Added tests for date_series & some for TimeSeries

dict_iter.py

@@ -0,0 +1,29 @@
+import pandas
+
+from fincal.fincal import TimeSeries
+
+dfd = pandas.read_csv('test_files/nav_history_daily - Copy.csv')
+dfm = pandas.read_csv('test_files/nav_history_monthly.csv')
+
+data_d = [(i.date, i.nav) for i in dfd.itertuples() if i.amfi_code == 118825]
+data_d.sort()
+data_m = [{'date': i.date, 'value': i.nav} for i in dfm.itertuples()]
+
+tsd = TimeSeries(data_d, frequency='D')
+
+md = dict(data_d)
+counter = 1
+for i in iter(md):
+    print(i)
+    counter += 1
+    if counter >= 5: break
+
+print('\n')
+counter = 1
+for i in reversed(md):
+    print('rev', i)
+    counter += 1
+    if counter >= 5: break
+
+x = [next(i) for i in iter(md)]
+print(x)

fincal/core.py

@@ -1,6 +1,6 @@
 import datetime
 from dataclasses import dataclass
-from typing import Dict, Iterable, List, Literal, Tuple, Union
+from typing import Iterable, List, Literal, Mapping, Sequence, Tuple, Union
 
 
 @dataclass
@@ -15,30 +15,31 @@ class Frequency:
     freq_type: str
     value: int
     days: int
+    symbol: str
 
 
 class AllFrequencies:
-    D = Frequency('daily', 'days', 1, 1)
-    W = Frequency('weekly', 'days', 7, 7)
-    M = Frequency('monthly', 'months', 1, 30)
-    Q = Frequency('quarterly', 'months', 3, 91)
-    H = Frequency('half-yearly', 'months', 6, 182)
-    Y = Frequency('annual', 'years', 1, 365)
+    D = Frequency('daily', 'days', 1, 1, 'D')
+    W = Frequency('weekly', 'days', 7, 7, 'W')
+    M = Frequency('monthly', 'months', 1, 30, 'M')
+    Q = Frequency('quarterly', 'months', 3, 91, 'Q')
+    H = Frequency('half-yearly', 'months', 6, 182, 'H')
+    Y = Frequency('annual', 'years', 1, 365, 'Y')
 
 
 def _preprocess_timeseries(
     data: Union[
-        List[Iterable[Union[str, datetime.datetime, float]]],
-        List[Dict[str, Union[float, datetime.datetime]]],
-        List[Dict[Union[str, datetime.datetime], float]],
-        Dict[Union[str, datetime.datetime], float]
+        Sequence[Iterable[Union[str, datetime.datetime, float]]],
+        Sequence[Mapping[str, Union[float, datetime.datetime]]],
+        Sequence[Mapping[Union[str, datetime.datetime], float]],
+        Mapping[Union[str, datetime.datetime], float]
     ],
     date_format: str
 ) -> List[Tuple[datetime.datetime, float]]:
     """Converts any type of list to the correct type"""
 
-    if isinstance(data, list):
-        if isinstance(data[0], dict):
+    if isinstance(data, Sequence):
+        if isinstance(data[0], Mapping):
             if len(data[0].keys()) == 2:
                 current_data = [tuple(i.values()) for i in data]
             elif len(data[0].keys()) == 1:
@@ -47,7 +48,7 @@ def _preprocess_timeseries(
                 raise TypeError("Could not parse the data")
             current_data = _preprocess_timeseries(current_data, date_format)
 
-        elif isinstance(data[0], Iterable):
+        elif isinstance(data[0], Sequence):
             if isinstance(data[0][0], str):
                 current_data = []
                 for i in data:
@@ -60,7 +61,7 @@ def _preprocess_timeseries(
         else:
             raise TypeError("Could not parse the data")
 
-    elif isinstance(data, dict):
+    elif isinstance(data, Mapping):
         current_data = [(k, v) for k, v in data.items()]
         current_data = _preprocess_timeseries(current_data, date_format)
 
@@ -99,8 +100,8 @@ class TimeSeriesCore:
     def __init__(
         self,
         data: List[Iterable],
-        date_format: str = "%Y-%m-%d",
-        frequency=Literal['D', 'W', 'M', 'Q', 'H', 'Y']
+        frequency: Literal['D', 'W', 'M', 'Q', 'H', 'Y'],
+        date_format: str = "%Y-%m-%d"
     ):
         """Instantiate a TimeSeries object
 
@@ -124,42 +125,58 @@ class TimeSeriesCore:
         data = _preprocess_timeseries(data, date_format=date_format)
 
         self.time_series = dict(data)
-        self.dates = set(list(self.time_series))
-        if len(self.dates) != len(data):
+        self.dates = list(self.time_series)
+        if len(self.time_series) != len(data):
             print("Warning: The input data contains duplicate dates which have been ignored.")
-        self.start_date = list(self.time_series)[0]
-        self.end_date = list(self.time_series)[-1]
+        self.start_date = self.dates[0]
+        self.end_date = self.dates[-1]
         self.frequency = getattr(AllFrequencies, frequency)
 
