Kelvin Oyanna's repositories
Churn-Prediction
The goal of this project was to solve the problem of a telecom operator losing customers to its competitor. A predictive model was built with classification algorithms to predict the likelihood of churn (leaving a service) of a telecom subscriber.
Football-Data-Scrapper-ETL-to-PostgreSQL
In this project, I build a web scrapper to scrappe: football-data.co.uk website and performed Extraction Transformation & loading (ETL) on the screapped data to a Mysql database
Server-Log-ETL-to-Database
This project leverages Python & SQL to Perform ETL and analysis on application users data.
Access-Database-Data-ETL-To-PostgreSQL
This repository contains the code, data and resource used to implement a data ingestion pipeline and analyzing the data to draw-out some insight. The project is part of the requirement for Kippa interview process.
API-Data-Ingestion-to-Data-Lake-using-AWS-Lambda
A data pipeline to pull from a stable API and store it in Amazon Cloud storage
awesome-courses
:books: List of awesome university courses for learning Computer Science!
awesome-datascience
:memo: An awesome Data Science repository to learn and apply for real world problems.
data-science-ipython-notebooks
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
DataSciencePython
common data analysis and machine learning tasks using python
dbt-core
dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
Grocery-Sales-Report
This project was carried out to understand the factors influencing sales over a period of 5 years. The data used was from a grocery store that captures all the different categories of product and their respective sales. A visualization dashboard was built to unearth the trend in sales pattern.
Historic-Events-Data
This project pulls historic event data, create a pipeline that move the data into a Postgresql database.
Internet-Data-Subscribers-Sentiment-Analysis
The goal of this project is to understand subscribers’ preferences as well as their positive or negative sentiments about internet service providers in Nigeria. The data for the analysis is majorly scraped from twitter via Twitter API and Tweepy (Python library for accessing twitter data). Other tools used includes Natural Language tool kit (nltk) for tokenizing tweets and StreamListener for scheduling and downloading tweets in real-time. The project is currently on-going, while allowing for collection of a robust data set.
KelvinOyanna.github.io
My resume/porfolio.
knowledge-repo
A next-generation curated knowledge sharing platform for data scientists and other technical professions.
Peg-Africa
This repository containts all work on Peg Africa Project.
Pycon-Nigeria-2018-Resource
Tutorial and Talk codes presented at Pycon Nigeria 2018
python-sprints.github.io
Python Sprints website
Sales-Dashboard-Using-Microsoft-PowerBI
This project was carried out to understand the factors influencing sales over a period of 5 years. The data used was from a grocery store that captures all the different categories of product and their respective sales. A visualization dashboard was built to unearth the trend in the sales pattern. The product category, customer segment and customer region/location were used to drill-down the report.
Student-Performance-Prediction
The goal of this project was to predict the future score of students based on their historic performance data. A predictive model was built using regression algorithms (Linear & Logistic regression algorithms) that had 85% accuracy. Much emphasis was placed on handling missing values as well as outliers in the data set.
Udacity-Machine-Learning
Contains all resource for Udacity Learning on Machine Learning
XE-API-And-Internal-Data-ETL-And-Analytics
This repository contains the code, data and resource used to implement an Exchange rate data pull pipeline. The project is part of the requirement for AutoChek's data engineer interview process.