Air Quality Insights: Understanding Pollution and Its Impact
📌 Overview This project aims to analyze real-time air quality data across various U.S. states and counties to uncover pollution trends, evaluate the most affected regions, and understand the impact of pollutants over time. It leverages data science tools in Python to conduct exploratory data analysis (EDA), visualize trends, and perform hypothesis testing.
🎯 Objectives 1.Identify the Top 10 most polluted states based on average pollutant levels 2.Analyze the year-wise trend in air quality across the U.S. 3.Study pollution patterns in the top counties 4.Visualize pollutant distribution by state using pie charts 5.Explore correlation between different air pollutants 6.Compare pollution across states using boxplots 7.Examine exceedance days for Ozone and PM2.5 using histograms 8.Perform a Z-test to check if a specific year had significantly different pollution levels
🛠️ Tools and Libraries Used Language: Python Libraries: pandas for data handling NumPy for numerical operations Matplotlib and Seaborn for data visualization statsmodels for statistical analysis
📂 Dataset Source link: https://catalog.data.gov/dataset/air-quality-measures-on-the-national-environmental-health-tracking-network
📊 Project Workflow Data Cleaning & Preprocessing Handled missing values and duplicates Converted data types and trimmed column names Exploratory Data Analysis (EDA) Generated summary statistics Visualized trends and patterns In-depth Analysis & Visualization Created multiple charts: bar, line, pie, box, histogram, heatmap Hypothesis Testing Applied Z-test for statistical significance
📈 Key Visualizations Bar chart for top polluted states Line chart showing pollution trends over years Multi-line chart for top counties Pie chart for year-specific pollution distribution Heatmap showing correlation between pollutants Boxplot for pollutant distributions across states Histogram for exceedance days Z-test result with significance interpretation
🔍 Conclusion This analysis provided deeper insights into pollution patterns in the U.S., helping identify regions with high pollution levels and analyze the effectiveness of environmental regulations. The study showcases how data science can support environmental policy-making and awareness.