|
|
@@ -855,7 +855,7 @@ def preprocess_data_simple(df_input, is_train=False):
|
|
|
df_input = df_input[~((df_input['is_filled'] == 1) & (_tail_filled == 1))]
|
|
|
|
|
|
# 价格变化最小量阈值
|
|
|
- price_change_amount_threshold = 5
|
|
|
+ price_change_amount_threshold = 1
|
|
|
df_input['_raw_price_diff'] = df_input.groupby(['gid', 'baggage'], group_keys=False)['adult_total_price'].diff()
|
|
|
|
|
|
# 计算价格变化量
|
|
|
@@ -1457,7 +1457,7 @@ def predict_data_simple(df_input, group_route_str, output_dir, predict_dir=".",
|
|
|
# 要展示在预测表里的字段
|
|
|
order_cols = ['city_pair', 'flight_day', 'flight_number_1', 'flight_number_2', 'from_time',
|
|
|
'baggage', 'seats_remaining', 'currency',
|
|
|
- 'adult_total_price', 'days_to_departure', 'hours_until_departure', 'price_change_percent', 'price_duration_hours',
|
|
|
+ 'adult_total_price', 'days_to_departure', 'hours_until_departure', 'price_change_percent', 'price_change_amount', 'price_duration_hours',
|
|
|
'update_hour', 'crawl_date',
|
|
|
'valid_begin_hour', 'valid_end_hour',
|
|
|
'simple_will_price_drop', 'simple_drop_in_hours', 'simple_drop_in_hours_prob', 'simple_drop_in_hours_dist',
|
node04