virgo-modules 0.0.32__tar.gz → 0.0.42__tar.gz

{virgo_modules-0.0.32 → virgo_modules-0.0.42}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.0.32
+Version: 0.0.42
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.0.32 → virgo_modules-0.0.42}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.0.32",
+    version="0.0.42",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.0.32 → virgo_modules-0.0.42}/virgo_app/virgo_modules/src/re_utils.py

@@ -2,6 +2,7 @@ import matplotlib.pyplot as plt
 import matplotlib.gridspec as gridspec
 import seaborn as sns; sns.set()
 import matplotlib.patheffects as path_effects
+from  matplotlib.dates import DateFormatter
 
 import plotly.express as px
 from plotly.subplots import make_subplots
@@ -403,7 +404,7 @@ def rank_by_return(data, lag_days, top_n = 5):
     
     return result
 
-def get_data(ticker_name:str, ticket_settings:dict, n_days:int = False, hmm_available: object = False) -> object:
+def get_data(ticker_name:str, ticket_settings:dict, n_days:int = False, hmm_available: object = False, data_window:str = '5y') -> object:
     """
     this functions runs the stock_eda_panel
     it is shared between train model and predictions
@@ -416,7 +417,7 @@ def get_data(ticker_name:str, ticket_settings:dict, n_days:int = False, hmm_avai
     returns: stock eda panel
     """
 
-    object_stock = stock_eda_panel(ticker_name , n_days )
+    object_stock = stock_eda_panel(ticker_name , n_days, data_window)
     object_stock.get_data()
 
     # computing features if they exists in the ticketr settings
@@ -898,4 +899,45 @@ class produce_plotly_plots:
         if self.show_plot:
             fig.show()
         if self.save_path and self.save_aws:
-            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{self.ticket_name}/'+result_json_name ,input_path = self.save_path+result_json_name)
+            upload_file_to_aws(bucket = 'VIRGO_BUCKET', key = f'market_plots/{self.ticket_name}/'+result_json_name ,input_path = self.save_path+result_json_name)
+
+def plot_hmm_analysis_logger(data_frame,test_data_size, save_path = False, show_plot = True):
+    
+    df = data_frame
+    df_ = df[['Date','hmm_feature','Close',"chain_return"]].sort_values('Date')
+    fig, axs = plt.subplots(1,2,figsize=(10,4))
+    df__ = df_.iloc[:-test_data_size,]
+    sns.boxplot(data=df__, x="hmm_feature", y="chain_return",ax = axs[0]).set_title('train dist')
+    df__ = df_.iloc[-test_data_size:,]
+    sns.boxplot(data=df__ , x="hmm_feature", y="chain_return",ax = axs[1]).set_title('test dist')
+    if save_path:
+        plt.savefig(save_path) 
+    if not show_plot:
+        plt.close()
+
+def plot_hmm_tsanalysis_logger(data_frame, test_data_size,save_path = False, show_plot = True):
+    
+    df = data_frame
+    df_ = df[['Date','hmm_feature','Close',"chain_return"]].sort_values('Date')
+    states = list(df_['hmm_feature'].unique())
+    states.sort()
+    
+    if test_data_size:
+        df__ = df_.iloc[-test_data_size:,]
+        date_limit = pd.Timestamp(str(df__.Date.min().strftime('%Y-%m-%d')))
+    
+    fig, ax1 = plt.subplots(figsize=(10,4))
+    ax1.plot(df_['Date'],df_["Close"])
+    
+    for state in states:
+        df__ = df_[df_.hmm_feature == state]
+        ax1.scatter(df__['Date'],df__["Close"], label = state)
+    formatter = DateFormatter('%Y-%m-%d')
+    if test_data_size:
+        plt.axvline(x=date_limit, color = 'r')
+    fig.legend()
+    fig.autofmt_xdate()
+    if save_path:
+        plt.savefig(save_path) 
+    if not show_plot:
+        plt.close()

{virgo_modules-0.0.32 → virgo_modules-0.0.42}/virgo_app/virgo_modules/src/ticketer_source.py

@@ -152,12 +152,13 @@ def states_relevance_score(data, default_benchmark_sd = 0.00003, t_threshold = 2
 
 class stock_eda_panel(object):
     
-    def __init__(self, stock_code, n_days):
+    def __init__(self, stock_code, n_days, data_window = '5y'):
         self.stock_code = stock_code
         self.n_days = n_days
         self.today = datetime.date.today()
         self.features = list()
         self.signals = list()
+        self.data_window = data_window
         
     def augmented_dickey_fuller_statistics(self,time_series, label):
         result = adfuller(time_series.dropna().values)
@@ -168,8 +169,7 @@ class stock_eda_panel(object):
         begin_date_str = begin_date.strftime('%Y-%m-%d')
 
         stock = yf.Ticker(self.stock_code)
-        #df = stock.history(period="max")
-        df = stock.history(period='5y')
+        df = stock.history(period=self.data_window)
         
         df = df.sort_values('Date')
         df.reset_index(inplace=True)
@@ -177,7 +177,12 @@ class stock_eda_panel(object):
         df['Date'] = pd.to_datetime(df['Date'])
         
         df = df[df.Date >= begin_date_str ]
-        self.settings_general = {'n_days':self.n_days, 'begin_date':begin_date_str}
+        self.settings_general = {
+            'n_days':self.n_days,
+            'begin_date':begin_date_str,
+            'data_window': self.data_window,
+            'execution_date': self.today.strftime('%Y-%m-%d')
+        }
         self.df = df
         
         ### cleaning volume
@@ -226,8 +231,6 @@ class stock_eda_panel(object):
         df["lower"] = df['Close_roll_mean'] - df["Close_roll_std"]*2
 
         df = df[df.Date >= begin_date_str ]
-        self.settings_general = {'n_days':self.n_days, 'begin_date':begin_date_str}
-        self.df = df
 
         fig = make_subplots(rows=1, cols=1,vertical_spacing = 0.1,shared_xaxes=True,
                            subplot_titles=(
@@ -562,8 +565,7 @@ class stock_eda_panel(object):
         begin_date_str = begin_date.strftime('%Y-%m-%d')
 
         stock = yf.Ticker(self.pair_symbol)
-        #df = stock.history(period="max")
-        df = stock.history(period='5y')
+        df = stock.history(period=self.data_window)
         df = df.sort_values('Date')
         df.reset_index(inplace=True)
         df['Date'] = pd.to_datetime(df['Date'], format='mixed',utc=True).dt.date

{virgo_modules-0.0.32 → virgo_modules-0.0.42}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.0.32
+Version: 0.0.42
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire