feat(Data): added daily_glassnode DataCollection (#99)

feature_extractors/feature_extractor_presets.py

@@ -31,10 +31,3 @@ presets = __presets | dict(
     level_2 = __presets["mom"] + __presets["vol"] + __presets["roc"] + __presets["rsi"] + __presets["stod"] + __presets["stok"],
 )
 
-def preprocess_feature_extractors_config(data_dict: dict) -> dict:
-    data_dict = data_dict.copy()
-    keys = ['own_features', 'other_features']
-    for key in keys:
-        preset_names = data_dict[key]
-        data_dict[key] = flatten([presets[preset_name] for preset_name in preset_names])
-    return data_dict

feature_extractors/feature_extractors.py

@@ -1,15 +1,6 @@
 import pandas as pd
 import numpy as np
-
-## Utility functions
-
-def __get_close_low_high(df: pd.DataFrame) -> tuple[pd.Series, pd.Series, pd.Series]:
-    close = df['close']
-    low = df['low']
-    high = df['high']
-    return close, low, high
-
-## Feature extractors
+from feature_extractors.utils import get_close_low_high
 
 def feature_debug_future_lookahead(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
     return df['returns'].shift(-period)
@@ -37,7 +28,7 @@ def feature_mom(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series
         return df['close'].pct_change(period)
 
 def feature_STOK(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
-    close, low, high = __get_close_low_high(df)
+    close, low, high = get_close_low_high(df)
 
     STOK = ((close - low.rolling(period).min()) / (high.rolling(period).max() - low.rolling(period).min())) * 100
     return STOK

feature_extractors/fractional_differentiation.py

@@ -3,8 +3,7 @@ import pandas as pd
 import numpy as np
 
 def feature_fractional_differentiation(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
-    feature_selector = FracdiffStat(window = period)
+    frac_diff = FracdiffStat(window = period)
     input_series = df["close"].to_numpy().reshape(-1, 1)
-    feature_selector.fit(input_series)
-    result = feature_selector.transform(input_series)
-    return pd.Series(np.log(result.squeeze()), index = df.index)
+    result = frac_diff.fit_transform(input_series)
+    return pd.Series(result.squeeze(), index = df.index)

feature_extractors/ta.py

@@ -0,0 +1,8 @@
+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, is_log_return: bool) -> pd.Series:
+    close, low, high = get_close_low_high(df)
+
+    return ta.ebsw(close, period)

feature_extractors/utils.py

@@ -0,0 +1,7 @@
+import pandas as pd
+
+def get_close_low_high(df: pd.DataFrame) -> tuple[pd.Series, pd.Series, pd.Series]:
+    close = df['close']
+    low = df['low']
+    high = df['high']
+    return close, low, high