Student: Diana Dalae (45612226)
In these 3 Portfolio tasks, I have managed to employ a number of data science skills, like data cleansing, data exploration, data analysis. I modeled Linear Regression, both with one feature and multiple selected by RFE. I have successfully demonstrated a good understanding of KMeans algorithm and implemented it from scratch.
Portfolio projects
-
Analysis of CSV data for cycling
- Joined two data sets from Strava and Cheetah and cleared the data.
- Cleared data by removing all rides not recording Power and dublicate columns
- Provided analysis on distribution of key variables
- Ploted important variables against each other to look for correlations
-
Analyisis of house power consumption
- Replicated most of the graphs in the first half of the paper
- Interpreted the graph data and provided an analysis
- Implemented a Linear Regression model
- Selected 5 best features for prediction using RFE
-
KMeans Clustering
- Successfully implemented step by step KMeans clustering algorithm