def errors(self):
indices = [] # index of a row, formatted YYYY-M (e.g. 2016-8, 2016-9)
predictions = []
errors = [] # errors. Lower is better
test_data_size = []
actuals = []
for i in range(0, self.num_months() - self.training_data_span_months):
m = self._model()
training_data = self.training_data(i,
self.training_data_span_months)
m.fit(training_data)
td = self.test_data(i + self.training_data_span_months)
print "Generating prediction..."
prediction = m.predict(\
BusinessForecast(\
td).convert(),
training_data=training_data)
actual = ActualSchedule(\
td).bins()
print "prediction "
print prediction
print "\n"
print "actual"
print actual
print "\n"
error = mean_absolute_error(actual, prediction)
errors.append(error)
index = self.year_month_index(i + self.training_data_span_months)
indices.append(index)
print "time: {}, error: {}".format(index, error)
predictions.append(prediction)
actuals.append(actual)
test_data_size.append(actual.sum())
return pd.DataFrame({
'errors': errors,
'test_data_size': test_data_size,
'predictions': predictions,
'actuals': actuals
}).set_index([indices])
