Pinned Repositories
Ad-Click-Prediction
Creating a model in R that predicts which individuals are most likely to click on Ads
Apartment-Rental-Management-System
A DBMS mini project on Apartment Rental Management System built for management of tasks such as tracking and storing tenant information, collecting rent and managing accounting needs.
awesome-gcp-certifications
Google Cloud Platform Certification resources.
Carrefour-Kenya-Marketing-Strategies
A Data Science Project to inform the Carrefour marketing department on the most relevant marketing strategies that will result in the highest no. of sales (total price including tax).
CHI-SQUARE-TEST-OF-INDEPENDENCE-PYTHON
Chi-Square using Scipy and Researchpy
Clustering-Algorithms-R
Supervised & Unsupervised Learning with R
Hypothesis-Testing
The data being described in the Hypothesis test is obtained from Autolib electric car-sharing service company. The data was collected over a period of 6 months in the year 2018 for the sum of cars taken in a given area with a specific postal code.
InstaDeep-Enzyme-Classification
In the UmojaHack Tunisia hackathon we invited participants to predict the functional class of enzymes called protein kinases based on their amino acid sequences. For this challenge we’re taking it one step further. Given a library of labelled sequences from some well-known organisms, your task is to create a model that can label sequences from new organisms. Each sequence could represent any kind of enzyme - not just kinases. All enzymes are made of one or more chains of amino acids, which determine their structure, behaviour, and interactions with other enzymes and molecules. That means it should be possible to predict the protein’s function and behaviour given just the amino acid sequence. A model able to perform this task would have many applications. In addition to enzymes from known organisms (which we have from studying their proteomes), there are vast numbers of metagenomic sequences - this is proteomic sequence data from environmental samples. Being able to quickly annotate them with function using this model (i.e. going beyond simple sequence similarity) would be indispensable. Models developed in the course of this challenge may contribute to furthering the understanding of the world around us.
KNN-Naive-Bayes-Classifiers
Performing K-Nearest Neighbours and Multinomial Naive Bayes Classification on different datasets.
Loan-Default-Prediction
SuperLender is a local digital lending company, which prides itself in its effective use of credit risk models to deliver profitable and high-impact loan alternative. This approach is based on two main risk drivers of loan default prediction which include willingness to pay and the ability to pay.
davidmuna's Repositories
davidmuna/Clustering-Algorithms-R
Supervised & Unsupervised Learning with R
davidmuna/InstaDeep-Enzyme-Classification
In the UmojaHack Tunisia hackathon we invited participants to predict the functional class of enzymes called protein kinases based on their amino acid sequences. For this challenge we’re taking it one step further. Given a library of labelled sequences from some well-known organisms, your task is to create a model that can label sequences from new organisms. Each sequence could represent any kind of enzyme - not just kinases. All enzymes are made of one or more chains of amino acids, which determine their structure, behaviour, and interactions with other enzymes and molecules. That means it should be possible to predict the protein’s function and behaviour given just the amino acid sequence. A model able to perform this task would have many applications. In addition to enzymes from known organisms (which we have from studying their proteomes), there are vast numbers of metagenomic sequences - this is proteomic sequence data from environmental samples. Being able to quickly annotate them with function using this model (i.e. going beyond simple sequence similarity) would be indispensable. Models developed in the course of this challenge may contribute to furthering the understanding of the world around us.
davidmuna/Ad-Click-Prediction
Creating a model in R that predicts which individuals are most likely to click on Ads
davidmuna/Apartment-Rental-Management-System
A DBMS mini project on Apartment Rental Management System built for management of tasks such as tracking and storing tenant information, collecting rent and managing accounting needs.
davidmuna/awesome-gcp-certifications
Google Cloud Platform Certification resources.
davidmuna/Carrefour-Kenya-Marketing-Strategies
A Data Science Project to inform the Carrefour marketing department on the most relevant marketing strategies that will result in the highest no. of sales (total price including tax).
