gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-17 21:08:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(Linter): reformatted code with black (#211)

Browse Source 
* chore(Linter): reformatted code with black

* Create black.yaml
This commit is contained in:
Mark Aron Szulyovszky
2022-02-17 19:22:17 +01:00
committed by GitHub
parent f3fee4a4e1
commit 8dd2d88740
101 changed files with 2595 additions and 2319 deletions
Download Patch File Download Diff File Expand all files Collapse all files
feature_extractors/feature_extractor_presets.py
+47 -27
View File
@@ -1,35 +1,55 @@
from .types import FeatureExtractorConfig
from .feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_expanding_zscore, feature_vol, feature_day_of_month, feature_day_of_week, feature_month, feature_debug_future_lookahead
from .fractional_differentiation import feature_fractional_differentiation, feature_fractional_differentiation_log
from .feature_extractors import (
feature_lag,
feature_mom,
feature_ROC,
feature_RSI,
feature_STOD,
feature_STOK,
feature_expanding_zscore,
feature_vol,
feature_day_of_month,
feature_day_of_week,
feature_month,
feature_debug_future_lookahead,
)
from .fractional_differentiation import (
feature_fractional_differentiation,
feature_fractional_differentiation_log,
)
__presets = dict(
debug_future_lookahead = [('debug_future', feature_debug_future_lookahead, [1])],
single_mom = [('mom', feature_mom, [30])],
single_vol = [('vol', feature_vol, [30])],
mom = [('mom', feature_mom, [10, 20, 30, 60, 90])],
vol = [('vol', feature_vol, [10, 20, 30, 60])],
lags_up_to_5 = [('lag', feature_lag, [1,2,3,4,5])],
lags_up_to_10 = [('lag', feature_lag, [1,2,3,4,5,6,7,8,9,10])],
date_all = [
('day_of_week', feature_day_of_week, [0]),
('day_of_month', feature_day_of_month, [0]),
('month', feature_month, [0])],
date_days = [
('day_of_week', feature_day_of_week, [0]),
('day_of_month', feature_day_of_month, [0]),
debug_future_lookahead=[("debug_future", feature_debug_future_lookahead, [1])],
single_mom=[("mom", feature_mom, [30])],
single_vol=[("vol", feature_vol, [30])],
mom=[("mom", feature_mom, [10, 20, 30, 60, 90])],
vol=[("vol", feature_vol, [10, 20, 30, 60])],
lags_up_to_5=[("lag", feature_lag, [1, 2, 3, 4, 5])],
lags_up_to_10=[("lag", feature_lag, [1, 2, 3, 4, 5, 6, 7, 8, 9, 10])],
date_all=[
("day_of_week", feature_day_of_week, [0]),
("day_of_month", feature_day_of_month, [0]),
("month", feature_month, [0]),
],
roc = [('roc', feature_ROC, [10, 30])],
rsi = [('rsi', feature_ROC, [10, 30, 100])],
stod = [('stod', feature_STOD, [10, 30, 200])],
stok = [('stok', feature_STOK, [10, 30, 200])],
fracdiff = [('fracdiff', feature_fractional_differentiation, [10, 30])],
fracdiff_log = [('fracdiff_log', feature_fractional_differentiation_log, [10, 30])],
z_score = [('z_score', feature_expanding_zscore, [10])],
date_days=[
("day_of_week", feature_day_of_week, [0]),
("day_of_month", feature_day_of_month, [0]),
],
roc=[("roc", feature_ROC, [10, 30])],
rsi=[("rsi", feature_ROC, [10, 30, 100])],
stod=[("stod", feature_STOD, [10, 30, 200])],
stok=[("stok", feature_STOK, [10, 30, 200])],
fracdiff=[("fracdiff", feature_fractional_differentiation, [10, 30])],
fracdiff_log=[("fracdiff_log", feature_fractional_differentiation_log, [10, 30])],
z_score=[("z_score", feature_expanding_zscore, [10])],
)
presets = __presets | dict(
level_1 = __presets["mom"] + __presets["vol"],
level_2 = __presets["mom"] + __presets["vol"] + __presets["roc"] + __presets["rsi"] + __presets["stod"] + __presets["stok"],
level_1=__presets["mom"] + __presets["vol"],
level_2=__presets["mom"]
+ __presets["vol"]
+ __presets["roc"]
+ __presets["rsi"]
+ __presets["stod"]
+ __presets["stok"],
)
feature_extractors/feature_extractors.py
+46 -19
View File
@@ -3,58 +3,85 @@ import numpy as np
from feature_extractors.utils import get_close_low_high
from feature_extractors.utils import apply_log_if_necessary_series
def feature_debug_future_lookahead(df: pd.DataFrame, period: int) -> pd.Series:
return df['returns'].shift(-period)
return df["returns"].shift(-period)
def feature_lag(df: pd.DataFrame, period: int) -> pd.Series:
assert period > 0
return df['returns'].shift(period)
return df["returns"].shift(period)
def feature_expanding_zscore(df: pd.DataFrame, period: int) -> pd.Series:
close = df['close']
close = df["close"]
return (close - close.expanding(period).mean()) / close.expanding(period).std()
def feature_day_of_week(df: pd.DataFrame, period: int) -> pd.DataFrame:
return pd.get_dummies(pd.DatetimeIndex(df.index).dayofweek, drop_first=True, prefix="date_day_week").set_index(df.index)
return pd.get_dummies(
