virgo-modules 0.1.3__py3-none-any.whl → 0.2.2__py3-none-any.whl

virgo_modules/src/transformer_utils.py

@@ -0,0 +1,250 @@
+from sklearn.base import BaseEstimator, TransformerMixin
+import pandas as pd
+import numpy as np
+
+class InverseHyperbolicSine(BaseEstimator, TransformerMixin):
+
+    """
+    Class that applies inverse hyperbolic sine for feature transformation.
+    this class is compatible with scikitlearn pipeline
+
+    Attributes
+    ----------
+    features : list
+        list of features to apply the transformation
+    prefix : str
+        prefix for the new features. is '' the features are overwrite
+
+    Methods
+    -------
+    fit(additional="", X=DataFrame, y=None):
+        fit transformation.
+    transform(X=DataFrame, y=None):
+        apply feature transformation
+    """
+
+    def __init__(self, features, prefix = ''):
+        self.features = features
+        self.prefix = prefix
+
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X, y=None):
+        for feature in self.features:
+            X[f'{self.prefix}{feature}'] = np.arcsinh(X[feature])
+        return X
+
+class VirgoWinsorizerFeature(BaseEstimator, TransformerMixin):
+
+    """
+    Class that applies winsorirization of a feature for feature transformation.
+    this class is compatible with scikitlearn pipeline
+
+    Attributes
+    ----------
+    feature_configs : dict
+        dictionary of features and configurations. the configuration has high and low limits per feature
+
+    Methods
+    -------
+    fit(additional="", X=DataFrame, y=None):
+        fit transformation.
+    transform(X=DataFrame, y=None):
+        apply feature transformation
+    """
+
+    def __init__(self, feature_configs):
+        self.feature_configs = feature_configs
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X, y=None):
+        for feature in self.feature_configs:
+            lower = self.feature_configs[feature]['min']
+            upper = self.feature_configs[feature]['max']
+            X[feature] = np.where( lower > X[feature], lower, X[feature])
+            X[feature] = np.where( upper < X[feature], upper, X[feature])
+        return X
+
+class FeatureSelector(BaseEstimator, TransformerMixin):
+
+    """
+    Class that applies selection of features.
+    this class is compatible with scikitlearn pipeline
+
+    Attributes
+    ----------
+    columns : list
+        list of features to select
+
+    Methods
+    -------
+    fit(additional="", X=DataFrame, y=None):
+        fit transformation.
+    transform(X=DataFrame, y=None):
+        apply feature transformation
+    """
+
+    def __init__(self, columns):
+        self.columns = columns
+
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X, y=None):
+        return X[self.columns]
+
+class FeaturesEntropy(BaseEstimator, TransformerMixin):
+    """
+    Class that creates a feature that calculate entropy for a given feature classes, but it might get some leackeage in the training set.
+    this class is compatible with scikitlearn pipeline
+
+    Attributes
+    ----------
+    columns : list
+        list of features to select
+    entropy_map: pd.DataFrame
+        dataframe of the map with the entropies per class
+    perc: float
+        percentage of the dates using for calculate the entropy map
+    
+    Methods
+    -------
+    fit(additional="", X=DataFrame, y=None):
+        fit transformation.
+    transform(X=DataFrame, y=None):
+        apply feature transformation
+    """
+    
+    def __init__(self, features, target, feature_name = None, feature_type = 'discrete', perc = 0.5, default_null = 0.99):
+        
+        self.features = features
+        self.feature_type = feature_type
+        self.target = target
+        self.perc = perc
+        self.default_null = default_null
+        
+        if not feature_name:
+            self.feature_name = '_'.join(features)
+            self.feature_name = self.feature_name + '_' + target + '_' + feature_type
+        else:
+            self.feature_name = feature_name
+            
+    def fit(self, X, y=None):
+
+        unique_dates = list(X['Date'].unique())
+        unique_dates.sort()
+        
+        total_length = len(unique_dates)
+        cut = int(round(total_length*self.perc,0))
+        train_dates = unique_dates[:cut]
+        max_train_date = max(train_dates)
+        
+        X_ = X[X['Date'] <= max_train_date].copy()
+        df = X_.join(y, how = 'left')
+
+        column_list = [f'{self.feature_type}_signal_{colx}' for colx in self.features]
+        
+        df_aggr = (
+            df
+            .groupby(column_list, as_index = False)
+            .apply(
+                lambda x: pd.Series(
+                    dict(
+                        counts = x[self.target].count(),
+                        trues=(x[self.target] == 1).sum(),
+                        falses=(x[self.target] == 0).sum(),
+                    )
+                )
+            )
+            .assign(
+                trues_rate=lambda x: x['trues'] / x['counts']
+            )
+            .assign(
+                falses_rate=lambda x: x['falses'] / x['counts']
+            )
+            .assign(
+                log2_trues = lambda x: np.log2(1/x['trues_rate'])
+            )
+            .assign(
+                log2_falses = lambda x: np.log2(1/x['falses_rate'])
+            )
+            .assign(
+                comp1 = lambda x: x['trues_rate']*x['log2_trues']
+            )
+            .assign(
+                comp2 = lambda x: x['falses_rate']*x['log2_falses']
+            )
+            .assign(
+                class_entropy = lambda x: np.round(x['comp1']+x['comp2'],3)
+            )
+        )
+        
+        self.column_list = column_list
+        self.entropy_map = (
+            df_aggr
+            [column_list+['class_entropy']]
+            .rename(columns = {'class_entropy': self.feature_name})
+            .copy()
+        )
+        
+        del df, df_aggr, X_
+        return self
+
+    def transform(self, X, y=None):
+
+        X = X.join(self.entropy_map.set_index(self.column_list), on=self.column_list, how = 'left')
+        X[self.feature_name] = X[self.feature_name].fillna(self.default_null)
+        return X
+
+class signal_combiner(BaseEstimator, TransformerMixin):
+
+    """
+    Class that applies feature combination of binary signals.
+    this class is compatible with scikitlearn pipeline
+
+    ...
+
+    Attributes
+    ----------
+    columns : list
+        list of features to select
+    drop : boolean
+        drop combining features
+    prefix_up : str
+        up prefix of the base feature
+    prefix_low : str
+        low prefix of the base feature
+
+    Methods
+    -------
+    fit(additional="", X=DataFrame, y=None):
+        fit transformation.
+    transform(X=DataFrame, y=None):
+        apply feature transformation
+    """
+
+    def __init__(self, columns, drop = True, prefix_up = 'signal_up_', prefix_low = 'signal_low_'):
+        self.columns = columns
+        self.drop = drop
+        self.prefix_up = prefix_up
+        self.prefix_low = prefix_low
+
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X, y=None):
+        for column in self.columns:
+            X['CombSignal_'+column] = np.where(
+                X[self.prefix_up + column] == 1,
+                1,
+                np.where(
+                    X[self.prefix_low + column] == 1,
+                    1,
+                    0
+                )
+            )
+            if self.drop:
+                X = X.drop(columns = [self.prefix_up + column, self.prefix_low + column])
+        return X

