error in finding similarity using NFM and Tfidf for a Data set for tag “unknown”












0












$begingroup$


import pandas as pd



df = pd.read_csv('india-news-headlines.csv')
df.head()



nf = ' '.join(df['headline_text'].tolist())



Labels = df['headline_category'][:1000]
News = df['headline_text'][:1000]
hf = pd.DataFrame({'Category':Labels, 'Headlines': News})



from sklearn.feature_extraction.text import TfidfVectorizer



tfidf = TfidfVectorizer()



features = tfidf.fit_transform(hf['Category']).toarray()
features.shape



Perform the necessary imports



from sklearn.decomposition import NMF
from sklearn.preprocessing import MaxAbsScaler, Normalizer
from sklearn.pipeline import make_pipeline



Create a MaxAbsScaler: scaler



scaler = MaxAbsScaler()



Create an NMF model: nmf



nmf = NMF(n_components=10)



Create a Normalizer: normalizer



normalizer = Normalizer()



Create a pipeline: pipeline



pipeline = make_pipeline(scaler, nmf, normalizer)



Apply fit_transform to artists: norm_features



norm_features = pipeline.fit_transform(features)



Import pandas



import pandas as pd



Create a DataFrame: df



nf = pd.DataFrame(norm_features, index=Labels)



Select row of 'Bruce Springsteen': artist



artist = nf.loc['unknown']



Compute cosine similarities: similarities



similarities = nf.dot(artist.T)



Display those with highest cosine similarity



print(similarities.nlargest( ))









share







New contributor




manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    0












    $begingroup$


    import pandas as pd



    df = pd.read_csv('india-news-headlines.csv')
    df.head()



    nf = ' '.join(df['headline_text'].tolist())



    Labels = df['headline_category'][:1000]
    News = df['headline_text'][:1000]
    hf = pd.DataFrame({'Category':Labels, 'Headlines': News})



    from sklearn.feature_extraction.text import TfidfVectorizer



    tfidf = TfidfVectorizer()



    features = tfidf.fit_transform(hf['Category']).toarray()
    features.shape



    Perform the necessary imports



    from sklearn.decomposition import NMF
    from sklearn.preprocessing import MaxAbsScaler, Normalizer
    from sklearn.pipeline import make_pipeline



    Create a MaxAbsScaler: scaler



    scaler = MaxAbsScaler()



    Create an NMF model: nmf



    nmf = NMF(n_components=10)



    Create a Normalizer: normalizer



    normalizer = Normalizer()



    Create a pipeline: pipeline



    pipeline = make_pipeline(scaler, nmf, normalizer)



    Apply fit_transform to artists: norm_features



    norm_features = pipeline.fit_transform(features)



    Import pandas



    import pandas as pd



    Create a DataFrame: df



    nf = pd.DataFrame(norm_features, index=Labels)



    Select row of 'Bruce Springsteen': artist



    artist = nf.loc['unknown']



    Compute cosine similarities: similarities



    similarities = nf.dot(artist.T)



    Display those with highest cosine similarity



    print(similarities.nlargest( ))









    share







    New contributor




    manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      0












      0








      0





      $begingroup$


      import pandas as pd



      df = pd.read_csv('india-news-headlines.csv')
      df.head()



      nf = ' '.join(df['headline_text'].tolist())



      Labels = df['headline_category'][:1000]
      News = df['headline_text'][:1000]
      hf = pd.DataFrame({'Category':Labels, 'Headlines': News})



      from sklearn.feature_extraction.text import TfidfVectorizer



      tfidf = TfidfVectorizer()



      features = tfidf.fit_transform(hf['Category']).toarray()
      features.shape



      Perform the necessary imports



      from sklearn.decomposition import NMF
      from sklearn.preprocessing import MaxAbsScaler, Normalizer
      from sklearn.pipeline import make_pipeline



      Create a MaxAbsScaler: scaler



      scaler = MaxAbsScaler()



      Create an NMF model: nmf



      nmf = NMF(n_components=10)



      Create a Normalizer: normalizer



      normalizer = Normalizer()



      Create a pipeline: pipeline



      pipeline = make_pipeline(scaler, nmf, normalizer)



      Apply fit_transform to artists: norm_features



      norm_features = pipeline.fit_transform(features)



      Import pandas



      import pandas as pd



      Create a DataFrame: df



      nf = pd.DataFrame(norm_features, index=Labels)



      Select row of 'Bruce Springsteen': artist



      artist = nf.loc['unknown']



      Compute cosine similarities: similarities



      similarities = nf.dot(artist.T)



      Display those with highest cosine similarity



      print(similarities.nlargest( ))









      share







      New contributor




      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      import pandas as pd



      df = pd.read_csv('india-news-headlines.csv')
      df.head()



      nf = ' '.join(df['headline_text'].tolist())



      Labels = df['headline_category'][:1000]
      News = df['headline_text'][:1000]
      hf = pd.DataFrame({'Category':Labels, 'Headlines': News})



      from sklearn.feature_extraction.text import TfidfVectorizer



      tfidf = TfidfVectorizer()



      features = tfidf.fit_transform(hf['Category']).toarray()
      features.shape



      Perform the necessary imports



      from sklearn.decomposition import NMF
      from sklearn.preprocessing import MaxAbsScaler, Normalizer
      from sklearn.pipeline import make_pipeline



      Create a MaxAbsScaler: scaler



      scaler = MaxAbsScaler()



      Create an NMF model: nmf



      nmf = NMF(n_components=10)



      Create a Normalizer: normalizer



      normalizer = Normalizer()



      Create a pipeline: pipeline



      pipeline = make_pipeline(scaler, nmf, normalizer)



      Apply fit_transform to artists: norm_features



      norm_features = pipeline.fit_transform(features)



      Import pandas



      import pandas as pd



      Create a DataFrame: df



      nf = pd.DataFrame(norm_features, index=Labels)



      Select row of 'Bruce Springsteen': artist



      artist = nf.loc['unknown']



      Compute cosine similarities: similarities



      similarities = nf.dot(artist.T)



      Display those with highest cosine similarity



      print(similarities.nlargest( ))







      recommender-system





      share







      New contributor




      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.










      share







      New contributor




      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.








      share



      share






      New contributor




      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked 7 mins ago









      manoj kumarmanoj kumar

      1




      1




      New contributor




      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      manoj kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          0






          active

          oldest

          votes











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          });
          });
          }, "mathjax-editing");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "557"
          };
          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: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          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
          });


          }
          });






          manoj kumar is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f44959%2ferror-in-finding-similarity-using-nfm-and-tfidf-for-a-data-set-for-tag-unknown%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








          manoj kumar is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          manoj kumar is a new contributor. Be nice, and check out our Code of Conduct.













          manoj kumar is a new contributor. Be nice, and check out our Code of Conduct.












          manoj kumar is a new contributor. Be nice, and check out our Code of Conduct.
















          Thanks for contributing an answer to Data Science Stack Exchange!


          • 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.


          Use MathJax to format equations. MathJax reference.


          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%2fdatascience.stackexchange.com%2fquestions%2f44959%2ferror-in-finding-similarity-using-nfm-and-tfidf-for-a-data-set-for-tag-unknown%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

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana