👨🏻🎓 Computer Scientist | 2018 Graduate
🧿 Data Analyst | IBM Certified
Area of expertise:
-
- DevOps CI/CD Pipelines & Practices
-
- Linux Administration
-
- Data Science & Analytics
-
- Sentiment Analysis
-
- IoT & Embedded Systems
|
DevOps |
Python
|
Vagrant
|
Terraform
|
Ansible
|
Kubernetes
|
|
Tools |
Code
|
Bash
|
git
|
Docker
|
|
|
Cloud |
Azure
|
AWS
|
GCP
|
||
|
OS |
Kali
|
Linux
|
|||
|
GitOps |
ArgoCD
|
My Badges on Credly
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
|
The system is designed for visually impaired people. It is an Arduino-based system integrated on a white cane (walking stick for the blind) that uses Ultrasonic sensors for obstacle detection.
If an obstacle is detected in the user’s range, the cane would tell the user in the form of different beeps and alarms. At this point, we are assuming that the user is not hearing impaired so that he or she can detect the alarm sounds.
Apart from an Ultrasonic sensor for obstacle detection, the system also has a GPS module to track the location of the user. This location can be checked by the user’s relative using mobile SMS service.
The module is capable of sending an SMS message to the family member periodically / on button press, that contains the google maps location of the device (and the person using it).
Repository Link
Presentation Link
Feb 2021 – Mar 2021
Extraction of financial data like historical share price and quarterly revenue reportings from various sources using Python libraries and web scraping on popular stocks. After collecting this data, I visualized it to identify patterns or trends. The stocks I worked with were:
View Project
Mar 2021
Tasked with determining the market price of a house given a set of features. Analysis and prediction of housing prices using attributes or features such as:
and so on
May 2021
Loaded a historical dataset from previous loan applications, cleaned the data, and applied different classification algorithms on the data. Used the following models to decide the best among them for this scenario:
The results are reported as the accuracy of each classifier, using the following metrics when these are applicable:
June 2021
I was required to explore, segment, and cluster the neighborhoods in the city of Toronto based on the postal code and borough information.
For the Toronto neighborhood data, a Wikipedia page exists that has all the information needed to explore and cluster the neighborhoods in Toronto. I was required to scrape the Wikipedia page and wrangle the data, clean it, and then read it into a pandas data frame so that it was in a structured format.
Once the data was in a structured format, I used the dataset to explore and cluster the neighborhoods in the city of Toronto, with the help of Foursquare API and K-means Clustering Algorithm for Unsupervised Machine Learning.
July 2021
The 2019–20 coronavirus pandemic was confirmed to have reached Pakistan on 26 February 2020, when a student in Karachi tested positive upon returning from Iran. By 18 March, cases had been registered in all four provinces, the two autonomous territories, and the federal territory of Islamabad. The dataset is completely acquired from NIH Publications, Governmental resources and extra mile contacts.
The dataset reflects at provincial level and details from all the aspects.
August 2021
This is an Exploratory Data Analysis Project on a Dataset used from Kaggle.com. Said Dataset containing Data on Accidents occured in USA uptil Dec 2020.
Sometimes Excel or Notepad will not recognize whitespaces when you try to remove extra spaces in an entire column of data, or a dataset.
So this script file in the code will help remove those white spaces, it converts them to "?" characters, which can then be manually removed.
This project comes out of an irritation I faced personally.
When I was first learning to code - setting up my local repo and syncing with Github
