%%time
import numpy as np
import pandas as pd
from pathlib import Path
from sklearn.metrics import mean_absolute_error
from datetime import timedelta
from functools import reduce
from tqdm import tqdm
import lightgbm as lgbm
import mlb
import os
import gc
BASE_DIR = Path('../input/mlb-player-digital-engagement-forecasting')
#train = pd.read_csv(BASE_DIR / 'train_updated.csv')
if os.path.isfile(BASE_DIR / 'train_updated.csv'):
train = pd.read_csv(BASE_DIR / 'train_updated.csv')
print(10*'=','train_updated.csv','load',10*'=')
else:
train = pd.read_csv(BASE_DIR / 'train.csv')
print(10*'=','train.csv','load',10*'=')
null = np.nan
true = True
false = False
for col in ['rosters','nextDayPlayerEngagement','playerBoxScores']:
print(10*'*','this is',col,10*'*')
if col == 'date': continue
_index = train[col].notnull()
train.loc[_index, col] = train.loc[_index, col].apply(lambda x: eval(x))
outputs = []
for index, date, record in train.loc[_index, ['date', col]].itertuples():
_df = pd.DataFrame(record)
_df['index'] = index
_df['date'] = date
outputs.append(_df)
outputs = pd.concat(outputs).reset_index(drop=True)
outputs.to_csv(f'{col}_train.csv', index=False)
outputs.to_pickle(f'{col}_train.pkl')
del outputs
del train[col]
gc.collect()
========== train_updated.csv load ========== ********** this is rosters ********** ********** this is nextDayPlayerEngagement ********** ********** this is playerBoxScores ********** CPU times: user 4min 38s, sys: 14.7 s, total: 4min 52s Wall time: 5min 31s
BASE_DIR = Path('../input/mlb-player-digital-engagement-forecasting')
TRAIN_DIR = Path('./')
players = pd.read_csv(BASE_DIR / 'players.csv')
rosters = pd.read_pickle(TRAIN_DIR / 'rosters_train.pkl')
targets = pd.read_pickle(TRAIN_DIR / 'nextDayPlayerEngagement_train.pkl')
scores = pd.read_pickle(TRAIN_DIR / 'playerBoxScores_train.pkl')
scores = scores.groupby(['playerId', 'date']).sum().reset_index()
targets_cols = ['playerId', 'target1', 'target2', 'target3', 'target4', 'date']
players_cols = ['playerId', 'primaryPositionName','heightInches','weight']
rosters_cols = ['playerId', 'teamId', 'status', 'date']
scores_cols = ['playerId', 'battingOrder', 'gamesPlayedBatting', 'flyOuts',
'groundOuts', 'runsScored', 'doubles', 'triples', 'homeRuns',
'strikeOuts', 'baseOnBalls', 'intentionalWalks', 'hits', 'hitByPitch',
'atBats', 'caughtStealing', 'stolenBases', 'groundIntoDoublePlay',
'groundIntoTriplePlay', 'plateAppearances', 'totalBases', 'rbi',
'leftOnBase', 'sacBunts', 'sacFlies', 'catchersInterference',
'pickoffs', 'gamesPlayedPitching', 'gamesStartedPitching',
'completeGamesPitching', 'shutoutsPitching', 'winsPitching',
'lossesPitching', 'flyOutsPitching', 'airOutsPitching',
'groundOutsPitching', 'runsPitching', 'doublesPitching',
'triplesPitching', 'homeRunsPitching', 'strikeOutsPitching',
'baseOnBallsPitching', 'intentionalWalksPitching', 'hitsPitching',
'hitByPitchPitching', 'atBatsPitching', 'caughtStealingPitching',
'stolenBasesPitching', 'inningsPitched', 'saveOpportunities',
'earnedRuns', 'battersFaced', 'outsPitching', 'pitchesThrown', 'balls',
'strikes', 'hitBatsmen', 'balks', 'wildPitches', 'pickoffsPitching',
'rbiPitching', 'gamesFinishedPitching', 'inheritedRunners',
'inheritedRunnersScored', 'catchersInterferencePitching',
'sacBuntsPitching', 'sacFliesPitching', 'saves', 'holds', 'blownSaves',
'assists', 'putOuts', 'errors', 'chances', 'date']
feature_cols = ['label_playerId', 'label_primaryPositionName', 'label_teamId',
'label_status', 'battingOrder', 'gamesPlayedBatting', 'flyOuts',
'groundOuts', 'runsScored', 'doubles', 'triples', 'homeRuns',
'strikeOuts', 'baseOnBalls', 'intentionalWalks', 'hits', 'hitByPitch',
'atBats', 'caughtStealing', 'stolenBases', 'groundIntoDoublePlay',
'groundIntoTriplePlay', 'plateAppearances', 'totalBases', 'rbi',
'leftOnBase', 'sacBunts', 'sacFlies', 'catchersInterference',
'pickoffs', 'gamesPlayedPitching', 'gamesStartedPitching',
'completeGamesPitching', 'shutoutsPitching', 'winsPitching',
'lossesPitching', 'flyOutsPitching', 'airOutsPitching',
'groundOutsPitching', 'runsPitching', 'doublesPitching',
'triplesPitching', 'homeRunsPitching', 'strikeOutsPitching',
