def predict_proba(self, X, regression=False):
X = self.tfidf.transform(X)
if regression:
raise ValueError('Cannot predict probabilites of a regression!')
else:
return self.rfc.predict_proba(X)
if __name__ == '__main__':
traits = ['OPN', 'CON', 'EXT', 'AGR', 'NEU']
model = Model()
for trait in traits:
dp = DataPrep()
X_regression, y_regression = dp.prep_data('status',
trait,
regression=True,
model_comparison=False)
X_categorical, y_categorical = dp.prep_data('status',
trait,
regression=False,
model_comparison=False)
print('Fitting trait ' + trait + ' regression model...')
model.fit(X_regression, y_regression, regression=True)
print('Done!')
print('Fitting trait ' + trait + ' categorical model...')
model.fit(X_categorical, y_categorical, regression=False)
print('Done!')
with open('static/' + trait + '_model.pkl', 'wb') as f:
# Write the model to a file.
pickle.dump(model, f)
if regression:
return self.rfr.predict(X)
else:
return self.rfc.predict(X)
def predict_prob(self, X, regression=False):
X = self.tfidf.transform(X)
if regression:
raise ValueError('Cannot predict probabilites of a regression!')
else:
return self.rfc.predict_proba(X)
if __name__ == '__main__':
traits = ['OPN', 'CON', 'EXT', 'AGR', 'NEU']
model = Model()
for trait in traits:
dp = DataPrep()
X_regression, y_regression = dp.prep_data(trait, regression=True)
X_categorical, y_categorical = dp.prep_data(trait, regression=False)
print('Entrenando rasgo ' + trait + ' con modelo regression...')
model.fit(X_regression, y_regression, regression=True)
print('Hecho!')
print('Entrenando rasgo ' + trait + ' con modelo categorical...')
model.fit(X_categorical, y_categorical, regression=False)
print('Hecho!')
with open('static/' + trait + '_model.pkl', 'wb') as f:
# Write the model to a file.
pickle.dump(model, f)
print("Entrenamiento terminado!")