make it a package, get it working with my data

backtester/backtester.py

@@ -97,8 +97,8 @@ class Backtest:
         if sma_days:
             self.stocks_data.sma(sma_days)
 
-        dates = pd.DataFrame(self.options_data._data[['quotedate',
-                                                      'volume']]).drop_duplicates('quotedate').set_index('quotedate')
+        dates = pd.DataFrame(self.options_data._data[['date',
+                                                      'volume']]).drop_duplicates('date').set_index('date')
         rebalancing_days = pd.to_datetime(
             dates.groupby(pd.Grouper(freq=str(rebalance_freq) +
                                      'BMS')).apply(lambda x: x.index.min()).values) if rebalance_freq else []

backtester/datahandler/__init__.py

@@ -2,5 +2,6 @@ from .schema import Schema
 
 from .historical_options_data import HistoricalOptionsData
 from .tiingo_data import TiingoData
+from .option_metrics_data import OptionMetricsData
 
 __all__ = ['Schema', 'HistoricalOptionsData', 'TiingoData']

backtester/datahandler/option_metrics_data.py

@@ -0,0 +1,111 @@
+import pandas as pd
+import os
+from .schema import Schema
+
+from bscsi_data.optm_lz.load import load_for_tickers
+
+
+class OptionMetricsData:
+    """Historical Options Data container class."""
+    def __init__(self, tickers, schema=None, **params):
+        if schema is None:
+            self.schema = OptionMetricsData.default_schema()
+
+        self._data = load_for_tickers(tickers).reset_index()
+        # self._data['date']=self._data.date.dt.tz_localize('utc')
+        # self._data['exdate']=self._data['exdate'].dt.tz_localize('utc')
+        # print(self._data.head(5))
+
+        columns = self._data.columns
+        for _key, col in self.schema:
+            assert col in columns, f"missing '{col}' in data"
+        # assert all((col in columns for _key, col in self.schema))
+
+        date_col = self.schema['date']
+        expiration_col = self.schema['expiration']
+
+        self._data['dte'] = (self._data[expiration_col] - self._data[date_col]).dt.days
+        self.schema.update({'dte': 'dte'})
+
+        self.start_date = self._data[date_col].min()
+        self.end_date = self._data[date_col].max()
+
+    def apply_filter(self, f):
+        """Apply Filter `f` to the data. Returns a `pd.DataFrame` with the filtered rows."""
+        return self._data.query(f.query)
+
+    def iter_dates(self):
+        """Returns `pd.DataFrameGroupBy` that groups contracts by date"""
+        return self._data.groupby(self.schema['date'])
+
+    def iter_months(self):
+        """Returns `pd.DataFrameGroupBy` that groups contracts by month"""
+        date_col = self.schema['date']
+        iterator = self._data.groupby(pd.Grouper(
+            key=date_col,
+            freq="MS")).apply(lambda g: g[g[date_col] == g[date_col].min()]).reset_index(drop=True).groupby(date_col)
+        return iterator
+
+    def __getattr__(self, attr):
+        """Pass method invocation to `self._data`"""
+
+        method = getattr(self._data, attr)
+        if hasattr(method, '__call__'):
+
+            def df_method(*args, **kwargs):
+                return method(*args, **kwargs)
+
+            return df_method
+        else:
+            return method
+
+    def __getitem__(self, item):
+        if isinstance(item, pd.Series):
+            return self._data[item]
+        else:
+            key = self.schema[item]
+            return self._data[key]
+
+    def __setitem__(self, key, value):
+        self._data[key] = value
+        if key not in self.schema:
+            self.schema.update({key: key})
+
+    def __len__(self):
+        return len(self._data)
+
+    def __repr__(self):
+        return self._data.__repr__()
+
+    def default_schema():
+        """Returns default schema for Historical Options Data"""
+        schema = Schema.options()
+        schema.update({
+            'underlying': 'secid',
+            'underlying_last': 'forward_price',  #last price of underlying
+            'date': 'date',
+            'contract': 'optionid',
+            'type': 'cp_flag',
+            'expiration': 'exdate',
+            'strike': 'strike_price',
+            'bid': 'best_bid',
+            'ask': 'best_offer',
+            'volume': 'volume',
+            'open_interest': 'open_interest',
+            'last': 'forward_price',
+            'impliedvol': 'impl_volatility',
+            'vega': 'vega',
+            'delta': 'delta',
+            'gamma': 'gamma',
+            'theta': 'theta',
+        })
+        return schema
+
+
+# Index(['symbol', 'symbol_flag', 'exdate', 'last_date', 'cp_flag',
+#        'strike_price', 'best_bid', 'best_offer', 'volume', 'open_interest',
+#        'impl_volatility', 'delta', 'gamma', 'vega', 'theta', 'optionid',
+#        'cfadj', 'am_settlement', 'contract_size', 'ss_flag', 'forward_price',
+#        'expiry_indicator', 'root', 'suffix', 'secid'],
+#       dtype='object')
+# Schema([Field(name='underlying', mapping='underlying'), Field(name='underlying_last', mapping='underlying_last'), Field(name='date', mapping='quotedate'), Field(name='contract', mapping='optionroot'), Field(name='type', mapping='type'), Field(name='expiration', mapping='expiration'), Field(name='strike', mapping='strike'), Field(name='bid', mapping='bid'), Field(name='ask', mapping='ask'), Field(name='volume', mapping='volume'), Field(name='open_interest', mapping='openinterest'), Field(name='last', mapping='last'), Field(name='impliedvol', mapping='impliedvol'), Field(name='delta', mapping='delta'), Field(name='gamma', mapping='gamma'), Field(name='theta', mapping='theta'), Field(name='vega', mapping='vega')])

setup.py

@@ -0,0 +1,10 @@
+from setuptools import find_packages, setup
+
+setup(
+    name='backtester',
+    packages=find_packages(),
+    version='0.1.0',
+    description='Backtesting moris idea of buying calls 5 qs before earnings, and selling them 1 week before. Apparently 30% annual return',
+    author='wassname',
+    license='proprietary',
+)