'baseOnBallsPitching', 'intentionalWalksPitching', 'hitsPitching',
'hitByPitchPitching', 'atBatsPitching', 'caughtStealingPitching',
'stolenBasesPitching', 'inningsPitched', 'saveOpportunities',
'earnedRuns', 'battersFaced', 'outsPitching', 'pitchesThrown', 'balls',
'strikes', 'hitBatsmen', 'balks', 'wildPitches', 'pickoffsPitching',
'rbiPitching', 'gamesFinishedPitching', 'inheritedRunners',
'inheritedRunnersScored', 'catchersInterferencePitching',
'sacBuntsPitching', 'sacFliesPitching', 'saves', 'holds', 'blownSaves',
'assists', 'putOuts', 'errors', 'chances','target1_mean',
'target1_median',
'target1_std',
'target1_min',
'target1_max',
'target1_prob',
'target2_mean',
'target2_median',
'target2_std',
'target2_min',
'target2_max',
'target2_prob',
'target3_mean',
'target3_median',
'target3_std',
'target3_min',
'target3_max',
'target3_prob',
'target4_mean',
'target4_median',
'target4_std',
'target4_min',
'target4_max',
'target4_prob']
feature_cols2 = ['label_playerId', 'label_primaryPositionName', 'label_teamId',
'label_status', 'battingOrder', 'gamesPlayedBatting', 'flyOuts',
'groundOuts', 'runsScored', 'doubles', 'triples', 'homeRuns',
'strikeOuts', 'baseOnBalls', 'intentionalWalks', 'hits', 'hitByPitch',
'atBats', 'caughtStealing', 'stolenBases', 'groundIntoDoublePlay',
'groundIntoTriplePlay', 'plateAppearances', 'totalBases', 'rbi',
'leftOnBase', 'sacBunts', 'sacFlies', 'catchersInterference',
'pickoffs', 'gamesPlayedPitching', 'gamesStartedPitching',
'completeGamesPitching', 'shutoutsPitching', 'winsPitching',
'lossesPitching', 'flyOutsPitching', 'airOutsPitching',
'groundOutsPitching', 'runsPitching', 'doublesPitching',
'triplesPitching', 'homeRunsPitching', 'strikeOutsPitching',
'baseOnBallsPitching', 'intentionalWalksPitching', 'hitsPitching',
'hitByPitchPitching', 'atBatsPitching', 'caughtStealingPitching',
'stolenBasesPitching', 'inningsPitched', 'saveOpportunities',
'earnedRuns', 'battersFaced', 'outsPitching', 'pitchesThrown', 'balls',
'strikes', 'hitBatsmen', 'balks', 'wildPitches', 'pickoffsPitching',
'rbiPitching', 'gamesFinishedPitching', 'inheritedRunners',
'inheritedRunnersScored', 'catchersInterferencePitching',
'sacBuntsPitching', 'sacFliesPitching', 'saves', 'holds', 'blownSaves',
'assists', 'putOuts', 'errors', 'chances','target1_mean',
'target1_median',
'target1_std',
'target1_min',
'target1_max',
'target1_prob',
'target2_mean',
'target2_median',
'target2_std',
'target2_min',
'target2_max',
'target2_prob',
'target3_mean',
'target3_median',
'target3_std',
'target3_min',
'target3_max',
'target3_prob',
'target4_mean',
'target4_median',
'target4_std',
'target4_min',
'target4_max',
'target4_prob',
'target1']
player_target_stats = pd.read_csv("../input/my-player-target-stat/player_target_stats.csv")
data_names=player_target_stats.columns.values.tolist()
data_names
['playerId', 'target1_mean', 'target1_median', 'target1_std', 'target1_min', 'target1_max', 'target1_prob', 'target2_mean', 'target2_median', 'target2_std', 'target2_min', 'target2_max', 'target2_prob', 'target3_mean', 'target3_median', 'target3_std', 'target3_min', 'target3_max', 'target3_prob', 'target4_mean', 'target4_median', 'target4_std', 'target4_min', 'target4_max', 'target4_prob']
# creat dataset
train = targets[targets_cols].merge(players[players_cols], on=['playerId'], how='left')
train = train.merge(rosters[rosters_cols], on=['playerId', 'date'], how='left')
train = train.merge(scores[scores_cols], on=['playerId', 'date'], how='left')
train = train.merge(player_target_stats, how='inner', left_on=["playerId"],right_on=["playerId"])
# label encoding
player2num = {c: i for i, c in enumerate(train['playerId'].unique())}
position2num = {c: i for i, c in enumerate(train['primaryPositionName'].unique())}
teamid2num = {c: i for i, c in enumerate(train['teamId'].unique())}
status2num = {c: i for i, c in enumerate(train['status'].unique())}
train['label_playerId'] = train['playerId'].map(player2num)
train['label_primaryPositionName'] = train['primaryPositionName'].map(position2num)
train['label_teamId'] = train['teamId'].map(teamid2num)
train['label_status'] = train['status'].map(status2num)
train_X = train[feature_cols]
