Add World Population Analysis & Visualization Notebook with EDA, ML, and Clustering

[Nikhil-tej108]

Summary:
This PR introduces a comprehensive Jupyter Notebook for World Population Analysis & Visualization, including:

Data Loading & Cleaning

Standardizes numeric and percentage columns.

Handles missing values in key population and demographic fields.

Exploratory Data Analysis (EDA)

Top 10 countries by population (bar chart).

Fertility Rate vs Median Age (bubble chart with population size and urbanization hue).

Urban Population vs Density (scatter plot).

Correlation heatmap for numeric variables.

Pie chart of world population share (top 10 countries).

Simple Machine Learning Model

Linear Regression to predict population using demographic features.

R² score and Mean Absolute Error reported.

Actual vs Predicted population visualization.

KMeans Clustering

Groups countries into 4 clusters based on Density, Median Age, Fertility Rate, and Urban Population.

Cluster visualization highlights demographic patterns globally.

Data Export

Cleaned and clustered dataset saved as population_data_cleaned.csv.

Key Features:

High-quality visualizations using Matplotlib and Seaborn.

Reusable data cleaning functions (clean_percent, clean_number).

Clear insights included as comments for easy understanding.

Fully reproducible workflow for population data analysis.

Benefits:

Provides a ready-to-use tool for global population analysis.

Enables open-source contributors and users to explore, visualize, and model population trends.

Can be extended for further predictive modeling or clustering improvements.

File Added:

population.ipynb (Notebook implementing all steps above)

Notes:

Requires Python packages: pandas, numpy, matplotlib, seaborn, scikit-learn.

Compatible with Jupyter Notebook / VS Code Notebook environment.

Suggested Labels:

enhancement

data-analysis

visualization