Added __contains__ and some tests for it

.gitignore

@@ -3,3 +3,4 @@
 .env
 *egg-info
 __pycache__
+.vscode

fincal/core.py

@@ -138,17 +138,17 @@ class Series(UserList):
     def __init__(
         self,
         data,
-        data_type: Literal['date', 'number', 'bool'],
+        data_type: Literal["date", "number", "bool"],
         date_format: str = None,
     ):
         types_dict = {
-            'date': datetime.datetime,
-            'datetime': datetime.datetime,
-            'datetime.datetime': datetime.datetime,
-            'float': float,
-            'int': float,
-            'number': float,
-            'bool': bool
+            "date": datetime.datetime,
+            "datetime": datetime.datetime,
+            "datetime.datetime": datetime.datetime,
+            "float": float,
+            "int": float,
+            "number": float,
+            "bool": bool,
         }
 
         if data_type not in types_dict.keys():
@@ -157,21 +157,17 @@ class Series(UserList):
         if not isinstance(data, Sequence):
             raise TypeError("Series object can only be created using Sequence types")
 
-        if data_type in ['date', 'datetime', 'datetime.datetime']:
+        if data_type in ["date", "datetime", "datetime.datetime"]:
             data = [_parse_date(i, date_format) for i in data]
         else:
             func = types_dict[data_type]
             data = [func(i) for i in data]
-        # elif data_type == 'number':
-        #     data = [float(i) for i in data]
-        # elif data_type == 'boolean':
-        #     data = [bool(i) for i in data]
 
         self.dtype = types_dict[data_type]
         self.data = data
 
     def __repr__(self):
-        return f"{self.__class__.__name__}({self.data})"
+        return f"{self.__class__.__name__}({self.data}, data_type='{self.dtype.__name__}')"
 
     def __getitem__(self, i):
         if isinstance(i, slice):
@@ -187,7 +183,7 @@ class Series(UserList):
             other = _parse_date(other)
 
         if self.dtype == float and isinstance(other, Number) or isinstance(other, self.dtype):
-            gt = Series([i > other for i in self.data], 'bool')
+            gt = Series([i > other for i in self.data], "bool")
         else:
             raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
 
@@ -201,7 +197,7 @@ class Series(UserList):
             other = _parse_date(other)
 
         if self.dtype == float and isinstance(other, Number) or isinstance(other, self.dtype):
-            ge = Series([i >= other for i in self.data], 'bool')
+            ge = Series([i >= other for i in self.data], "bool")
         else:
             raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
 
@@ -215,7 +211,7 @@ class Series(UserList):
             other = _parse_date(other)
 
         if self.dtype == float and isinstance(other, Number) or isinstance(other, self.dtype):
-            lt = Series([i < other for i in self.data], 'bool')
+            lt = Series([i < other for i in self.data], "bool")
         else:
             raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
         return lt
@@ -228,7 +224,7 @@ class Series(UserList):
             other = _parse_date(other)
 
         if self.dtype == float and isinstance(other, Number) or isinstance(other, self.dtype):
-            le = Series([i <= other for i in self.data], 'bool')
+            le = Series([i <= other for i in self.data], "bool")
         else:
             raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
         return le
@@ -238,7 +234,7 @@ class Series(UserList):
             other = _parse_date(other)
 
         if self.dtype == float and isinstance(other, Number) or isinstance(other, self.dtype):
-            eq = Series([i == other for i in self.data], 'bool')
+            eq = Series([i == other for i in self.data], "bool")
         else:
             raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
         return eq
@@ -286,14 +282,14 @@ class TimeSeriesCore(UserDict):
         if self._dates is None or len(self._dates) != len(self.data):
             self._dates = list(self.data.keys())
 
-        return Series(self._dates, 'date')
+        return Series(self._dates, "date")
 
     @property
     def values(self):
         if self._values is None or len(self._values) != len(self.data):
             self._values = list(self.data.values())
 
-        return Series(self._values, 'number')
+        return Series(self._values, "number")
 
     @property
     def start_date(self):
@@ -391,6 +387,10 @@ class TimeSeriesCore(UserDict):
             self.n += 1
             return key, self.data[key]
 
+    def __contains__(self, key: object) -> bool:
+        key = _parse_date(key)
+        return super().__contains__(key)
+
     def head(self, n: int = 6):
         """Returns the first n items of the TimeSeries object"""
 
