datascienceprojectweek3

[datascienceprojectweek3]

Assignment Week 3: Making Data Management decisions

Based on the Week 2 EDA, this week assignment is to make data management decisions primarily focusing on cleaning the data where we will handle the missing values and create distribution plots to better understand our data and create secondary variables like creating a group range of incomeperperson

Full Code: https://github.com/sonarsujit/MSC-Data-Science_Project/blob/main/week3assignment.py

Income per Person: The distribution is highly skewed, with most countries having lower incomes and a few having very high incomes. This indicates global income inequality. Employment Rate: Employment rates are more evenly distributed, suggesting that most countries have similar employment levels, with few extreme cases. Suicide Rate per 100,000: The majority of countries have low suicide rates, but there are notable outliers with higher rates, potentially indicating areas where mental health support may be lacking.

Conclusion:

Income per Person (Binned): The distribution of countries across the income categories shows a concentration in the Low Income category, with fewer countries in the Medium Income and High Income categories. This suggests that a significant number of countries in the dataset have lower average income per person, indicating a skew towards less affluent nations. Employment Rate (Binned): The distribution of employment rates is fairly even across the three categories: Low Employment, Medium Employment, and High Employment. This indicates a diverse representation of countries with varying levels of employment, without a strong skew towards any particular category. Suicide Rate per 100,000 (Binned): The suicide rate distribution is also quite balanced, with similar numbers of countries in each of the Low, Medium, and High Suicide Rate categories. This suggests that suicide rates vary widely across countries, with no single category overwhelmingly dominating.

These plots provide a preliminary understanding of how countries are distributed across different economic, employment, and health-related metrics. They offer insights into the diversity and spread of these variables, setting the stage for further analysis of potential relationships, such as the impact of employment rates on mental health outcomes like suicide rates.