Udacity Data Scientist Nanodegree Project
This is the repo of the Write a Data Science Blog Post project for the Udacity Data Scientist Nanodegree Project.
1- Business Understanding
We investigated if North America was a better place to immigrate rather then Europe for a software developer.
For this we need to understand what is important to a person searching for a new job, things such as salary, salary growth, and satisfaction in what they do are important factors that determine which location is a better choice.
For this, we asked 3 questions:
- Which location has the highest salary?
- Which location has the highest salary growth?
- which location has the highest career satisfaction?
2- Data Understanding
The data comes from the stack overflow 2017 survey. the rows are the different respondants to the survey, and the columns are the answer to the survey questions. It contains data that comes as numerical, categorical and text. It has missing values and outliers as well.
3- Prepare Data
For the data preparation phase, we gathered the data, assessed it and then proceeded to clean it, focusing on our columns of interest, with python libraries of Numpy and Pandas
4- Data Modeling
we graphed different behaviours that were relevant to the 3 questions, with the python libraries matplotlib and seaborn.
5- Evaluate the Results
for the 3 questions, we arrived at the following conclusions:
- Which location has the highest salary? North America
- Which location has the highest salary growth? Both follow a similar pattern
- which location has the highest career satisfaction? THey start the same in the first year of work, but then Europe has a drop in satisfaction of which never truly recovers until 20 years later.
The blog is written on the following link
Finally, the readme format:
- the libraries used: Numpy, Pandas, Matplotlib and Seaborn
- the motivation for the project: This is a question close to my heart since my country is unstable at the moment an immigration is always a choice.
- the files in the repository with a small description of each: I included the zip file with the survey_results_public.csv file that is used as the dataset. Also, the Code file is the jupyter notebook script. a summary of the results of the analysis: In the end, we concluded that North America is the best choice.