def __prediction(self, extractor: AppearanceExtractor, classifier: Classifier, predict_season: int) -> \
Dict[Player, MultiLayerResult]:
""" Execute the prediction phase of the Appearance Layer.
Arguments:
extractor (AppearanceExtractor): The extractor which delivers the prediction data.
classifier (Classifier): A classifier which classifies players as either Mol or non-Mol based on how often
they appear.
predict_season (int): For which season we make the prediction.
Returns:
A dictionary with as key the players that participated in the prediction season and as value a
MultiLayerResult which contains the predictions.
"""
all_predictions = dict()
predict_data = extractor.get_predict_data()
if not predict_data:
return EmptyMultiLayer().predict(predict_season, 0, set())
for player in get_players_in_season(predict_season):
if player in predict_data:
predictions = []
for data in predict_data[player]:
predictions.append(classifier.predict_proba([data]))
all_predictions[player] = MultiLayerResult(np.array(predictions), False)
else:
all_predictions[player] = MultiLayerResult(np.array([]), True)
return all_predictions
def predict(self, predict_season: int, latest_episode: int, train_seasons: Set[int]) -> Dict[Player, np.array]:
train_seasons = {season for season in train_seasons if season >= self.__first_season}
max_episode = self.__latest_available_episode(predict_season, latest_episode)
if max_episode == 0 or predict_season < self.__first_season:
return EmptyMultiLayer().predict(predict_season, latest_episode, train_seasons)
extractor = AppearanceExtractor(predict_season, max_episode, train_seasons, self.__aug_num_cuts,
self.__aug_min_cuts_on)
classifier = self.__training(extractor)
return self.__prediction(extractor, classifier, predict_season)
def predict(self, predict_season: int, latest_episode: int,
train_seasons: Set[int]) -> Dict[Player, MultiLayerResult]:
available_seasons = MONEY_DATA.keys()
train_seasons = train_seasons.intersection(available_seasons)
if predict_season not in available_seasons:
return EmptyMultiLayer().predict(predict_season, latest_episode,
train_seasons)
extractor = MoneyExtractor(predict_season, latest_episode,
train_seasons, self.__pca_explain,
self.__spline_clusters,
self.__num_other_money_quantiles,
self.__random_generator)
classifier = self.__training(extractor)
predict_data = extractor.get_predict_data()
if not predict_data:
return EmptyMultiLayer().predict(predict_season, latest_episode,
train_seasons)
return self.__predict(predict_season, latest_episode, predict_data,
classifier)
def predict(self, predict_season: int, latest_episode: int,
train_seasons: Set[int]) -> Dict[Player, MultiLayerResult]:
available_seasons = EXAM_DATA.keys()
train_seasons = train_seasons.intersection(available_seasons)
if predict_season not in available_seasons:
return EmptyMultiLayer().predict(predict_season, latest_episode,
train_seasons)
extractor = ExamDropExtractor(predict_season, latest_episode,
train_seasons,
self.__anova_f_significance,
self.__pca_explain, self.__max_splits)
classifier = self.__training(extractor)
predict_data = extractor.get_predict_data()
if not predict_data:
alive_players = EXAM_DATA[predict_season].get_alive_players(
latest_episode)
return EmptyMultiLayer(alive_players).predict(
predict_season, latest_episode, train_seasons)
return self.__predict(predict_season, latest_episode, predict_data,
classifier)
def predict(self, predict_season: int, latest_episode: int,
train_seasons: Set[int]) -> Dict[Player, MultiLayerResult]:
available_seasons = EXAM_DATA.keys()
train_seasons = train_seasons.intersection(available_seasons)
if predict_season not in available_seasons:
return EmptyMultiLayer().predict(predict_season, latest_episode,
train_seasons)
extractor = ExamDropExtractor(predict_season, latest_episode,
train_seasons, self.__min_cluster_size,
self.__spline_curves,
self.__random_generator)
in_classifier, out_classifier = self.__training(extractor)
predict_data = extractor.get_predict_data()
if not predict_data:
alive_players = EXAM_DATA[predict_season].get_alive_players(
latest_episode)
return EmptyMultiLayer(alive_players).predict(
predict_season, latest_episode, train_seasons)
return self.__predict(predict_season, latest_episode, predict_data,
in_classifier, out_classifier)
def __prediction(self, extractor: AppearanceExtractor,
non_mol_kde: gaussian_kde, mol_kde: gaussian_kde,
predict_season: int) -> Dict[Player, MultiLayerResult]:
""" Execute the prediction phase of the Appearance Layer.
Arguments:
extractor (AppearanceExtractor): The extractor which delivers the prediction data.
non_mol_kde (gaussian_kde): The Kernel Density Estimator for non-Mol appearance values.
mol_kde (gaussian_kde): The Kernel Density Estimator for Mol appearance values.
predict_season (int): For which season we make the prediction.
Returns:
A dictionary with as key the players that participated in the prediction season and as value a
MultiLayerResult which contains the predictions.
"""
all_predictions = dict()
predict_data = extractor.get_predict_data()
if not predict_data:
return EmptyMultiLayer().predict(predict_season, 0, set())
min_value = self.get_boundary(non_mol_kde, mol_kde, len(predict_data),
self.__cdf_cutoff / 2, self.MIN_VALUE,
self.MAX_VALUE)
max_value = self.get_boundary(non_mol_kde, mol_kde, len(predict_data),
1 - self.__cdf_cutoff / 2,
self.MIN_VALUE, self.MAX_VALUE)
for player in get_players_in_season(predict_season):
if player in predict_data:
predictions = []
for data in predict_data[player]:
data = min(max(data, min_value), max_value)
non_mol_likelihood = non_mol_kde.pdf(data)[0] * (
len(predict_data) - 1) / len(predict_data)
mol_likelihood = mol_kde.pdf(data)[0] / len(predict_data)
likelihood = mol_likelihood / (non_mol_likelihood +
mol_likelihood)
predictions.append(likelihood)
all_predictions[player] = MultiLayerResult(
np.array(predictions), False)
else:
all_predictions[player] = MultiLayerResult(np.array([]), True)
return all_predictions