Introduction:
A Healthcare firm has gathered a month data of few of its selected employees to analyse various attributes about them. These pertain to Employee working patterns, their age, income, education, marital status and other such metrics. The idea to find corresponding trends between any related attributes as well as distribution patterns of metrics across the varied set. For decision makers to take actions, it is required to carry out univariate, bivariate and categorical analysis on some of the key attributes that are identified and represent them visually with relevant information.Also , some information is required for key questions
Data Description Dataset employee_data.csv has 978 records of various employees in a TAB delimited format with the header.
The following attributes (columns) are present FIELD Description
- Age : Age of the Employee
- employment_type : Working in which employment type
- salary : Salary being paid to Employee
- education : Education of the Employee
- marital-status: Marital status
- relationship: Relationship status
- gender: Male or Female
- hours_per_week: Average working hours in a week put by Employee
Problem Statement
From the dataset, the decision makers seek the following metrics
-
Identify Categorical variables & Continuous Variables
-
Carry on a Univariate analysis on all the Variables/Fields. User bar plots for Categorical Variables & histogram or line plot for Continuous ones. Label the plot and axis clearly for intuitive understanding. Mention observations drawn from each Univariate plot
-
Show a bivariate analysis between Salary and hour_per_week.Choose a plot of your choice. Mention the inferences drawn
-
For each Education type , showcase the distribution of Salary .Use Seaborn Facetgrid & Line plot.Identify the key observations and mention them
-
Categorizing each Gender & Relationship status (combination of all values) , plot the hours_per_week worked.Choose appropriate plots.Mention the inferences drawn
-
How many Males that have Marital status ‘Married-civ-spouse’ are earning above 150,000 ?
-
Are Divorced Individuals of higher age compared to Individuals that are Not-in-family ? Using mean as a measure , answer the above question & mention the respective age of the two groups