Data Science 🐍 Features

The video tutorial introduces key machine learning terminology, focusing on concepts like features, labels, and loss functions. It explains feature generation and selection using stock data, highlighting methods like volatility analysis and feature importance. The tutorial also includes a TCC Lab activity, demonstrating feature development to predict heater status using temperature and derivatives.

What is the role of features in a machine learning model?

• They are the outputs of the model.

• They are the inputs to the model.

• They are the errors in the model.

• They are the labels of the model.

In supervised learning, what is the purpose of labels?

• To cluster data points.

• To guide the learning process.

• To measure the model's performance.

• To provide input data.

What is the main difference between supervised and unsupervised learning?

• Supervised learning uses labels, unsupervised does not.

• Unsupervised learning uses labels, supervised does not.

• Both use labels but in different ways.

• Neither uses labels.

What is the purpose of using a min-max scaler in feature selection?

• To standardize data to a mean of 0.

• To normalize data between 0 and 1.

• To decrease the range of data.

• To increase the range of data.

Which feature was identified as the most important for predicting stock price changes?

• Change

• Volume

• Volatility

• Open price

How does a heat map help in feature selection?

• By ranking features based on their scores.

• By predicting the output variable.

• By displaying the correlation between features.

• By showing the order of importance of features.

What is the purpose of using a tree-based classifier in feature importance?

• To visualize the data.

• To provide a score for each feature.

• To cluster the data points.

• To scale the features.

What is the significance of the second derivative in the TC lab application?

• It helps in predicting the initial temperature.

• It is irrelevant to the prediction.

• It improves prediction in regions with no slope change.

• It is used to calculate the first derivative.

What is the main goal of the TC lab activity?

• To determine the best time to turn off the heater.

• To calculate the exact derivative values.

• To predict the heater's status using features.

• To measure the temperature accurately.

Why is it important to drop 'not a number' values in data processing?

• They improve the accuracy of predictions.

• They can cause errors in calculations.

• They are necessary for feature scaling.

• They are always incorrect data points.