def main(debug=False, use_pkl=False):
num_rows = 10000 if debug else None
if use_pkl:
df = loadpkl('../output/df.pkl')
else:
with timer("train & test"):
df = train_test(num_rows)
with timer("nightley"):
df = pd.merge(df, nightley(num_rows), on=['datetime', 'park'], how='outer')
with timer("hotlink"):
df = pd.merge(df, hotlink(num_rows), on='datetime', how='outer')
with timer("colopl"):
df = pd.merge(df, colopl(num_rows), on=['park', 'year', 'month'], how='outer')
with timer("weather"):
df = pd.merge(df, weather(num_rows), on=['datetime', 'park'], how='outer')
with timer("nied_oyama"):
df = pd.merge(df, nied_oyama(num_rows), on=['datetime', 'park'], how='outer')
with timer("agoop"):
df = pd.merge(df, agoop(num_rows), on=['park', 'year','month'], how='outer')
with timer("jorudan"):
df = pd.merge(df, jorudan(num_rows), on=['datetime', 'park'], how='outer')
with timer("save pkl"):
save2pkl('../output/df.pkl', df)
with timer("Run XGBoost with kfold"):
print("df shape:", df.shape)
feat_importance = kfold_xgboost(df, num_folds=NUM_FOLDS, stratified=True, debug=debug)
display_importances(feat_importance ,'../output/xgb_importances.png', '../output/feature_importance_xgb.csv')
################################################################################
# optunaによるhyper parameter最適化
# 参考: https://github.com/pfnet/optuna/blob/master/examples/lightgbm_simple.py
################################################################################
NUM_ROWS = None
USE_PKL = True
if USE_PKL:
DF = loadpkl('../output/df.pkl')
else:
DF = train_test(NUM_ROWS)
DF = pd.merge(DF, nightley(NUM_ROWS), on=['datetime', 'park'], how='outer')
DF = pd.merge(DF, hotlink(NUM_ROWS), on='datetime', how='outer')
DF = pd.merge(DF, colopl(NUM_ROWS), on=['year', 'month'], how='outer')
DF = pd.merge(DF, weather(NUM_ROWS), on=['datetime', 'park'], how='outer')
DF = pd.merge(DF,
nied_oyama(NUM_ROWS),
on=['datetime', 'park'],
how='outer')
DF = pd.merge(DF,
agoop(num_rows),
on=['park', 'year', 'month'],
how='outer')
DF = pd.merge(DF, jorudan(num_rows), on=['datetime', 'park'], how='outer')
# split test & train
TRAIN_DF = DF[DF['visitors'].notnull()]
FEATS = [f for f in TRAIN_DF.columns if f not in FEATS_EXCLUDED]