added two methods

script/processing.py

@@ -77,7 +77,8 @@ def get_processing_result_of_stocks_df(stock_df, profile_df):
     stock_df['sector_pct'] = stock_df['pct'] * stock_df['prev_w_in_sectore']
 
     # portfolio return
-    stock_df['portfolio_return'] = (stock_df.groupby('ticker')['portfolio_pct'].cumprod() + 1) - 1
+    stock_df['portfolio_return'] = (stock_df.groupby(
+        'ticker')['portfolio_pct'].cumprod() + 1) - 1
     # stock_df['cum_p_pct'] = stock_df.groupby(
     #     'ticker')['portfolio_pct'].cumsum()
     # stock_df['portfolio_return'] = np.exp(stock_df['cum_p_pct']) - 1
@@ -151,8 +152,6 @@ def get_portfolio_evaluation(portfolio_stock, benchmark_stock, profile_df):
     return merged_df
 
 
-
-
 def get_portfolio_sector_evaluation(portfolio_stock, benchmark_df):
     # aggregate on sector and day
     p_sector_df = portfolio_stock.groupby(['date', 'aggregate_sector'], as_index=False)\
@@ -291,8 +290,10 @@ def calculate_return(df, start, end):
     # set the pct of first row to null
     selected_df.iloc[0, selected_df.columns.get_indexer(
         ['portfolio_pct_p', 'portfolio_pct_b'])] = 0
-    selected_df['return_p'] = (1 + selected_df['portfolio_pct_p']).cumprod() - 1
-    selected_df['return_b'] = (1 + selected_df['portfolio_pct_b']).cumprod() - 1
+    selected_df['return_p'] = (
+        1 + selected_df['portfolio_pct_p']).cumprod() - 1
+    selected_df['return_b'] = (
+        1 + selected_df['portfolio_pct_b']).cumprod() - 1
     selected_df['active_return'] = selected_df.return_p - selected_df.return_b
     return selected_df
 
@@ -367,3 +368,32 @@ def change_resolution(df, freq='W'):
     '''
     df['freq'] = pd.to_datetime(df['date']).dt.to_period(freq)
     return df.groupby('freq').first().reset_index()
+
+
+def calculate_weight_using_cash(df):
+    '''
+    patch df with current weight for each entry
+    use cash to calculate weight
+
+    Parameters
+    ----------
+    df : dataframe
+        dataframe with processed cash column
+
+    '''
+    df['cur_w'] = float('nan')
+    grouped = df.groupby('time')
+    df.cur_w = grouped.cash.transform(lambda x: x / x.sum())
+
+
+def calculate_cash(df):
+    '''
+    patch df with cash column
+    cash = shares * close
+
+    Parameters
+    ----------
+    df : dataframe
+        dataframe with processed shares and close column
+    '''
+    df['cash'] = df['shares'] * df['close']