statsmodels. The mlflow.statsmodels module provides an API for logging and loading statsmodels models. This module exports statsmodels models with the following ...MLflowQuickstartTutorialsandExamplesConceptsMLflowTrackingMLflowProjectsMLflowModelsMLflowModelRegistryMLflowPluginsCommand-LineInterfaceSearchPythonAPImlflowmlflow.azuremlmlflow.catboostmlflow.deploymentsmlflow.entitiesmlflow.fastaimlflow.gluonmlflow.h2omlflow.kerasmlflow.lightgbmmlflow.mleapmlflow.modelsmlflow.onnxmlflow.paddlemlflow.projectsmlflow.pyfuncmlflow.pyspark.mlmlflow.pytorchmlflow.sagemakermlflow.shapmlflow.sklearnmlflow.spacymlflow.sparkmlflow.statsmodelsmlflow.tensorflowmlflow.trackingmlflow.typesmlflow.xgboostRAPIJavaAPIRESTAPIContributeDocumentationPythonAPImlflow.statsmodelsEditonGitHubmlflow.statsmodelsThemlflow.statsmodelsmoduleprovidesanAPIforloggingandloadingstatsmodelsmodels.Thismoduleexportsstatsmodelsmodelswiththefollowingflavors:statsmodels(native)formatThisisthemainflavorthatcanbeloadedbackintostatsmodels,whichreliesonpickleinternallytoserializeamodel.mlflow.pyfuncProducedforusebygenericpyfunc-baseddeploymenttoolsandbatchinference.classmlflow.statsmodels.AutologHelpers[source]Bases:objectshould_autolog=Truemlflow.statsmodels.autolog(log_models=True,disable=False,exclusive=False,disable_for_unsupported_versions=False,silent=False)[source]NoteExperimental:Thismethodmaychangeorberemovedinafuturereleasewithoutwarning.NoteAutologgingisknowntobecompatiblewiththefollowingpackageversions:0.11.1<=statsmodels<=0.12.2.Autologgingmaynotsucceedwhenusedwithpackageversionsoutsideofthisrange.Enables(ordisables)andconfiguresautomaticloggingfromstatsmodelstoMLflow.Logsthefollowing:resultsmetricsreturnedbymethodfitofanysubclassofstatsmodels.base.model.Modeltrainedmodel.Parameterslog_models–IfTrue,trainedmodelsareloggedasMLflowmodelartifacts.IfFalse,trainedmodelsarenotlogged.Inputexamplesandmodelsignatures,whichareattributesofMLflowmodels,arealsoomittedwhenlog_modelsisFalse.disable–IfTrue,disablest

Statsmodels is a Python visualization library built specifically for statistics. It includes advanced functions for statistical testing and modeling.NOWLIVEEmpoweryourenduserswithExplorationsinMode.TryitnowSQLTutorialBasicSQLIntermediateSQLAdvancedSQLSQLAnalyticsTrainingPythonTutorialLearnPythonforbusinessanalysisusingreal-worlddata.Nocodingexperiencenecessary.StartNowModeStudioTheCollaborativeDataSciencePlatformSignUpFreeStatsmodelsAsitsnameimplies,statsmodelsisaPythonlibrarybuiltspecificallyforstatistics.StatsmodelsisbuiltontopofNumPy,SciPy,andmatplotlib,butitcontainsmoreadvancedfunctionsforstatisticaltestingandmodelingthatyouwon'tfindinnumericallibrarieslikeNumPyorSciPy.StatsmodelstutorialsThetutorialsbelowcoveravarietyofstatsmodels'features.LinearregressionAfriendlyintroductiontolinearregression(usingPython)(DataSchool)LinearRegressionwithPython(ConnorJohnson)UsingPythonstatsmodelsforOLSlinearregression(MarktheGraph)LinearRegression(Officialstatsmodelsdocumentation)MultipleregressionMultipleRegressionusingStatsmodels(DataRobot)LogisticregressionLogisticRegressioninPython(Yhat)TimeseriesanalysisASimpleTimeSeriesAnalysisOfTheS&P500Index(JohnWittenauer)TimeSeriesAnalysisinPythonwithstatsmodels(WesMcKinney,JosefPerktold,andSkipperSeabold)TimeSeriesAnalysis(Officialstatsmodelsdocumentation)StatisticaltestsRegressionDiagnosticsandSpecificationTests(Officialstatsmodelsdocumentation)StatsmodelsresourcesChapter11:RegressionofThinkStats(AllenB.Downey)-Thischaptercoversaspectsofmultipleandlogisticregressioninstatsmodels.Itexplainstheconceptsbehindthecode,butyou'llstillneedfamiliaritywithbasicstatisticsbeforedivingin.ThestatsmodelssectionofCrossValidated-Aquestionandanswersiteforpeopleinterestedinstatistics,machinelearning,dataanalysis,datamining,anddatavisualization.Logisticregressionvs.multipleregression(CoolData)-NotPythonrelated,butthisprovidesahelpfulbreakdownofthedifferencesbetweenlogisticandmultipleregression.OfficialstatsmodelsdocumentationGetourweeklydatanewsletter

