from medcat.cat import CAT
from medcat.utils.vocab import Vocab
from medcat.cdb import CDB 

vocab = Vocab()
# Load the vocab model you downloaded
vocab.load_dict('<path to the vocab file>')

# Load the cdb model you downloaded
cdb = CDB()
cdb.load_dict('<path to the cdb file>') 

# create cat
cat = CAT(cdb=cdb, vocab=vocab)
cat.train = False

# Test it
doc = "My simple document with kidney failure"
doc_spacy = cat(doc)
# Entities are in
doc_spacy._.ents
# Or to get a json
doc_json = cat.get_json(doc)

# To have a look at the results:
from spacy import displacy
# Note that this will not show all entites, but only the longest ones
displacy.serve(doc_spacy, style='ent')

# To train - unsupervised, set the train flag to True and run
#documents through MedCAT
cat.train = True

# To run cat on a large number of documents, this will
#also run trainnig as the flag is set to True.
data = [(<doc_id>, <text>), (<doc_id>, <text>), ...]
docs = cat.multi_processing(data)

# To explicitly run trainnig you can do
f = open("<some file with a lot of medical text>", 'r')
# If you want fine tune set it to True, old training will be preserved
cat.run_training(f, fine_tune=True)

from medcat.cat import CAT
from medcat.utils.vocab import Vocab
from medcat.cdb import CDB 

vocab = Vocab()
# Load the vocab model you downloaded
vocab.load_dict('<path to the vocab file>')

# If you have an existing CDB
cdb = CDB()
cdb.load_dict('<path to the cdb file>') 

# You can now add concepts from a CSV file, examples of the files can be found in ./examples
preparator = PrepareCDB(vocab=vocab)
csv_paths = ['<path to your csv_file>', '<another one>', ...] 
# e.g.
csv_paths = ['./examples/simple_cdb.csv']
cdb = preparator.prepare_csvs(csv_paths)

# Save the new CDB for later
cdb.save_dict("<path to a file where it will be saved>")
# Done