train_y = train[['target1', 'target2', 'target3', 'target4']]
#_index = (train['date'] < 20210401)
_index = ((train['date'] > 20200529) & (train['date'] <= 20200831)) | ((train['date'] > 20190529) & (train['date'] <= 20190831)) | ((train['date'] > 20180529) & (train['date'] <= 20180831))
x_train1 = train_X.loc[~_index].reset_index(drop=True)
y_train1 = train_y.loc[~_index].reset_index(drop=True)
x_valid1 = train_X.loc[_index].reset_index(drop=True)
y_valid1 = train_y.loc[_index].reset_index(drop=True)
train_X = train[feature_cols2]
train_y = train[['target1', 'target2', 'target3', 'target4']]
#_index = (train['date'] < 20210401)
x_train2 = train_X.loc[~_index].reset_index(drop=True)
y_train2 = train_y.loc[~_index].reset_index(drop=True)
x_valid2 = train_X.loc[_index].reset_index(drop=True)
y_valid2 = train_y.loc[_index].reset_index(drop=True)
def fit_lgbm(x_train, y_train, x_valid, y_valid, params: dict=None, verbose=100):
oof_pred = np.zeros(len(y_valid), dtype=np.float32)
model = lgbm.LGBMRegressor(**params)
model.fit(x_train, y_train,
eval_set=[(x_valid, y_valid)],
early_stopping_rounds=verbose,
verbose=verbose)
oof_pred = model.predict(x_valid)
score = mean_absolute_error(oof_pred, y_valid)
print('mae:', score)
return oof_pred, model, score
params1 = {'objective':'mae',
'reg_alpha': 0.14547461820098767,
'reg_lambda': 0.10185644384043743,
'n_estimators': 3333,
'learning_rate': 0.1046301304430488,
'num_leaves': 674,
'feature_fraction': 0.8101240539122566,
'bagging_fraction': 0.8884451442950513,
'bagging_freq': 8,
'min_child_samples': 51}
params2 = {
'objective':'mae',
'reg_alpha': 0.14947461820098767,
'reg_lambda': 0.10185644384043743,
'n_estimators': 3633,
'learning_rate': 0.08046301304430488,
'num_leaves': 64,
'feature_fraction': 0.9101240539122566,
'bagging_fraction': 0.9884451442950513,
'bagging_freq': 3,
'min_child_samples': 15
}
params4 = {'objective':'mae',
'reg_alpha': 0.016468100279441976,
'reg_lambda': 0.09128335764019105,
'n_estimators': 9868,
'learning_rate': 0.10528150510326864,
'num_leaves': 157,
'feature_fraction': 0.5419185713426886,
'bagging_fraction': 0.2637405128936662,
'bagging_freq': 19,
'min_child_samples': 71}
params = {
'objective':'mae',
# 'reg_alpha': 0.1,
# 'reg_lambda': 0.1,
'n_estimators': 10000,
'learning_rate': 0.1,
'random_state': 2021,
"num_leaves": 127,
'feature_fraction': 0.5419185713426886,
'bagging_fraction': 0.5637405128936662,
'bagging_freq': 15,
}
oof1, model1, score1 = fit_lgbm(
x_train1, y_train1['target1'],
x_valid1, y_valid1['target1'],
params1
)
oof2, model2, score2 = fit_lgbm(
x_train2, y_train2['target2'],
x_valid2, y_valid2['target2'],
params2
)
oof3, model3, score3 = fit_lgbm(
x_train2, y_train2['target3'],
x_valid2, y_valid2['target3'],
params
)
oof4, model4, score4 = fit_lgbm(
x_train2, y_train2['target4'],
x_valid2, y_valid2['target4'],
params4
)
score = (score1+score2+score3+score4) / 4
print(f'score: {score}')
[LightGBM] [Warning] feature_fraction is set=0.8101240539122566, colsample_bytree=1.0 will be ignored. Current value: feature_fraction=0.8101240539122566 [LightGBM] [Warning] bagging_freq is set=8, subsample_freq=0 will be ignored. Current value: bagging_freq=8 [LightGBM] [Warning] bagging_fraction is set=0.8884451442950513, subsample=1.0 will be ignored. Current value: bagging_fraction=0.8884451442950513 Training until validation scores don't improve for 100 rounds [100] valid_0's l1: 0.603681 [200] valid_0's l1: 0.602494 [300] valid_0's l1: 0.602064 [400] valid_0's l1: 0.602072 [500] valid_0's l1: 0.601976 [600] valid_0's l1: 0.601959 [700] valid_0's l1: 0.601676 Early stopping, best iteration is: [673] valid_0's l1: 0.601666 mae: 0.6016661242531858 [LightGBM] [Warning] feature_fraction is set=0.9101240539122566, colsample_bytree=1.0 will be ignored. Current value: feature_fraction=0.9101240539122566 [LightGBM] [Warning] bagging_freq is set=3, subsample_freq=0 will be ignored. Current value: bagging_freq=3 [LightGBM] [Warning] bagging_fraction is set=0.9884451442950513, subsample=1.0 will be ignored. Current value: bagging_fraction=0.9884451442950513 Training until validation scores don't improve for 100 rounds [100] valid_0's l1: 1.72755 [200] valid_0's l1: 