Read Aloud the Text Content

This audio was created by Woord's Text to Speech service by content creators from all around the world.

Text Content or SSML code:

<speak> Here if you run,<break strength="weak"/> you can see that deviation is 0.03. <break strength="strong"/>The absolute error means the absolute value of the actual value minus the predicted value. <break strength="strong"/>The range of chance of admit is between 0 to 1. <break strength="strong"/>Hence 0.03 error is acceptable,<break strength="weak"/> which means our algorithm is accurately predicting the chance of admit for a given student.<break strength="x-strong"/> So far, <break strength="weak"/>we trained the model on training data.<break strength="strong"/> As far as training is concerned,<break strength="weak"/> our model is performing well. <break strength="x-strong"/> We have trained the model on the data train_x and train_y. <break strength="x-strong"/> We measured the absolute error for the trained model.<break strength="strong"/> We call this error a training error.<break strength="strong"/> When we use the training input as the input for the model,<break strength="weak"/> the error we are getting we call it a training error.<break strength="strong"/> That means when you are using the training data for the prediction. <break strength="strong"/>We call it a training error. <break strength="x-strong"/> For trained data, <break strength="weak"/>it may give accurately, <break strength="weak"/>but it should be generalized to unseen data. <break strength="x-strong"/> Now we will test the model on data that is not in the training set.<break strength="x-strong"/> For this data also, the error should be small.<break strength="strong"/> The error measured based on testing data is testing error.<break strength="strong"/> Now we are giving the testing data. <break strength="strong"/>We kept 20% of the data aside, <break strength="weak"/>which is not present in the training data. <break strength="strong"/>We will use this 20% data to see whether it is predicting accurately or not.<break strength="strong"/> Now in this lr.predict, <break strength="weak"/>we are giving test_x, test data as the input to the trained model lr. <break strength="strong"/>We are saving these predicted values or output values in a variable test_predict. <break strength="strong"/>Just like the previous case, <break strength="weak"/>the actual values of the output is test_x. <break strength="strong"/>And predicted values from the trained model are test_predict. <break strength="strong"/>You see that the error is 0.046.<break strength="strong"/> Earlier for the training data, <break strength="weak"/>we got 0.039. <break strength="strong"/>This error is close to the training error. <break strength="strong"/>That means our trained model is performing well on the testing data also. <break strength="x-strong"/> </speak>