virgo-modules 0.4.5__py3-none-any.whl → 0.5.1__py3-none-any.whl

virgo_modules/src/edge_utils/edge_utils.py

@@ -1,5 +1,7 @@
 import numpy as np
 import itertools
+import random
+import math
 
 from sklearn.metrics import roc_auc_score, precision_score, recall_score
 from sklearn.pipeline import Pipeline
@@ -310,7 +312,7 @@ class ExpandingMultipleTimeSeriesKFold:
         get number of splits
     """
     
-    def __init__(self, df, window_size = 100, number_window=3, overlap_size = 0):
+    def __init__(self, df, window_size = 100, number_window=3, overlap_size = 0, sample_parts = None):
         """
         Initialize object
 
@@ -320,6 +322,7 @@ class ExpandingMultipleTimeSeriesKFold:
         number_window (int): number of train splits
         window_size (int): window size data
         overlap_size (int): overlap size
+        sample_individuals (tuple(float, str)): sample partition units to remove from the train set, tuple()
 
         Returns
         -------
@@ -329,6 +332,7 @@ class ExpandingMultipleTimeSeriesKFold:
         self.number_window = number_window
         self.window_size = window_size
         self.overlap_size = overlap_size
+        self.sample_parts = sample_parts
         
     def split(self, X, y, groups=None):
         """
@@ -372,9 +376,21 @@ class ExpandingMultipleTimeSeriesKFold:
             max_train_date = max(train_dates)
             min_test_date, max_test_date = min(test_dates), max(test_dates)
             
-            cut = cut - (self.window_size - self.overlap_size) 
-        
-            train_index = self.df[self.df.index.get_level_values('Date_i') <= max_train_date].index.get_level_values('i')
+            cut = cut - (self.window_size - self.overlap_size)
+
+            if self.sample_parts:
+                sample_part = self.sample_parts[0]
+                part_col = self.sample_parts[1]
+                unique_parts = list(self.df.index.get_level_values(part_col).unique())
+                random.shuffle(unique_parts)
+                n_select = math.ceil(len(unique_parts)*sample_part)
+                to_drop = unique_parts[0:n_select]
+                train_index = self.df[
+                    (self.df.index.get_level_values('Date_i') <= max_train_date) 
+                    & 
+                    (~self.df.index.get_level_values(part_col).isin(to_drop))].index.get_level_values('i')
+            else:
+                train_index = self.df[self.df.index.get_level_values('Date_i') <= max_train_date].index.get_level_values('i')
             test_index = self.df[(self.df.index.get_level_values('Date_i') >= min_test_date) & (self.df.index.get_level_values('Date_i') <= max_test_date)].index.get_level_values('i')
         
             yield train_index, test_index

virgo_modules/src/edge_utils/stack_model.py

@@ -0,0 +1,94 @@
+import numpy as np
+import pandas as pd
+
+from sklearn.base import BaseEstimator, ClassifierMixin
+
+class MyStackingClassifierMultiClass(ClassifierMixin, BaseEstimator):
+    def __init__(self,  estimators, meta_estimators,targets,perc=None,stack_size=None, **kwargs):
+        self.estimators = estimators
+        self.meta_estimators = meta_estimators
+        self.targets = targets
+        if stack_size and perc:
+            raise Exception('just one option')
+        if not stack_size and not perc:
+            raise Exception('set one option')
+        self.stack_size = stack_size
+        self.perc = perc
+        
+    def get_index_training(self, X):
+        if self.stack_size:
+            unique_dates = list(X.index.get_level_values('Date_i').unique())
+            unique_dates.sort()
+            stack_chunk = unique_dates[-self.stack_size:]
+            base_indexes = X[~X.index.get_level_values('Date_i').isin(stack_chunk)].index.get_level_values('i')
+            meta_indexes = X[X.index.get_level_values('Date_i').isin(stack_chunk)].index.get_level_values('i')
+        elif self.perc:
+            meta_indexes = X.sample(frac = self.perc).index.get_level_values('i')
+            base_indexes = X[~X.index.get_level_values('i').isin(meta_indexes)].index.get_level_values('i')
+        else:
+            raise Exception("error", self.stack_size, self.perc)
+        return base_indexes, meta_indexes
+    def train_base_learner(self, classifier, X, y,indexes):
+        base_X = X[X.index.get_level_values('i').isin(indexes)]
+        base_y = y[y.index.get_level_values('i').isin(indexes)]
+        classifier.fit(base_X, base_y)
+    def fit(self, X, y):
+        # #base learners
+        base_indexes, meta_indexes = self.get_index_training(X)
+        for name,estimator in self.estimators:
+            self.train_base_learner(estimator,X, y, base_indexes)
+    
+        #stack meta learner
+        metas_pred = dict()
+        for i,cont in enumerate(self.estimators, start=1):
+            _,estimator = cont
+            meta_pred = estimator.predict_proba(X[X.index.get_level_values('i').isin(meta_indexes)])
+            metas_pred[f"meta{i}0"] = meta_pred[0][:,1]
+            metas_pred[f"meta{i}1"] = meta_pred[1][:,1]
+        meta_preds_df = pd.DataFrame(metas_pred)
+    
+        for i,metaest in enumerate(self.meta_estimators,start=0):
+            _,metaest = metaest
+            metacols = [f"meta{j}{i}" for j in range(1,len(self.estimators)+1)]
+            metaest.fit(
+                meta_preds_df[metacols],
+                y[X.index.get_level_values('i').isin(meta_indexes)][self.targets[i]]
+            )
+        self.is_fitted_ = True
+        self.classes_ = np.array([[0,1],[0,1]])
+        
+    def predict_proba(self, X):
+        metas_pred = dict()
+        for i,cont in enumerate(self.estimators, start=1):
+            _,estimator = cont
+            meta_pred = estimator.predict_proba(X)
+            metas_pred[f"meta{i}0"] = meta_pred[0][:,1]
+            metas_pred[f"meta{i}1"] = meta_pred[1][:,1]
+        self.meta_preds_df__ = pd.DataFrame(metas_pred)
+
+        prediction_vector = list()
+        for i,cont in enumerate(self.meta_estimators, start=0):
+            _,estimator = cont
+            metacols = [f"meta{j}{i}" for j in range(1,len(self.estimators)+1)]
+            preds = estimator.predict_proba(self.meta_preds_df__[metacols].values)
+            prediction_vector.append(preds)
+        return prediction_vector
+        
+    def predict(self, X):
+        prediction_vector = list()
+        _ = self.predict_proba(X)
+        for i,cont in enumerate(self.meta_estimators, start=0):
+            _,estimator = cont
+            metacols = [f"meta{j}{i}" for j in range(1,len(self.estimators)+1)]
+            preds = estimator.predict(self.meta_preds_df__[metacols].values)
+            prediction_vector.append(preds) 
+        
+        p = np.array(tuple(prediction_vector))
+        return p.reshape((p.shape[1],p.shape[0]))
+        
+    def get_params(self, deep=True):
+        return {k:v for k, v in self.__dict__.items()}
+        
+    def set_params(self, **parms):
+        for k,v in parms.items():
+            setattr(self,k,v)