pd.DatetimeIndex(df.index).dayofweek, drop_first=True, prefix="date_day_week"
).set_index(df.index)
def feature_day_of_month(df: pd.DataFrame, period: int) -> pd.DataFrame:
return pd.get_dummies(pd.DatetimeIndex(df.index).day, drop_first=True, prefix="date_day_month").set_index(df.index)
return pd.get_dummies(
pd.DatetimeIndex(df.index).day, drop_first=True, prefix="date_day_month"
).set_index(df.index)
def feature_month(df: pd.DataFrame, period: int) -> pd.DataFrame:
return pd.get_dummies(pd.DatetimeIndex(df.index).month, drop_first=True, prefix="date_month").set_index(df.index)
return pd.get_dummies(
pd.DatetimeIndex(df.index).month, drop_first=True, prefix="date_month"
).set_index(df.index)
def feature_vol(df: pd.DataFrame, period: int) -> pd.Series:
return df['returns'].rolling(period).std() * (252**0.5)
return df["returns"].rolling(period).std() * (252**0.5)
def feature_mom(df: pd.DataFrame, period: int) -> pd.Series:
return np.log(df['close']).diff(period)
return np.log(df["close"]).diff(period)
def feature_STOK(df: pd.DataFrame, period: int) -> pd.Series:
close, low, high = get_close_low_high(df)
STOK = ((close - low.rolling(period).min()) / (high.rolling(period).max() - low.rolling(period).min())) * 100
STOK = (
(close - low.rolling(period).min())
/ (high.rolling(period).max() - low.rolling(period).min())
) * 100
return apply_log_if_necessary_series(STOK, "stok")
def feature_STOD(df: pd.DataFrame, period: int) -> pd.Series:
stok = feature_STOK(df, period)
return stok.rolling(3).mean()
def feature_RSI(df: pd.DataFrame, period: int) -> pd.Series:
returns = df['returns']
returns = df["returns"]
delta = returns.diff().dropna()
u=delta*0
u = delta * 0
d = u.copy()
u[delta > 0] = delta[delta > 0]
d[delta < 0] = -delta[delta < 0]
u[u.index[period-1]] = np.mean( u[:period] ) #first value is sum of avg gains u = u.drop(u.index[:(period-1)])
d[d.index[period-1]] = np.mean( d[:period] ) #first value is sum of avg losses d = d.drop(d.index[:(period-1)])
rs = u.ewm(com=period-1, adjust=False).mean() / \
d.ewm(com=period-1, adjust=False).mean()
return apply_log_if_necessary_series(100-100/(1+rs), "rsi")
u[u.index[period - 1]] = np.mean(
u[:period]
) # first value is sum of avg gains u = u.drop(u.index[:(period-1)])
d[d.index[period - 1]] = np.mean(
d[:period]
) # first value is sum of avg losses d = d.drop(d.index[:(period-1)])
rs = (
u.ewm(com=period - 1, adjust=False).mean()
/ d.ewm(com=period - 1, adjust=False).mean()
)
return apply_log_if_necessary_series(100 - 100 / (1 + rs), "rsi")
def feature_ROC(df: pd.DataFrame, period: int) -> pd.Series:
returns = df['returns']
returns = df["returns"]
M = returns.diff(period - 1)
N = returns.shift(period - 1)
roc = pd.Series(((M / N) * 100), name = 'ROC_' + str(period))
return apply_log_if_necessary_series(roc, "roc")
roc = pd.Series(((M / N) * 100), name="ROC_" + str(period))
return apply_log_if_necessary_series(roc, "roc")
feature_extractors/fractional_differentiation.py
+4 -3
View File
@@ -3,13 +3,14 @@ import pandas as pd
import numpy as np
from feature_extractors.utils import apply_log_if_necessary_series
def feature_fractional_differentiation(df: pd.DataFrame, period: int) -> pd.Series:
frac_diff = FracdiffStat(window = period)
frac_diff = FracdiffStat(window=period)
input_series = df["close"].to_numpy().reshape(-1, 1)
result = frac_diff.fit_transform(input_series)
return pd.Series(result.squeeze(), index = df.index)
return pd.Series(result.squeeze(), index=df.index)
def feature_fractional_differentiation_log(df: pd.DataFrame, period: int) -> pd.Series:
series = feature_fractional_differentiation(df, period, is_log_return)
return apply_log_if_necessary_series(series, "fracdiff")
feature_extractors/ta.py
+1
View File
@@ -2,6 +2,7 @@ import pandas_ta as ta
import pandas as pd
from feature_extractors.utils import get_close_low_high
def feature_EBSW(df: pd.DataFrame, period: int) -> pd.Series:
close, low, high = get_close_low_high(df)
feature_extractors/types.py
+1 -1
View File
@@ -6,4 +6,4 @@ IsLogReturn = bool
FeatureExtractor = Callable[[pd.DataFrame, Period], Union[pd.DataFrame, pd.Series]]
Name = str
FeatureExtractorConfig = tuple[Name, FeatureExtractor, list[Period]]
ScalerTypes = Literal['normalize', 'minmax', 'standardize', 'none']
ScalerTypes = Literal["normalize", "minmax", "standardize", "none"]
feature_extractors/utils.py
+4 -3
View File
@@ -2,10 +2,11 @@ import pandas as pd
import numpy as np
from scipy.stats import shapiro
def get_close_low_high(df: pd.DataFrame) -> tuple[pd.Series, pd.Series, pd.Series]:
close = df['close']
low = df['low']
high = df['high']
close = df["close"]
low = df["low"]
high = df["high"]
return close, low, high