Emeka Boris Ama

Data Scientist/Machine Learning Engineer
πŸ’‚β€β™‚οΈ βš–οΈ

My files has been disappearing from deepnote lately

πŸ’‚β€β™‚οΈ βš–οΈ
Sometimes when I try moving files from one folder to the work dir and my internet is a little bit unstable, the file disappears when the internet becomes stable.Β 


This isnt the first, nor secondΒ  time i have experience this

I can't display CV2.show image on deepnote

πŸ’‚β€β™‚οΈ βš–οΈ
Anytime i try displaying image with cv2, I keep getting this error below

error: OpenCV(4.5.2) /tmp/pip-req-build-gvmai4nm/opencv/modules/highgui/src/window.cpp:679: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage'
Like Comment

ETL pipeline with GitHub API

πŸ’‚β€β™‚οΈ βš–οΈ
Objective:
Β Build a Github ETL pipeline with python, SQLite and Bigquery that extract the amount of repo and other valuable information about an applicant.


ο»Ώ
ο»Ώ
Project link
Like Comment

Sentiment analysis for under resource language

πŸ’‚β€β™‚οΈ βš–οΈ
Objective:

Train a sentiment classifier (Positive, Negative, Neutral) on a corpus of the provided documents.Β 
The goal is to maximize accuracy. There is special interest in being able to
accurately detect negative sentiment. The training data includes documents from a
wide variety of sources, not merely social media, and some of them may be inconsistently
labelled.


Project:

There are over 6900 languages in the world today and only a small fraction offers the resources required for the implementation of Natural Language processing or Human Language Technologies.

However, most technologies are concerned with the language for which large resources are available or which have suddenly become of interest because of economic and political science. Unfortunately, most languages from developing countries received only a little attention so far. One way we intend to improve the language divide is by building Natural Language applications.

Although our goal is to maximize accuracy, bias and variance are other important factors to consider since our focus is on an under resource language and also adequately detecting negative sentiment without been bias.

In this project, we build a sentiment classifier that adequately classifier sentiment of Roman Urdu text



ο»Ώ
ο»Ώ
Notebook Link

Like Comment

I would love to push to github on click of a button

πŸ’‚β€β™‚οΈ βš–οΈ
It will be great to push to github after work done on deepnote
Like Comment