RFECV converged and stagnate between 30 to 40 features but best model had 140 features












0















I have 145 features on 7800 samples and I am trying to use RFECV to train Gaussian Naive Bayes, Logistic Regression, and Linear SVM.





Looking at the graph above, both the LR and SVM models starts to stagnate between 30 to 40 features. Is this a sign of overfitting? It still spat out 140 features for both models since RFECV would only tell you the feature set which achieved the highest accuracy. There is only a subtle accuracy differences between 30 to 140 features, so what is the smartest thing to do here? Do I just apply the same number of features which the Naive Bayes had on both LR and SVM, (which is 39 features in this case)?



Thanks






feature-selection rfe







share|improve this question



























    0















    I have 145 features on 7800 samples and I am trying to use RFECV to train Gaussian Naive Bayes, Logistic Regression, and Linear SVM.





    Looking at the graph above, both the LR and SVM models starts to stagnate between 30 to 40 features. Is this a sign of overfitting? It still spat out 140 features for both models since RFECV would only tell you the feature set which achieved the highest accuracy. There is only a subtle accuracy differences between 30 to 140 features, so what is the smartest thing to do here? Do I just apply the same number of features which the Naive Bayes had on both LR and SVM, (which is 39 features in this case)?



    Thanks






    feature-selection rfe







    share|improve this question

























      0












      0








      0








      I have 145 features on 7800 samples and I am trying to use RFECV to train Gaussian Naive Bayes, Logistic Regression, and Linear SVM.





      Looking at the graph above, both the LR and SVM models starts to stagnate between 30 to 40 features. Is this a sign of overfitting? It still spat out 140 features for both models since RFECV would only tell you the feature set which achieved the highest accuracy. There is only a subtle accuracy differences between 30 to 140 features, so what is the smartest thing to do here? Do I just apply the same number of features which the Naive Bayes had on both LR and SVM, (which is 39 features in this case)?



      Thanks






      feature-selection rfe







      share|improve this question














      I have 145 features on 7800 samples and I am trying to use RFECV to train Gaussian Naive Bayes, Logistic Regression, and Linear SVM.





      Looking at the graph above, both the LR and SVM models starts to stagnate between 30 to 40 features. Is this a sign of overfitting? It still spat out 140 features for both models since RFECV would only tell you the feature set which achieved the highest accuracy. There is only a subtle accuracy differences between 30 to 140 features, so what is the smartest thing to do here? Do I just apply the same number of features which the Naive Bayes had on both LR and SVM, (which is 39 features in this case)?



      Thanks






      feature-selection rfe




      feature-selection rfe






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked 20 hours ago









      chmscrbbrfckchmscrbbrfck

      177




      177
























          0






          active

          oldest

          votes











          Your Answer






          StackExchange.ifUsing("editor", function () {
          StackExchange.using("externalEditor", function () {
          StackExchange.using("snippets", function () {
          StackExchange.snippets.init();
          });
          });
          }, "code-snippets");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "1"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54250215%2frfecv-converged-and-stagnate-between-30-to-40-features-but-best-model-had-140-fe%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Stack Overflow!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid …



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54250215%2frfecv-converged-and-stagnate-between-30-to-40-features-but-best-model-had-140-fe%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          -

          Popular posts from this blog

          Homophylophilia

          Image
          Haec pagina ad tempus protecta est ob maleficia perpetua. Quaesemus, emendationes suggere in pagina disputationis vel magistratum ad hanc deprotegendam pete. Homophylophilia Hyacinthus complexus ab amante suo Apolline, in pictura Mors Hyacinthi quam Jean Broc pinxit. Homophylophilia est sui sexus vel generis amor vel mores romantici vel sexuales, res venerea masculina in masculos, aut mulier in mulieres appetentes. Hoc ingenium sexuale est "exemplar permanens vel inclinatio ad experiendam sexualem, adfectionalem, vel romanticam vim attrahendi," praecipue vel solum ex hominibus eiusdem sexús; notio "etiam ad hominis iudicium identitatis privatae socialisque in illis attractionibus conditum refert, in moribus quoque qui illos exprimant, et in societate communitatis aliorum qui illos communicent." [1] [2] Per aevos alii aliter rem definiverunt, sed Occidentali nostrae aetatis cultu civili non tantum ad ipsa acta erotica spectat, sed etiam igitur
          Read more

          Updating UILabel text programmatically using a function

          Image
          0 so I am trying to update the UIlabel text using a func. I have seen few other questions like mine and I tried their method but it doesn't work. fun returns no value when used in the UIlabel. I have shown my code below.It has to be noted that when I use the function in viewdidload I can retrieve the data. lazy var name: UILabel = { let lb = UILabel() lb.text? = getthename() lb.lineBreakMode = NSLineBreakMode.byWordWrapping lb.textColor = .mainGreen lb.textAlignment = .left lb.font = UIFont.boldSystemFont(ofSize:12.0) return lb }() func getthename() -> String { var wins : String = "" let ud = (Auth.auth().currentUser?.uid) self.ref = Database.database().reference() self.ref.child("Users").child(ud!).observeSingleEvent(of: .value, with: {(snapshot) in
          Read more

          Cloud Functions - OpenCV Videocapture Read method fails for larger files from cloud storage

          Image
          0 I created a cloud function to read a video file from cloud storage and read frames and create an image for each frame. This function works for small files which is 1-2 MB, However, this method fails while reading larger file 130 MB. import cv2 from google.cloud import storage vidcap = cv2.VideoCapture("https://storage.googleapis.com/[bucker_name]/[filename.mp4]") if vidcap.isOpened(): vidcap.open("https://storage.googleapis.com/[bucker_name]/[filename.mp4]") success,image = vidcap.read() print(success) Expected the print will return true and an image will hold an image of a first frame. python-3.x function opencv cloud share | improve this question
          Read more