ShuweiLeung / ECE-143

The Chinese Silicon Valley on Housing Prices

The Chinese Silicon Valley on Housing Prices

Dataset

• Our dataset is scraped from Lianjia.

File Structure

• ECE 143 Presentation.pdf - slides for final project presentation

• visualization_prediction.ipynb - jupyter notebook for data cleaning, visualization and price prediction

• dataset - contains csv housing data

• scraping - contains scraper code

• spatial distribution - contains ArcGis spatial visualizations

Modules and Tools

• bs4, urllib.request, pandas, numpy, matplotlib, sklearn

How to Run Scraper

python scraping/scraper.py

Data Cleaning

• The code for data cleaning is written in the visualization_prediction.ipynb file.

Visualization

• Data visualization is shown in visualization_prediction.ipynb file.

Prediction

• We used two regression models to predict the housing price. The accuracy is very high.