def concat_pred_item(T, dryrun=False):
if T==-1:
name = 'test'
else:
name = 'trainT-'+str(T)
df = utils.load_pred_item(name)
df = pd.merge(df, pd.read_pickle('../feature/{}/f317_user-product.p'.format(name)),
on=['user_id', 'product_id'],how='left')
gc.collect()
#==============================================================================
print('output')
#==============================================================================
if dryrun == True:
return df
else:
utils.to_pickles(df, '../feature/{}/all_apdx'.format(name), 20, inplace=True)
'silent':1,
'nthread':27,
# 'scale_pos_weight':y_build.mean(),
# 'eval_metric':'auc',
'eval_metric':'logloss',
'objective':'binary:logistic',
'tree_method':'hist'}
print("""#==== print param ======""")
print('seed:', seed)
#==============================================================================
# prepare
#==============================================================================
train = pd.concat([utils.load_pred_item('trainT-0', True).sample(frac=.1),
utils.load_pred_item('trainT-1', True).sample(frac=.1)
], ignore_index=True, join='inner')
#train = utils.load_pred_item('trainT-0')
sub_train = train[['order_id', 'product_id', 'y']]
y_train = train['y']
X_train = train.drop('y', axis=1)
del train
gc.collect()
# drop id
col = [c for c in X_train.columns if '_id' in c] + ['is_train']
col.remove('user_id')
print('drop1',col)
X_train.drop(col, axis=1, inplace=True) # keep user_id
'silent': 1,
'nthread': 27,
'eval_metric': 'logloss',
'objective': 'binary:logistic',
'tree_method': 'hist'
}
print("""#==== print param ======""")
print('DATE:', DATE)
print('seed:', seed)
#==============================================================================
# prepare
#==============================================================================
train = pd.concat([
utils.load_pred_item('trainT-0'),
utils.load_pred_item('trainT-1'),
utils.load_pred_item('trainT-2')
],
ignore_index=True)
y_train = train['y']
X_train = train.drop('y', axis=1)
del train
gc.collect()
# drop id
col = [c for c in X_train.columns if '_id' in c] + ['is_train']
col.remove('user_id')
print('drop1', col)
X_train.drop(col, axis=1, inplace=True) # keep user_id
'nthread': 27,
# 'scale_pos_weight':y_build.mean(),
# 'eval_metric':'auc',
'eval_metric': 'logloss',
'objective': 'binary:logistic',
'tree_method': 'hist'
}
print("""#==== print param ======""")
print('seed:', seed)
#==============================================================================
# prepare
#==============================================================================
train = pd.concat([
utils.load_pred_item('trainT-0', True).sample(frac=.1),
utils.load_pred_item('trainT-1', True).sample(frac=.1)
],
ignore_index=True,
join='inner')
#train = utils.load_pred_item('trainT-0')
sub_train = train[['order_id', 'product_id', 'y']]
y_train = train['y']
X_train = train.drop('y', axis=1)
del train
gc.collect()
# drop id
col = [c for c in X_train.columns if '_id' in c] + ['is_train']
col.remove('user_id')
'subsample':0.75,
'silent':1,
'nthread':27,
'eval_metric':'logloss',
'objective':'binary:logistic',
'tree_method':'hist'
}
print("""#==== print param ======""")
print('DATE:', DATE)
print('seed:', seed)
#==============================================================================
# prepare
#==============================================================================
train = pd.concat([utils.load_pred_item('trainT-0'),
utils.load_pred_item('trainT-1'),
utils.load_pred_item('trainT-2')
], ignore_index=True)
y_train = train['y']
X_train = train.drop('y', axis=1)
#X_train = pd.merge(train.drop('y', axis=1),
# pd.read_pickle('../output/sub/811_1/train_stack_item.p').drop('y', axis=1),
# on=['order_id', 'product_id'], how='left')
del train
gc.collect()
# drop id
col = [c for c in X_train.columns if '_id' in c] + ['is_train']
col.remove('user_id')