Skiptocontentstatisticalmodels,hypothesistests,anddataexplorationstatsmodelsv0.13.0.dev0(+600)statsmodelsInstallingstatsmodelsGettingstartedUserGuideExamplesAPIReferenceAboutstatsmodelsDeveloperPageReleaseNotesContentsIntroductionCitationIndexShowSourcestatsmodelsisaPythonmodulethatprovidesclassesandfunctionsfortheestimationofmanydifferentstatisticalmodels,aswellasforconductingstatisticaltests,andstatisticaldataexploration.Anextensivelistofresultstatisticsareavailableforeachestimator.Theresultsaretestedagainstexistingstatisticalpackagestoensurethattheyarecorrect.ThepackageisreleasedundertheopensourceModifiedBSD(3-clause)license.Theonlinedocumentationishostedatstatsmodels.org.Introduction¶statsmodelssupportsspecifyingmodelsusingR-styleformulasandpandasDataFrames.Hereisasimpleexampleusingordinaryleastsquares:In[1]:importnumpyasnpIn[2]:importstatsmodels.apiassmIn[3]:importstatsmodels.formula.apiassmf#LoaddataIn[4]:dat=sm.datasets.get_rdataset("Guerry","HistData").data#Fitregressionmodel(usingthenaturallogofoneoftheregressors)In[5]:results=smf.ols('Lottery~Literacy+np.log(Pop1831)',data=dat).fit()#InspecttheresultsIn[6]:print(results.summary())OLSRegressionResults==============================================================================Dep.Variable:LotteryR-squared:0.348Model:OLSAdj.R-squared:0.333Method:LeastSquaresF-statistic:22.20Date:Tue,03Aug2021Prob(F-statistic):1.90e-08Time:09:33:22Log-Likelihood:-379.82No.Observations:86AIC:765.6DfResiduals:83BIC:773.0DfModel:2CovarianceType:nonrobust===================================================================================coefstderrtP>|t|[0.0250.975]-----------------------------------------------------------------------------------Intercept246.434135.2336.9950.000176.358316.510Literacy-0.48890.128-3.8320.000-0.743-0.235np.log(Pop1831)-31.31145.977-5.2390.000-43.199-19.424==============================================================================Omnibus:3.713Durbin-Watson:2.019Prob(Omnibus):0.156Jarque-Bera(JB):3

