def get_candles_for_feature(candle_types, start_dt, end_dt):
candles_for_feature = {}
for candle_type in candle_types:
candles = API().get_candles(pair, candle_type=candle_type,
start_dt=(start_dt - timedelta(1)).strftime('%Y-%m-%d %H:%M:%S'),
end_dt=end_dt.strftime('%Y-%m-%d %H:%M:%S'))
candles = pd.DataFrame(candles, columns=['open', 'high', 'low', 'close', 'volume', 'timestamp'])
candles.index = candles.timestamp.map(lambda x: datetime.fromtimestamp(x / 1000))
candles_for_feature[candle_type] = candles
return candles_for_feature
def summary_messages(self, start_dt, end_dt):
messages_summary = {}
pair = 'xrp_jpy'
candle_types = ['1min', '5min', '15min', '30min', '1hour']
for candle_type in candle_types:
candles = API().get_candles(pair, candle_type, start_dt, end_dt)
candles = pd.DataFrame(candles, columns=['open', 'high', 'low', 'close', 'volume', 'timestamp'])
candles.index = candles['timestamp']
messages_summary[candle_type] = candles
return messages_summary
def extract_feature(start_dt, end_dt, pair, candle_types, df_all=None):
features_all = None
for candle_type in candle_types:
params = get_params(candle_type)
if df_all is not None:
logger.debug('candle type: {}'.format(candle_type))
candles = df_all[candle_type]
candles.index = candles.timestamp.map(lambda x: datetime.fromtimestamp(x / 1000))
# 時刻ごとに特徴量を算出（並列処理）
args = [(candles[(d - timedelta(minutes=130) <= candles.index) & (candles.index <= d)], params, candle_type, d) for d in datetimerange(str2dt(start_dt), str2dt(end_dt) + timedelta(minutes=1))]
tmp_features = multi_process(args)
# 必要な時間のみ抽出
features = None
dts = [d for d in datetimerange(str2dt(start_dt), str2dt(end_dt) + timedelta(minutes=1))]
for dt, tmp_feature in zip(dts, tmp_features):
feature = tmp_feature[tmp_feature.index == dt]
if features is None:
features = feature
else:
features = pd.concat([features, feature])
del tmp_features
gc.collect()
else:
start_dt_ext = (datetime.strptime(start_dt, '%Y-%m-%d %H:%M:%S') - timedelta(minutes=130)).strftime('%Y-%m-%d %H:%M:%S')
candles = API().get_candles(pair, candle_type=candle_type, start_dt=start_dt_ext, end_dt=end_dt)
candles = pd.DataFrame(candles, columns=['open', 'high', 'low', 'close', 'volume', 'timestamp'])
candles.index = candles.timestamp.map(lambda x: datetime.fromtimestamp(x / 1000))
candles.to_csv('candles_{}_{}.csv'.format(end_dt, candle_type))
features = _extract_feature(candles, params, candle_type, end_dt)
features.to_csv('features_{}_{}.csv'.format(end_dt, candle_type))
'''
features = features.loc[(start_dt <= features.index) & (features.index <= end_dt)]
'''
features.columns = [c + '_' + candle_type for c in features.columns]
if features_all is None:
features_all = features
else:
features_all = pd.concat([features_all, features], axis=1)
features_all = features_all.fillna(method='ffill')
del features
gc.collect()
return features_all