Keras model predicting experience from hours










0















I am very new to Keras, neural networks and machine learning having just started to learn yesterday. I decided to try predicting the experience over an hour (0 to 23) (for a game and my own generated data-set) that a user would earn. Currently running what I have the predictions seem to be very low and very poor. I have tried a relu activation, which produced predictions all to be zero and from a bit of research, LeakyReLU.



This is the code I have for the prediction model so far:



from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LeakyReLU
import numpy

numpy.random.seed(7)
dataset = numpy.loadtxt("experience.csv", delimiter=",")

X = dataset[: ,0]
Y = dataset[: ,1]

model = Sequential()
model.add(Dense(12, input_dim = 1, activation=LeakyReLU(0.3)))
model.add(Dense(8, activation=LeakyReLU(0.3)))
model.add(Dense(1, activation=LeakyReLU(0.3)))

model.compile(loss = 'mean_absolute_error', optimizer='adam', metrics = ['accuracy'])

model.fit(X, Y, epochs=120, batch_size=10, verbose = 0)

predictions = model.predict(X)

rounded = [round(x[0]) for x in predictions]

print(rounded)


I have also tried playing around with the hidden levels of the network, but honestly have no idea how many there should be or a good way to justify an amount.



If it helps here is the data-set I have been using:



https://raw.githubusercontent.com/NightShadeII/xpPredictor/master/experience.csv



Thankyou for any help










share|improve this question


























    0















    I am very new to Keras, neural networks and machine learning having just started to learn yesterday. I decided to try predicting the experience over an hour (0 to 23) (for a game and my own generated data-set) that a user would earn. Currently running what I have the predictions seem to be very low and very poor. I have tried a relu activation, which produced predictions all to be zero and from a bit of research, LeakyReLU.



    This is the code I have for the prediction model so far:



    from keras.models import Sequential
    from keras.layers import Dense
    from keras.layers import LeakyReLU
    import numpy

    numpy.random.seed(7)
    dataset = numpy.loadtxt("experience.csv", delimiter=",")

    X = dataset[: ,0]
    Y = dataset[: ,1]

    model = Sequential()
    model.add(Dense(12, input_dim = 1, activation=LeakyReLU(0.3)))
    model.add(Dense(8, activation=LeakyReLU(0.3)))
    model.add(Dense(1, activation=LeakyReLU(0.3)))

    model.compile(loss = 'mean_absolute_error', optimizer='adam', metrics = ['accuracy'])

    model.fit(X, Y, epochs=120, batch_size=10, verbose = 0)

    predictions = model.predict(X)

    rounded = [round(x[0]) for x in predictions]

    print(rounded)


    I have also tried playing around with the hidden levels of the network, but honestly have no idea how many there should be or a good way to justify an amount.



    If it helps here is the data-set I have been using:



    https://raw.githubusercontent.com/NightShadeII/xpPredictor/master/experience.csv



    Thankyou for any help










    share|improve this question
























      0












      0








      0








      I am very new to Keras, neural networks and machine learning having just started to learn yesterday. I decided to try predicting the experience over an hour (0 to 23) (for a game and my own generated data-set) that a user would earn. Currently running what I have the predictions seem to be very low and very poor. I have tried a relu activation, which produced predictions all to be zero and from a bit of research, LeakyReLU.



      This is the code I have for the prediction model so far:



      from keras.models import Sequential
      from keras.layers import Dense
      from keras.layers import LeakyReLU
      import numpy

      numpy.random.seed(7)
      dataset = numpy.loadtxt("experience.csv", delimiter=",")

      X = dataset[: ,0]
      Y = dataset[: ,1]

      model = Sequential()
      model.add(Dense(12, input_dim = 1, activation=LeakyReLU(0.3)))
      model.add(Dense(8, activation=LeakyReLU(0.3)))
      model.add(Dense(1, activation=LeakyReLU(0.3)))

      model.compile(loss = 'mean_absolute_error', optimizer='adam', metrics = ['accuracy'])

      model.fit(X, Y, epochs=120, batch_size=10, verbose = 0)

      predictions = model.predict(X)

      rounded = [round(x[0]) for x in predictions]

      print(rounded)


      I have also tried playing around with the hidden levels of the network, but honestly have no idea how many there should be or a good way to justify an amount.



      If it helps here is the data-set I have been using:



      https://raw.githubusercontent.com/NightShadeII/xpPredictor/master/experience.csv



      Thankyou for any help










      share|improve this question














      I am very new to Keras, neural networks and machine learning having just started to learn yesterday. I decided to try predicting the experience over an hour (0 to 23) (for a game and my own generated data-set) that a user would earn. Currently running what I have the predictions seem to be very low and very poor. I have tried a relu activation, which produced predictions all to be zero and from a bit of research, LeakyReLU.



      This is the code I have for the prediction model so far:



      from keras.models import Sequential
      from keras.layers import Dense
      from keras.layers import LeakyReLU
      import numpy

      numpy.random.seed(7)
      dataset = numpy.loadtxt("experience.csv", delimiter=",")

      X = dataset[: ,0]
      Y = dataset[: ,1]

      model = Sequential()
      model.add(Dense(12, input_dim = 1, activation=LeakyReLU(0.3)))
      model.add(Dense(8, activation=LeakyReLU(0.3)))
      model.add(Dense(1, activation=LeakyReLU(0.3)))

      model.compile(loss = 'mean_absolute_error', optimizer='adam', metrics = ['accuracy'])

      model.fit(X, Y, epochs=120, batch_size=10, verbose = 0)

      predictions = model.predict(X)

      rounded = [round(x[0]) for x in predictions]

      print(rounded)


      I have also tried playing around with the hidden levels of the network, but honestly have no idea how many there should be or a good way to justify an amount.



