fmqbl Goto Github PK

analytics

bigschedulesscrapp

Extraction of ocean carriers schedules given origin, destination and carrier option. Resources used are: Python, Selenium Webdriver, Chrome Driver

classification-of-urdu-mnist-dataset

Using pre-trained models of ResNet-50 and VGG16 for classification of Urdu MNIST dataset

dbt-tips

Collection of dbt Tips and Tricks

dbt2looker

Generate lookml for views from dbt models

deeplearningspecialization

The repository contains content of Deep Learning Specialization Course from Coursera. Majorly course assignments and learning notebooks against each topic.

dengai-predicting-disease-spread

Practice solution of Driven data competition 'DengAI Predicting disease spread'. (Preprocessing, Visualization & Hypothesis Testing)

deterministic-words-segmentation-for-urdu

Implementation of the MaxMatch algorithm for Deterministic Segmentation of words (Language: Urdu)

drivendata

Data analysis and model codes for DrivenData Projects.

dvc-test

Repo to test features of dvc for MLops

exploratory-notebooks

Preprocessing and implementation of decision tree algorithm(Supervised Learning) using Lending Club Loan Data from kaggle

javascript-space

Repo for JavaScript Basics for learning purpose.

natural-language-processing-course

Natural Language Processing Course (ITU 2019-2020) Repository. Have codes for projects and assignments

personal

Contains Jupiter Notebooks of stuff I am working on.

personalized-medicine-redefining-cancer-treatment

Repository to develop a deep learning based system which can mimic the work of a Pathologist by distinguishing different types of mutations based on clinical evidence.

predicting-post-procedural-complications-using-mimiciii

The repository is intended to be a central hub for sharing, refining, and reusing code used for analysis of the MIMIC critical care database and my masters thesis for Data Science. To find out more about MIMIC, please see: https://mimic.physionet.org

roads-segmentation-mnih

Deep learning based scripts which, given an aerial image can output a binary mask for the input image showing for each pixel if it belongs to a road or not. Approach is based on Massachusetts Roads Dataset (Mnih) containing total 1438 high resolution images along with their road masks.