A recruiting firm $($Gazelle Recruiting$)$ has just received a data file from a college campus with over two hundred graduates who have received job offers. The data file gives a good deal of information about these graduates, ranging from how well they did in grade school, high school, college etc. The file also contains the salary the graduates were offered for their jobs and whether they were placed or not.

The recruiting firm has no experience reading datasets. They don$$t have an idea of who these graduates are in terms of demographics. Senior management have asked for your guidance. They have provided a data file and a data dictionary. The data dictionary contains a list of fields in the dataset and an explanation for each one.

To help our client, here are the steps to take:

Cleanse

Look for null data in the table, and use the appropriate strategy to handle null data for each column. Explain why this was the strategy that you used.

Outliers

Search the data for outliers and remove them. Use the appropriate outlier method$($s$).$ Show all work.

Who are these graduates $?$

Create $4-5$ visualizations providing useful and explanatory information about these graduates. The visualizations should show trends, correlations, and other useful patterns that the data provides.

Remember, we are dealing with senior management. The charts must be readable, meaningful and at a summary level.

Use at least one group by and bin in your analysis.

Who are most likely to get placed?

Create visualizations to show management qualities specific to those who are likely to get placed at jobs. Show three meaningful visualizations.

Use at least one group$/$by or bin in your analysis.

Prepare the data for a regression analysis

The Gazelle management team has heard that it might be possible to use their data to make predictions. They don$$t know much about data analytics. We are hoping that an example of what is possible will help them understand better.

Prepare the data file to run with a regression analysis. Use the techniques and methods discussed in class.

Run the regression analysis

Show the regression scoring. Split the data into training and test sets. Show a confusion matrix for both.

Two files are attached to this assignment. The data file and the Data dictionary which explains every column in the set.

The code should be commented appropriately