def get_test_df(parameters={}):
from kaggle.competitions import nflrush
env = nflrush.make_env()
test_df_list = []
for (test_df, sample_prediction_df) in env.iter_test():
test_df_list.append(test_df)
env.predict(sample_prediction_df)
test_df = pd.concat(test_df_list)
return test_df
def infer(model, base_probas=None, transformer=None, parameters={}):
from kaggle.competitions import nflrush
env = nflrush.make_env()
for (test_df, sample_prediction_df) in env.iter_test():
test_df = preprocess(test_df)
if transformer is not None:
test_df = transformer.transform(test_df)
sample_prediction_df.iloc[0, :] = _predict_cdf(test_df, model, base_probas, parameters)
env.predict(sample_prediction_df)
env.write_submission_file()
return sample_prediction_df
def predict(x_te):
model_num = len(models)
for k, m in enumerate(models):
if k == 0:
y_pred = m.predict(x_te, batch_size=1024)
else:
y_pred += m.predict(x_te, batch_size=1024)
y_pred = y_pred / model_num
return y_pred
if TRAIN_OFFLINE == False:
from kaggle.competitions import nflrush
env = nflrush.make_env()
iter_test = env.iter_test()
for (test_df, sample_prediction_df) in tqdm(iter_test):
basetable = create_features(test_df, deploy=True)
basetable.drop(['GameId', 'PlayId'], axis=1, inplace=True)
scaled_basetable = scaler.transform(basetable)
y_pred = predict(scaled_basetable)
y_pred = np.clip(np.cumsum(y_pred, axis=1), 0, 1).tolist()[0]
preds_df = pd.DataFrame(data=[y_pred],
columns=sample_prediction_df.columns)
env.predict(preds_df)
env.write_submission_file()