@@ -407,6 +407,9 @@ class TimeSeriesCore(UserDict):
         result = [(key, self.data[key]) for key in keys]
         return result
 
+    def items(self):
+        return self.data.items()
+
     @property
     def iloc(self):
         """Returns an item or a set of items based on index"""

fincal/fincal.py

@@ -17,6 +17,8 @@ def create_date_series(
     if eomonth and frequency.days < AllFrequencies.M.days:
         raise ValueError(f"eomonth cannot be set to True if frequency is higher than {AllFrequencies.M.name}")
 
+    start_date = _parse_date(start_date)
+    end_date = _parse_date(end_date)
     datediff = (end_date - start_date).days / frequency.days + 1
     dates = []
 

my_test.py

@@ -1,16 +1,19 @@
+import datetime
 import time
+import timeit
 
 import pandas
 
-from fincal.fincal import AllFrequencies, Frequency, TimeSeries, create_date_series
+from fincal.fincal import AllFrequencies, TimeSeries, create_date_series
 
-dfd = pandas.read_csv('test_files/nav_history_daily - Copy.csv')
+dfd = pandas.read_csv('test_files/msft.csv')
 dfm = pandas.read_csv('test_files/nav_history_monthly.csv')
 dfq = pandas.read_csv('test_files/nav_history_quarterly.csv')
 
 data_d = [(i.date, i.nav) for i in dfd.itertuples()]
 data_m = [{'date': i.date, 'value': i.nav} for i in dfm.itertuples()]
 data_q = {i.date: i.nav for i in dfq.itertuples()}
+data_q.update({'14-02-2022': 93.7})
 
 tsd = TimeSeries(data_d, frequency='D')
 tsm = TimeSeries(data_m, frequency='M', date_format='%d-%m-%Y')
@@ -18,6 +21,6 @@ tsq = TimeSeries(data_q, frequency='Q', date_format='%d-%m-%Y')
 
 start = time.time()
 # ts.calculate_rolling_returns(datetime.datetime(2015, 1, 1), datetime.datetime(2022, 2, 1), years=1)
-# fdata = tsd.ffill()
+bdata = tsq.bfill()
 # rr = tsd.calculate_rolling_returns(datetime.datetime(2022, 1, 1), datetime.datetime(2022, 2, 1), years=1)
 print(time.time() - start)

test.py

@@ -0,0 +1,35 @@
+# type: ignore
+
+import datetime
+import time
+
+import pandas as pd
+
+from fincal.fincal import TimeSeries
+
+df = pd.read_csv('test_files/nav_history_daily.csv')
+df = df.sort_values(by=['amfi_code', 'date'])  # type: ignore
+data_list = [(i.date, i.nav) for i in df[df.amfi_code == 118825].itertuples()]
+
+start = time.time()
+ts_data = TimeSeries(data_list, frequency='M')
+print(f"Instantiation took {round((time.time() - start)*1000, 2)} ms")
+# ts_data.fill_missing_days()
+start = time.time()
+# ts_data.calculate_returns(as_on=datetime.datetime(2022, 1, 4), closest='next', years=1)
+rr = ts_data.calculate_rolling_returns(datetime.datetime(2015, 1, 1),
+                                       datetime.datetime(2022, 1, 21),
+                                       frequency='M',
+                                       as_on_match='next',
+                                       prior_match='previous',
+                                       closest='previous',
+                                       years=1)
+
+# ffill_data = ts_data.bfill()
+print(f"Calculation took {round((time.time() - start)*1000, 2)} ms")
+rr.sort()
+for i in rr[:10]:
+    print(i)
+# print(ffill_data)
+# print(ts_data)
+# print(repr(ts_data))

