Francis Ndaruga (@Ndaruga)
github

Ndaruga

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    17
  • Global Rank 708,062 (Top 25 %)
  • Followers 5
  • Following 4
  • Registered over 4 years ago
  • Most used languages
    Jupyter Notebook
         40.0 %
    Python
         20.0 %
    TSQL     10.0 %
    Batchfile     10.0 %
    JavaScript
         10.0 %
    SCSS     10.0 %
  • Location πŸ‡°πŸ‡ͺ Kenya
  • Country Total Rank 1,303
  • Country Ranking
    Batchfile     9
    SCSS     18
    TSQL     22
    Jupyter Notebook
         136
    Python
         866
    JavaScript
         2,082

Top repositories

1

Web-application-using-php

My website code from scratch
SCSS
3
star
2

Twitter-Bot

Auto tweet from Open AI and telegram
Python
2
star
3

Facial-Attributes-Recognition-Using-Machine-Learning

This is a supervised Machine Learning project that recognizes if a face has attributes such as wrinkles, freckles, has glasses, hair color, and a couple of other attributes.
Jupyter Notebook
2
star
4

Expert-Sytem-AI

Jupyter Notebook
1
star
5

Integration-Services-with-ETL-using-MSSQL-server-and-power-BI

ETL using MSSQL server and Power BI
TSQL
1
star
6

Real-Time-Flight-Tracking-Dashboard

Track the location and status of an aircraft in real time
1
star
7

Auto-configuration-of-virtual-Machines-with-ansible

configuring and automating servers with ansible.
Batchfile
1
star
8

Multiple-Machine-Learning-Projects

This repository contains multiple machine learning projects for supervised, semi-supervised, unsupervised and reinforcement machine learning
Jupyter Notebook
1
star
9

Node.js-App-with-Express-MongoDB-and-Google-OAuthentication

JavaScript
1
star
10

Extract-weather-data-from-open-weather-API-using-python-and-AWS-EC2

Extracting weather data from the OpenWeatherMap API using Python and AWS EC2
Python
1
star
11

Fraud-Detection-in-credit-cards-using-anormaly-detection

This project involves identifying unusual patterns or behaviors that may indicate fraudulent activity in credit cards. Anomaly detection algorithms work by learning patterns from historical data and then detecting deviations from those patterns in new data. Three algorithms have been utilized. i.e Autoencoders & Angle-based Outlier Detection (ABOD)
Jupyter Notebook
1
star
12

demo

0
star