This is a repository to store my personal notes about my learnings in Data Science and other resources.
Classification
- Accuracy:
$accuracy = \frac{TP+TN}{TP+TN+FP+FN}$ - Precision -
$precision = \frac{TP}{TP+FP}$ - High precision = lower FP rate, i.e. not many TP are incorrectly classified as FN
- Recall:
$recall = \frac{TP}{TP+FN}$ - High recall = lower FN rate, i.e. most TP are classified correctly
- F1 Score:
$f1 = 2\times \frac{precision\times recall}{precision + recall}$
KNeighborsClassifier
- Used for supervised classification
- measured by Accuracy
- https://www.qrcode-monkey.com/
- https://www.canva.com/
- https://slidesgo.com/
- https://coolors.co/
- https://www.flaticon.com/
- https://www.freepik.com/
- https://matplotlib.org/stable/gallery/color/named_colors.html
- https://matplotlib.org/stable/users/explain/colors/colormaps.html
eBooks
To generate a requirements.txt file from the command line: pip freeze > requirements.txt