Home page

Documentation page

Map view

• Processes remote sensing weather data
• For all the cities in the database, latitute and longitude coordinates are extracted
• Using Django REST api, a call is made to the METAR API to fetch the METAR code for each city
• Statistical analysis skills:
  • Data Gathering: Developed a python script for a backup mechanism to scrape data from public weather data warehouses
  • Data Cleaning: The scraped data contains a lot of missing information, from error-prone HTML to unescaped spaces. Several data cleaning methods were developed using Regexp
  • Categorization: After decoding the METAR code, the remote sensing weather data was categorized into "good", "marginal" and "bad" weather using variables such as temperature, pressure and visibility
  • Statistical Summary: Utilized descriptive statistics such as mean, mode, interquartile range, variance, standard deviation and range to calculate additional metrics
  • Time Series Analysis: Considered historical data to identify patterns within the usual weather cycle

On-the-go tools

METAR code decoder

Satellite images

Radar images

Lat-Long Fetcher