virgo-modules 0.0.90__tar.gz → 0.1.0__tar.gz

{virgo_modules-0.0.90 → virgo_modules-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.0.90
+Version: 0.1.0
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.0.90 → virgo_modules-0.1.0}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.0.90",
+    version="0.1.0",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

virgo_modules-0.1.0/virgo_app/virgo_modules/src/backtester.py

@@ -0,0 +1,360 @@
+import pandas as pd
+import numpy as np
+import json
+
+import matplotlib.pyplot as plt
+import matplotlib.gridspec as gridspec
+import seaborn as sns; sns.set()
+
+import warnings
+warnings.filterwarnings('ignore')
+
+from .aws_utils import upload_file_to_aws
+
+def sharpe_ratio(return_series):
+
+    '''
+    calculate sharpe ratio for given array.
+
+            Parameters:
+                    return_series (pd.series): pandas series of the asset returns
+
+            Returns:
+                    sharpe (float): sharpe ratio
+    '''
+
+    N = 255 # Trading days in the year (change to 365 for crypto)
+    rf = 0.005 # Half a percent risk free rare
+    mean = return_series.mean() * N -rf
+    sigma = return_series.std() * np.sqrt(N)
+    sharpe = round(mean / sigma, 3)
+    return sharpe
+
+
+class SignalAnalyserObject:
+    """
+    Class that produces back-tests analysis for a given feature
+
+    Attributes
+    ----------
+    symbol_name : str
+        stock or asset to assess
+    feature_name : str
+    test_size: int
+        testing data size
+    show_plot: boolean
+    save_path: str
+        if available, save result locally
+    save_aws: str
+        if available, save result locally
+    aws_credentials: dict
+    signal_position: int
+        if available, signal position to open a position
+    df: pd.DataFrame:
+        transformed data of the selected feature to perform back-test
+
+    Methods
+    -------
+    signal_analyser(days_list=list):
+        given a signal position for either botton or roof signal, calculate the espected return and distributions for a time scope in the days list (time horizons)
+    create_backtest_signal(days_strategy=int, high_exit=float, low_exit=float, open_in_list=list):
+        create a back-test analysis using the test data using some opening anc closing postion criterias
+    """
+
+    def __init__(self, data,symbol_name, feature_name, test_size, signal_position = False, correct_signals = False, show_plot = True, save_path = False, save_aws = False, aws_credentials = False, return_fig = False):
+        """
+        Initialize object
+
+        Parameters
+        ----------
+        data (pd.DataFrame): data
+        ticket_name (str): name of the asset
+        feature_name (str): name of the features
+        test_size (int): size of the test data
+        signal_position (int): signal position to open the position, False by default
+        correct_signals (int): clean abnormal signals using interpolation
+        show_plot (boolean): if true show plot for every method
+        save_path (str): if true, save results in file e.g r'C:/path/to/the/file/'
+        save_aws (str): if true, export results to remote repo e.g. 'path/to/file/'
+        aws_credentials (dict): credentials for aws
+        return_fig (boolean): if true, methods will return objects
+
+        Returns
+        -------
+        None
+        """
+        self.ticket_name = symbol_name
+        self.feature_name=feature_name
+        self.test_size=test_size
+        self.show_plot = show_plot
+        self.save_path = save_path
+        self.save_aws = save_aws
+        self.aws_credentials = aws_credentials
+        self.return_fig = return_fig
+        self.signal_position = signal_position
+        ## preprocessing 
+        up_signal, low_signal= f'signal_up_{feature_name}', f'signal_low_{feature_name}'
+        features_base = ['Date', up_signal, low_signal, 'Close','Open','High','Low']
+
+        df = data[features_base].sort_values('Date')
+
+        df['signal_type'] = np.where(
+            df[up_signal] == 1,
+            'up',
+            np.where(
+                df[low_signal] == 1,
+                'down',
+                'no signal'
+            )
+        )
+        def correct_sygnals(df,correct_i = 1):
+            ### signal cleaning
+            for i in range(1+correct_i, len(df)-1):
+                start_i, end_i = i-(correct_i+1), i+1
+                dfw = df.iloc[start_i: end_i,]
+                before_type = dfw.iloc[0].signal_type
+                after_type = dfw.iloc[-1].signal_type
+                window_types = dfw.iloc[1:-1].signal_type.unique()
+                n_window_type = len(window_types)
+                if n_window_type == 1:
+                    if (before_type == after_type) and (window_types[0] != after_type):
+                        df.iloc[start_i+1: end_i-1, df.columns.get_loc('signal_type')] = before_type
+            return df.copy()
+
+        if correct_signals:
+            for correct_i in range(1,correct_signals+1):
+                df = correct_sygnals(df,correct_i = correct_i)
+            df[up_signal] = np.where(df['signal_type'] == 'up', 1,0)
+            df[low_signal] = np.where(df['signal_type'] == 'down', 1,0)
+
+        ## indexing chains
+        df['lag_signal_type'] = df['signal_type'].shift(1)
+        df['lag_Date'] = df['Date'].shift(1)
+        df['span'] = (pd.to_datetime(df['Date']) - pd.to_datetime(df['lag_Date'])).dt.days - 1
+        df['break'] = np.where((df['span'] > 3) & (df['lag_signal_type'] == df['signal_type']), 1, 0)
+        df['break'] = np.where((df['lag_signal_type'] != df['signal_type']), 1, df['break'])
+        df['chain_id'] = df.sort_values(['Date']).groupby(['break']).cumcount() + 1
+        df['chain_id'] = np.where(df['break'] == 1, df['chain_id'], np.nan )
+        df['chain_id'] = df['chain_id'].fillna(method = 'ffill')
+
+        df['internal_rn'] = df.sort_values(['Date']).groupby(['chain_id']).cumcount() + 1
+        df['inv_internal_rn'] = df.sort_values(['Date'],ascending = False).groupby(['chain_id']).cumcount() + 1
+
+        df['first_in_chain'] = np.where(df['internal_rn'] == 1, True, False)
+        df['last_in_chain'] = np.where(df['inv_internal_rn'] == 1, True, False)
+
+        df['span'] = (pd.to_datetime(df['Date']) - pd.to_datetime(df['lag_Date'])).dt.days - 1
+        self.df = df.drop(columns = ['span','break','lag_signal_type','lag_Date']).copy()
+        
+    def signal_analyser(self, days_list):
+        """
+        Initialize object
+
+        Parameters
+        ----------
+        days_list (list): list of integers to calculate expected returns
+
+        Returns
+        -------
+        if returns_fig is true, returns a matplotlib fig
+        """
+        signal_position = self.signal_position
+        df = self.df.iloc[0:-self.test_size,:].copy()
+        returns_list = list()
+
+        for days in days_list:
+            feature_ = f'return_{days}d'
+            df[feature_] = (df['Close'].shift(-days)/df['Close']-1)*100
+            returns_list.append(feature_)
+            
+        df['open_long'] = np.where(df.last_in_chain == True, True, np.nan)
+        df['open_short'] = np.where(df.first_in_chain == True, True, np.nan)
+        
+        # plotting
+        fig, axs = plt.subplots(1, 4, figsize = (20,5))
+        palette ={"go down": "tomato", "go up": "lightblue"}
+        
+        df2 = df[df.signal_type.isin(['up','down'])]
+        df2['lag_Date'] = df2['Date'].shift(1)
+        df2['lag_signal_type'] = df2['signal_type'].shift(1)
+        df2 = df2[df2.lag_signal_type != df2.signal_type]
+        df2['span'] = (pd.to_datetime(df2['Date']) - pd.to_datetime(df2['lag_Date'])).dt.days - 1
+        sns.violinplot(data=df2, y="span",ax = axs[0], color = 'lightblue', linewidth=0.7,inner="quart")
+        sns.stripplot(data=df2, y="span",ax = axs[0], jitter=True, zorder=1)
+        axs[0].set_title('span between last signals')
+
+        df.signal_type = df.signal_type.map({'up':'go down', 'down': 'go up'})
+        df_ = df[df.last_in_chain == True]
+        df_['part'] = '-'
+        sns.violinplot(data=df_, y="internal_rn", x='part', ax = axs[1], hue="signal_type", inner="quart",palette = palette,gap=0.1, split=True, linewidth=0.7)
+        axs[1].set_title('signal duration distribution')
+
+        if signal_position:
+            for feature in returns_list:
+                df[feature] = df[feature].shift(-signal_position)
+        
+        df_melt = df[df.open_long == 1].melt(id_vars=['signal_type'], value_vars=returns_list, var_name='time', value_name='value')
+        df_melt = df_melt.dropna()
+        sns.violinplot(data=df_melt, x="time", y="value", hue="signal_type",ax = axs[2], split=True, gap=0.1, inner="quart",palette = palette, linewidth=0.8)
+        axs[2].axhline(y=0, color='grey', linestyle='--')
+        axs[2].set_title('E. returns - end of the signal')
+
+        df_melt = df[df.open_short == 1].melt(id_vars=['signal_type'], value_vars=returns_list, var_name='time', value_name='value')
+        df_melt = df_melt.dropna()
+        sns.violinplot(data=df_melt, x="time", y="value", hue="signal_type",ax = axs[3], split=True, gap=0.1, inner="quart",palette = palette, linewidth=0.8)
+        axs[3].axhline(y=0, color='grey', linestyle='--')
+        axs[3].set_title('E. returns - start of the signal')
+        
+        if self.show_plot:
+            plt.show()
+
+        if self.save_path:
+            result_plot_name = f'signals_strategy_distribution_{self.feature_name}.png'
+            fig.savefig(self.save_path+result_plot_name)
+            # pickle.dump(axs, open(self.save_path+result_plot_name, 'wb'))
+
+        if self.save_path and self.save_aws:
+            # upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{self.ticket_name}/'+result_plot_name, input_path = self.save_path+result_plot_name)
+            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = self.save_aws + result_plot_name, input_path = self.save_path + result_plot_name, aws_credentials = self.aws_credentials)
+        if not self.show_plot:
+            plt.close()
+
+        del df
+
+        if self.return_fig:
+            return fig
+        
+    def create_backtest_signal(self,days_strategy, high_exit = False, low_exit = False, open_in_list = ['down']):
+        """
+        Initialize object
+
+        Parameters
+        ----------
+        days_strategy (int): position horizon
+        high_exit (float): max threshold to close position
+        low_exit (float): min threshold to close position, this parameter has to be positive
+        open_in_list (list): list of strings ("down","up") to assess signals
+        Returns
+        -------
+        if returns_fig is true, returns a matplotlib fig and list of dicts containing analysis
+        """
+        asset_1 = 'Close'
+        up_signal, low_signal= f'signal_up_{self.feature_name}', f'signal_low_{self.feature_name}'
+        signal_position = self.signal_position
+        dft = self.df.iloc[-self.test_size:,:].reset_index(drop=True).copy()
+        
+        dft['lrets_bench'] = np.log(dft[asset_1]/dft[asset_1].shift(1))
+        dft['bench_prod'] = dft['lrets_bench'].cumsum()
+        dft['bench_prod_exp'] = np.exp(dft['bench_prod']) - 1
+
+        map_ = {'down':'END LOW TREND', 'up': 'BEGINNING HIGH TREND'}
+
+        open_in_list_items = len(open_in_list)
+        fig, axs = plt.subplots(1,open_in_list_items, figsize = (7*open_in_list_items,6))
+        messages = list()
+        for i, open_in in enumerate(open_in_list):
+            axs_ = axs if open_in_list_items == 1 else axs[i]
+            if open_in == 'down':
+                dft['open_long'] = np.where((dft.last_in_chain == True) & (dft.signal_type == 'down'), True, np.nan) # open strat
+            elif open_in == 'up':
+                dft['open_long'] = np.where((dft.first_in_chain == True) & (dft.signal_type == 'up'), True, np.nan) # open strat
+                
+            def chain_position(dft):
+                dft['open_long_id'] = np.where(dft['open_long'] == True, dft.chain_id, np.nan)
+                dft['open_long_id'] = dft['open_long_id'].fillna(method = 'ffill')
+                dft['open_long_rn'] = dft.sort_values(['Date']).groupby(['open_long_id']).cumcount() + 1
+                return dft
+            
+            if signal_position:
+                dft['open_long'] = dft.sort_values(['Date'])['open_long'].shift(signal_position)
+        
+            dft = chain_position(dft)
+            dft['flag'] = np.where(dft['open_long_rn'] < days_strategy, 1,0)
+        
+            if high_exit and low_exit:
+                dft['open_strat'] = np.where(dft.open_long == True, dft.Open, np.nan) # open strat
+                dft['open_strat'] = dft['open_strat'].fillna(method = 'ffill')
+                dft['open_strat'] = np.where(dft.flag == 1, dft.open_strat, np.nan)
+                dft['high_strat_ret'] = (dft['High']/dft['open_strat']-1)*100
+                dft['low_strat_ret'] = (dft['Low']/dft['open_strat']-1)*100
+                dft['max_step_chain'] = dft.groupby(['open_long_id'])['open_long_rn'].transform('max')
+                dft['high_exit'] =  np.where(((dft['high_strat_ret'] >= high_exit) | (dft['open_long_rn'] == days_strategy) | (dft['max_step_chain'] == dft['open_long_rn'])), 1, np.nan)
+                dft['low_exit'] =  np.where((dft['low_strat_ret'] <= low_exit), -1, np.nan)
+        
+                dft["exit_type"] = dft[["high_exit", "low_exit"]].max(axis=1)
+                dft['exit_type'] = np.where(dft["exit_type"] == 1, 1, np.where(dft["exit_type"] == -1,-1,np.nan))
+                dft['exit'] = np.where(dft['exit_type'].isnull(), np.nan, 1)
+                dft['exit_order'] = dft.sort_values(['Date']).groupby(['open_long_id','exit']).cumcount() + 1
+                dft['exit'] = np.where(dft['exit_order'] == 1, True, np.nan)
+                dft = dft.drop(columns = ['exit_order'])
+                ## if last signal is near
+                max_id = dft.open_long_id.max()
+                dft['max_internal_rn'] = dft.sort_values(['Date']).groupby(['open_long_id']).open_long_rn.transform('max')
+                dft['exit'] = np.where((dft.open_long_id == max_id) & (dft.max_internal_rn < days_strategy) & (dft.max_internal_rn == dft.open_long_rn), 1, dft['exit'])
+        
+                dft['exit_step'] = np.where(dft.exit == 1, dft.open_long_rn, np.nan)
+                dft['exit_step'] = dft.sort_values(['Date']).groupby(['open_long_id']).exit_step.transform('max')
+        
+                dft['flag'] = np.where(dft.open_long_rn <= dft.exit_step, 1, 0)
+        
+            dft['lrets_strat'] = np.log(dft[asset_1].shift(-1)/dft[asset_1]) * dft['flag']
+            dft['lrets_strat'] = np.where(dft['lrets_strat'].isna(),-0.0,dft['lrets_strat'])
+            dft['lrets_prod'] = dft['lrets_strat'].cumsum()
+            dft['strat_prod_exp'] = np.exp(dft['lrets_prod']) - 1
+        
+            bench_rets = round(dft['bench_prod_exp'].values[-1]*100,1)
+            strat_rets = round(dft['strat_prod_exp'].values[-1]*100,1)
+        
+            bench_sr = round(sharpe_ratio(dft.bench_prod_exp.dropna()),1)
+            strat_sr = round(sharpe_ratio(dft.strat_prod_exp.dropna()),1)
+        
+            message1 = f'{bench_rets}%'
+            message2 = f'{strat_rets}%'
+        
+            messages_ = {
+                'type strategy':map_[open_in],
+                'benchmark return:':message1,
+                'benchmark sharpe ratio:': bench_sr,
+                'strategy return:':message2,
+                'strategy sharpe ratio:': strat_sr,
+            }
+            messages.append(messages_)
+            if self.show_plot:
+                print('----------------------------')
+                print(messages_)
+                print('----------------------------')
+        
+            
+            axs_.plot(dft.bench_prod_exp.values, label = 'benchmark', color = 'steelblue')
+            axs_.scatter(range(len(dft)),np.where(dft[low_signal] == 1,dft.bench_prod_exp.values,np.nan),color = 'red', label = 'signal')
+            axs_.scatter(range(len(dft)),np.where(dft[up_signal] == 1,dft.bench_prod_exp.values,np.nan),color = 'green', label = 'signal')
+            axs_.plot(dft.strat_prod_exp.values, label = 'strategy', color = 'darksalmon')
+            axs_.set_xlabel("index")
+            axs_.set_ylabel("comulative return")
+            axs_.set_title(f'{map_[open_in]} strategy and cumulative returns based on signals')
+            axs_.legend()
+            
+        if self.show_plot:
+            plt.plot()
+
+        if self.save_path:
+            result_json_name = f'signals_strategy_return_{self.feature_name}.json'
+            result_plot_name = f'signals_strategy_return_{self.feature_name}.png'
+
+            plt.savefig(self.save_path+result_plot_name)
+
+            with open(self.save_path+result_json_name, "w") as outfile:
+                json.dump(messages, outfile)
+
+        if self.save_path and self.save_aws:
+
+            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = self.save_aws + result_json_name, input_path = self.save_path + result_json_name, aws_credentials = self.aws_credentials)
+            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = self.save_aws + result_plot_name, input_path = self.save_path + result_plot_name, aws_credentials = self.aws_credentials)
+
+        if not self.show_plot:
+            plt.close()
+
+        del dft
+
+        if self.return_fig:
+            return fig, messages

{virgo_modules-0.0.90 → virgo_modules-0.1.0}/virgo_app/virgo_modules/src/re_utils.py

@@ -1378,7 +1378,8 @@ def extract_data_traintest(object_stock,features_to_search,configs, target_confi
         arguments_to_use = configs[feature_name]['config_params']
         method_to_use = configs[feature_name]['method']
         getattr(object_stock, method_to_use)(**arguments_to_use, plot = False, save_features = False)
-        object_stock.produce_order_features(feature_name)
+        if method_to_use not in ['minmax_pricefeature']:
+            object_stock.produce_order_features(feature_name)
     # geting targets
     object_stock.get_categorical_targets(**target_params_up)
     object_stock.df = object_stock.df.drop(columns = ['target_down']).rename(columns = {'target_up':'target_up_save'})

{virgo_modules-0.0.90 → virgo_modules-0.1.0}/virgo_app/virgo_modules/src/ticketer_source.py

@@ -250,25 +250,6 @@ class FeaturesEntropy(BaseEstimator, TransformerMixin):
         X[self.feature_name] = X[self.feature_name].fillna(self.default_null)
         return X
 
-def sharpe_ratio(return_series):
-
-    '''
-    calculate sharpe ratio for given array.
-
-            Parameters:
-                    return_series (pd.series): pandas series of the asset returns
-
-            Returns:
-                    sharpe (float): sharpe ratio
-    '''
-
-    N = 255 # Trading days in the year (change to 365 for crypto)
-    rf = 0.005 # Half a percent risk free rare
-    mean = return_series.mean() * N -rf
-    sigma = return_series.std() * np.sqrt(N)
-    sharpe = round(mean / sigma, 3)
-    return sharpe
-
 class signal_combiner(BaseEstimator, TransformerMixin):
 
     """
@@ -1803,7 +1784,7 @@ class stock_eda_panel(object):
         if plot:
             self.signal_plotter(feature_name)
 
-    def minmax_pricefeature(self, type_func, window, distance = False, save_features = False):
+    def minmax_pricefeature(self, type_func, window, distance = False, plot = False, save_features = False):
         """
         perform relative price/distance with respect to the min/max price in a given time scope
 
@@ -2809,103 +2790,453 @@ class hmm_feature_selector():
         self.feature_results = feature_results
         self.best_features = pd.DataFrame(self.feature_results).T.sort_values('mean relevance').iloc[-1,:].features
 
-class signal_analyser_object:
+def execute_signal_analyser(test_data_size, feature_name, days_list, configuration, method, object_stock, signal_analyser_object, plot = False, backtest= False, exit_params = {}):
+    '''
+    code snippet that is going run some objects. The analysis is signal analyse which is backtesting
+
+            Parameters:
+                    test_data_size (int): test data size
+                    feature_name (str): name of the feature to assess
+                    days_list (list): tome scope to assess the returns
+                    configuration (dict): parameters of the method to run
+                    object_stock (obj): object with data to assess
+                    signal_analyser_object (obj): signal_analyser object
+                    plot (boolean): if true, plot results
+                    backtest (boolean): if true, run backtest 
+                    exit_params (dict): parameters of exit returns
+
+            Returns:
+                    mean_median_return (float): median return of the backtests
+    '''
+    method(**configuration)
+    signal_assess = signal_analyser_object(object_stock.df,object_stock.stock_code,show_plot = plot)
+    signal_assess.signal_analyser(test_size = test_data_size, feature_name = feature_name, days_list = days_list, threshold = 1)
+
+    if backtest:
+        print('-----------------------back test ---------------------------')
+        signal_assess.create_backtest_signal(backtest, test_data_size, feature_name, **exit_params )
+
+    return signal_assess.mean_median_return
+
+def iterate_signal_analyser(test_data_size,feature_name, days_list, arguments_to_test, method, object_stock, signal_analyser_object, plot = True):
+    '''
+    code snippet is going to iterate signal analyser
+
+            Parameters:
+                    test_data_size (int): test data size
+                    feature_name (str): name of the feature to assess
+                    days_list (list): tome scope to assess the returns
+                    arguments_to_test: parameters to test
+                    method: methods to run
+                    object_stock (obj): object with data to assess
+                    signal_analyser_object (obj): signal_analyser object
+                    plot (boolean): if true, plot results
+
+            Returns:
+                    best_result (int): index from the arguments_to_test with the best result
+    '''
+    results = list()
+    for key in arguments_to_test.keys():
+        configuration = arguments_to_test.get(key)
+        mean_median_return = execute_signal_analyser(test_data_size, feature_name, days_list, configuration, method, object_stock, signal_analyser_object)
+        results.append(mean_median_return)
+
+    df_result = pd.DataFrame({'keys':arguments_to_test.keys(),'results':results})
+    if plot:
+        plt.plot(df_result['keys'], df_result['results'])
+        plt.scatter(df_result['keys'], df_result['results'])
+        plt.title('simulation between configurations')
+        plt.ylabel('median expected return')
+        plt.show()
+
+    best_result = df_result.sort_values('results',ascending = False)['keys'].values[0]
+    return best_result
+
+class analyse_index(stock_eda_panel):
     """
-    class that is going to analyse signals
+    class that is going to train hmm models to perform feature selection
 
     Attributes
     ----------
-    data  : pd.DataFrame
-        symbol of the asset
-    ticket_name :str
-        asset symbol
-    show_plot : boolean
-        if true show plot for every method
+    data_index : pd.DataFrame
+         name of the index
+    indexes: list
+        list of indexes
+    asset : str
+         name of the asset
+    n_obs : int
+         number of rows to extract
+    lag : int
+         lag to apply
+    data_window : str
+         5y 10y 15y
+    show_plot : bool
+         If True, show plots
     save_path : str
-        if true, save results in file
+         local path for saving e.g r'C:/path/to/the/file/'
     save_aws : str
-        if true, export results to remote repo
+         remote key in s3 bucket path e.g. 'path/to/file/'
     aws_credentials : dict
-        credentials for aws
-    return_fig : boolean
-        if true, methods will return objects
-    create_backtest_signal(days_strategy=list, test_size=int, feature_name=str, high_exit=float, low_exit=float):
-        perform backtest signal analysis
-        
+         dict with the aws credentials
+    merger_df : pd.DataFrame
+        dataframe with the index and asset data
+    states_result = dict
+        betas and correlation score results
+
     Methods
     -------
-    signal_analyser(test_size=int, feature_name=str, days_list=list, threshold=float,verbose=boolean, signal_position=boolean):
-        perform signal analysis and feature extraction
-
+    process_data():
+        using stock_eda_panel, get data and merge data
+    plot_betas(sample_size=int, offset=int, subsample_ts=int):
+        display beta analysis plot
+    get_betas(subsample_ts=int)
+        get general beta and last sample beta, correlation score is included too
     """
-
-    def __init__(self, data,symbol_name, show_plot = True, save_path = False, save_aws = False, aws_credentials = False, return_fig = False):
+    def __init__(self, index_data, asset, n_obs, lag, data_window = '5y', show_plot = False, save_path = False, save_aws = False, aws_credentials = False, return_fig = False):
         """
         Initialize object
 
         Parameters
         ----------
-        data (pd.DataFrame): data
-        ticket_name (str): name of the asset
-        show_plot (boolean): if true show plot for every method
-        save_path (str): if true, save results in file e.g r'C:/path/to/the/file/'
-        save_aws (str): if true, export results to remote repo e.g. 'path/to/file/'
-        aws_credentials (dict): credentials for aws
-        return_fig (boolean): if true, methods will return objects
+        index_data (pd.DataFrame or str): index data dataframe or index string
+        asset (str): name of the asset
+        n_obs (int): number of rows to extract
+        lag (int): lag to apply
+        data_window (str): 5y 10y 15y
+        show_plot (bool): If True, show plots
+        save_path (str): local path for saving e.g r'C:/path/to/the/file/'
+        save_aws (str): remote key in s3 bucket path e.g. 'path/to/file/'
+        aws_credentials (dict): dict with the aws credentials
 
         Returns
         -------
         None
         """
-        self.data = data.copy()
-        self.ticket_name = symbol_name
+
+        
+        if type(index_data) != str:
+            index_data['Date'] = pd.to_datetime(index_data['Date'])
+            self.index_data = index_data
+            self.indexes = [ x for x in list(index_data.columns) if x != 'Date']
+        else:
+            self.indexes = [index_data]
+            
+        self.index_data = index_data
+        self.asset = asset
+        self.n_obs = n_obs
+        self.data_window = data_window
+        self.lag = lag
+
         self.show_plot = show_plot
+        self.return_fig = return_fig
         self.save_path = save_path
         self.save_aws = save_aws
-        self.aws_credentials = aws_credentials
-        self.return_fig = return_fig
 
-    def signal_analyser(self, test_size, feature_name, days_list, threshold = 0.05,verbose = False, signal_position = False):
+    def process_data(self):
         """
-        perform signal analysis and feature extraction
+        using stock_eda_panel, get data and merge data
+    
+        Parameters
+        ----------
+        None
+    
+        Returns
+        -------
+        None
+        """
+        asset =  stock_eda_panel(self.asset, self.n_obs, data_window=self.data_window)
+        asset.get_data()
+        df = asset.df[['Date','Close']]
+        
+        if type(self.index_data) != str:
+            df_merge = df.merge(self.index_data, on = ['Date'], how = 'left').sort_values('Date')
+            
+        else:
+            indx =  stock_eda_panel(self.index_data, self.n_obs, data_window=self.data_window)
+            indx.get_data()
+            indx_df = indx.df[['Date','Close']].rename(columns = {'Close':self.index_data})
+            df_merge = df.merge(indx_df, on = ['Date'], how = 'left').sort_values('Date')
+            
+        for colx in ['Close'] + self.indexes:
+            df_merge[f'{colx}_pct'] = df_merge[colx]/df_merge[colx].shift(self.lag) - 1
+            
+        df_merge.dropna(inplace = True)
+        self.merger_df = df_merge.rename(columns = {'Close_pct': 'asset_return'})
+
+    def plot_betas(self,sample_size, offset, subsample_ts =False, index = False):
+        """
+        display beta analysis plot
 
         Parameters
         ----------
-        test_size (int): test data size
-        feature_name (str): name of the feature to assess
-        days_list (list): list of integers [3,8,10] to assess
-        threshold (float): alpha or z threshold
-        verbose (boolean): print metrics
-        signal_position (int): if true, the signal is taken at the given step after the signal end
+        sample_size (int): number of days or window size to calculate beta
+        offset (int): overlap between windows
+        subsample_ts (int): subsample size of data 
 
         Returns
         -------
         None
         """
-        data = self.data
-        self.feature_name = feature_name
-        up_signal, low_signal= f'signal_up_{feature_name}', f'signal_low_{feature_name}'
-        features_base = ['Date', up_signal, low_signal, 'Close']
+        if (type(self.index_data) == str) & (index != False):
+            raise Exception("No need of index argument")
+        else:
+            index = self.indexes[0]
+            
+        index_pct = f'{index}_pct'
+        ### ploting analysis
+        figure, ax = plt.subplot_mosaic(
+            [["scatter_total", "scatter_sample",'ts','ts']],
+            layout="constrained",
+            figsize=(18, 5)
+        )
 
-        df = data[features_base].sort_values('Date').iloc[0:-test_size,:]
-        returns_list = list()
+        ax['scatter_total'].scatter(self.merger_df.asset_return, self.merger_df[index_pct])
+    
+        huber_regr = HuberRegressor(fit_intercept = True)
+        huber_regr.fit(self.merger_df.asset_return.values.reshape(-1,1), self.merger_df[index_pct].values.reshape(-1,1))
+        b, a = huber_regr.coef_[0], huber_regr.intercept_
+    
+        # b, a = np.polyfit(self.merger_df.asset_return, self.merger_df[index_pct], 1)
+        ax['scatter_total'].plot(self.merger_df.asset_return, b*self.merger_df.asset_return+a, color='red')
 
-        for days in days_list:
+        ax['ts'].plot(self.merger_df.Date, self.merger_df.Close, color = 'grey', alpha = 0.3)
 
-            feature_ = f'return_{days}d'
-            days = days + signal_position if signal_position else days
-            df[feature_] = (df['Close'].shift(-days)/df['Close']-1)*100
-            returns_list.append(feature_)
+        if subsample_ts:
+            self.merger_df = self.merger_df.iloc[-subsample_ts:,:].dropna()
 
-        df['signal_type'] = np.where(
-            df[up_signal] == 1,
-            'up',
-            np.where(
-                df[low_signal] == 1,
-                'down',
-                None
-            )
-        )
+        for i in range(0,len(self.merger_df)-sample_size,offset):
+
+            merger_ = self.merger_df.sort_values('Date', ascending = False).iloc[i:i+sample_size,:]
+            x = merger_[index_pct]
+            y = merger_.asset_return
+            # b, a = np.polyfit(x,y, 1)
+            huber_regr = HuberRegressor(fit_intercept = True)
+            huber_regr.fit(x.values.reshape(-1,1), y.values.reshape(-1,1))
+            b, a = huber_regr.coef_[0], huber_regr.intercept_
+            
+            normalize = mcolors.Normalize(vmin=-1, vmax=1)
+            colormap = cm.jet
+
+            ax['scatter_sample'].plot(x, y,'o', color = 'blue', alpha = 0.1)
+            ax['scatter_sample'].plot(x, b*x+a, color=colormap(normalize(b)))
+            ax['scatter_sample'].set_xlim(-0.06, 0.06)
+            ax['scatter_sample'].set_ylim(-0.06, 0.06)
+
+            plot = ax['ts'].scatter(merger_.Date, merger_.Close, color=colormap(normalize(b)), s = 10)
+
+        scalarmappaple = cm.ScalarMappable(norm=normalize, cmap=colormap)
+        scalarmappaple.set_array(x)
+
+        plt.title(f'{self.asset} using index: {index}')
+        plt.colorbar(scalarmappaple)
+
+        if self.show_plot:
+            plt.show()
+            
+        if self.save_path:
+            result_plot_name = f'market_best_fit.png'
+            figure.savefig(self.save_path+result_plot_name)
+
+        if self.save_path and self.save_aws:
+            # upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{self.asset}/'+result_plot_name,input_path = self.save_path+result_plot_name)
+            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = self.save_aws + result_plot_name, input_path = self.save_path + result_plot_name, aws_credentials = self.aws_credentials)
+            
+        if not self.show_plot:
+            plt.close() 
+            
+        if self.return_fig:
+            return figure
+            
+    def get_betas(self,subsample_ts=False):
+        """
+        get general beta and last sample beta, correlation score is included too
+    
+        Parameters
+        ----------
+        subsample_ts (int): subsample size of data 
+    
+        Returns
+        -------
+        None
+        """
+        result = list()
+        for index in self.indexes:
+            
+            index_pct = f'{index}_pct'
+            huber_regr = HuberRegressor(fit_intercept = True)
+            huber_regr.fit(self.merger_df.asset_return.values.reshape(-1,1), self.merger_df[index_pct].values.reshape(-1,1))
+            general_beta, a = huber_regr.coef_[0], huber_regr.intercept_
+            general_r = stats.mstats.pearsonr(self.merger_df.asset_return, self.merger_df[index])[0]
+
+            dict_res = {
+                    'index':index,
+                    'general_beta':general_beta,
+                    'general_r':general_r,
+                }
+    
+            if subsample_ts:
+                tmp_df = self.merger_df.iloc[-subsample_ts:,:].dropna()
+                huber_regr = HuberRegressor(fit_intercept = True)
+                huber_regr.fit(tmp_df.asset_return.values.reshape(-1,1), tmp_df[index_pct].values.reshape(-1,1))
+                sample_beta, a = huber_regr.coef_[0], huber_regr.intercept_
+                sample_r = stats.mstats.pearsonr(tmp_df.asset_return, tmp_df[index])[0]
+                dict_res['sample_beta'] = sample_beta
+                dict_res['sample_r'] = sample_r
+                
+            result.append(dict_res)
+    
+        self.states_result = result
+
+
+def get_relevant_beta(data_market, ticket_name,  show_plot = True, save_path = False, save_aws = False, aws_credentials = False):
+    '''
+    select relevant beta result data of a given asset
+
+            Parameters:
+                    data_market (pd.DataFrame): dataframe of the market results 
+                    ticket_name (str): name of the asset
+                    show_plot (bool): If tru, plot results
+                    save_path (str): local path for saving e.g r'C:/path/to/the/file/'
+                    save_aws (str):  remote key in s3 bucket path e.g. 'path/to/file/'
+                    aws_credentials (dict): dict of the aws credentials
+
+            Returns:
+                    selection (pd.DataFrame): dataframe of the most relevant beta
+    '''
+    all_betas = data_market[data_market.asset == ticket_name].sort_values('general_r', ascending = False)
+    all_betas['gen_r2'] = all_betas.general_r ** 2
+    all_betas['sampl_r2'] = all_betas.sample_r ** 2
+    selection = all_betas.sort_values('gen_r2',ascending =False).head(2).sort_values('sampl_r2',ascending =False).head(1).drop(columns = ['gen_r2','sampl_r2'])
+
+    if show_plot:
+        print(selection)
+    if save_path:
+        result_plot_name = f'market_best_fit.csv'
+        selection.to_csv(save_path+result_plot_name)
+
+    if save_path and save_aws:
+        # upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{ticket_name}/'+result_plot_name,input_path = save_path+result_plot_name)
+        upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = save_aws + result_plot_name, input_path = save_path + result_plot_name, aws_credentials = aws_credentials)
+    return selection
+
+#### to deprecate
+
+def sharpe_ratio(return_series):
+
+    '''
+    calculate sharpe ratio for given array.
+
+            Parameters:
+                    return_series (pd.series): pandas series of the asset returns
+
+            Returns:
+                    sharpe (float): sharpe ratio
+    '''
+
+    N = 255 # Trading days in the year (change to 365 for crypto)
+    rf = 0.005 # Half a percent risk free rare
+    mean = return_series.mean() * N -rf
+    sigma = return_series.std() * np.sqrt(N)
+    sharpe = round(mean / sigma, 3)
+    return sharpe
+
+class signal_analyser_object:
+    """
+    class that is going to analyse signals
+
+    Attributes
+    ----------
+    data  : pd.DataFrame
+        symbol of the asset
+    ticket_name :str
+        asset symbol
+    show_plot : boolean
+        if true show plot for every method
+    save_path : str
+        if true, save results in file
+    save_aws : str
+        if true, export results to remote repo
+    aws_credentials : dict
+        credentials for aws
+    return_fig : boolean
+        if true, methods will return objects
+    create_backtest_signal(days_strategy=list, test_size=int, feature_name=str, high_exit=float, low_exit=float):
+        perform backtest signal analysis
+        
+    Methods
+    -------
+    signal_analyser(test_size=int, feature_name=str, days_list=list, threshold=float,verbose=boolean, signal_position=boolean):
+        perform signal analysis and feature extraction
+
+    """
+
+    def __init__(self, data,symbol_name, show_plot = True, save_path = False, save_aws = False, aws_credentials = False, return_fig = False):
+        """
+        Initialize object
+
+        Parameters
+        ----------
+        data (pd.DataFrame): data
+        ticket_name (str): name of the asset
+        show_plot (boolean): if true show plot for every method
+        save_path (str): if true, save results in file e.g r'C:/path/to/the/file/'
+        save_aws (str): if true, export results to remote repo e.g. 'path/to/file/'
+        aws_credentials (dict): credentials for aws
+        return_fig (boolean): if true, methods will return objects
+
+        Returns
+        -------
+        None
+        """
+        self.data = data.copy()
+        self.ticket_name = symbol_name
+        self.show_plot = show_plot
+        self.save_path = save_path
+        self.save_aws = save_aws
+        self.aws_credentials = aws_credentials
+        self.return_fig = return_fig
+
+    def signal_analyser(self, test_size, feature_name, days_list, threshold = 0.05,verbose = False, signal_position = False):
+        """
+        perform signal analysis and feature extraction
+
+        Parameters
+        ----------
+        test_size (int): test data size
+        feature_name (str): name of the feature to assess
+        days_list (list): list of integers [3,8,10] to assess
+        threshold (float): alpha or z threshold
+        verbose (boolean): print metrics
+        signal_position (int): if true, the signal is taken at the given step after the signal end
+
+        Returns
+        -------
+        None
+        """
+        data = self.data
+        self.feature_name = feature_name
+        up_signal, low_signal= f'signal_up_{feature_name}', f'signal_low_{feature_name}'
+        features_base = ['Date', up_signal, low_signal, 'Close']
+
+        df = data[features_base].sort_values('Date').iloc[0:-test_size,:]
+        returns_list = list()
+
+        for days in days_list:
+
+            feature_ = f'return_{days}d'
+            days = days + signal_position if signal_position else days
+            df[feature_] = (df['Close'].shift(-days)/df['Close']-1)*100
+            returns_list.append(feature_)
+
+        df['signal_type'] = np.where(
+            df[up_signal] == 1,
+            'up',
+            np.where(
+                df[low_signal] == 1,
+                'down',
+                None
+            )
+        )
         df = df[~df.signal_type.isna()]
         df['lag_Date'] = df['Date'].shift(1)
         df['lag_signal_type'] = df['signal_type'].shift(1)
@@ -3173,332 +3504,3 @@ class signal_analyser_object:
 
         if self.return_fig:
             return fig, messages
-
-def execute_signal_analyser(test_data_size, feature_name, days_list, configuration, method, object_stock, signal_analyser_object, plot = False, backtest= False, exit_params = {}):
-    '''
-    code snippet that is going run some objects. The analysis is signal analyse which is backtesting
-
-            Parameters:
-                    test_data_size (int): test data size
-                    feature_name (str): name of the feature to assess
-                    days_list (list): tome scope to assess the returns
-                    configuration (dict): parameters of the method to run
-                    object_stock (obj): object with data to assess
-                    signal_analyser_object (obj): signal_analyser object
-                    plot (boolean): if true, plot results
-                    backtest (boolean): if true, run backtest 
-                    exit_params (dict): parameters of exit returns
-
-            Returns:
-                    mean_median_return (float): median return of the backtests
-    '''
-    method(**configuration)
-    signal_assess = signal_analyser_object(object_stock.df,object_stock.stock_code,show_plot = plot)
-    signal_assess.signal_analyser(test_size = test_data_size, feature_name = feature_name, days_list = days_list, threshold = 1)
-
-    if backtest:
-        print('-----------------------back test ---------------------------')
-        signal_assess.create_backtest_signal(backtest, test_data_size, feature_name, **exit_params )
-
-    return signal_assess.mean_median_return
-
-def iterate_signal_analyser(test_data_size,feature_name, days_list, arguments_to_test, method, object_stock, signal_analyser_object, plot = True):
-    '''
-    code snippet is going to iterate signal analyser
-
-            Parameters:
-                    test_data_size (int): test data size
-                    feature_name (str): name of the feature to assess
-                    days_list (list): tome scope to assess the returns
-                    arguments_to_test: parameters to test
-                    method: methods to run
-                    object_stock (obj): object with data to assess
-                    signal_analyser_object (obj): signal_analyser object
-                    plot (boolean): if true, plot results
-
-            Returns:
-                    best_result (int): index from the arguments_to_test with the best result
-    '''
-    results = list()
-    for key in arguments_to_test.keys():
-        configuration = arguments_to_test.get(key)
-        mean_median_return = execute_signal_analyser(test_data_size, feature_name, days_list, configuration, method, object_stock, signal_analyser_object)
-        results.append(mean_median_return)
-
-    df_result = pd.DataFrame({'keys':arguments_to_test.keys(),'results':results})
-    if plot:
-        plt.plot(df_result['keys'], df_result['results'])
-        plt.scatter(df_result['keys'], df_result['results'])
-        plt.title('simulation between configurations')
-        plt.ylabel('median expected return')
-        plt.show()
-
-    best_result = df_result.sort_values('results',ascending = False)['keys'].values[0]
-    return best_result
-
-class analyse_index(stock_eda_panel):
-    """
-    class that is going to train hmm models to perform feature selection
-
-    Attributes
-    ----------
-    data_index : pd.DataFrame
-         name of the index
-    indexes: list
-        list of indexes
-    asset : str
-         name of the asset
-    n_obs : int
-         number of rows to extract
-    lag : int
-         lag to apply
-    data_window : str
-         5y 10y 15y
-    show_plot : bool
-         If True, show plots
-    save_path : str
-         local path for saving e.g r'C:/path/to/the/file/'
-    save_aws : str
-         remote key in s3 bucket path e.g. 'path/to/file/'
-    aws_credentials : dict
-         dict with the aws credentials
-    merger_df : pd.DataFrame
-        dataframe with the index and asset data
-    states_result = dict
-        betas and correlation score results
-
-    Methods
-    -------
-    process_data():
-        using stock_eda_panel, get data and merge data
-    plot_betas(sample_size=int, offset=int, subsample_ts=int):
-        display beta analysis plot
-    get_betas(subsample_ts=int)
-        get general beta and last sample beta, correlation score is included too
-    """
-    def __init__(self, index_data, asset, n_obs, lag, data_window = '5y', show_plot = False, save_path = False, save_aws = False, aws_credentials = False, return_fig = False):
-        """
-        Initialize object
-
-        Parameters
-        ----------
-        index_data (pd.DataFrame or str): index data dataframe or index string
-        asset (str): name of the asset
-        n_obs (int): number of rows to extract
-        lag (int): lag to apply
-        data_window (str): 5y 10y 15y
-        show_plot (bool): If True, show plots
-        save_path (str): local path for saving e.g r'C:/path/to/the/file/'
-        save_aws (str): remote key in s3 bucket path e.g. 'path/to/file/'
-        aws_credentials (dict): dict with the aws credentials
-
-        Returns
-        -------
-        None
-        """
-
-        
-        if type(index_data) != str:
-            index_data['Date'] = pd.to_datetime(index_data['Date'])
-            self.index_data = index_data
-            self.indexes = [ x for x in list(index_data.columns) if x != 'Date']
-        else:
-            self.indexes = [index_data]
-            
-        self.index_data = index_data
-        self.asset = asset
-        self.n_obs = n_obs
-        self.data_window = data_window
-        self.lag = lag
-
-        self.show_plot = show_plot
-        self.return_fig = return_fig
-        self.save_path = save_path
-        self.save_aws = save_aws
-
-    def process_data(self):
-        """
-        using stock_eda_panel, get data and merge data
-    
-        Parameters
-        ----------
-        None
-    
-        Returns
-        -------
-        None
-        """
-        asset =  stock_eda_panel(self.asset, self.n_obs, data_window=self.data_window)
-        asset.get_data()
-        df = asset.df[['Date','Close']]
-        
-        if type(self.index_data) != str:
-            df_merge = df.merge(self.index_data, on = ['Date'], how = 'left').sort_values('Date')
-            
-        else:
-            indx =  stock_eda_panel(self.index_data, self.n_obs, data_window=self.data_window)
-            indx.get_data()
-            indx_df = indx.df[['Date','Close']].rename(columns = {'Close':self.index_data})
-            df_merge = df.merge(indx_df, on = ['Date'], how = 'left').sort_values('Date')
-            
-        for colx in ['Close'] + self.indexes:
-            df_merge[f'{colx}_pct'] = df_merge[colx]/df_merge[colx].shift(self.lag) - 1
-            
-        df_merge.dropna(inplace = True)
-        self.merger_df = df_merge.rename(columns = {'Close_pct': 'asset_return'})
-
-    def plot_betas(self,sample_size, offset, subsample_ts =False, index = False):
-        """
-        display beta analysis plot
-
-        Parameters
-        ----------
-        sample_size (int): number of days or window size to calculate beta
-        offset (int): overlap between windows
-        subsample_ts (int): subsample size of data 
-
-        Returns
-        -------
-        None
-        """
-        if (type(self.index_data) == str) & (index != False):
-            raise Exception("No need of index argument")
-        else:
-            index = self.indexes[0]
-            
-        index_pct = f'{index}_pct'
-        ### ploting analysis
-        figure, ax = plt.subplot_mosaic(
-            [["scatter_total", "scatter_sample",'ts','ts']],
-            layout="constrained",
-            figsize=(18, 5)
-        )
-
-        ax['scatter_total'].scatter(self.merger_df.asset_return, self.merger_df[index_pct])
-    
-        huber_regr = HuberRegressor(fit_intercept = True)
-        huber_regr.fit(self.merger_df.asset_return.values.reshape(-1,1), self.merger_df[index_pct].values.reshape(-1,1))
-        b, a = huber_regr.coef_[0], huber_regr.intercept_
-    
-        # b, a = np.polyfit(self.merger_df.asset_return, self.merger_df[index_pct], 1)
-        ax['scatter_total'].plot(self.merger_df.asset_return, b*self.merger_df.asset_return+a, color='red')
-
-        ax['ts'].plot(self.merger_df.Date, self.merger_df.Close, color = 'grey', alpha = 0.3)
-
-        if subsample_ts:
-            self.merger_df = self.merger_df.iloc[-subsample_ts:,:].dropna()
-
-        for i in range(0,len(self.merger_df)-sample_size,offset):
-
-            merger_ = self.merger_df.sort_values('Date', ascending = False).iloc[i:i+sample_size,:]
-            x = merger_[index_pct]
-            y = merger_.asset_return
-            # b, a = np.polyfit(x,y, 1)
-            huber_regr = HuberRegressor(fit_intercept = True)
-            huber_regr.fit(x.values.reshape(-1,1), y.values.reshape(-1,1))
-            b, a = huber_regr.coef_[0], huber_regr.intercept_
-            
-            normalize = mcolors.Normalize(vmin=-1, vmax=1)
-            colormap = cm.jet
-
-            ax['scatter_sample'].plot(x, y,'o', color = 'blue', alpha = 0.1)
-            ax['scatter_sample'].plot(x, b*x+a, color=colormap(normalize(b)))
-            ax['scatter_sample'].set_xlim(-0.06, 0.06)
-            ax['scatter_sample'].set_ylim(-0.06, 0.06)
-
-            plot = ax['ts'].scatter(merger_.Date, merger_.Close, color=colormap(normalize(b)), s = 10)
-
-        scalarmappaple = cm.ScalarMappable(norm=normalize, cmap=colormap)
-        scalarmappaple.set_array(x)
-
-        plt.title(f'{self.asset} using index: {index}')
-        plt.colorbar(scalarmappaple)
-
-        if self.show_plot:
-            plt.show()
-            
-        if self.save_path:
-            result_plot_name = f'market_best_fit.png'
-            figure.savefig(self.save_path+result_plot_name)
-
-        if self.save_path and self.save_aws:
-            # upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{self.asset}/'+result_plot_name,input_path = self.save_path+result_plot_name)
-            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = self.save_aws + result_plot_name, input_path = self.save_path + result_plot_name, aws_credentials = self.aws_credentials)
-            
-        if not self.show_plot:
-            plt.close() 
-            
-        if self.return_fig:
-            return figure
-            
-    def get_betas(self,subsample_ts=False):
-        """
-        get general beta and last sample beta, correlation score is included too
-    
-        Parameters
-        ----------
-        subsample_ts (int): subsample size of data 
-    
-        Returns
-        -------
-        None
-        """
-        result = list()
-        for index in self.indexes:
-            
-            index_pct = f'{index}_pct'
-            huber_regr = HuberRegressor(fit_intercept = True)
-            huber_regr.fit(self.merger_df.asset_return.values.reshape(-1,1), self.merger_df[index_pct].values.reshape(-1,1))
-            general_beta, a = huber_regr.coef_[0], huber_regr.intercept_
-            general_r = stats.mstats.pearsonr(self.merger_df.asset_return, self.merger_df[index])[0]
-
-            dict_res = {
-                    'index':index,
-                    'general_beta':general_beta,
-                    'general_r':general_r,
-                }
-    
-            if subsample_ts:
-                tmp_df = self.merger_df.iloc[-subsample_ts:,:].dropna()
-                huber_regr = HuberRegressor(fit_intercept = True)
-                huber_regr.fit(tmp_df.asset_return.values.reshape(-1,1), tmp_df[index_pct].values.reshape(-1,1))
-                sample_beta, a = huber_regr.coef_[0], huber_regr.intercept_
-                sample_r = stats.mstats.pearsonr(tmp_df.asset_return, tmp_df[index])[0]
-                dict_res['sample_beta'] = sample_beta
-                dict_res['sample_r'] = sample_r
-                
-            result.append(dict_res)
-    
-        self.states_result = result
-
-
-def get_relevant_beta(data_market, ticket_name,  show_plot = True, save_path = False, save_aws = False, aws_credentials = False):
-    '''
-    select relevant beta result data of a given asset
-
-            Parameters:
-                    data_market (pd.DataFrame): dataframe of the market results 
-                    ticket_name (str): name of the asset
-                    show_plot (bool): If tru, plot results
-                    save_path (str): local path for saving e.g r'C:/path/to/the/file/'
-                    save_aws (str):  remote key in s3 bucket path e.g. 'path/to/file/'
-                    aws_credentials (dict): dict of the aws credentials
-
-            Returns:
-                    selection (pd.DataFrame): dataframe of the most relevant beta
-    '''
-    all_betas = data_market[data_market.asset == ticket_name].sort_values('general_r', ascending = False)
-    all_betas['gen_r2'] = all_betas.general_r ** 2
-    all_betas['sampl_r2'] = all_betas.sample_r ** 2
-    selection = all_betas.sort_values('gen_r2',ascending =False).head(2).sort_values('sampl_r2',ascending =False).head(1).drop(columns = ['gen_r2','sampl_r2'])
-
-    if show_plot:
-        print(selection)
-    if save_path:
-        result_plot_name = f'market_best_fit.csv'
-        selection.to_csv(save_path+result_plot_name)
-
-    if save_path and save_aws:
-        # upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{ticket_name}/'+result_plot_name,input_path = save_path+result_plot_name)
-        upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = save_aws + result_plot_name, input_path = save_path + result_plot_name, aws_credentials = aws_credentials)
-    return selection

{virgo_modules-0.0.90 → virgo_modules-0.1.0}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.0.90
+Version: 0.1.0
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.0.90 → virgo_modules-0.1.0}/virgo_app/virgo_modules.egg-info/SOURCES.txt

@@ -9,6 +9,7 @@ virgo_app/virgo_modules.egg-info/requires.txt
 virgo_app/virgo_modules.egg-info/top_level.txt
 virgo_app/virgo_modules/src/__init__.py
 virgo_app/virgo_modules/src/aws_utils.py
+virgo_app/virgo_modules/src/backtester.py
 virgo_app/virgo_modules/src/edge_utils.py
 virgo_app/virgo_modules/src/pull_artifacts.py
 virgo_app/virgo_modules/src/re_utils.py