      If it helps here is the data-set I have been using:



      https://raw.githubusercontent.com/NightShadeII/xpPredictor/master/experience.csv



      Thankyou for any help







      python tensorflow keras






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 15 '18 at 6:35









      NightShadeNightShade

      11410




      11410






















          1 Answer
          1






          active

          oldest

          votes


















          0














          Looking at your data it does not seem like a classification problem.
          You have two options:



          -> Look at the second column and bucket them depending on the ranges and make classes that can be predicted, for instance: 0, 1, 2 etc. Now it tries to train but does not have enough examples for millions of classes that it thinks you are trying to predict.



          -> If you want real valued output and not classes, try using linear regression.






          share|improve this answer

























          • I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

            – NightShade
            Nov 18 '18 at 11:01












          • @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

            – power.puffed
            Nov 19 '18 at 10:39











          • Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

            – NightShade
            Nov 19 '18 at 23:28











          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%2f53313712%2fkeras-model-predicting-experience-from-hours%23new-answer', 'question_page');

          );

          Post as a guest















          Required, but never shown

























          1 Answer
          1






          active

          oldest

          votes








          1 Answer
          1






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes









          0














          Looking at your data it does not seem like a classification problem.
          You have two options:



          -> Look at the second column and bucket them depending on the ranges and make classes that can be predicted, for instance: 0, 1, 2 etc. Now it tries to train but does not have enough examples for millions of classes that it thinks you are trying to predict.



          -> If you want real valued output and not classes, try using linear regression.






          share|improve this answer

























          • I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

            – NightShade
            Nov 18 '18 at 11:01












          • @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

            – power.puffed
            Nov 19 '18 at 10:39











          • Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

            – NightShade
            Nov 19 '18 at 23:28















          0














          Looking at your data it does not seem like a classification problem.
          You have two options:



          -> Look at the second column and bucket them depending on the ranges and make classes that can be predicted, for instance: 0, 1, 2 etc. Now it tries to train but does not have enough examples for millions of classes that it thinks you are trying to predict.



          -> If you want real valued output and not classes, try using linear regression.






          share|improve this answer

























          • I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

            – NightShade
            Nov 18 '18 at 11:01












          • @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

            – power.puffed
            Nov 19 '18 at 10:39











          • Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

            – NightShade
            Nov 19 '18 at 23:28













          0












          0








          0







          Looking at your data it does not seem like a classification problem.
          You have two options:



          -> Look at the second column and bucket them depending on the ranges and make classes that can be predicted, for instance: 0, 1, 2 etc. Now it tries to train but does not have enough examples for millions of classes that it thinks you are trying to predict.



          -> If you want real valued output and not classes, try using linear regression.






          share|improve this answer















          Looking at your data it does not seem like a classification problem.
          You have two options:



          -> Look at the second column and bucket them depending on the ranges and make classes that can be predicted, for instance: 0, 1, 2 etc. Now it tries to train but does not have enough examples for millions of classes that it thinks you are trying to predict.



          -> If you want real valued output and not classes, try using linear regression.







          share|improve this answer














          share|improve this answer



          share|improve this answer








          edited Nov 15 '18 at 14:43

























          answered Nov 15 '18 at 14:35









          power.puffedpower.puffed

          119




          119












          • I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

            – NightShade
            Nov 18 '18 at 11:01












          • @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

            – power.puffed
            Nov 19 '18 at 10:39











          • Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

            – NightShade
            Nov 19 '18 at 23:28

















          • I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

            – NightShade
            Nov 18 '18 at 11:01












          • @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

            – power.puffed
            Nov 19 '18 at 10:39











          • Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

            – NightShade
            Nov 19 '18 at 23:28
















          I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

          – NightShade
          Nov 18 '18 at 11:01






          I tried separating them into classes of [0 - 100,000), [100,000- 200,000)... etc. and changed the outputs to [1, 0, 0...0], [0, 1, 0, ... 0], etc. however the model does not really seem to improve and gets stuck at an accuracy of 85% from the start and a loss of 0.55. Do you think you could elaborate on why this does not work I am a bit confused. Really this was just an exercise and something that does seem more suited for linear regression

          – NightShade
          Nov 18 '18 at 11:01














          @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

          – power.puffed
          Nov 19 '18 at 10:39





          @NightShade I am a bit confused what are you asking here. Did you try linear regression, does that work better and why? or are you asking how to improve the NN, in that case you could you update the code that you are using, I will have a look at it

          – power.puffed
          Nov 19 '18 at 10:39













          Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

          – NightShade
          Nov 19 '18 at 23:28





          Sorry If I was unclear, essentially, I want to try predicting the data as an exercise using a NN rather than linear regression although it is not of the most importance. What I am saying is I tried bucketing the second column into ranges and tried it as a classification problem however that does not seem to help much, and the model does not seem to improve. I will share what I have for now: github.com/NightShadeII/xpPredictor

          – NightShade
          Nov 19 '18 at 23:28



















          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%2f53313712%2fkeras-model-predicting-experience-from-hours%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

          Darth Vader #20

          How to how show current date and time by default on contact form 7 in WordPress without taking input from user in datetimepicker

          Ondo