Diamer-Bhasha Dam

In July 2019, the Government of Pakistan initiated a public fundraising campaign for the development of the Diamer-Bhasha dam. As part of my course project, I undertook the task of predicting the date when the required amount of donations would be collected.

To gather the necessary data, I accessed the donation records published by the State Bank of Pakistan (SBP) on their website. These records were in PDF format, so I utilized the BeautifulSoup library to scrape the data from web pages. I then converted the scraped data into a more manageable CSV format using the Zamzar API.

After performing data preprocessing to clean and organize the dataset, over 160,000 records were obtained for further analysis. This allowed me to conduct exploratory data analysis and create meaningful visualizations to gain insights from the data.

Using the cleaned dataset, I developed an Elastic-Net Linear Regression model. This model effectively predicted the timeline for reaching the target donation amount. Based on the model’s predictions, it was estimated that raising the desired donation amount would take approximately 70 years (2096 AD).