def get_orderbook(feed_df: pd.DataFrame, ob_state: dd, ob_state_seq) -> dd:
"""Gets those orders which are still active at the end of the feed"""
# Find those orders which are no longer on the book
# TODO: find those orders which were modified, handle carefully
open_messages = feed_df[feed_df['type'] == 'open']
open_messages['size'] = open_messages['remaining_size']
residual_orders = open_messages[
open_messages['sequence'] > ob_state_seq]
all_orders = ob_state.append(residual_orders)
done_messages = feed_df[feed_df['type'] == 'done']
done_order_ids = list(done_messages['order_id'])
# Find those orders which are still on the book
ob_filtered = all_orders[~all_orders['order_id'].isin(done_order_ids)]
# This variable is used in the pandas query below
# final_trade_price = trades['price'].dropna().iloc[-1]
# ob_final = DataSplitter.get_side("buy", ob_filtered).query('price < @final_trade_price').append(
# DataSplitter.get_side("sell", ob_filtered).query('price > @final_trade_price')
# )
if not OrderBookCreator.check_ob_valid(ob_filtered):
raise AssertionError("OrderBook does not appear to be valid")
final_seq = ob_filtered['sequence'].sort_values().iloc[-1]
return ob_filtered.reset_index(drop=True)[[
'side', 'order_id', 'price', 'size'
]], final_seq
def agg_insert_by_group(data: dd = None,
groupby_columns: List[str] = None,
agg_dict: dict = None,
insert_dict: dict = None) -> dd:
"""
Split input dataframe into groups, apply aggregations on each group according to the aggregation dict,
insert aggregated results back into the original dataframe with column values specified in insert dict
:param data: input dask dataframe
:param groupby_columns: list of column names to group by
:param agg_dict: dictionary of the format {column name: aggregation to preform to column name}
:param insert_dict: dictionary of the format {column name: value of column to be set prior to insertion}
:return: modified datafraeme
"""
agg_data = data.groupby(groupby_columns).agg(agg_dict).reset_index()
agg_data.columns = agg_data.columns.droplevel(1)
for column, value in insert_dict.items():
agg_data[column] = 'COMBINED'
data = data.append(agg_data)
return data