def main(filename, category_filename, answer_col, predictor_col, hidden_nodes):
df = pd.read_csv(filename, usecols=[answer_col, predictor_col])
categories = pd.read_csv(category_filename,
usecols=[predictor_col])[predictor_col].values
vectorizer = Vectorizer(df, categories, predictor_col, answer_col)
vectorizer.format(0.6, 0.2)
batch_size = 1000
epocs = 50
learning_rate = 1e-3
model = build_and_train(vectorizer, batch_size, epocs, learning_rate,
hidden_nodes)
validate(model, vectorizer)
joblib.dump(model, filename + '.joblib')
batch_size = 1000
epocs = 50
learning_rate = 1e-3
model = build_and_train(vectorizer, batch_size, epocs, learning_rate,
hidden_nodes)
validate(model, vectorizer)
joblib.dump(model, filename + '.joblib')
# main(filename, category_filename, answer_col, predictor_col, 600)
df = pd.read_csv(filename, usecols=[answer_col, predictor_col])
categories = pd.read_csv(category_filename,
usecols=[predictor_col])[predictor_col].values
vectorizer = Vectorizer(df, categories, predictor_col, answer_col)
vectorizer.format(0.6, 0.2)
# interactive_test(filename, vectorizer )
test_cases = [['Amie Adams', 'Amy Adams'], ['Michael Fox', 'Michael J. Fox'],
['Minny Driver', 'Minnie Driver'],
['BLair Underwood', 'Blair Underwood'],
['Ralph Finnes', 'Ralph Fiennes'],
['Kate Blanchette', 'Cate Blanchett'],
['Joakin Pheonix', 'Joaquin Phoenix'],
['Ane Hathaway', 'Anne Hathaway'],
['Mickey Rorke', 'Mickey Rourke'],
['Collin Farrell',
'Colin Farrell'], ['Ben Stiler', 'Ben Stiller'],
['Cate Winslet', 'Kate Winslet'], ['John Hawks', 'John Hawkes'],
['George Cloney', 'George Clooney'],
['Cathlene Turner', 'Kathleen Turner'],