BackApplyDocsSettings

statsmodels is a Python package that provides a complement to scipy for statistical ... See INSTALL.txt for requirements or see the documentation.SkiptomaincontentSwitchtomobileversionSearchPyPISearchstatsmodels0.12.2pipinstallstatsmodelsCopyPIPinstructionsLatestversionReleased:Feb2,2021StatisticalcomputationsandmodelsforPythonNavigationProjectdescriptionReleasehistoryDownloadfilesProjectlinksHomepageSourceCodeDocumentationBugTrackerStatisticsGitHubstatistics:Stars:Forks:Openissues/PRs:ViewstatisticsforthisprojectviaLibraries.io,orbyusingourpublicdatasetonGoogleBigQueryMetaLicense:BSDLicense(BSDLicense)Maintainer:statsmodelsDevelopersRequires:Python>=3.6Maintainersbashtagejosefpktdmatthew.brettrgommersSkipper.SeaboldClassifiersDevelopmentStatus4-BetaEnvironmentConsoleIntendedAudienceDevelopersEndUsers/DesktopScience/ResearchLicenseOSIApproved::BSDLicenseNaturalLanguageEnglishOperatingSystemOSIndependentProgrammingLanguageCythonPython::3.6Python::3.7Python::3.8TopicOffice/Business::FinancialScientific/EngineeringProjectdescriptionProjectdetailsReleasehistoryDownloadfilesProjectdescriptionAboutstatsmodelsstatsmodelsisaPythonpackagethatprovidesacomplementtoscipyforstatisticalcomputationsincludingdescriptivestatisticsandestimationandinferenceforstatisticalmodels.DocumentationThedocumentationforthelatestreleaseisathttps://www.statsmodels.org/stable/Thedocumentationforthedevelopmentversionisathttps://www.statsmodels.org/dev/Recentimprovementsarehighlightedinthereleasenoteshttps://www.statsmodels.org/stable/release/version0.9.htmlBackupsofdocumentationareavailableathttps://statsmodels.github.io/stable/andhttps://statsmodels.github.io/dev/.MainFeaturesLinearregressionmodels:OrdinaryleastsquaresGeneralizedleastsquaresWeightedleastsquaresLeastsquareswithautoregressiveerrorsQuantileregressionRecursiveleastsquaresMixedLinearModelwithmixedeffectsandvariancecomponentsGLM:Generalizedlinearmodelswithsupportforalloftheone-parameterexponentialfamilydistributionsBayesianMixedGLMforBin

Skiptocontentstatsmodelsv0.12.2statsmodelsInstallingstatsmodelsInstallingstatsmodelsContentsInstallingstatsmodelsPythonSupportAnacondaPyPI(pip)ObtainingtheSourceInstallationfromSourceCompilersLinuxWindowsMacDependenciesOptionalDependenciesShowSourcePythonSupportAnacondaPyPI(pip)ObtainingtheSourceInstallationfromSourceCompilersDependenciesOptionalDependenciesGettingstartedUserGuideExamplesAPIReferenceAboutstatsmodelsDeveloperPageReleaseNotesContentsInstallingstatsmodelsPythonSupportAnacondaPyPI(pip)ObtainingtheSourceInstallationfromSourceCompilersLinuxWindowsMacDependenciesOptionalDependenciesShowSourceInstallingstatsmodels¶TheeasiestwaytoinstallstatsmodelsistoinstallitaspartoftheAnacondadistribution,across-platformdistributionfordataanalysisandscientificcomputing.Thisistherecommendedinstallationmethodformostusers.InstructionsforinstallingfromPyPI,sourceoradevelopmentversionarealsoprovided.PythonSupport¶statsmodelssupportsPython3.6,3.7and3.8.Anaconda¶statsmodelsisavailablethroughcondaprovidedbyAnaconda.Thelatestreleasecanbeinstalledusing:condainstall-cconda-forgestatsmodelsPyPI(pip)¶Toobtainthelatestreleasedversionofstatsmodelsusingpip:pipinstallstatsmodelsFollowthislinktoourPyPIpagetodirectlydownloadwheelsorsource.ForWindowsusers,unofficialrecentbinaries(wheels)areoccasionallyavailablehere.ObtainingtheSource¶Wedonotreleaseveryoftenbutthemasterbranchofoursourcecodeisusuallyfineforeverydayuse.Youcangetthelatestsourcefromourgithubrepository.Orifyouhavegitinstalled:gitclonegit://github.com/statsmodels/statsmodels.gitIfyouwanttokeepuptodatewiththesourceongithubjustperiodicallydo:gitpullinthestatsmodelsdirectory.InstallationfromSource¶YouwillneedaCcompilerinstalledtobuildstatsmodels.Ifyouarebuildingfromthegithubsourceandnotasourcerelease,thenyouwillalsoneedCython.YoucanfollowtheinstructionsbelowtogetaCcompilersetupforWindows.Ifyoursystemisalreadysetupwithpip,acompiler,andgit,youcantry:pipinstallgit+https://github.com/statsmodels/statsmodelsIfyoudonothavepipinstalledorwant