test2.py

@@ -0,0 +1,37 @@
+# type: ignore
+
+if __name__ == "__main__":
+
+    import datetime
+    import time
+
+    import pandas as pd
+
+    from fincal.fincal import TimeSeries
+
+    df = pd.read_csv('test_files/msft.csv')
+    df = df.sort_values(by='Date')  # type: ignore
+    data_list = [(i.Date, i.Close) for i in df.itertuples()]
+
+    start = time.time()
+    ts_data = TimeSeries(data_list, frequency='D', date_format='%d-%m-%Y')
+    print(f"Instantiation took {round((time.time() - start)*1000, 2)} ms")
+    # ts_data.fill_missing_days()
+    start = time.time()
+    # ts_data.calculate_returns(as_on=datetime.datetime(2022, 1, 4), closest='next', years=1)
+    rr = ts_data.calculate_rolling_returns(datetime.datetime(1994, 1, 1),
+                                        datetime.datetime(2022, 2, 17),
+                                        frequency='D',
+                                        as_on_match='next',
+                                        prior_match='previous',
+                                        closest='previous',
+                                        years=1)
+
+    # ffill_data = ts_data.bfill()
+    print(f"Calculation took {round((time.time() - start)*1000, 2)} ms")
+    rr.sort()
+    for i in rr[:10]:
+        print(i)
+    # print(ffill_data)
+    # print(ts_data)
+    # print(repr(ts_data))

test_series.py

@@ -0,0 +1,25 @@
+import datetime
+
+from fincal.core import Series
+
+s1 = Series([2.5, 6.2, 5.6, 8.4, 7.4, 1.5, 9.6, 5])
+
+dt_lst = [
+    datetime.datetime(2020, 12, 4, 0, 0),
+    datetime.datetime(2019, 5, 16, 0, 0),
+    datetime.datetime(2019, 9, 25, 0, 0),
+    datetime.datetime(2016, 2, 18, 0, 0),
+    datetime.datetime(2017, 8, 14, 0, 0),
+    datetime.datetime(2018, 1, 4, 0, 0),
+    datetime.datetime(2017, 5, 21, 0, 0),
+    datetime.datetime(2018, 7, 17, 0, 0),
+    datetime.datetime(2016, 4, 8, 0, 0),
+    datetime.datetime(2020, 1, 7, 0, 0),
+    datetime.datetime(2016, 12, 24, 0, 0),
+    datetime.datetime(2020, 6, 19, 0, 0),
+    datetime.datetime(2016, 3, 16, 0, 0),
+    datetime.datetime(2017, 4, 25, 0, 0),
+    datetime.datetime(2016, 7, 10, 0, 0)
+]
+
+s2 = Series(dt_lst)

tests/test_core.py

@@ -1,6 +1,7 @@
 import datetime
+from typing import Mapping
 
-from fincal.core import AllFrequencies, Frequency, Series
+from fincal.core import AllFrequencies, Frequency, Series, TimeSeriesCore
 from fincal.fincal import create_date_series
 
 
@@ -40,10 +41,41 @@ class TestAllFrequencies:
 
 class TestSeries:
     def test_creation(self):
-        series = Series([1, 2, 3, 4, 5, 6, 7], data_type=int)
+        series = Series([1, 2, 3, 4, 5, 6, 7], data_type='number')
         assert series.dtype == float
         assert series[2] == 3
 
-        dates = create_date_series('2021-01-01', '2021-01-31', 'D')
-        series = Series(dates, data_type=datetime.datetime)
-        assert Series.dtype == datetime.datetime
+        dates = create_date_series('2021-01-01', '2021-01-31', frequency='D')
+        series = Series(dates, data_type='date')
+        assert series.dtype == datetime.datetime
+
+
+class TestTimeSeriesCore:
+    data = [('2021-01-01', 220), ('2021-02-01', 230), ('2021-03-01', 240)]
+
+    def test_creation(self):
+        ts = TimeSeriesCore(self.data, frequency='M')
+        assert isinstance(ts, TimeSeriesCore)
+        assert isinstance(ts, Mapping)
+
+    def test_getitem(self):
+        ts = TimeSeriesCore(self.data, frequency='M')
+        assert ts.dates[0] == datetime.datetime(2021, 1, 1, 0, 0)
+        assert ts.values[0] == 220
+        assert ts['2021-01-01'][1] == 220
+        assert len(ts[ts.dates > '2021-01-01']) == 2
+        assert ts[ts.dates == '2021-02-01'].iloc[0][1] == 230
+        assert ts.iloc[2][0] == datetime.datetime(2021, 3, 1)
+        assert len(ts.iloc[:2]) == 2
+
+    def test_contains(self):
+        ts = TimeSeriesCore(self.data, frequency='M')
+        assert datetime.datetime(2021, 1, 1) in ts
+        assert '2021-01-01' in ts
+        assert '2021-01-14' not in ts
+
+    def test_items(self):
+        ts = TimeSeriesCore(self.data, frequency='M')
+        for i, j in ts.items():
+            assert j == self.data[0][1]
+            break