conmatrix : Confusion Matrix # Data Imbalance # Evaluation # Weights & Biases

• Build a confusion matrix
• Assess performance of classification models.
• Resolve biases in a classification model
• Evaluate results of binary classification models using a confusion matrix.
• Use weighted classes to address class imbalances when training a model and evaluating the results.
• Review metrics to improve classification models.
• Mitigate performance issues from data imbalances.
• Calculate the very basic measurements used in the evaluation of classification models: TP, FP, TN, FN.
• Use the measurement aboves to calculate more meaningful metrics, such as:
  • Accuracy
  • Sensitivity/Recall
  • Specificity
  • Precision
  • False positive rate

conmatrix001.png

conmatrix002.png

conmatrix003.png

conmatrix004.png

conmatrix005.png

conmatrix006.png

conmatrix007.png

conmatrix008.png

conmatrix009.png

conmatrix010.png

conmatrix011.png

conmatrix012.png

conmatrix013.png

conmatrix014.png

conmatrix015.png

conmatrix016.png

conmatrix017.png

conmatrix018.png

conmatrix019.png

conmatrix020.png

conmatrix021.png

conmatrix022.png

conmatrix023.png