gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-12 18:38:06 +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
labeling/event_filters/cusum.py
+14 -13
View File
@@ -1,5 +1,3 @@
from numpy import float32
from ..types import EventFilter
from data_loader.types import ReturnSeries
@@ -7,8 +5,8 @@ import pandas as pd
from numba import njit
from numba.typed import List
class CUSUMVolatilityEventFilter(EventFilter):
class CUSUMVolatilityEventFilter(EventFilter):
def __init__(self, vol_period: int):
self.vol_period = vol_period
@@ -36,34 +34,37 @@ class CUSUMVolatilityEventFilter(EventFilter):
return pd.DatetimeIndex(filtered_indices)
class CUSUMFixedEventFilter(EventFilter):
class CUSUMFixedEventFilter(EventFilter):
def __init__(self, threshold: float):
self.threshold = threshold
def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
diffed_returns = returns.diff()
int_indicies = _process(List(diffed_returns.to_list()), abs(returns.mean()) * self.threshold)
int_indicies = _process(
List(diffed_returns.to_list()), abs(returns.mean()) * self.threshold
)
return pd.DatetimeIndex([returns.index[i] for i in int_indicies])
@njit
def _process(diffed_returns: List, threshold: float32) -> List:
pos_threshold: float32 = 0.0 # type: ignore
neg_threshold: float32 = 0.0 # type: ignore
pos_threshold: float32 = 0.0 # type: ignore
neg_threshold: float32 = 0.0 # type: ignore
filtered_indicies = List()
for index in range(1, len(diffed_returns[1:])):
pos_threshold, neg_threshold = ( # type: ignore
max(0, pos_threshold + diffed_returns[index]), # type: ignore
min(0, neg_threshold + diffed_returns[index]), # type: ignore
pos_threshold, neg_threshold = ( # type: ignore
max(0, pos_threshold + diffed_returns[index]), # type: ignore
min(0, neg_threshold + diffed_returns[index]), # type: ignore
)
if neg_threshold < -threshold:
neg_threshold = 0.0 # type: ignore
neg_threshold = 0.0 # type: ignore
filtered_indicies.append(index)
elif pos_threshold > threshold:
pos_threshold = 0.0 # type: ignore
pos_threshold = 0.0 # type: ignore
filtered_indicies.append(index)
return filtered_indicies
return filtered_indicies
labeling/event_filters/nofilter.py
+1 -2
View File
@@ -2,8 +2,7 @@ from ..types import EventFilter
from data_loader.types import ReturnSeries
import pandas as pd
class NoEventFilter(EventFilter):
class NoEventFilter(EventFilter):
def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
return returns.index
labeling/eventfilters_map.py
+4 -4
View File
@@ -2,7 +2,7 @@ from .event_filters.nofilter import NoEventFilter
from .event_filters.cusum import CUSUMVolatilityEventFilter, CUSUMFixedEventFilter
eventfilters_map = dict(
none = NoEventFilter(),
cusum_vol = CUSUMVolatilityEventFilter(vol_period = 20),
cusum_fixed = CUSUMFixedEventFilter(threshold = 500)
)
none=NoEventFilter(),
cusum_vol=CUSUMVolatilityEventFilter(vol_period=20),
cusum_fixed=CUSUMFixedEventFilter(threshold=500),
)
labeling/labellers/fixed_time_three_class_balanced.py
+19 -10
View File
@@ -3,6 +3,7 @@ from ..types import EventLabeller, EventsDataFrame
import pandas as pd
from .utils import create_forward_returns
class FixedTimeHorionThreeClassBalancedEventLabeller(EventLabeller):
time_horizon: int
@@ -10,7 +11,9 @@ class FixedTimeHorionThreeClassBalancedEventLabeller(EventLabeller):
def __init__(self, time_horizon: int):
self.time_horizon = time_horizon
def label_events(self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries) -> tuple[EventsDataFrame, ForwardReturnSeries]:
def label_events(
self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries
) -> tuple[EventsDataFrame, ForwardReturnSeries]:
forward_returns = create_forward_returns(returns, self.time_horizon)
cutoff_point = returns.index[-self.time_horizon]
@@ -18,7 +21,7 @@ class FixedTimeHorionThreeClassBalancedEventLabeller(EventLabeller):
event_candidates = forward_returns[event_start_times]
def get_bins_threeway(x):
bins = pd.qcut(event_candidates, 3, retbins=True, duplicates = 'drop')[1]
bins = pd.qcut(event_candidates, 3, retbins=True, duplicates="drop")[1]
if len(bins) != 4:
# if we don't have enough data for the quantiles, we'll need to add hard-coded values
@@ -26,6 +29,7 @@ class FixedTimeHorionThreeClassBalancedEventLabeller(EventLabeller):
upper_bound = bins[-1]
bins = [lower_bound] + [-0.02, 0.02] + [upper_bound]
return bins
bins = get_bins_threeway(event_candidates)
def map_class_threeway(current_value):
@@ -37,12 +41,17 @@ class FixedTimeHorionThreeClassBalancedEventLabeller(EventLabeller):
return 0
else:
return 1
labels = event_candidates.map(map_class_threeway)
return (pd.DataFrame({
'start': event_start_times,
'end': event_start_times + pd.Timedelta(days=self.time_horizon),
'label': labels,
'returns': forward_returns[event_start_times]
}), forward_returns[event_start_times])
labels = event_candidates.map(map_class_threeway)
return (
pd.DataFrame(
{
"start": event_start_times,
"end": event_start_times + pd.Timedelta(days=self.time_horizon),
"label": labels,
"returns": forward_returns[event_start_times],
}
),
forward_returns[event_start_times],
)
labeling/labellers/fixed_time_three_class_imbalanced.py
+18 -10
View File
@@ -2,6 +2,7 @@ from ..types import EventLabeller, EventsDataFrame, ReturnSeries, ForwardReturnS
import pandas as pd
from .utils import create_forward_returns
class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
time_horizon: int
@@ -9,7 +10,9 @@ class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
def __init__(self, time_horizon: int):
self.time_horizon = time_horizon
def label_events(self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries) -> tuple[EventsDataFrame, ForwardReturnSeries]:
def label_events(
self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries
) -> tuple[EventsDataFrame, ForwardReturnSeries]:
forward_returns = create_forward_returns(returns, self.time_horizon)
cutoff_point = returns.index[-self.time_horizon]
@@ -17,7 +20,7 @@ class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
event_candidates = forward_returns[event_start_times]
def get_bins_threeway(x):
bins = pd.qcut(event_candidates, 4, retbins=True, duplicates = 'drop')[1]
bins = pd.qcut(event_candidates, 4, retbins=True, duplicates="drop")[1]
if len(bins) != 5:
# if we don't have enough data for the quantiles, we'll need to add hard-coded values
@@ -25,6 +28,7 @@ class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
upper_bound = bins[-1]
bins = [lower_bound] + [-0.02, 0.0, 0.02] + [upper_bound]
return bins
bins = get_bins_threeway(event_candidates)
def map_class_threeway(current_value):
@@ -36,13 +40,17 @@ class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
return 0
else:
return 1
labels = event_candidates.map(map_class_threeway)
return (pd.DataFrame({
'start': event_start_times,
'end': event_start_times + pd.Timedelta(days=self.time_horizon),
'label': labels,
'returns': forward_returns[event_start_times]
}), forward_returns[event_start_times])
return (
pd.DataFrame(
{
"start": event_start_times,
"end": event_start_times + pd.Timedelta(days=self.time_horizon),
"label": labels,
"returns": forward_returns[event_start_times],
}
),
forward_returns[event_start_times],
)
labeling/labellers/fixed_time_two_class.py
+16 -10
View File
@@ -2,6 +2,7 @@ from ..types import EventLabeller, EventsDataFrame, ReturnSeries, ForwardReturnS
import pandas as pd
from .utils import create_forward_returns
class FixedTimeHorionTwoClassEventLabeller(EventLabeller):
time_horizon: int
@@ -9,7 +10,9 @@ class FixedTimeHorionTwoClassEventLabeller(EventLabeller):
def __init__(self, time_horizon: int):
self.time_horizon = time_horizon
def label_events(self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries) -> tuple[EventsDataFrame, ForwardReturnSeries]:
def label_events(
self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries
) -> tuple[EventsDataFrame, ForwardReturnSeries]:
forward_returns = create_forward_returns(returns, self.time_horizon)
cutoff_point = returns.index[-self.time_horizon]
@@ -18,14 +21,17 @@ class FixedTimeHorionTwoClassEventLabeller(EventLabeller):