1.71505 [300] valid_0's l1: 1.71076 [400] valid_0's l1: 1.70847 [500] valid_0's l1: 1.70694 [600] valid_0's l1: 1.70668 [700] valid_0's l1: 1.7052 [800] valid_0's l1: 1.70479 [900] valid_0's l1: 1.70432 [1000] valid_0's l1: 1.7037 [1100] valid_0's l1: 1.703 [1200] valid_0's l1: 1.70253 [1300] valid_0's l1: 1.70207 [1400] valid_0's l1: 1.702 [1500] valid_0's l1: 1.70185 [1600] valid_0's l1: 1.7011 [1700] valid_0's l1: 1.70071 [1800] valid_0's l1: 1.70073 [1900] valid_0's l1: 1.70063 [2000] valid_0's l1: 1.7004 [2100] valid_0's l1: 1.70023 [2200] valid_0's l1: 1.69993 Early stopping, best iteration is: [2192] valid_0's l1: 1.69993 mae: 1.699927207171509 [LightGBM] [Warning] bagging_fraction is set=0.5637405128936662, subsample=1.0 will be ignored. Current value: bagging_fraction=0.5637405128936662 [LightGBM] [Warning] feature_fraction is set=0.5419185713426886, colsample_bytree=1.0 will be ignored. Current value: feature_fraction=0.5419185713426886 [LightGBM] [Warning] bagging_freq is set=15, subsample_freq=0 will be ignored. Current value: bagging_freq=15 Training until validation scores don't improve for 100 rounds [100] valid_0's l1: 0.715969 [200] valid_0's l1: 0.714891 [300] valid_0's l1: 0.714887 [400] valid_0's l1: 0.714884 [500] valid_0's l1: 0.714883 [600] valid_0's l1: 0.714882 [700] valid_0's l1: 0.714879 [800] valid_0's l1: 0.714878 [900] valid_0's l1: 0.714714 [1000] valid_0's l1: 0.714713 [1100] valid_0's l1: 0.714712 [1200] valid_0's l1: 0.714711 [1300] valid_0's l1: 0.714711 [1400] valid_0's l1: 0.71471 [1500] valid_0's l1: 0.714709 [1600] valid_0's l1: 0.714709 [1700] valid_0's l1: 0.71455 [1800] valid_0's l1: 0.71455 [1900] valid_0's l1: 0.714549 [2000] valid_0's l1: 0.714549 [2100] valid_0's l1: 0.714548 [2200] valid_0's l1: 0.714548 [2300] valid_0's l1: 0.714547 [2400] valid_0's l1: 0.714547 [2500] valid_0's l1: 0.714546 [2600] valid_0's l1: 0.714546 [2700] valid_0's l1: 0.714545 [2800] valid_0's l1: 0.714545 [2900] valid_0's l1: 0.714544 [3000] valid_0's l1: 0.714543 [3100] valid_0's l1: 0.714543 [3200] valid_0's l1: 0.714543 [3300] valid_0's l1: 0.714542 [3400] valid_0's l1: 0.714542 [3500] valid_0's l1: 0.714543 Early stopping, best iteration is: [3473] valid_0's l1: 0.714542 mae: 0.7145421805738932 [LightGBM] [Warning] feature_fraction is set=0.5419185713426886, colsample_bytree=1.0 will be ignored. Current value: feature_fraction=0.5419185713426886 [LightGBM] [Warning] bagging_freq is set=19, subsample_freq=0 will be ignored. Current value: bagging_freq=19 [LightGBM] [Warning] bagging_fraction is set=0.2637405128936662, subsample=1.0 will be ignored. Current value: bagging_fraction=0.2637405128936662 Training until validation scores don't improve for 100 rounds [100] valid_0's l1: 0.82029 [200] valid_0's l1: 0.817858 [300] valid_0's l1: 0.816503 [400] valid_0's l1: 0.815647 [500] valid_0's l1: 0.815143 [600] valid_0's l1: 0.814731 [700] valid_0's l1: 0.814472 [800] valid_0's l1: 0.814144 [900] valid_0's l1: 0.813819 [1000] valid_0's l1: 0.813664 [1100] valid_0's l1: 0.813584 Early stopping, best iteration is: [1053] valid_0's l1: 0.813545 mae: 0.8135446889692893 score: 0.9574200502419693
import pickle
from catboost import CatBoostRegressor
def fit_lgbm(x_train, y_train, x_valid, y_valid, target, params: dict=None, verbose=100):
oof_pred_lgb = np.zeros(len(y_valid), dtype=np.float32)
oof_pred_cat = np.zeros(len(y_valid), dtype=np.float32)
if os.path.isfile(f'../input/mlb-lightgbm-training/mymodel_lgb_{target}.pkl'):
with open(f'../input/mlb-lightgbm-training/mymodel_lgb_{target}.pkl', 'rb') as fin:
model = pickle.load(fin)
oof_pred_lgb = model.predict(x_valid)
score_lgb = mean_absolute_error(oof_pred_lgb, y_valid)
print('*'*10,fin,'*'*10)
print('mae:', score_lgb)
else:
with open(f'mymodel_lgb_{target}.pkl', 'wb') as handle:
pickle.dump(model, handle, protocol=pickle.HIGHEST_PROTOCOL)
if os.path.isfile(f'../input/mlb-catboost-training/mymodel_cb_{target}.pkl'):
with open(f'../input/mlb-catboost-training/mymodel_cb_{target}.pkl', 'rb') as fin:
model_cb = pickle.load(fin)
oof_pred_cat = model_cb.predict(x_valid)
score_cat = mean_absolute_error(oof_pred_cat, y_valid)
print('*'*10,fin,'*'*10)
print('mae:', score_cat)
else:
with open(f'model_cb_{target}.pkl', 'wb') as handle:
pickle.dump(model_cb, handle, protocol=pickle.HIGHEST_PROTOCOL)
return oof_pred_lgb, model, oof_pred_cat, model_cb, score_lgb, score_cat
params = {
'boosting_type': 'gbdt',
'objective':'mae',
'subsample': 0.6,
'subsample_freq': 1,
'learning_rate': 0.03,
'num_leaves': 2**11-1,
'min_data_in_leaf': 2**12-1,
'feature_fraction': 0.6,
'max_bin': 100,
'n_estimators': 2500,
'boost_from_average': False,
"random_seed":2021,
}
oof_pred_lgb2, model_lgb2, oof_pred_cat2, model_cb2, score_lgb2, score_cat2 = fit_lgbm(
x_train1, y_train1['target2'],
x_valid1, y_valid1['target2'],
2, params
)
oof_pred_lgb1, model_lgb1, oof_pred_cat1, model_cb1, score_lgb1, score_cat1 = fit_lgbm(
x_train1, y_train1['target1'],
x_valid1, y_valid1['target1'],
1, params
)
oof_pred_lgb3, model_lgb3, oof_pred_cat3, model_cb3, score_lgb3, score_cat3 = fit_lgbm(
x_train1, y_train1['target3'],
x_valid1, y_valid1['target3'],
3, params
)
oof_pred_lgb4, model_lgb4, oof_pred_cat4, model_cb4, score_lgb4, score_cat4= fit_lgbm(
x_train1, y_train1['target4'],
x_valid1, y_valid1['target4'],
4, params
)
score = (score_lgb1+score_lgb2+score_lgb3+score_lgb4) / 4
print(f'LightGBM score: {score}')
score = (score_cat1+score_cat2+score_cat3+score_cat4) / 4
print(f'Catboost score: {score}')
********** <_io.BufferedReader name='../input/mlb-lightgbm-training/mymodel_lgb_2.pkl'> ********** mae: 1.7495870137280762 ********** <_io.BufferedReader name='../input/mlb-catboost-training/mymodel_cb_2.pkl'> ********** mae: 1.8092167805205939 ********** <_io.BufferedReader name='../input/mlb-lightgbm-training/mymodel_lgb_1.pkl'> ********** mae: 0.613446416791378 ********** <_io.BufferedReader name='../input/mlb-catboost-training/mymodel_cb_1.pkl'> ********** mae: 0.6265251914020156 ********** <_io.BufferedReader name='../input/mlb-lightgbm-training/mymodel_lgb_3.pkl'> ********** mae: 0.7371395237381603 ********** <_io.BufferedReader name='../input/mlb-catboost-training/mymodel_cb_3.pkl'> ********** mae: 0.7406471371942968 ********** <_io.BufferedReader name='../input/mlb-lightgbm-training/mymodel_lgb_4.pkl'> ********** mae: 0.8178008821616221 ********** <_io.BufferedReader name='../input/mlb-catboost-training/mymodel_cb_4.pkl'> ********** mae: 0.846635209540955 LightGBM score: 0.9794934591048092 Catboost score: 1.0057560796644653
players_cols = ['playerId', 'primaryPositionName']
rosters_cols = ['playerId', 'teamId', 'status']
scores_cols = ['playerId', 'battingOrder', 'gamesPlayedBatting', 'flyOuts',
'groundOuts', 'runsScored', 'doubles', 'triples', 'homeRuns',
'strikeOuts', 'baseOnBalls', 'intentionalWalks', 'hits', 'hitByPitch',
'atBats', 'caughtStealing', 'stolenBases', 'groundIntoDoublePlay',
'groundIntoTriplePlay', 'plateAppearances', 'totalBases', 'rbi',
'leftOnBase', 'sacBunts', 'sacFlies', 'catchersInterference',
'pickoffs', 'gamesPlayedPitching', 'gamesStartedPitching',
'completeGamesPitching', 'shutoutsPitching', 'winsPitching',
'lossesPitching', 'flyOutsPitching', 'airOutsPitching',
'groundOutsPitching', 'runsPitching', 'doublesPitching',
'triplesPitching', 'homeRunsPitching', 'strikeOutsPitching',
'baseOnBallsPitching', 'intentionalWalksPitching', 'hitsPitching',
'hitByPitchPitching', 'atBatsPitching', 'caughtStealingPitching',
'stolenBasesPitching', 'inningsPitched', 'saveOpportunities',
'earnedRuns', 'battersFaced', 'outsPitching', 'pitchesThrown', 'balls',
'strikes', 'hitBatsmen', 'balks', 'wildPitches', 'pickoffsPitching',
'rbiPitching', 'gamesFinishedPitching', 'inheritedRunners',
'inheritedRunnersScored', 'catchersInterferencePitching',
'sacBuntsPitching', 'sacFliesPitching', 'saves', 'holds', 'blownSaves',
'assists', 'putOuts', 'errors', 'chances']
null = np.nan
true = True
false = False
import pandas as pd
import numpy as np
from datetime import timedelta
from tqdm import tqdm
import gc
from functools import reduce
from sklearn.model_selection import StratifiedKFold
ROOT_DIR = "../input/mlb-player-digital-engagement-forecasting"
#=======================#
def flatten(df, col):
du = (df.pivot(index="playerId", columns="EvalDate",
values=col).add_prefix(f"{col}_").
