print('------------------------ 模型训练 start time:{}'.format(time_str))
# submit = train_model_lgb(feature_all, recall_rate=hit_rate, hot_list=hot_list, valid=0.2, topk=50, num_boost_round=1, early_stopping_rounds=1)
# submit = train_model_rf(train_test, recall_rate=1, hot_list=hot_list, valid=0.2, topk=50)
model = rank_rf(train_x, train_y)
# model = rank_xgb(train_x, train_y)
print('train set: auc:{}'.format(
roc_auc_score(train_y,
model.predict_proba(train_x)[:, 1])))
with open('./cache/rf.pickle', 'wb') as f:
pickle.dump(model, f)
''' 模型验证 '''
print('------------------------ 模型验证 start time:{}'.format(time_str))
time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
pre_y = model.predict_proba(valid_x)[:, 1]
print('valid set: auc:{}'.format(roc_auc_score(valid_y, pre_y)))
answer = make_answer(valid_df[valid_df['label'] == 1], hot_df, phase=1)
my_eval(pre_y, valid_df, answer)
# ''' qtime 提交集 特征 '''
# for phase in range(0, conf.now_phase + 1):
# pass
print('------------------------ underexpose_test_qtime 预测 start time:{}'.
format(time_str))
submit_all = pd.DataFrame()
for phase in range(0, conf.now_phase + 1):
print('----------------------- phase:{} -------------------------'.
format(phase))
if conf.is_recall_cached:
one_phase_recall_item_df = \
pd.read_csv(conf.recall_cache_path.format(phase), dtype={'user_id': np.int, 'item_id': np.int})
def _get_model(params):
feature_df = params.get("feature")
hot_df = params.get("hot_df")
eta = None
if 'eta' in params:
eta = params['eta']
min_child_weight = None
if 'min_child_weight' in params:
min_child_weight = params['min_child_weight']
max_depth = None
if 'max_depth' in params:
max_depth = int(params['max_depth'])
gamma = None
if 'gamma' in params:
gamma = params['gamma']
subsample = None
if 'subsample' in params:
subsample = params['subsample']
colsample_bytree = None
if 'colsample_bytree' in params:
colsample_bytree = params['colsample_bytree']
reg_lambda = None
if 'reg_lambda' in params:
reg_lambda = params['reg_lambda']
scale_pos_weight = None
if 'scale_pos_weight' in params:
scale_pos_weight = params['scale_pos_weight']
tree_method = None
if 'tree_method' in params:
tree_method = params['tree_method']
n_estimators = None
if 'n_estimators' in params:
n_estimators = int(params['n_estimators'])
train_auc = valid_auc = 0
pre_score_arr = np.zeros(5).reshape(-1, )
rank_score_arr = np.zeros(5).reshape(-1, )
for i in range(conf.k):
''' 训练集/验证集划分 '''
train_df, valid_df = featuring.train_test_split(feature_df, seed=1)
train_x = train_df[train_df.columns.difference(
['user_id', 'item_id', 'label'])].values
train_y = train_df['label'].values
valid_df = valid_df.sort_values('sim').reset_index(drop=True)
valid_x = valid_df[valid_df.columns.difference(
['user_id', 'item_id', 'label'])].values
valid_y = valid_df['label'].values
''' 模型训练 '''
model = rank.rank_xgb(train_x,
train_y,
eta=eta,
min_child_weight=min_child_weight,
max_depth=max_depth,
gamma=gamma,
subsample=subsample,
colsample_bytree=colsample_bytree,
reg_lambda=reg_lambda,
scale_pos_weight=scale_pos_weight,
tree_method=tree_method,
n_estimators=n_estimators)
one_train_auc = roc_auc_score(train_y,
model.predict_proba(train_x)[:, 1])
train_auc += one_train_auc
''' 模型验证 '''
pre_y = model.predict_proba(valid_x)[:, 1]
one_valid_auc = roc_auc_score(valid_y, pre_y)
valid_auc += one_valid_auc
answer = eval.make_answer(valid_df[valid_df['label'] == 1],
hot_df,
phase=1)
pre_score_arr += eval.my_eval(list(valid_df['sim']),
valid_df,
answer,
print_mark=False)
rank_score_arr += eval.my_eval(pre_y,
valid_df,
answer,
print_mark=False)
avg_valid_auc = valid_auc / conf.k
avg_pre_ndcg = pre_score_arr / conf.k
avg_rank_ndcg = rank_score_arr / conf.k
diff = avg_rank_ndcg - avg_pre_ndcg
print('avg valid auc:{}, ndcg full gain:{}, ndcg half gain:{}'.format(
avg_valid_auc, diff[0], diff[2]))
return -diff[2]