Statsmodels: statistical modeling and econometrics in Python - GitHub ... Installing from sources. See INSTALL.txt for requirements or see the documentation.Skiptocontent{{message}}statsmodels/statsmodelsNotificationsStar6.5kFork2.3kStatsmodels:statisticalmodelingandeconometricsinPythonwww.statsmodels.org/devel/BSD-3-ClauseLicense6.5kstars2.3kforksStarNotificationsCodeIssues2kPullrequests154ActionsProjects11WikiSecurityInsightsMoreCodeIssuesPullrequestsActionsProjectsWikiSecurityInsightsmainBranchesTagsCouldnotloadbranchesNothingtoshow{{refName}}defaultCouldnotloadtagsNothingtoshow{{refName}}default18branches40tagsCodeCloneHTTPSGitHubCLIUseGitorcheckoutwithSVNusingthewebURL.WorkfastwithourofficialCLI.Learnmore.OpenwithGitHubDesktopDownloadZIPLaunchingGitHubDesktopIfnothinghappens,downloadGitHubDesktopandtryagain.GobackLaunchingGitHubDesktopIfnothinghappens,downloadGitHubDesktopandtryagain.GobackLaunchingXcodeIfnothinghappens,downloadXcodeandtryagain.GobackLaunchingVisualStudioCodeYourcodespacewillopenonceready.Therewasaproblempreparingyourcodespace,pleasetryagain.LatestcommitbashtageMergepullrequest#7620frombashtage/fix-optim-param…47137ebAug3,2021Mergepullrequest#7620frombashtage/fix-optim-paramMAINT:Avoidpassingbadoptimizationparam47137ebGitstats13,970commitsFilesPermalinkFailedtoloadlatestcommitinformation.TypeNameLatestcommitmessageCommittime.githubMAINT:RemoverecarraysJul15,2021archiveMAINT:RemovedeprecatedfunctionsandkeywordsJul7,2020docsMergepullrequest#7614frombashtage/small-clean-copulaJul30,2021examplesMergepullrequest#7614frombashtage/small-clean-copulaJul30,2021statsmodelsMAINT:AvoidpassingbadoptimizationparamAug2,2021toolsMAINT:ClarifyminimumversionsJul20,2021.codacy.ymlCLN/MAINT:Portnon-diagnosticchangesJan14,2020.gitattributesBLD:StartsimplifyingsetupSep8,2018.gitignoreENH:AddCFAsimulationsmoother.Feb5,2020.mailmapMAINT:Updatemailmap.Oct15,2014.pep8speaks.ymlBLD/DOC:AdddocstringchecktodocbuildJul30,2019.travis.ymlMAINT:Removeappveyoranddownscaletravis

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

conda install -c conda-forge statsmodels conda install -c conda-forge/label/gcc7 statsmodels conda install -c conda-forge/label/cf201901 statsmodelsMenuGalleryAboutAnacondaHelpDownloadAnacondaSignInconda-forge/packages/statsmodels0.12.214StatisticalcomputationsandmodelsforusewithSciPyCondaFilesLabelsBadgesLicense:BSD-3-Clause4633371totaldownloadsLastupload:5monthsand22daysagoInstallersInfo:Thispackagecontainsfilesinnon-standardlabels.condainstalllinux-ppc64le v0.11.1osx-arm64 v0.12.2linux-64 v0.12.2win-32 v0.8.0linux-aarch64 v0.12.2osx-64 v0.12.2win-64 v0.12.2Toinstallthispackagewithcondarunoneofthefollowing:condainstall-cconda-forgestatsmodelscondainstall-cconda-forge/label/gcc7statsmodelscondainstall-cconda-forge/label/cf201901statsmodelscondainstall-cconda-forge/label/cf202003statsmodelsDescriptionNone©2021Anaconda,Inc.AllRightsReserved.(v2.35.5ff55f896)Legal|PrivacyPolicy