Temitope Bamidele

Data Scientist

I am a skilled data analyst, Data Scientist, and Geospatial Analyst, with a professional master's degree in Geographic Information Systems and data science training from Stutern and Udacity, I have developed expertise in data analysis, sentiment analysis, and machine learning. Through various hands-on Projects, I have honed skills in analyzing and processing large data using Python, SQL, and Microsoft Excel. I have also demonstrated proficiency in Python, SQL, Git, and data visualization tools like Matplotlib and Power BI.

Learning to be a Data Science Practitioner through practical sessions and hand on project-based working with real dataset by:

Developing excellent problem-solving skills

Performing Data cleaning and Exploratory Data Analysis

Developing strong Data Analysis skills to derive insights from messy data through Excellent Data Visualization.

GIS Officer at Rubber Estates Nigeria Limited

Analyzed and processed Data using ArcGIS and Microsoft Excel

Actively involved in Land Surveying and Land partitioning of the Estate into blocks with the aid of GPS

Accurate Report writing and presentation to managers.

Carrying out other task as stipulated by the manager.

GIS ANALYST INTERN AT GEOTECHNICS SERVICES LIMITED

Analyzed and processed Spatial Data

Ensured that Interns assigned to me are properly trained in the theories and practice of GIS

Carrying out any other task as stipulated by the manager.

Udacity Data Analyst Nanodegree projects

Investigating a DataSet Project

- In this project I demonstrate the flow of the data analysis process from questioning, exploring, analyzing, and communicating data findings.

Data Wrangling project

- In this project I showed strong data-wrangling skills which involved, gathering, assessing, and cleaning data. I showed how to explicitly wrangle data programmatically making it fit for deeper analysis.

Data Visualization Project

- I applied sound design and data visualization principles to data analysis. I choose a dataset and perform exploratory data analysis on it using Python, then create presentation plots that convey my findings

Outcomes – Gained practical skills in Data analyst/ Data scientist environment setup, Data Wrangling, data cleaning, data visualization, and communication.

Tools used: Jupyter Notebook, Python, Pandas, NumPy, matplotlib, seaborn, Git & Git hub

Sentiment Analysis Projects

Sentiment Analysis on Presidential Candidates for the 2023 Nigeria Presidential Elections

This project performs a sentiment analysis on the disposition of the public on social media(Twitter) on the three major presidential candidates in the 2023 presidential elections in Nigeria and identifies the candidate with the most positive tweets.

Visualization Project for Power BI

This project performs sentiment analysis on random tweets by Nigerians at a moment in time(December 2022) to be specific. The data was scraped from Twitter, cleaned, and analyzed using Python, and visualized using PowerBi I used the city parameter of Twint to get tweets for all the cities in Nigeria by iterating over a list of cities. The `City` parameter works with a town at a time.

Outcome: I gained a thorough understanding of web scraping using Python libraries and open-source libraries built in Python like (Twint) for scraping information from Twitter.

I also gained a deep understanding of using the natural language tool kit(nltk) in Python

Tools used:Python, twint, Pandas, NumPy, matplotlib, seaborn, powerBI, Git & Git hub

Machine Learning Project

Predicting loan Eligibility

A machine learning project that uses supervised machine learning classification algorithms to classify customers who are eligible to collect loans from a financial company. This project predicts whether a customer is eligible for a loan or not, you can get similar results by following my notebook. Play around with the model's hyperparameter to get better accuracy.

Citrone Performance Project

This project trains a machine learning model to predict whether a student qualifies from the beginner class to the intermediate class or not from the Stutern learning management platform (Citrone). The model makes this prediction base on the student data provided to it. The model was thereafter deployed locally using streamlit to evaluate its performance.

- Outcome: A strong grasp of how the Supervised Machine learning model can be applied in real-world scenarios.

The basis of model deployment

Tools used: Python, Pandas, NumPy, matplotlib, seaborn, sci-kit learn, Statistics, Git & Git hub, streamlit, Spyder IDE.

English & Yoruba

Nigeria