Our analysis delves into the global happiness index across various countries. Through a comprehensive approach, we utilize a variety of graphs to elucidate the intricate relationships between different features encapsulating the essence of happiness.
The Happiness Index is a survey that measures your happiness in 14 different areas of your life. The data collected from the survey is used to evaluate the happiness of people. These factor including:
- Business and Economic
- Citizen Engagement
- Communications and Technology
- Diversity (Social Issues)
- Education and Families
- Emotions (Well-being)
- Environment and Energy
- Food and Shelter
- Government and politics
- Law and Order (safety)
- Health
- Religion and Ethics
- Transportation
- Work
The data is collected from surveys conducted with people from over 150 countries/regions. Each measured variable is recorded using weighted average scores, ranging from 0 to 10. These scores are tracked over time along a timeline and compared with other countries.
This ranking is done using the Cantril ladder survey method: representative respondents from each country are asked to imagine the concept of a ladder, where the best possible life is rated as 10 and the worst possible life as 0. Then they are asked to rate their current life on a scale from 0 to 10.
These numbers reflect people's perceptions of six major economic and social factors: per capita real GDP (income), social support, healthy life expectancy, freedom, trust, and generosity.
Each country's survey results are then compared with an extreme value. This extreme value represents the lowest national average level, and the residual of this extreme value (Dystopia Residual) is regressed together, resulting in weighted average scores for the six major variables.
- We are going to conduct AI analysis in the field of social sciences. As we know happiness index is the field of social science, we are going to use the integration of database to perform the analysis, using it to analyse the data.
- We are going to use aggregation and purification ov huge amount of data.
- Correlation analysis between source indicators of happiness index.
- Comparison of secondary features and analyze the consistency of the result
- Use different presentation of database
- At least ten types of graphics parts to present high-quality visual results
- Programming language: Python
- Libraries: Pandas, Numpy, Bubbly, matplotlib, seaborn
- Datasets: include in the dataset files