def finish(cls):
dv.fit(all_players)
for (g, y, w) in all_games:
this_games_players = list()
for p in g.players:
this_games_players.append({'name': p.__dict__["name"]})
rows = dv.transform(this_games_players)
result_array = None
for row in rows:
if result_array == None:
result_array = row
else:
result_array = result_array + row
features.append(result_array.toarray()[0])
labels_home.append(g.score_home)
labels_away.append(g.score_away)
pca.fit(features)
for (home, away, week, year) in future_games:
rows = dv.transform(last_known_players[home] + last_known_players[away])
result_array = None
for row in rows:
if result_array == None:
result_array = row
else:
result_array = result_array + row
futures_home.append({
'name': home,
'features': pca.transform(result_array.toarray()[0])
})
futures_away.append({
'name': away,
'features': pca.transform(result_array.toarray()[0])
})
train_home = (np.array(pca.transform(features)), np.array(labels_home,))
train_away = (np.array(pca.transform(features)), np.array(labels_away,))
dir_name = os.path.dirname(Transformer.get_pickle_filename(cls.__name__))
train_home_name = os.path.join(dir_name, "train_home.pickle.gz")
train_away_name = os.path.join(dir_name, "train_away.pickle.gz")
future_home_name = os.path.join(dir_name, "futures_home.pickle.gz")
future_away_name = os.path.join(dir_name, "futures_away.pickle.gz")
cPickle.dump(train_home, gzip.open(train_home_name,'wb'), cPickle.HIGHEST_PROTOCOL)
cPickle.dump(train_away, gzip.open(train_away_name,'wb'), cPickle.HIGHEST_PROTOCOL)
cPickle.dump(futures_home, gzip.open(future_home_name,'wb'), cPickle.HIGHEST_PROTOCOL)
cPickle.dump(futures_away, gzip.open(future_away_name,'wb'), cPickle.HIGHEST_PROTOCOL)
def finish(cls):
df = pd.DataFrame.from_dict(rows)
df.index.name = "index"
df.to_csv(Transformer.get_csv_filename(cls.__name__))
df.to_pickle(Transformer.get_pickle_filename(cls.__name__))