rename_axis(None, axis=1).reset_index())
return du
#============================#
def reducer(left, right):
return left.merge(right, on="playerId")
#========================
TGTCOLS = ["target1","target2","target3","target4"]
def train_lag(df, lag=1):
dp = df[["playerId","EvalDate"]+TGTCOLS].copy()
dp["EvalDate"] =dp["EvalDate"] + timedelta(days=lag)
df = df.merge(dp, on=["playerId", "EvalDate"], suffixes=["",f"_{lag}"], how="left")
return df
#=================================
def test_lag(sub):
sub["playerId"] = sub["date_playerId"].apply(lambda s: int( s.split("_")[1] ) )
assert sub.date.nunique() == 1
dte = sub["date"].unique()[0]
eval_dt = pd.to_datetime(dte, format="%Y%m%d")
dtes = [eval_dt + timedelta(days=-k) for k in LAGS]
mp_dtes = {eval_dt + timedelta(days=-k):k for k in LAGS}
sl = LAST.loc[LAST.EvalDate.between(dtes[-1], dtes[0]), ["EvalDate","playerId"]+TGTCOLS].copy()
sl["EvalDate"] = sl["EvalDate"].map(mp_dtes)
du = [flatten(sl, col) for col in TGTCOLS]
du = reduce(reducer, du)
return du, eval_dt
#
#===============
tr = pd.read_csv("../input/my-mlb-data/target.csv")
print(tr.shape)
gc.collect()
tr["EvalDate"] = pd.to_datetime(tr["EvalDate"])
tr["EvalDate"] = tr["EvalDate"] + timedelta(days=-1)
tr["EvalYear"] = tr["EvalDate"].dt.year
MED_DF = tr.groupby(["playerId","EvalYear"])[TGTCOLS].median().reset_index()
MEDCOLS = ["tgt1_med","tgt2_med", "tgt3_med", "tgt4_med"]
MED_DF.columns = ["playerId","EvalYear"] + MEDCOLS
LAGS = list(range(1,21))
FECOLS = [f"{col}_{lag}" for lag in reversed(LAGS) for col in TGTCOLS]
for lag in tqdm(LAGS):
tr = train_lag(tr, lag=lag)
gc.collect()
#===========
tr = tr.sort_values(by=["playerId", "EvalDate"])
print(tr.shape)
tr = tr.dropna()
print(tr.shape)
tr = tr.merge(MED_DF, on=["playerId","EvalYear"])
gc.collect()
X = tr[FECOLS+MEDCOLS].values
y = tr[TGTCOLS].values
cl = tr["playerId"].values
NFOLDS = 5
skf = StratifiedKFold(n_splits=NFOLDS)
folds = skf.split(X, cl)
folds = list(folds)
import tensorflow as tf
import tensorflow.keras.layers as L
import tensorflow.keras.models as M
from sklearn.metrics import mean_absolute_error, mean_squared_error
from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau, EarlyStopping
tf.random.set_seed(2021)
def make_model(n_in):
inp = L.Input(name="inputs", shape=(n_in,))
x = L.Dense(50, activation="relu", name="d1")(inp)
x = L.Dense(50, activation="relu", name="d2")(x)
preds = L.Dense(4, activation="linear", name="preds")(x)
model = M.Model(inp, preds, name="ANN")
model.compile(loss="mean_absolute_error", optimizer="adam")
return model
net = make_model(X.shape[1])
print(net.summary())
oof = np.zeros(y.shape)
nets = []
for idx in range(NFOLDS):
print("FOLD:", idx)
tr_idx, val_idx = folds[idx]
ckpt = ModelCheckpoint(f"../input/mlb-ann-training/w{idx}.h5", monitor='val_loss', verbose=1, save_best_only=True,mode='min')
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2,patience=3, min_lr=0.0001)
es = EarlyStopping(monitor='val_loss', patience=5)
reg = make_model(X.shape[1])
# reg.fit(X[tr_idx], y[tr_idx], epochs=10, batch_size=30_000, validation_data=(X[val_idx], y[val_idx]),
# verbose=1, callbacks=[ckpt, reduce_lr, es])
reg.load_weights(f"../input/mlb-ann-training/w{idx}.h5")
oof[val_idx] = reg.predict(X[val_idx], batch_size=50_000, verbose=1)
nets.append(reg)
gc.collect()
mae = mean_absolute_error(y, oof)
mse = mean_squared_error(y, oof, squared=False)
print("mae:", mae)
print("mse:", mse)
# Historical information to use in prediction time
bound_dt = pd.to_datetime("2021-01-01")
LAST = tr.loc[tr.EvalDate>bound_dt].copy()
LAST_MED_DF = MED_DF.loc[MED_DF.EvalYear==2021].copy()
LAST_MED_DF.drop("EvalYear", axis=1, inplace=True)
del tr
#"""
import mlb
FE = []; SUB = [];
(2506176, 6)
100%|██████████| 20/20 [01:08<00:00, 3.43s/it]
(2506176, 87) (2464956, 87) Model: "ANN" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= inputs (InputLayer) [(None, 84)] 0 _________________________________________________________________ d1 (Dense) (None, 50) 4250 _________________________________________________________________ d2 (Dense) (None, 50) 2550 _________________________________________________________________ preds (Dense) (None, 4) 204 ================================================================= Total params: 7,004 Trainable params: 7,004 Non-trainable params: 0 _________________________________________________________________ None FOLD: 0 10/10 [==============================] - 0s 17ms/step FOLD: 1 10/10 [==============================] - 0s 14ms/step FOLD: 2 10/10 [==============================] - 0s 15ms/step FOLD: 3 10/10 [==============================] - 0s 14ms/step FOLD: 4 10/10 [==============================] - 0s 16ms/step mae: 0.7727517316297969 mse: 3.9314386784209567
import copy
env = mlb.make_env() # initialize the environment
iter_test = env.iter_test() # iterator which loops over each date in test set
for (test_df, sample_prediction_df) in iter_test: # make predictions here
sub = copy.deepcopy(sample_prediction_df.reset_index())
sample_prediction_df = copy.deepcopy(sample_prediction_df.reset_index(drop=True))
# LGBM summit
# creat dataset
sample_prediction_df['playerId'] = sample_prediction_df['date_playerId']\
.map(lambda x: int(x.split('_')[1]))
# Dealing with missing values
if test_df['rosters'].iloc[0] == test_df['rosters'].iloc[0]:
test_rosters = pd.DataFrame(eval(test_df['rosters'].iloc[0]))
else:
test_rosters = pd.DataFrame({'playerId': sample_prediction_df['playerId']})
for col in rosters.columns:
if col == 'playerId': continue
test_rosters[col] = np.nan
if test_df['playerBoxScores'].iloc[0] == test_df['playerBoxScores'].iloc[0]:
test_scores = pd.DataFrame(eval(test_df['playerBoxScores'].iloc[0]))
else:
test_scores = pd.DataFrame({'playerId': sample_prediction_df['playerId']})
for col in scores.columns:
if col == 'playerId': continue
test_scores[col] = np.nan
test_scores = test_scores.groupby('playerId').sum().reset_index()
test = sample_prediction_df[['playerId']].copy()
test = test.merge(players[players_cols], on='playerId', how='left')
test = test.merge(test_rosters[rosters_cols], on='playerId', how='left')
test = test.merge(test_scores[scores_cols], on='playerId', how='left')
test = test.merge(player_target_stats, how='inner', left_on=["playerId"],right_on=["playerId"])
test['label_playerId'] = test['playerId'].map(player2num)
test['label_primaryPositionName'] = test['primaryPositionName'].map(position2num)
test['label_teamId'] = test['teamId'].map(teamid2num)
test['label_status'] = test['status'].map(status2num)
test_X = test[feature_cols]
# predict
pred1 = model1.predict(test_X)
# predict
pred_lgd1 = model_lgb1.predict(test_X)
pred_lgd2 = model_lgb2.predict(test_X)
pred_lgd3 = model_lgb3.predict(test_X)
pred_lgd4 = model_lgb4.predict(test_X)
pred_cat1 = model_cb1.predict(test_X)
pred_cat2 = model_cb2.predict(test_X)
pred_cat3 = model_cb3.predict(test_X)
pred_cat4 = model_cb4.predict(test_X)
test['target1'] = np.clip(pred1,0,100)
test_X = test[feature_cols2]
pred2 = model2.predict(test_X)
pred3 = model3.predict(test_X)
pred4 = model4.predict(test_X)
# merge submission
sample_prediction_df['target1'] = 1.00*np.clip(pred1, 0, 100)+0.00*np.clip(pred_lgd1, 0, 100)+0.00*np.clip(pred_cat1, 0, 100)
sample_prediction_df['target2'] = 0.05*np.clip(pred2, 0, 100)+0.54*np.clip(pred_lgd2, 0, 100)+0.405*np.clip(pred_cat2, 0, 100)
sample_prediction_df['target3'] = 0.76*np.clip(pred3, 0, 100)+0.14*np.clip(pred_lgd3, 0, 100)+0.10*np.clip(pred_cat3, 0, 100)
sample_prediction_df['target4'] = 0.77*np.clip(pred4, 0, 100)+0.13*np.clip(pred_lgd4, 0, 100)+0.10*np.clip(pred_cat4, 0, 100)
sample_prediction_df = sample_prediction_df.fillna(0.)