{virgo_modules-0.4.5.dist-info → virgo_modules-0.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.4.5
+Version: 0.5.1
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.4.5.dist-info → virgo_modules-0.5.1.dist-info}/RECORD

@@ -9,10 +9,11 @@ virgo_modules/src/ticketer_source.py,sha256=jxP-OOeoyN2JxRQg-mX6t6WNJXiIrhWKDywD
 virgo_modules/src/transformer_utils.py,sha256=ysCUp3cB3_7Jr9OHDqhg2_6Vu0k1YVjfqbvQNbxpbhI,8990
 virgo_modules/src/edge_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 virgo_modules/src/edge_utils/conformal_utils.py,sha256=WK54ctvdnFrCAv3_slFBC71Ojy9xgC1wODR7xmvXGgg,3743
-virgo_modules/src/edge_utils/edge_utils.py,sha256=unCrkimwzlJx-osUWz6f6Vfiuv-unIATYva5UkK-Xik,18661
+virgo_modules/src/edge_utils/edge_utils.py,sha256=7nYPLDNyKqeKIuOOwQi4wsBibzs9gP1HgYMISXJX1Y8,19522
 virgo_modules/src/edge_utils/shap_utils.py,sha256=OMKVO-4gtOng9GeSuhEgAEQe4FF3AtqXjm-GUBLqYFc,3349
-virgo_modules-0.4.5.dist-info/LICENSE,sha256=pNgFyCYgmimaw0o6V20JupZLROycAnOA_HDDh1tX2V4,1097
-virgo_modules-0.4.5.dist-info/METADATA,sha256=GR7pTBoguHajgjq17Z6gXRSdjRz-3w4X5QD3-0N7Ge4,876
-virgo_modules-0.4.5.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-virgo_modules-0.4.5.dist-info/top_level.txt,sha256=ZjI-qEkDtT-8mFwGAWnXfqPOKEGlIhWRW1es1VyXc60,14
-virgo_modules-0.4.5.dist-info/RECORD,,
+virgo_modules/src/edge_utils/stack_model.py,sha256=QqE91uLo2KauGEj91AVNANB1xE7J4Fa49YOX7k5mFng,4257
+virgo_modules-0.5.1.dist-info/LICENSE,sha256=pNgFyCYgmimaw0o6V20JupZLROycAnOA_HDDh1tX2V4,1097
+virgo_modules-0.5.1.dist-info/METADATA,sha256=cDHMIPEJe-YznvEfgdToAL6GsMIrcrB0ti9sTjPlhcw,876
+virgo_modules-0.5.1.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+virgo_modules-0.5.1.dist-info/top_level.txt,sha256=ZjI-qEkDtT-8mFwGAWnXfqPOKEGlIhWRW1es1VyXc60,14
+virgo_modules-0.5.1.dist-info/RECORD,,