Framework that will allow me to scafold text analysis projects, designed to work totally in Google Drive and Google Colab
- Copy as template, and rename according
- Create folder that will be where you project is stored
- Copy the settings.yaml file into this Google Drive Folder
- Provide
$FOLDER
as path to your Google Drive folder intosettings.yaml
- Provide
$SPEADSHEET
URLto Google spreadsheet that has the list of files you want to harvest intosettings.yaml
- Deploy the notebook you need by opening in Colab using
link
below. - Modify
YAML_LOCATION
in first line of notebook to be the 'Shared' URL of your YAML file
Notebook | Description | Link |
---|---|---|
Harvest | Grabs the contents of the files in the $SPREADSHEET and creates Text documents of them in $FOLDER |
link |
PreProcess_LDA | Preprocesses text to create BOW, Corpus, etc and saves to $FOLDER\preprocess |
link |
Contruct_LDA | Builds actual model and gives some exploratory parameters and saves to $FOLDER\model |
link |