franciszekruszkowski Goto Github PK

automated-playlist-generator-final-year-project

Data Science and Analytics BSc Dissertation - dividing music into playlists based on bassiline, harmonics or percussive similarity.

database-foodtooyou

FOODTOOYOO is a fast grocery delivery service based in London. FOODTOOYOO allows signed up members to have groceries from a number of registered retailing stores rapidly delivered at home, on the same day or on the following day. The idea was initiated during the COVID-19 lockdown that was put in place in UK from March to June 2020 when access to groceries became challenging for many households.

facility-location-problem

The project explores the potential placement of 5G tower across 3 states in The Netherlands: North Holland, South Holland, Utrecht. This abstract problem includes a scale used to messure the demand of 5G signal for the 19 biggest cities, as well as the cost of delivering it as well as building the towers.

ford-fulkerson-algorithm

Ford Fulkerson will be the chosen and implement algorithm which computes a maximum flow for a network and outputs it along with additional information explaining how it was obtained (such as incremental improvements for iterative algorithms like Ford-Fulkerson).

housesalesprices

kaggle.com competition - predict house sales prices : advanced regression techniques

imagesegmentation

The task was to segment colour images into meaningful parts. To assess the quality of the segmentations the codes produced output was compared to ground-truth segmentations generated by human observers.

k-means-car-types

we consider a set of observations on a number of silhouettes related to different type of vehicles, using a set of features extracted from the silhouette. Each vehicle may be viewed from one of many different angles. The features were extracted from the silhouettes by the HIPS (Hierarchical Image Processing System) extension BINATTS, which extracts a combination of scale independent features utilising both classical moments based measures such as scaled variance, skewness and kurtosis about the major/minor axes and heuristic measures such as hollows, circularity, rectangularity and compactness.

leeds-road-network-analysis

Analysis of Leeds Road Network in terms of car accidents locations as well as potential division of city for 10 simultaneous marathons

nlp-coronavirus-tweets

Sentiment analysis for COVID related tweets using NLP techniques and a Mutlinomial Naive Bayes classfieir Coronavirus tweets

opply-image-similarity-coding-task

Opply Coding Task - Image Similarity

pageviews_forecast

Time Series Forecast for number of pageviews on Figma website

shopify-coding-task-

stock-forecasting-algorithmic-bot

stock-predction-trading-bot

A project consisting of an algorithmic trading bot using LSTM model's forecasts of 16 different stock markets. 12/16 postivie return on investment after training the neural network on a 3-year long training set and trading on 2-year long test set from 2012-2018 for all 16 stocks.

tabular-october

For this competition, you will be predicting a binary target based on a number of feature columns given in the data. The columns are a mix of scaled continuous features and binary features. The data is synthetically generated by a GAN that was trained on real-world molecular response data.

troll-track-and-track-wikidata

used-cars-pricing-model-and-eda

Explaratory Data Analysis performed on a dataset on used cars consisting of 70.000+ rows. Data preprocessing and cleaning with a number of regression models fit to predict the target variable - "price".

vianova-case-study

vianova-data-intern-case-study