-
Elaine Zhou
-
Jossie Jiang
-
Swakhar Poddar
-
Weihao Sun
The data set we used is the Zoo (1990) provided by UCL Machine Learning Repository. It stores data about 7 classes of animals and their related factors including animal name, hair, feathers and so on. In this project, we picked classification as our method to classify a given animal to its most likely type. All of 16 factors including hair, feathers, eggs, milk, airborne, aquatic, predator, toothed, backbone, breathes, venomous, fins, legs, tail, domestic, and catsize were selected as our predictors. To best predict the class of a new observation, we implemented and evaluated models based on a list of algorithms including k-Nearest Neighbor(k-NN), Decision Tree, Support Vector Machine and Logistic Regression. After a comparison among accuracies of different models, we finally found that algorithm k-NN produced the most accurate result of predicting animal type. There are several ways to repeat/reproduce our analysis, please kindly find details in Usage section.
Documents about Project Manners:
The final report can be viewed from the following:
A list of the dependencies packaged in the image:
Package Name | Version |
---|---|
python | 3.9.7 |
pandas | 1.4.1 |
scikit-learn | 1.0.2 |
matplotlib | 3.5.1 |
numpy | 1.22.2 |
pytest | 7.0.1 |
R | 4.1.2 |
knitr | 1.38 |
reticulate | 1.24 |
tidyverse | 1.3.1 |
jupyter-book | 0.12.1. |
see dockerfile and docker image
-
You should sign up/on a Docker account.
-
Install Docker in your computer.
-
Clone this repo
You can find the detailed instructions of repository clone from here
git clone https://github.com/DSCI-310/DSCI-310-Group-7.git
Then, choose one of following two suggested ways to repeat/reproduce this analysis:
a. Pull down the docker image
docker pull sasiburi/dsci-310-group-7:latest
Up to the present, the latest version is v3.2.0. You can replace latest
by another specific version.
b. Run the docker image
cd
to the root of the cloned repo, then run the command:
docker run --rm -p 8888:8888 -v ${PWD}:/home/jovyan/work sasiburi/dsci-310-group-7:latest
Open the link provided on your console. Now you should be able to see the repo under work/
.
Possible Errors & Solutions
- If you see the following error message:
docker: Error response from daemon: Mounts denied: The path /YOURPATH is not shared from the host and is not known to Docker.
Try following steps:
- Open Preferences
- Click Resources -> FILE SHARING
- Add your /path/to/exported/directory
- Restart Docker and try the command above again
- If a token is required, it can be obtained on your console. For example,
token=3912f59232fe3b260fda201da4e822e69bfed02e649dc56b
, then3912f59232fe3b260fda201da4e822e69bfed02e649dc56b
is the token. - If the port
8888
has been occupied, you can replace the first8888
by another four-digit number.
a. Install all the dependencies
b. reproduce the analysis
cd
to the root of the cloned repo, then run the command:
make all
c. reset the repo
make clean
Releases relate to each milestone are listed as follows:
more details could be found on the right-hand-side panel, Releases or our docker web.
a. an MIT license for the project code
b. a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International(CC BY-NC-ND 4.0) license for the project report