Part 09 - Constructing Multi-Class Classifier Using SVM with Python

แชร์
ฝัง

ความคิดเห็น • 9

  • @banderallogmany1912
    @banderallogmany1912 3 ปีที่แล้ว +2

    For lines 20 & 21, what is the benefit of using validation?

  • @sabrinahuda7308
    @sabrinahuda7308 4 ปีที่แล้ว +1

    can this be apply for multi-label classification too? if yes, where is the part i can change the algorithm to multi-label ?

  • @curosaquila9995
    @curosaquila9995 ปีที่แล้ว

    My jupyter code on line 2 pd.read_csv('iris_dataset.csv') error "FileNotFoundError". what yould i do?

  • @kccchiu
    @kccchiu 3 ปีที่แล้ว +1

    Nice video. I followed your tutorial and it worked brilliantly on my project.
    On thing at the end, did you made a mistake on the confusion matrix? it seems like you are plotting predicted results against predicted results.

    • @嗨您好-h1r
      @嗨您好-h1r 3 ปีที่แล้ว +1

      yeah, i think he made a mistake on the confusion matrix, and i correct it into "cm = confusion_matrix(test_labels, y_pred)"
      but i'am not really sure that is correct. XD

  • @嗨您好-h1r
    @嗨您好-h1r 3 ปีที่แล้ว

    Hello, your video is very good!
    But may I ask a question? Is this multi-class classifier is using OVO(One vs. One) or OVA(One vs. All) or RCC?

  • @LLFRA
    @LLFRA 3 ปีที่แล้ว

    so no one-hot encoding is needed?

    • @hggaming911
      @hggaming911 3 ปีที่แล้ว

      If all data types in your dataset are integer or float so no need to use any encoding. Encoding is used for transfering your non-numircal data to numerical values because the model can work only with numbers.

    • @beautyisinmind2163
      @beautyisinmind2163 3 ปีที่แล้ว

      @@hggaming911 if i want to change the order, what is the code for example "Iris-setosa" = 3, "Iris-versicolor"=2, Iris-virginica" =1 instead of writing "Iris-setosa" = 1, "Iris-versicolor"=2, Iris-virginica" =3