def predict(self, X):
if self.test_batch % 1 == 0:
logging.info('Running test batch {}'.format(self.test_batch))
X = self.lectures_pipeline.transform(X)
X = RiiidModel.remove_lectures(X)
if len(X) > 0:
predictions = X[['row_id']].copy()
X = self.pipeline.transform(X)
self._update_context_with_priors(X)
inputs = self._create_prediction_data(X)
self._roll_context_on_priors(X)
self._update_context(X, self.independent_features)
predictions['answered_correctly'] = self.model.predict(inputs)[:, -1, -1]
else:
predictions = pd.DataFrame(columns=['row_id', 'answered_correctly'])
self.test_batch += 1
return X, predictions
def fit_transform(self, X):
logging.info('- Fit')
self._init_fit(X)
self.lectures_pipeline = make_pipeline(
LecturesTransformer(self.lectures)
)
X = self.lectures_pipeline.fit_transform(X)
X = RiiidModel.remove_lectures(X)
cv = self._build_cv(X)
self.pipeline = make_pipeline(
ScoreEncoder('content_id', cv=cv, smoothing_min=5, smoothing_value=1, noise=0.005),
QuestionsTransformer(self.questions, time_bins=self.time_bins, lag_bins=self.lag_bins)
)
X = self.pipeline.fit_transform(X)
self._create_context(X)
return X
def update(self, test):
prior_user_answer = eval(test['prior_group_responses'].values[0])
prior_answered_correctly = eval(test['prior_group_answers_correct'].values[0])
test = test.drop(columns=['prior_group_answers_correct', 'prior_group_responses'])
if self.previous_test is not None:
self.previous_test['user_answer'] = prior_user_answer
self.previous_test['answered_correctly'] = prior_answered_correctly
X = self.previous_test
# X = update_pipeline(self.lectures_pipeline, X) # Not required
X = RiiidModel.remove_lectures(X)
if len(X) > 0:
y = X['answered_correctly']
X = update_pipeline(self.pipeline, X, y)
self._update_context(X, self.dependent_features)
self.previous_test = test.copy()
return test