Visual data exploration

The purpose of this assignment is for you to analyze and discover stories from a dataset that is given to you. This exploration should be performed via visualizations which will allow you to raise hypotheses and look for evidence to refute/verify them. You can find lecture slides in this link: https://drive.google.com/drive/folders/1HPmnXO4kLX… The dataset that you must wrok with can be found in the csv file I uploaded. It is a small dataset containing 26828 rows and 50 columns (you can ignore the column named “X”) in the CSV format and it contains the U.S. financial summaries about each candidate that has registered with the U.S. Federal Election Commission between the years 2008 and 2022. Each row represents a single candidate at a single year (thus the same candidate can appear multiple times). You can see the details of the contents of each column of the dataset in this link: https://www.fec.gov/campaign-finance-data/candidate-summary-file-description/ (Links to an external site.) This assignment has two parts: Note that the analysis that you will be performing in this assignment will very likely be a realistic scenario in your future professional life! For some of you this might even become a daily routine! General instructions Note: You cannot use visualization code written by your classmates. Use code found over the Internet at your own peril — it may not do exactly what the assignment requests. If you do end up using code you find on the Internet you must disclose the origin of the code and properly cite it. Concealing the origin of a piece of code is plagiarism. Use Piazza for general questions whose answers can benefit you and everyone. Requirements: 3-4 pages | .doc file (7 points) In the first part of the assignment you will be exploring the dataset through the creation of several different types of visual representations that you learnt so far in the course. You must add to the report at least six visualizations but no more than eight (but you are free to create many more while you are exploring the dataset). You can use the same type of visualization more than once (i.e. to visualize different variables from the dataset). Write a brief paragraph for each visualization to explain what you can see from it (i.e. what information from the dataset is made clear because of the visual support; and/or what are the relationships that you can see in the data). The visualizations that you are creating in this part can be seen as one aspect of what is called visual data exploration. (8 points) Then as the second part of the assignment you must raise at least two hypotheses from the data that you have and from some of the visualizations that you created look to see if you can find some evidence to verify or refute your hypothesis. To support your argumentation you must use any type of visual clues such as the existence of relationships between the variables (quantitative and/or qualitative) the existence of data outliers the existence of (or absence of) trends in time and/or between different categories etc. Feel free to modify the data to perform this analysis (e.g. computing mean/median values log or asinh transforms filtering the data etc.) but you must disclose any type of manipulation in your text. Your assignment must be submitted as a PDF file with at most five pages with at most three pages dedicated to part 1 and two pages for part 2. Make sure to add your name to the top of all the pages. You must include the code as a part of the PDF file. The codes do not count towards the page limit. You shall submit the assignment by the due date. You can share the visualizations that you create on Piazza and ask for feedback from other students but you shall not share the code that you are using. This assignment is to be done either individually or in a group of two (i.e. a pair). If you are working in a pair you are expected to contribute equally to the assignment and to discuss and raise hypotheses together. Also if you are working in pairs you shall add a paragraph describing which visualizations were created mainly by each member of the group. (7 points) In the first part of the assignment you will be exploring the dataset through the creation of several different types of visual representations that you learnt so far in the course. You must add to the report at least six visualizations but no more than eight (but you are free to create many more while you are exploring the dataset). You can use the same type of visualization more than once (i.e. to visualize different variables from the dataset). Write a brief paragraph for each visualization to explain what you can see from it (i.e. what information from the dataset is made clear because of the visual support; and/or what are the relationships that you can see in the data). The visualizations that you are creating in this part can be seen as one aspect of what is called visual data exploration.(8 points) Then as the second part of the assignment you must raise at least two hypotheses from the data that you have and from some of the visualizations that you created look to see if you can find some evidence to verify or refute your hypothesis. To support your argumentation you must use any type of visual clues such as the existence of relationships between the variables (quantitative and/or qualitative) the existence of data outliers the existence of (or absence of) trends in time and/or between different categories etc. Feel free to modify the data to perform this analysis (e.g. computing mean/median values log or asinh transforms filtering the data etc.) but you must disclose any type of manipulation in your text. Your assignment must be submitted as a PDF file with at most five pages with at most three pages dedicated to part 1 and two pages for part 2. Make sure to add your name to the top of all the pages.You must include the code as a part of the PDF file. The codes do not count towards the page limit.You shall submit the assignment by the due date.You can share the visualizations that you create on Piazza and ask for feedback from other students but you shall not share the code that you are using.This assignment is to be done either individually or in a group of two (i.e. a pair). If you are working in a pair you are expected to contribute equally to the assignment and to discuss and raise hypotheses together. Also if you are working in pairs you shall add a paragraph describing which visualizations were created mainly by each member of the group.