def get_class_binary(x: float) -> int:
return -1 if x <= 0.0 else 1
labels = event_candidates.map(get_class_binary)
return (pd.DataFrame({
'start': event_start_times,
'end': event_start_times + pd.Timedelta(days=self.time_horizon),
'label': labels,
'returns': forward_returns[event_start_times]
}), forward_returns[event_start_times])
return (
pd.DataFrame(
{
"start": event_start_times,
"end": event_start_times + pd.Timedelta(days=self.time_horizon),
"label": labels,
"returns": forward_returns[event_start_times],
}
),
forward_returns[event_start_times],
)
labeling/labellers/utils.py
+3 -2
View File
@@ -1,9 +1,10 @@
import pandas as pd
from data_loader.types import ForwardReturnSeries
def create_forward_returns(series: pd.Series, period: int) -> ForwardReturnSeries:
assert period > 0
indexer = pd.api.indexers.FixedForwardWindowIndexer(window_size=period)
forward_returns = series.rolling(window=indexer).sum()
return forward_returns
return forward_returns
labeling/labellers_map.py
+10 -6
View File
@@ -1,9 +1,13 @@
from .labellers.fixed_time_three_class_balanced import FixedTimeHorionThreeClassBalancedEventLabeller
from .labellers.fixed_time_three_class_imbalanced import FixedTimeHorionThreeClassImbalancedEventLabeller
from .labellers.fixed_time_three_class_balanced import (
FixedTimeHorionThreeClassBalancedEventLabeller,
)
from .labellers.fixed_time_three_class_imbalanced import (
FixedTimeHorionThreeClassImbalancedEventLabeller,
)
from .labellers.fixed_time_two_class import FixedTimeHorionTwoClassEventLabeller
labellers_map = dict(
two_class = FixedTimeHorionTwoClassEventLabeller,
three_class_balanced = FixedTimeHorionThreeClassBalancedEventLabeller,
three_class_imbalanced = FixedTimeHorionThreeClassImbalancedEventLabeller
)
two_class=FixedTimeHorionTwoClassEventLabeller,
three_class_balanced=FixedTimeHorionThreeClassBalancedEventLabeller,
three_class_imbalanced=FixedTimeHorionThreeClassImbalancedEventLabeller,
)
labeling/process.py
+17 -11
View File
@@ -1,19 +1,25 @@
from .types import EventFilter, EventLabeller, EventsDataFrame
from data_loader.types import ForwardReturnSeries, XDataFrame, ReturnSeries, ySeries
def label_data(
event_filter: EventFilter,
event_labeller: EventLabeller,
X: XDataFrame,
returns: ReturnSeries) -> tuple[EventsDataFrame, XDataFrame, ySeries, ForwardReturnSeries]:
event_filter: EventFilter,
event_labeller: EventLabeller,
X: XDataFrame,
returns: ReturnSeries,
) -> tuple[EventsDataFrame, XDataFrame, ySeries, ForwardReturnSeries]:
event_start_times = event_filter.get_event_start_times(returns)
print("| Filtered out ", (1 - (len(event_start_times) / len(returns))) * 100, "% of timestamps" )
event_start_times = event_filter.get_event_start_times(returns)
print(
"| Filtered out ",
(1 - (len(event_start_times) / len(returns))) * 100,
"% of timestamps",
)
events, forward_returns = event_labeller.label_events(event_start_times, returns)
events, forward_returns = event_labeller.label_events(event_start_times, returns)
X = X.filter(items = events.index, axis = 0)
y = events['label']
forward_returns = events['returns']
X = X.filter(items=events.index, axis=0)
y = events["label"]
forward_returns = events["returns"]
return events, X, y, forward_returns
return events, X, y, forward_returns
labeling/types.py
+5 -4
View File
@@ -4,8 +4,8 @@ import pandas as pd
import pandera as pa
from pandera.typing import DataFrame, Series
class EventFilter(ABC):
class EventFilter(ABC):
@abstractmethod
def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
raise NotImplementedError
@@ -17,12 +17,13 @@ class EventSchema(pa.SchemaModel):
label: Series[int]
returns: Series[float]
EventsDataFrame = DataFrame[EventSchema]
class EventLabeller(ABC):
@abstractmethod
def label_events(self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries) -> tuple[EventsDataFrame, ForwardReturnSeries]:
def label_events(
self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries
) -> tuple[EventsDataFrame, ForwardReturnSeries]:
raise NotImplementedError