Dashboard Link : https://world-happiness-report-analysis-for-the-years-2015-to-2019-cbf.streamlit.app
This project is a data visualization and analytics dashboard that explores global happiness and economic trends. It utilizes the World Happiness Report dataset to derive insights for governments, NGOs, and researchers. The dashboard is built using Streamlit, offering interactive visualizations and intuitive filters for exploration.
-
🌟 Key Performance Indicators (KPIs):
- Average Happiness Score
- Country with the Highest GDP
- Average Life Expectancy
- Number of Countries in the Dataset
-
🥇 Top 10 Happiest Countries:
- Interactive horizontal bar charts using Plotly.
-
🔗 Correlation Heatmap:
- Explore relationships between factors like GDP, Social Support, and Life Expectancy.
-
💰 GDP vs Happiness Score:
- Scatter plot showcasing the relationship between economic strength and well-being.
-
🎯 Insights & Recommendations:
- Recommendations for governments and NGOs based on trends and correlations.
- Standardized column names for consistency.
- Removed irrelevant columns such as "Lower Whisker," "Upper Whisker," and "Lower Interval."
- Combined datasets from 2015 to 2019 into a unified DataFrame.
- Filled null values with default values for seamless analysis.
- Exported cleaned dataset as
World_happiness_report.csv
.
The project involves the integration of five datasets (2015-2019). Key steps:
- Standardized column names for consistency.
- Dropped irrelevant columns.
- Merged datasets into one comprehensive file with an additional
Year
column. - Identified and filled null values.
- Conducted exploratory data analysis (EDA) to ensure data quality.
Key visualizations during data cleaning:
- Distribution of Happiness Scores.
- Average Happiness Score by Year.
- Correlation between Happiness and factors like GDP, Life Expectancy, and Social Support.
-
Distribution Analysis:
- Histogram to analyze the spread of happiness scores.
-
Trend Analysis:
- Bar plots showing the average happiness score by year.
-
Correlation Analysis:
- Heatmaps to reveal relationships between factors.
-
Country-Specific Insights:
- Top 10 happiest countries each year.
- Countries with low life expectancy or social support.
-
Recommendations:
- Identified high-GDP, low-happiness countries to address policy gaps.
- Python: Data manipulation and analysis.
- Pandas: Data cleaning and aggregation.
- Seaborn & Matplotlib: Data visualization during EDA.
- Plotly: Interactive visualizations in Streamlit.
- Streamlit: Web-based dashboard application.
main.py
:- Main Streamlit app.
cleaning.py
:- Script for cleaning and preparing the dataset.
World_happiness_report.csv
:- Cleaned dataset used in the app.
World Happiness Report Analysis (EDA).ipynb
:- EDA and visualization of Cleaned dataset.
2015.csv,2016.csv,2017.csv,2018.csv,2019.csv
:- The dataset has been initially cleaned and organized in Excel, and then used for further exploratory data analysis (EDA)
- Explore the dashboard locally by running
main.py
. - Use the cleaned dataset for further analysis.
- Use the interactive dashboard to gain insights into happiness trends.
- Adjust filters to analyze specific years or countries.
- Invest in health systems for regions with low life expectancy but high GDP.
- Address social inequalities to improve overall well-being.
- Focus on countries with low scores in Social Support and Generosity.
- Target healthcare and social support improvements for maximum impact.
- Ismail Pasha
- Devesh Ghai
- Data Source: https://www.kaggle.com/datasets/unsdsn/world-happiness
- Libraries: Streamlit, Pandas, Plotly, Seaborn, Matplotlib