Practice Session $1$

For the practice sessions, you will follow the same model as done for the previous course in R programming language. Follow the faculty's lead in the Descriptive Analysis in Python session and carry out basic descriptive statistical analysis on the Facebook Friends dataset.

$1.$ Load the dataset into the Jupyter Notebook and carry out data examination, including the following:

a$.$ Data type and structure

b$.$ Statistical summary of all attributes

c$.$ Breakdown of the data by variables

$2.$ Visualize the data, including the following:

a$.$ Frequency$/$Distribution plots

b$.$ Univariate and Multivariate plots

FacebookFriends.xlsx

Excel column names:

Sample Age Photos # of Tags Albums Gender Emp Profile Cover Orientation Relationship Posts Replies Children Likes Edu Events Friends

$1577275111011103210068$

Photos # of Photos

# of Tags # of photos individual is tagged in

Albums # of Albums

Gender $($Male$=1$; Female$=0)$

Emp $\text{'}1\text{'}$ if individual is listed as working., $\text{'}0\text{'}$ if Unemployed

Profile To identify the individual on the webpage, does the individual use a picture of himself $(=1)$ or of something else $(=0)$ on the PROFILE Picture.

Cover To identify the individual on the webpage, does the individual use a picture of himself $(=1)$ or of something else $(=0)$ on the COVER.

Orientation Sexual orientation of the individual: heterosexual $(=1),$ not heterosexual $(=0)$

Relationship $($In a relationship $=1$; Not in a relationship $=0)$

Posts This indicates thetotal number of posts on their 'timeline' last month.

Replies This indicates the total number of replies from the individual themself on their 'timeline' last month.

MidWest $1$ if individual lists their current location residing in a state located in the Midwestern region of the U$.$S$.,0$ otherwise.

Seast $1$ if individual lists their current location residing in a state located in the Southeastern region of the U$.$S$.,0$ otherwise.

West $1$ if individual lists their current location residing in a state located in the Western region of the U$.$S$.,0$ otherwise.

Children $($Children$=1$; No Children $=0)$

Likes # of 'Likes' visible on main page

Edu $1$ if individual lists only a High School education or less., otherwise $0.$

Events # of events listed

USA $($Lives in the USA $=1$; lives ouside USA $=0)$

Response variable $($y$)$ Friends # of Friends

Background: Data were collected to allow students to create a regression model which might predict$$ the number of friends an individual user of Facebook social network should have based on certain attributes of that individual. An individual is defined as a person registered within the Facebook.com community and 'owning' a personal webpage in that community. Attributes are characteristics of which values can be obtained by viewing that individual's webpage. Friends are defined as individuals who have consciously agreed to have a relationship together in the community which allows the two parties greater communication and availability between webpages. Data came from $40$ students in a second semester business statistics course, based on a random selection of $21$ of their Facebook 'friends.$\text{'}$ Some data were missing or incomplete so that n $=715($instead of $40$ x $21=840)$ The database was organized by the instructor, Amy Sheikh. This database is intended purely for statistical education, and may not be distributed or published without prior written permission.