Result-driven Data Scientist with keen attention to detail, strong ability in sifting through lots of data,
analyzing and distilling it down to bring out what is important and easily understandable. Excellent
data storyteller with extensive knowledge in visualizing data, I use visualization tools to effectively
communicate insights from data, identify opportunities for improvement and develop strategies for
achieving overall business goals.
SKILLS
Python: Pandas, NumPy, Matplotlib, Scikit-learn, Tensorflow, Beautiful Soup, Requests, Tweepy
SQL: Oracle SQL, MySQL, MS SQL, PostgreSQL, BigQuery
Visualization tools: Tableau, Power BI
Spreadsheets: Excel, Google Sheets
ETL: Microsoft SSIS
Machine learning: regression, classification, neural networks, deep learning.
Used Tweepy library to mine tweets on DataFestAfrica2022 conference from twitter, analyzed and visualized it using Python and Microsoft Power BI, identified the top locations, top hashtags, days with most engagements and also carried out a sentiment analysis using Natural Language Processing technique. [GITHUB REPOSITORY].
Created a simple database that helps manage the booking process of a sports complex. Designed and incorporated triggers, functions, stored procedures, and other database code objects which help speed up performance when working with the database [FULL REPORT].
Used Python Visualization tools such as seaborn, matplotlib, and plotly to systematically explore a loan dataset from Prosper. Designed a presentation that illustrated the properties, trends, and relationships discovered in the dataset and identified the features that were best for predicting the outcome of a loan [GITHUB REPOSITORY].
Created an ETL package that automatically loads data into a SQL server database. The data extracted is transformed and cleaned in Microsoft SSIS before it is loaded into the database in Microsoft SQL server. This automation frees up several hours that can be spent on a more productive task. [FULL REPORT].
Used Tweepy API and Request Library to gather over 5000 @WeRateDogs twitter archive and stored the file into a pandas dataframe, assessed them visually and programmatically for quality and tidiness issues. Used the define-code-test framework to clean the data, analyzed and visualized the data to derive insights [GITHUB REPOSITORY].
Analyzed 2010–2020 Greater Manchester County road accidents dataset using Python and identified the periods most accidents occurred. Provided recommendations on how to reduce road accidents [FULL REPORT].
I create dashboards using Power BI, Tableau, Excel and Python visualization libraries.
Here are some of the ones I have created.
Used Power BI to visualize the insights derived from the DataFestAfrica2022 tweets analysis.
Used Tableau to visualize the insights derived from the Greater Manchester Road Accidents Analysis. Tableau link [HERE].
Worked on a project where I was able to identify the different roles in the data science fields, their salary structure and also the top roles in demand. Visualization was done with Tableau. Tableau link [HERE].
Used python visualization libraries such as matplotlib, plotly, and seaborn to visualize the insights from the data wrangling project.
Do you have a project and you don't know how to go about it? Contact me let's discuss how my skills can be of help to you.