Skip to content

jyotsnakhatter/data-science-with-python

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 

Repository files navigation

Statistical analysis of assets traded internationally using data science tools

(Built as part of INFO 52272 - Data Science using python in Summer'18 under guidance of Prof. Dino)

🌎 The project analyses trading statistics of goods across nations with tools like- Bayesian model, statistical hypothesis testing, ANOVA and feed forward neural network along with visualisations! 🌎

💰 💰 💰


About the data:

The United Nations Commodity Trade Statistics Database (UN Comtrade) complete trade records between countries and publishes it for free. We have fetched data from 1985 to 2016 which is ~1.2 Gb in size. Over 140 reporter countries provide the United Nations Statistics Division with their annual international trade statistics detailed by commodities and partner countries.

Data URL: http://data.un.org/Explorer.aspx

Features of the table:

Features Name
1 Country
2 Year
3 Commodity_code
4 Commodity_description
5 Flow (import/export)
6 Trade Value in USD
7 Weight of commodity in Kg
8 Quantity measurement type
9 Quantity
10 Category

Aim for project:

The aim/acceptance criteria for the project was to successfully analyse international assets data to give meaningful insights and also test models like- Bayesian, Feed-forward neural network, ANOVA and statistical hypothesis testing.


Technologies:

python3 

🐍


🌟 🌟 🌟

Libraries used:

Pymc3, keras, numpy, pandas, scipy, matplotlib, seaborn, sklearn, plotly, squarify, 

Types of analysis conducted:

ANOVA, One T testing, Two T Testing, Principal Component Analysis, Neural Networks, Statistical Hypothesis testing, Visual Analysis

Authors

  1. Jyotsna Khatter
  2. Parth Gargava

License

This project is licensed under the MIT License - see the LICENSE.md file for details


Acknowledgments:

Made with ❤️ at Northeastern University

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors