virgo-modules 0.8.4__py3-none-any.whl → 0.9.0__py3-none-any.whl

virgo_modules/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.9.0"

virgo_modules/src/markowitz/markowitz_utils.py

@@ -0,0 +1,44 @@
+from scipy import optimize
+import pandas as pd
+import numpy as np
+
+class MarkowitzOptimizer:
+    def __init__(self, data, return_cols, window_cov=10):
+        self.data_ = data[["Date"]+return_cols].dropna().sort_values("Date").copy()
+        self.window_cov = window_cov
+        self.return_cols = return_cols
+        self.n_features = len(return_cols)
+        
+    def execute_markowitz(self):
+        cons = {'type':'eq','fun':self._check_sum}
+        bounds = tuple((0,1) for _ in range(self.n_features))  # weights bounds
+        init_guess = [1/self.n_features for _ in range(self.n_features)] ## initial guess of weiths
+        feature_result_names = [f"optimal_{x}" for x in self.return_cols]
+        self.data_[feature_result_names] = np.nan
+
+        for i in range(self.window_cov,len(self.data_)):
+            self.cov = self.data_.iloc[i-self.window_cov:i,:][self.return_cols].cov()
+            self.returns = self.data_.iloc[i][self.return_cols].values
+            
+            opt_results = optimize.minimize(self._neg_sr, init_guess, constraints=cons, bounds=bounds, method='SLSQP')
+            optimal_weights = opt_results.x
+            self.data_.iloc[i,-self.n_features:] = [float(x) for x in optimal_weights]
+            
+        self.data_[feature_result_names] = self.data_[feature_result_names].astype(float).round(6) 
+        self.data_["sum_weights"] = self.data_[feature_result_names].sum(axis=1)
+        self.feature_result_names = feature_result_names
+        return self.data_
+    
+    def _get_ret_vol_sr(self, weights):
+        weights = np.array(weights)
+        ret = self.returns.dot(weights)
+        vol = np.sqrt(weights.T.dot(self.cov.dot(weights)))
+        sr = ret / vol
+        return np.array([ret, vol, sr])
+
+    def _neg_sr(self, weights):
+        return self._get_ret_vol_sr(weights)[-1] * -1
+        
+    @staticmethod
+    def _check_sum(weights):
+        return np.sum(weights) - 1

virgo_modules/src/ticketer_source.py

@@ -174,6 +174,12 @@ class stock_eda_panel(object):
         perfom fast stochastic oscilator or william indicator
     vortex_feature(window=int, threshold=float, plot=boolean, save_features=boolean):
         perform vortex oscilator
+    expected_return(trad_days:int, feature:str, feature_name:str):
+        perform expected log return based on inversed shift of historical data and applying
+    rolling_feature(feature: str, window:int, function:callable):
+        perform rolling (non expanding) window operation for a given feature
+    time_distance(feature_base:str,feature_window:str, result_feature_name:str, max_window:int):
+        perform distancce time to a given window feature
     minmax_pricefeature(type_func=str, window=int, distance=bolean, save_features=boolean)
         get relative price/ distance feature with respect to the min/max price in a given window
     pair_index_feature(pair_symbol=str, feature_label=str, window=int, threshold=float, plot=boolean, save_features=boolean):
@@ -1382,6 +1388,73 @@ class stock_eda_panel(object):
                 name_attr = f'{type_func}_relprice'
                 
             setattr(self,f'settings_{name_attr}_pricefeature' , {'type_func': type_func, 'window': window, 'distance': distance})
+    
+    def expected_return(self, trad_days, feature, feature_name=False):
+        """
+        perform expected log return based on inversed shift of historical data and applying
+
+        Parameters
+        ----------
+        trad_days (int): window or differenciation
+        feature (int): feature to apply expected log return
+        feature_name (str): resulting feature name
+        
+        Returns
+        -------
+        None
+        """
+        feature_name = feature_name if feature_name else f"{feature}_log_return_{trad_days}"
+        tmp_names = list()
+        for ind in range(1,trad_days+1):
+            tmp_name = f"expected_{ind}"
+            self.df[tmp_name] = self.df[feature].shift(-ind)/self.df[feature]-1
+            tmp_names.append(tmp_name)
+        self.df[feature_name] = self.df[tmp_names].max(axis=1)
+        self.df = self.df.drop(columns = tmp_names)
+    
+    def rolling_feature(self, feature, window, function):
+        """
+        perform rolling (non expanding) window operation for a given feature
+
+        Parameters
+        ----------
+        feature (int): feature to apply window operation
+        window (int): window size
+        function (str): window function e.g MIN, MAX, AVG
+        
+        Returns
+        -------
+        None
+        """
+        feature_name = f"{feature}_{window}_{function}"
+        self.df[feature_name] = getattr(self.df.sort_values("Date")[feature].rolling(window), function)()
+
+    def time_distance(self, feature_base,feature_window, result_feature_name, max_window=None):
+        """
+        perform distancce time to a given window feature
+
+        Parameters
+        ----------
+        feature_base (str): name of the underlaying feature
+        feature_window (str): name of the window feature
+        result_feature_name (str): resulting feature name
+        max_window (int): apply a top value to the time to distance feature
+        
+        Returns
+        -------
+        None
+        """
+        self.df["Date_pivot"] = np.nan
+        self.df["Date_pivot"] = self.df["Date_pivot"].case_when([
+            (self.df[feature_base] == self.df[feature_window], self.df["Date"]), 
+
+        ])
+        self.df["Date_pivot"] = self.df.sort_values("Date")["Date_pivot"].fillna(method="ffill")
+        self.df[result_feature_name] = self.df["Date"] - self.df["Date_pivot"]
+        self.df[result_feature_name] = self.df[result_feature_name].dt.days
+        if max_window:
+            self.df[result_feature_name] = self.df[result_feature_name].clip(0,max_window)
+        self.df = self.df.drop(columns = ["Date_pivot"])
 
