Members:
- Jayme Gordon
- Mo Garoub
- Sasha Babicki
- Syad Khan
Data analysis project for DSCI 522: Data Science Workflows
We are trying to answer the question, did the median ice thickness in the Canadian Arctic change by a statistically significant amount from the years 1984 to 1996? This question stems from the rising global temperatures and a curiosity of how this warming impacts the depth of the ice. The dataset used in this analysis contains measurements of ice thickness at various established monitoring stations in the Canadian Arctic on a weekly basis. Using exploratory data analysis (EDA) we determined that the data are skewed. We decided to use a hypothesis test for independence of a difference in medians using permutation for our analysis.
The dataset used in this analysis contains measurements of ice thickness at various established monitoring stations in the Canadian Arctic on a weekly basis. The data is made available from the Government of Canada and the monitoring is done by the Canadian Ice Thickness Program. Information about the program can be accessed through the Government of Canada and the specific dataset we are using is publicly available here.
The summary report can be found here.
To replicate the analysis, clone this GitHub repository and follow the instructions for one of the options below:
Install Docker. Run the following command in the command line from the root directory of this project:
docker run -it --rm -v $(pwd):/home/ice_thickness syadk/ice-thickness:v0.3.0 make -C /home/ice_thickness all
To reset the repo to a clean state, with no intermediate or results files, run the following command at the command line/terminal from the root directory of this project:
docker run -it --rm -v $(pwd):/home/ice_thickness syadk/ice-thickness:v0.3.0 make -C /home/ice_thickness clean
Install all the dependencies listed under the "Dependencies" header.
Python dependencies can be installed using the conda environment file provided in the 522_grp_13.yaml. To create and activate the environment, run the following commands in the command line from the root directory of this project:
conda env create --file 522_grp_13.yaml
conda activate 522_grp_13
R dependencies can be installed by running the following command in the R terminal:
install.packages(c("tidyverse", "dplyr", "infer", "ggplot2", "purrr", "knitr", "docopt", "svglite", "rmarkdown"))
Once dependencies are installed, run the following command at the command line from the root directory of this project:
make all
To reset the repo to a clean state, with no intermediate or results files, run the following command at the command line from the root directory of this project:
make clean
-
Python 3.8.0 and Python packages:
- pandas==1.1.4
- ipykernel==5.3.4
- xlrd==1.2.0
- docopt==0.6.2
- altair==4.1.0
- pandas-profiling==2.9.0
- pytest==6.1.2
- altair_saver==0.5.0
- vega_datasets==0.9.0
- python-chromedriver-binary==88.0.*
-
R 4.0.3 and R libraries:
- tidyverse==1.3.0
- dplyr==1.0.2
- datateachr==0.2.1
- infer==0.5.3
- ggplot2==3.3.2
- purrr==0.3.4
- knitr==1.30
- docopt==0.7.1
- svglite==1.2.3.2
- rmarkdown==2.5
The Ice Thickness Program Collection, 1947-2002 data contains information licensed under the Open Government Licence โ Canada (version 2.0).
Government of Canada (2020). Ice thickness data. Retrieved from: https://www.canada.ca/en/environment-climate-change/services/ice-forecasts-observations/latest-conditions/archive-overview/thickness-data.html
Timbers, T. (2020). DSCI 522 Statistical Inference and Computation I. Retrieved from: https://github.ubc.ca/MDS-2020-21/DSCI_552_stat-inf-1_students