{virgo_modules-0.1.3.dist-info → virgo_modules-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.1.3
+Version: 0.2.2
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

virgo_modules-0.2.2.dist-info/RECORD

@@ -0,0 +1,15 @@
+virgo_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+virgo_modules/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+virgo_modules/src/aws_utils.py,sha256=q0l7D7ofo09Lu1QQjv-esheQ06uiSy1Pdq3xMul8zvk,2571
+virgo_modules/src/backtester.py,sha256=OhiWyzDX0PthXGuhChyWUmDN3cLkzVYe95zS4nGtia8,22106
+virgo_modules/src/edge_utils.py,sha256=XN2oEOwADXF9IGNUGx0Ai8B1yDAiU2WDateLnEJh5FE,14243
+virgo_modules/src/hmm_utils.py,sha256=fFWxmh9q3rjiKRHnxNk9k7O4fDrxVxkmp3pbpLvktjc,21116
+virgo_modules/src/pull_artifacts.py,sha256=5OPrgR7pcMSdpbevDRhf0ebk7g7ZRjff4NpTIIWAKjE,1989
+virgo_modules/src/re_utils.py,sha256=05pSVzGKBybPMFGm2wcbYgkSOZs3bZECLjyHvlPlFjM,72490
+virgo_modules/src/ticketer_source.py,sha256=8YInJJF_OzjWXaAuOjAzdaQrgkemmsIpQSTkCZs5VFA,95918
+virgo_modules/src/transformer_utils.py,sha256=LLwKYZRq5hrPVimnq3taD0Lh-q3Bq21fy1I4Icbnxi8,7677
+virgo_modules-0.2.2.dist-info/LICENSE,sha256=pNgFyCYgmimaw0o6V20JupZLROycAnOA_HDDh1tX2V4,1097
+virgo_modules-0.2.2.dist-info/METADATA,sha256=4jz0IHgWzYOrvqW4UnCgHkZHJQWCD9wWWaEm2du9hRY,1428
+virgo_modules-0.2.2.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+virgo_modules-0.2.2.dist-info/top_level.txt,sha256=ZjI-qEkDtT-8mFwGAWnXfqPOKEGlIhWRW1es1VyXc60,14
+virgo_modules-0.2.2.dist-info/RECORD,,

virgo_modules-0.1.3.dist-info/RECORD

@@ -1,13 +0,0 @@
-virgo_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-virgo_modules/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-virgo_modules/src/aws_utils.py,sha256=q0l7D7ofo09Lu1QQjv-esheQ06uiSy1Pdq3xMul8zvk,2571
-virgo_modules/src/backtester.py,sha256=OhiWyzDX0PthXGuhChyWUmDN3cLkzVYe95zS4nGtia8,22106
-virgo_modules/src/edge_utils.py,sha256=i3Hm3fO-QA-u17jDpnRodLLILMWZ2VTMEkMKijdGKLg,14287
-virgo_modules/src/pull_artifacts.py,sha256=5OPrgR7pcMSdpbevDRhf0ebk7g7ZRjff4NpTIIWAKjE,1989
-virgo_modules/src/re_utils.py,sha256=05pSVzGKBybPMFGm2wcbYgkSOZs3bZECLjyHvlPlFjM,72490
-virgo_modules/src/ticketer_source.py,sha256=fgwF34LJAL_Nr5Pzmp0p5RgHI81-ilRnCXxIBzrfVk4,129045
-virgo_modules-0.1.3.dist-info/LICENSE,sha256=pNgFyCYgmimaw0o6V20JupZLROycAnOA_HDDh1tX2V4,1097
-virgo_modules-0.1.3.dist-info/METADATA,sha256=AZMtEKvf-j0TTyWMXhczfq1rfIXugowm630MiCzCl7s,1428
-virgo_modules-0.1.3.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-virgo_modules-0.1.3.dist-info/top_level.txt,sha256=ZjI-qEkDtT-8mFwGAWnXfqPOKEGlIhWRW1es1VyXc60,14
-virgo_modules-0.1.3.dist-info/RECORD,,