     def pair_index_feature(self, pair_symbol, feature_label,threshold, window = None,ta_method='ROC',param_set=False,plot = False, save_features = False):
         """

{virgo_modules-0.8.4.dist-info → virgo_modules-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: virgo_modules
-Version: 0.8.4
+Version: 0.9.0
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.8.4.dist-info → virgo_modules-0.9.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
-virgo_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+virgo_modules/__init__.py,sha256=7NrzGOSBvO9S73thMlxEh5aNYKS5SYKLgTxC1YIIPRk,21
 virgo_modules/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 virgo_modules/src/aws_utils.py,sha256=QCyxJwZ6bNCkMpuuxzxkNxejj-hJf4kj2arb1SQPNug,2582
 virgo_modules/src/backtester.py,sha256=OhiWyzDX0PthXGuhChyWUmDN3cLkzVYe95zS4nGtia8,22106
 virgo_modules/src/hmm_utils.py,sha256=D7axAnCdSe1_1EgRyli2PAnM2f6699hTY9GcxjPXG-o,21221
 virgo_modules/src/pull_artifacts.py,sha256=5OPrgR7pcMSdpbevDRhf0ebk7g7ZRjff4NpTIIWAKjE,1989
 virgo_modules/src/re_utils.py,sha256=AQlhyO0cvU-G42dolhedz5E-sniRzeFhf40RD5QVYpo,75506
-virgo_modules/src/ticketer_source.py,sha256=ig6kgR6qSPhyFePRuO52pNmVsYawpgUXCn7RIO3xf5E,104623
+virgo_modules/src/ticketer_source.py,sha256=nGjQdZRDWto8cGKhMQCyAqYwvqYy1m6djkCpffiX3Dk,107747
 virgo_modules/src/transformer_utils.py,sha256=SnYdtsFPnSF6u4UFIat0-X3-qVuUWvv_T46kiB-H0Sk,13682
 virgo_modules/src/edge_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 virgo_modules/src/edge_utils/conformal_utils.py,sha256=cKm4KSM261Eu1FJn4oowKYiKIesW81VbqITIvopGSVk,5410
@@ -15,8 +15,10 @@ virgo_modules/src/edge_utils/shap_utils.py,sha256=FgcHkfddvdFSeUqEubYa2ExRGVAWSt
 virgo_modules/src/edge_utils/stack_model.py,sha256=QqE91uLo2KauGEj91AVNANB1xE7J4Fa49YOX7k5mFng,4257
 virgo_modules/src/market/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 virgo_modules/src/market/market_tools.py,sha256=vBt66_7E3ANz7avzfeNw_RHMGvG9lh5PRhxmcf_Oyjc,6880
-virgo_modules-0.8.4.dist-info/licenses/LICENSE,sha256=pNgFyCYgmimaw0o6V20JupZLROycAnOA_HDDh1tX2V4,1097
-virgo_modules-0.8.4.dist-info/METADATA,sha256=38imVZ-hn5ncMOXvxQx5VoyJfjdEY6C9-rhTStvhc50,1122
-virgo_modules-0.8.4.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
-virgo_modules-0.8.4.dist-info/top_level.txt,sha256=ZjI-qEkDtT-8mFwGAWnXfqPOKEGlIhWRW1es1VyXc60,14
-virgo_modules-0.8.4.dist-info/RECORD,,
+virgo_modules/src/markowitz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+virgo_modules/src/markowitz/markowitz_utils.py,sha256=2bsnk_QlfWB5QytSNZ5n8elto9hhsEiukcEJBqWEYX4,1970
+virgo_modules-0.9.0.dist-info/licenses/LICENSE,sha256=pNgFyCYgmimaw0o6V20JupZLROycAnOA_HDDh1tX2V4,1097
+virgo_modules-0.9.0.dist-info/METADATA,sha256=z7zb755kS0k15I2FddBWXbFzrTaSmEqUiPvxvtEEzIM,1122
+virgo_modules-0.9.0.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
+virgo_modules-0.9.0.dist-info/top_level.txt,sha256=ZjI-qEkDtT-8mFwGAWnXfqPOKEGlIhWRW1es1VyXc60,14
+virgo_modules-0.9.0.dist-info/RECORD,,