Work

Residential prognostication

Data analytics
Web scraping
Data visualization

Developed a Python-based tool to scrape housing data from a website using BeautifulSoup and requests. Utilized pandas, NumPy for data manipulation and performed exploratory data analysis to identify key market trends

In this comprehensive project, Python serves as the primary tool for gathering and analyzing data sourced from a housing research website, providing invaluable insights into the real estate market.

Libraries Utilized:

BeautifulSoup (bs4): Employed for parsing HTML and XML documents, facilitating seamless data extraction. Pandas: A versatile library instrumental in data manipulation and analysis, enabling efficient handling of datasets. NumPy: Leveraged for executing mathematical operations on arrays and matrices, enhancing computational efficiency. Requests: Empowered the project with the capability to make HTTP requests to websites, facilitating data retrieval. Regular Expressions (re): Facilitated pattern matching and string manipulation, streamlining data processing tasks. Seaborn: A powerful data visualization library built on top of Matplotlib, enabling the creation of insightful visualizations. Matplotlib: Provided essential plotting capabilities, enabling the creation of static, animated, and interactive visualizations. Sample of Researches Conducted:

Exploratory Data Analysis: Unveiling hidden patterns and trends within the dataset to gain a comprehensive understanding of the housing market dynamics. Price Distribution Across Houses: Analyzing the distribution of house prices to identify common price ranges and outliers. Average Increase in House Price for Each City: Evaluating the average increase in house prices across different cities, providing valuable insights for investors. Factors Affecting House Prices: Investigating various factors influencing house prices, ranging from location to property characteristics. Average Housing Prices by Cities: Comparing the average housing prices across different cities to identify lucrative investment opportunities. Effects of Bedroom Count on House Prices: Assessing the impact of the number of bedrooms on house prices, aiding in property valuation. Average Bath per Price: Examining the relationship between the number of bathrooms and house prices to discern buyer preferences. County-wise Average Price per Square Feet: Analyzing the average price per square foot across different counties, offering valuable insights for buyers and sellers. Models Utilized:

OLS (Ordinary Least Squares) - Multiple Linear Regression: Employed for predictive modeling, enabling the estimation of house prices based on multiple variables.

Residual Plots: Utilized to assess the goodness of fit of the regression model, aiding in identifying potential areas for model improvement.

This project exemplifies the power of Python programming in conducting comprehensive data analysis, offering invaluable insights into the intricate dynamics of the housing market and empowering stakeholders to make informed decisions.