workflow example

README.md

 # Newseye
 
-Newseye Jupyter Notebook: János Békési, Martin Gasteiner
\ No newline at end of file
+Newseye Jupyter Notebook: János Békési, Martin Gasteiner
+
+
+## Data
+
+22 MB transkribus json data (down to article level) resp. 12 MB csv data of the same
+
+
+## Workflow
+
+Sometimes the generating of topic models is rather tedious, since difficulties can arise regarding
+input data (datetime series with different starting or ending points, unforeseen gaps, etc.), or 
+the output formatting has to consider presentation quirks or sequence fittings. Though time aufgewendet 
+will mostly be more than estimated, any of those obstructions will be mastered (?) with a bit of
+patience and thoughtfulness.
+
+When preparing data for topic modelling, especially when using scanned data, it is crucious to allow for
+some document structure (pages, sections, documents).
+