강의

N
챌린지

멘토링

N
클립

로드맵

BEST
Data Science

/

Certificate (Data Science)

[Side Project After Work] Big Data Analysis Certification Practical Exam (Type 1, 2, 3)

We guide non-majors and beginners to quickly obtain the Big Data Analysis Certification (Practical Exam)! Keep the theory light and the practice solid—focusing on core points that are guaranteed to appear on the exam through past questions, without the need for complex background knowledge.

(4.9) 814 reviews

5,513 learners

Level Beginner

Course period 12 months

  • roadmap
Engineer Big Data Analysis
Engineer Big Data Analysis
Big Data
Big Data
Python
Python
Pandas
Pandas
Machine Learning(ML)
Machine Learning(ML)
Engineer Big Data Analysis
Engineer Big Data Analysis
Big Data
Big Data
Python
Python
Pandas
Pandas
Machine Learning(ML)
Machine Learning(ML)
News list
roadmap님의 프로필 이미지
roadmap

[Multiple classification] Guide to evaluation criteria

Let me introduce you to the multi-classification evaluation index 💪💪💪

You can use the evaluation criteria as required by the problem.

If you don't know, please use the evaluation criteria you know, even if it's a shortcut :)

F1 score

  • Predict with predict

  • micro, macro, weighted

from sklearn.metrics import f1_score f1_score(y_true, y_pred, average='macro') # micro, macro, weighted

Accuracy (no difference from binary classification)

  • Predict with predict

from sklearn.metrics import accuracy_score accuracy_score(y_true, y_pred)

roc-auc

  • Predict with predict_proba -> like binary classification, pred[:,1] ❌ Pred as is 👌

  • ovo, ovr

from sklearn.metrics import roc_auc_score roc_auc_score(y_val, pred, multi_class='ovo') roc_auc_score(y_val, pred, multi_class='ovr')


 

 

 

 

 

Comment