del sample_prediction_df['playerId']
# TF summit
# Features computation at Evaluation Date
sub_fe, eval_dt = test_lag(sub)
sub_fe = sub_fe.merge(LAST_MED_DF, on="playerId", how="left")
sub_fe = sub_fe.fillna(0.)
_preds = 0.
for reg in nets:
_preds += reg.predict(sub_fe[FECOLS + MEDCOLS]) / NFOLDS
sub_fe[TGTCOLS] = np.clip(_preds, 0, 100)
sub.drop(["date"]+TGTCOLS, axis=1, inplace=True)
sub = sub.merge(sub_fe[["playerId"]+TGTCOLS], on="playerId", how="left")
sub.drop("playerId", axis=1, inplace=True)
sub = sub.fillna(0.)
# Blending
blend = pd.concat(
[sub[['date_playerId']],
(0.22*sub.drop('date_playerId', axis=1) + 0.78*sample_prediction_df.drop('date_playerId', axis=1))],
axis=1
)
env.predict(blend)
# Update Available information
sub_fe["EvalDate"] = eval_dt
#sub_fe.drop(MEDCOLS, axis=1, inplace=True)
LAST = LAST.append(sub_fe)
LAST = LAST.drop_duplicates(subset=["EvalDate","playerId"], keep="last")
This version of the API is not optimized and should not be used to estimate the runtime of your code on the hidden test set.
pd.concat(
[sub[['date_playerId']],
(sub.drop('date_playerId', axis=1) + sample_prediction_df.drop('date_playerId', axis=1)) / 2],
axis=1
)
date_playerId | target1 | target2 | target3 | target4 | |
---|---|---|---|---|---|
0 | 20210501_488726 | 1.417833 | 5.650557 | 6.859939e-02 | 1.995048 |
1 | 20210501_605218 | 0.003536 | 0.396355 | 1.702673e-03 | 0.868064 |
2 | 20210501_621563 | 0.099256 | 2.386864 | 7.695223e-02 | 0.771513 |
3 | 20210501_670084 | 0.022301 | 0.878644 | 6.095328e-04 | 0.277289 |
4 | 20210501_670970 | 0.010307 | 0.251098 | 2.952593e-02 | 0.118300 |
... | ... | ... | ... | ... | ... |
1182 | 20210501_596049 | 0.000276 | 0.009644 | 2.608818e-12 | 0.035421 |
1183 | 20210501_642851 | 0.000176 | 0.041358 | 1.818041e-07 | 0.079906 |
1184 | 20210501_596071 | 0.000451 | 0.083687 | 1.183390e-04 | 0.070381 |
1185 | 20210501_664901 | 0.003308 | 0.309083 | 3.068393e-02 | 0.199449 |
1186 | 20210501_605525 | 0.002655 | 0.555847 | 4.771943e-04 | 0.116648 |
1187 rows × 5 columns
sample_prediction_df
date_playerId | target1 | target2 | target3 | target4 | |
---|---|---|---|---|---|
0 | 20210501_488726 | 2.728486e+00 | 8.022509 | 1.070538e-01 | 2.425154 |
1 | 20210501_605218 | 2.152436e-03 | 0.566561 | 3.182109e-03 | 0.828016 |
2 | 20210501_621563 | 1.422361e-01 | 2.763233 | 1.348766e-02 | 0.880154 |
3 | 20210501_670084 | 2.031692e-03 | 0.647363 | 1.219066e-03 | 0.119984 |
4 | 20210501_670970 | 5.941349e-04 | 0.162923 | 9.765327e-03 | 0.048072 |
... | ... | ... | ... | ... | ... |
1182 | 20210501_596049 | 9.109051e-15 | 0.016895 | 5.217635e-12 | 0.032081 |
1183 | 20210501_642851 | 0.000000e+00 | 0.072513 | 3.636082e-07 | 0.081339 |
1184 | 20210501_596071 | 1.820810e-04 | 0.109463 | 1.856178e-05 | 0.085482 |
1185 | 20210501_664901 | 6.615386e-03 | 0.358820 | 3.113339e-03 | 0.202974 |
1186 | 20210501_605525 | 8.827960e-04 | 0.593431 | 4.494436e-10 | 0.107011 |
1187 rows × 5 columns