fastai wget unzip

inspired from
https://colab.research.google.com/github/corykendrick/fastai_in_colab/blob/master/Using_Google_Colab_for_Fastai.ipynb#scrollTo=8w2pvt26J6al

!curl -s https://course.fast.ai/setup/colab | bash
%reload_ext autoreload
%autoreload 2

from google.colab import drive
drive.mount('/content/gdrive', force_remount=True)
root_dir = "/content/gdrive/My Drive/"
base_dir = root_dir + 'fastai-v3/'

%matplotlib inline

!pwd

path = Path(base_dir + 'data/planet')
path

# Make sure the data is where you think it is:
!ls '/content/gdrive/My Drive/fastai-v3/data/planet'

#get the train tar here
#https://forums.fast.ai/t/lesson-2-amazon-dataset-no-tar-or-zip-file/63926/4
#get the labelling csv from kaggle
#upload both to '/content/gdrive/My Drive/fastai-v3/data/planet'
#intended directory structure as reference https://i.imgur.com/dfQFUsZ.png

# In order to unzip the 7z files, need to install p7zip
# This was helpful: http://forums.fast.ai/t/unzipping-tar-7z-files-in-google-collab-notebook/14857/4
!apt-get install p7zip-full
!apt install unzip

# unzip a file named 'train_v2.csv.zip'
# no need extension to include the .zip extension
# -d is the name of the directory to extract to
!unzip "/content/gdrive/My Drive/fastai-v3/data/planet/train_v2.csv" -d "/content/gdrive/My Drive/fastai-v3/data/planet"

# Unzip the .tar files to 'somewhere'
!tar -xvf /content/gdrive/My\ Drive/fastai-v3/data/planet/train-jpg.tar

# Move the unzipped folders('somewhere') back into data/planet/
#
!mv train-jpg /content/gdrive/My\ Drive/fastai-v3/data/planet/

#la di da
df = pd.read_csv(path/'train_v2.csv')
df.head()