21 Jan

*python -m venv LPU* -> To create a virtual environment *.\\LPU\\bin\\activate* -> To activate the environment

*deactivate* -> to deactivate the environment *rm -r LPU* - > to remove directory recursively, all the file & sub folders *mv oldname newname* -> To rename the Folder

'm' -> stands for message 'venv' -> virtual environment

22 Jan

Wider Range -> Class Derived -> Objects

Animals -> Class Lion, Tiger -> Objects

'.' -> Location, LEKE AAO

*python [filename.py](<http://filename.py/>)* -> To run the file

<aside> 📖

Supervised Learning -> Where we have both input and output. y = mx + c. Labeled Data. Unsupervised Learning -> Where we don't have the output. Not Labeled data. The model try to find the pattern. Reinforcement Learning -> Which tries to learn from the experience. Reward based learning.

</aside>

<aside> 💡

Overfitting -> Where the model gives alot of accuracy on the training data but fails in testing data. Underfitting -> Which fails at the training data as well as testing data. TradeOff -> Which performs well on training data as well as testing data.

</aside>

Sklearn -> warehouse of ML.

                                   PV
                                Yes  No
                               __________
								              | TP  | FN |
												Yes   |_____**|____| 
										AV        | FP  | TN |
												No    |_____**|____|

                                    PV
                                 No  Yes
                               __________
                              |  TN | FP |
                        No    |_____|____|
                    AV        |  FN | TP |
                        Yes   |_____|____|

                                    AV
                                 Yes  No
                               __________
                              |  TP | FP |
                        Yes   |_____|____|
                    PV        |  FN | TN |
                        No    |_____|____|

                                    AV
                                 No  Yes
                               __________
                              |  TN | FN |
                        No    |_____|____|
                    PV        |  FP | TP |
                        Yes   |_____|____|

<aside> 💡

Accuracy Score -> TP+TN / TP+TN+FP+FN Precision -> TP / TP+FP //Predicted mai kitna sahi predict kia. Recall -> TP / TP+FN //Actual mai kitna sahi predict kia. F1 Score -> 2 * ( Precision * Recall / Precision + Recall )

</aside>

*from sklearn.metrics import classification_marix*→ Classification Matrix