Up to Data 2/24 Review

How is the LSR line for linear regression analysis determined?

• Enumerating all lines to find one that minimizes the sum of Euclidean distances

• Finding the line that minimizes the residual sum of squares (RSS)

• Trying out all possible lines that pass through >1 data point

• Finding the line that minimizes the sum of square distances

• True

• False

What does the Pandas library in Python serve to do in our data analysis code?

• Reading csv files that contain input data

• Predicting results using linear regression

• Constructing an effective data analysis model to test

• Creating data frames to store and organize imported data

What is a data frame?

• All of the above

• Organizes data to better visualize based on specific attributes

• Two-dimensional tabular structures to store data

• Resembles a Python dictionary or Excel spreadsheet

• True

• False

In which of the following field(s) is data science used in?

• Airline Planning

• Healthcare

• Advertisement

• Economics

What is Jupyter Notebook and what does it seek to accomplish?

• Application that is useful to directly break down data sets into simpler subsets

• Application that enables you to write lines of input/output code

• A physical notebook that documents code

• A website that contains scores of data sets open to the public

What is the library within Python that helps generate visualizations of data (including scatterplots, graphs, etc)?

• Kaggle

• Pandas

• Matplotlib

• Scikit learn

What are the parameters that are passed into the function below to create the Linear Regression model? (fill in the blanks)

reg.fit(______, ______)

• 2D array of training data, 2D array of testing data values

• data frame of dependent variable values, independent variable values

• 2D array of dependent variable values, independent variable values

• 2D array of independent variable values, dependent variable values

What is the purpose for creating separate training and testing data subsets?

• To streamline internal calculations when forming our initial regression model

• To supply our user with the ability to design the testing subset

• To establish a greater accuracy for our model and reduce bias

• To improve organization of data within our input data set