofOLSThereshouldbenomulticollinearitybetweenanytwoindependentvariables.Thevalueofthemeanoftheerrortermsshouldbezeroforgivenindependentvariables.ThesampletakenfortheOLSregressionmodelshouldbetakenrandomlyfromthepopulation.Alltheerrortermsintheregressionshouldhavethesamevariance,whichmeanshomoscedasticity.Photoby@chairulfajar_onUnsplashOLSusingStatsmodelsStatsmodelsispartofthescientificPythonlibrarythat’sinclinedtowardsdataanalysis,datascience,andstatistics.It’sbuiltontopofthenumericlibraryNumPyandthescientificlibrarySciPy.

---