This package is an attempt at predicting common types in CSVs about Italian people and places using ensemble heuristics with Decision Random Forests and Spacy NLP tool.
As usual, just download it using pip:
apt-get update -y
apt-get install -qyy apt-utils build-essential software-properties-common locales locales-all curl autoconf automake libtool python-dev pkg-config
curl https://raw.githubusercontent.com/LucaCappelletti94/italian_csv_type_prediction/master/setup.sh | sh
pip install italian_csv_type_prediction
Since some software handling coverages sometimes get slightly different results, here's three of them:
To get the typization of a list of data you can use:
from italian_csv_type_prediction import predict_types
predictions = predict_types([
#list of words to predict goes here
])