Initial

.gitignore

@@ -0,0 +1,2 @@
+# Ignore raw csv data files. 
+data/*.csv

Dockerfile

@@ -0,0 +1,79 @@
+# Copyright (c) Jupyter Development Team.
+# Distributed under the terms of the Modified BSD License.
+ARG BASE_CONTAINER=jupyter/minimal-notebook
+FROM $BASE_CONTAINER
+
+LABEL maintainer="Jupyter Project <[email protected]>"
+
+USER root
+
+# ffmpeg for matplotlib anim
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends ffmpeg && \
+    rm -rf /var/lib/apt/lists/*
+
+USER $NB_UID
+
+# Install Python 3 packages
+# Remove pyqt and qt pulled in for matplotlib since we're only ever going to
+# use notebook-friendly backends in these images
+RUN conda install --quiet --yes \
+    'conda-forge::blas=*=openblas' \
+    'ipywidgets=7.4*' \
+    'pandas=0.24*' \
+    'numexpr=2.6*' \
+    'matplotlib=3.0*' \
+    'scipy=1.2*' \
+    'seaborn=0.9*' \
+    'scikit-learn=0.20*' \
+    'scikit-image=0.14*' \
+    'sympy=1.3*' \
+    'cython=0.29*' \
+    'patsy=0.5*' \
+    'statsmodels=0.9*' \
+    'cloudpickle=0.8*' \
+    'dill=0.2*' \
+    'dask=1.1.*' \
+    'numba=0.42*' \
+    'bokeh=1.0*' \
+    'sqlalchemy=1.3*' \
+    'hdf5=1.10*' \
+    'h5py=2.9*' \
+    'vincent=0.4.*' \
+    'beautifulsoup4=4.7.*' \
+    'protobuf=3.7.*' \
+    'xlrd'  && \
+    conda remove --quiet --yes --force qt pyqt && \
+    conda clean --all -f -y && \
+    # Activate ipywidgets extension in the environment that runs the notebook server
+    jupyter nbextension enable --py widgetsnbextension --sys-prefix && \
+    # Also activate ipywidgets extension for JupyterLab
+    # Check this URL for most recent compatibilities
+    # https://github.com/jupyter-widgets/ipywidgets/tree/master/packages/jupyterlab-manager
+    jupyter labextension install @jupyter-widgets/jupyterlab-manager@^0.38.1 && \
+    jupyter labextension install [email protected] && \
+    npm cache clean --force && \
+    rm -rf $CONDA_DIR/share/jupyter/lab/staging && \
+    rm -rf /home/$NB_USER/.cache/yarn && \
+    rm -rf /home/$NB_USER/.node-gyp && \
+    fix-permissions $CONDA_DIR && \
+    fix-permissions /home/$NB_USER
+
+# Install facets which does not have a pip or conda package at the moment
+RUN cd /tmp && \
+    git clone https://github.com/PAIR-code/facets.git && \
+    cd facets && \
+    jupyter nbextension install facets-dist/ --sys-prefix && \
+    cd && \
+    rm -rf /tmp/facets && \
+    fix-permissions $CONDA_DIR && \
+    fix-permissions /home/$NB_USER
+
+# Import matplotlib the first time to build the font cache.
+ENV XDG_CACHE_HOME /home/$NB_USER/.cache/
+RUN MPLBACKEND=Agg python -c "import matplotlib.pyplot" && \
+    fix-permissions /home/$NB_USER
+
+RUN mkdir colab
+COPY . colab/.
+USER $NB_UID

README.md

@@ -13,8 +13,7 @@ Download `python` from [https://www.python.org/downloads/](https://www.python.or
 # Setup
 
 Two methods are provided:
-
-1. Install a `Python` virtual environment [https://docs.python.org/3/library/venv.html](https://docs.python.org/3/library/venv.html)
+1 Install a `Python` virtual environment [https://docs.python.org/3/library/venv.html](https://docs.python.org/3/library/venv.html)
 ```
 python3 -m venv colab-venv
 ```
@@ -27,7 +26,7 @@ source colab-venv/bin/activate
 pip install -r requirements.txt
 ```
 
-2. Install with `conda`:
+2 Install with `conda`:
 ```
 conda env create -f environment.yml
 ```
@@ -49,10 +48,42 @@ conda activate colab-2019
 jupyter-notebook
 ```
 
+## Docker
+There is also a `Dockerfile` e.g
+Build
+```
+docker build -t colab .
+```
+Run
+```
+docker run -p 8888:8888 -t colab
+```
+
+The docker file can be improved to handle e.g. data mounting and run name tagging
+
 # Documentation
 
 Documentation is in the `docs` folder
 
 # Data
 
-Data can be put in the `data` folder. A `.gitignore` file ignores `data/*.csv` files.
+Data can be put in the `data` folder. A `.gitignore` file ignores
+`data/*.csv` files. The data from
+[https://analyse.kmi.open.ac.uk/open_dataset#data](https://analyse.kmi.open.ac.uk/open_dataset#data)
+is used.
+
+Use `download_data.sh` for help downloading the data files to the `data` folder
+```
+bash ./download_data.sh
+```
+
+# Packages used
+```
+jupyter
+matplotlib
+numpy
+pandas
+scikit-learn
+scipy
+seaborn
+```

download_data.sh

@@ -0,0 +1,18 @@
+#! /bin/bash
+
+# Go to `data` folder
+cd data
+# Instructions about data at https://analyse.kmi.open.ac.uk/open_dataset/download
+#Download data set from https://analyse.kmi.open.ac.uk/open_dataset/download
+wget --output-document=vle_data.zip https://analyse.kmi.open.ac.uk/open_dataset/download
+# Download checksum from https://analyse.kmi.open.ac.uk/open_dataset/downloadCheckSum
+wget --output-document=md5_vle_data https://analyse.kmi.open.ac.uk/open_dataset/downloadCheckSum
+# Check integrity matches
+md5 vle_data.zip
+cat md5_vle_data
+# Unzip
+unzip vle_data.zip
+# See which files were extracted
+ls -lh
+
+