davidmuna/CHI-SQUARE-TEST-OF-INDEPENDENCE-PYTHON
Chi-Square using Scipy and Researchpy
davidmuna/Hypothesis-Testing
The data being described in the Hypothesis test is obtained from Autolib electric car-sharing service company. The data was collected over a period of 6 months in the year 2018 for the sum of cars taken in a given area with a specific postal code.
davidmuna/KNN-Naive-Bayes-Classifiers
Performing K-Nearest Neighbours and Multinomial Naive Bayes Classification on different datasets.
davidmuna/Loan-Default-Prediction
SuperLender is a local digital lending company, which prides itself in its effective use of credit risk models to deliver profitable and high-impact loan alternative. This approach is based on two main risk drivers of loan default prediction which include willingness to pay and the ability to pay.
davidmuna/Credit-Scoring-Data-Sets
These common credit score data sets are collected to empirical evaluations, and I will update dynamically.
davidmuna/davidmuna
davidmuna/electric-car-sharing-service
This is an analysis of an Electric Car-Sharing Company on processing stations data to understand electric car usage over time
davidmuna/FaceMask-Detector-with-CNN
Building face mask detector with Convolutional Neural Network.
davidmuna/FIFA-Supervised-Learning-Model
Supervised Learning with Exploratory Data Analysis using Polynomial and Logistic Regression.
davidmuna/Financial-Inclusion-Project
Financial Inclusion remains one of the main obstacles to economic and human development in Africa Despite the proliferation of mobile money in Africa and the growth of innovative fintech solutions, banks still play a pivotal role in facilitating access to financial services. Access to bank accounts enables households to save and facilitate payments while also helping businesses build up their credit-worthiness and improve their access to other financial services. My role as a Data Scientist is to predict which individuals are most likely to have or use a bank account and provide an indication of the state of financial inclusion in Kenya, Rwanda, Tanzania, and Uganda, while providing insights into some of the key demographic factors that might drive individuals’ financial outcomes. The Null hypothesis is that 9.1 million adults (or 13.9% of the adult population in Kenya, Rwanda, Uganda and Tanzania) have access to a bank account.
davidmuna/Flight-Price-Prediction
Now you can get Flight ticket fare with this wonderful end to end project.
davidmuna/Google-Map-Api
We will implement a map with some custom markers, info window, event listeners and we will optimize the code so that we can easily add new markers with new properties to it. We will also go through how to remove the water mark (only for developer purpose) and go through how to make this project your own and add more properties and methods
davidmuna/Government-Expenditure-Project
The government's role in economic growth has been an issue since way back with the perception that, for sustainable development and efficient output, the government's role in economic policies should be reduced. Given this fiscal scenario, there is a need to identify the relationship between GDP, Government Expenditure on the two sectors, and how they relate to growth of GDP in Kenya's economy.
davidmuna/Hass-Consulting-Company
Creating a model that would allow Hass Consult to accurately predict the sale of prices upon being provided with the predictor variables.
davidmuna/Instadeep-Competition
davidmuna/InstaDeep-Enzyme-Classification-Challenge
https://zindi.africa/competitions/instadeep-enzyme-classification-challenge
davidmuna/microrealestate
This is an Open Source Real estate management system that helps landlords to manage their rentals and properties
davidmuna/mlproject
davidmuna/Moringa_Data_Science_Prep_W3_Independent_Project_2020_07
This is an analysis of how MTN Cote D'Ivoire can upgrade its technology infrastructure for its mobile users in Ivory Coast. I studied the given datasets and identified how MTN Cote d'Ivoire can go about the upgrade of its infrastructure strategy within the given cities, based on my recommendations.
davidmuna/Nairobi-Hospital-Clinical-Hypothyroidism-Camp
Using Ensemble Classification Methods to test for hypothyroidism. The data collected focused on Thyroid patients. The healthcare datasets provided will be used for classification.
davidmuna/Network-Anomaly-Detection
Network intrusion detection has become increasingly important with the rapid rise of internet technology and the accompanying growth in the number of network attacks. Our goal is to create an anomaly detection model to detect a cyber attack based on the UNSW-NB 15 dataset.
davidmuna/Python-programming-exercises
100+ Python challenging programming exercises
davidmuna/U-2-Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."