+    def _get_slice(self, n: int):
+        """Returns a slice of the dataframe from beginning and end"""
+
+        printable = {}
+        iter_f = iter(self.time_series)
+        first_n = [next(iter_f) for i in range(n//2)]
+
+        iter_b = reversed(self.time_series)
+        last_n = [next(iter_b) for i in range(n//2)]
+        last_n.sort()
+
+        printable['start'] = [str((i, self.time_series[i])) for i in first_n]
+        printable['end'] = [str((i, self.time_series[i])) for i in last_n]
+        return printable
+
     def __repr__(self):
         if len(self.time_series) > 6:
-            printable_data_1 = list(self.time_series)[:3]
-            printable_data_2 = list(self.time_series)[-3:]
-            printable_str = "TimeSeries([{}\n\t...\n\t{}])".format(
-                                ',\n\t'.join([str((i, self.time_series[i])) for i in printable_data_1]),
-                                ',\n\t'.join([str((i, self.time_series[i])) for i in printable_data_2])
+            printable = self._get_slice(6)
+            printable_str = "{}([{}\n\t    ...\n\t    {}], frequency={})".format(
+                                self.__class__.__name__,
+                                ',\n\t    '.join(printable['start']),
+                                ',\n\t    '.join(printable['end']),
+                                repr(self.frequency.symbol)
                                 )
         else:
-            printable_data = self.time_series
-            printable_str = "TimeSeries([{}])".format(',\n\t'.join(
-                                [str((i, self.time_series[i])) for i in printable_data]))
+            printable_str = "{}([{}], frequency={})".format(
+                                              self.__class__.__name__,
+                                              ',\n\t'.join([str(i) for i in self.time_series.items()]),
+                                              repr(self.frequency.symbol)
+                                             )
         return printable_str
 
     def __str__(self):
         if len(self.time_series) > 6:
-            printable_data_1 = list(self.time_series)[:3]
-            printable_data_2 = list(self.time_series)[-3:]
+            printable = self._get_slice(6)
             printable_str = "[{}\n ...\n {}]".format(
-                                ',\n '.join([str((i, self.time_series[i])) for i in printable_data_1]),
-                                ',\n '.join([str((i, self.time_series[i])) for i in printable_data_2])
+                                ',\n '.join(printable['start']),
+                                ',\n '.join(printable['end']),
                                 )
         else:
-            printable_data = self.time_series
-            printable_str = "[{}]".format(',\n '.join([str((i, self.time_series[i])) for i in printable_data]))
+            printable_str = "[{}]".format(',\n '.join([str(i) for i in self.time_series.items()]))
         return printable_str
 
     def __getitem__(self, n):
-        all_keys = list(self.time_series.keys())
+        all_keys = list(self.time_series)
         if isinstance(n, int):
             keys = [all_keys[n]]
         else:
@@ -171,7 +188,7 @@ class TimeSeriesCore:
         return item
 
     def __len__(self):
-        return len(self.time_series.keys())
+        return len(self.time_series)
 
     def head(self, n: int = 6):
         keys = list(self.time_series.keys())

fincal/fincal.py

@@ -5,14 +5,15 @@ from typing import List, Union
 
 from dateutil.relativedelta import relativedelta
 
-from .core import AllFrequencies, Frequency, TimeSeriesCore, _preprocess_match_options
+from .core import AllFrequencies, TimeSeriesCore, _preprocess_match_options
 
 
 def create_date_series(
-    start_date: datetime.datetime, end_date: datetime.datetime, frequency: Frequency, eomonth: bool = False
+    start_date: datetime.datetime, end_date: datetime.datetime, frequency: str, eomonth: bool = False
 ) -> List[datetime.datetime]:
     """Creates a date series using a frequency"""
 
+    frequency = getattr(AllFrequencies, frequency)
     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}")
 
@@ -27,7 +28,8 @@ def create_date_series(
                 date = date.replace(day=31)
             else:
                 date = date.replace(day=1).replace(month=date.month+1) - relativedelta(days=1)
-        dates.append(date)
+        if date <= end_date:
+            dates.append(date)
 
     return dates
 
@@ -59,7 +61,7 @@ class TimeSeries(TimeSeriesCore):
         """
 
         eomonth = True if self.frequency.days >= AllFrequencies.M.days else False
-        dates_to_fill = create_date_series(self.start_date, self.end_date, self.frequency, eomonth)
+        dates_to_fill = create_date_series(self.start_date, self.end_date, self.frequency.symbol, eomonth)
 
         new_ts = dict()
         for cur_date in dates_to_fill:
@@ -177,10 +179,14 @@ class TimeSeries(TimeSeriesCore):
     ) -> List[tuple]:
         """Calculates the rolling return"""
 
-        all_dates = create_date_series(from_date, to_date, getattr(AllFrequencies, frequency))
-        dates = set(all_dates)
+        try:
+            frequency = getattr(AllFrequencies, frequency)
+        except AttributeError:
+            raise ValueError(f"Invalid argument for frequency {frequency}")
+
+        dates = create_date_series(from_date, to_date, frequency)
         if frequency == AllFrequencies.D:
-            dates = all_dates.intersection(self.dates)
+            dates = [i for i in dates if i in self.time_series]
 
         rolling_returns = []
         for i in dates:
@@ -193,8 +199,8 @@ class TimeSeries(TimeSeriesCore):
                 closest=closest,
             )
             rolling_returns.append((i, returns))
-        self.rolling_returns = rolling_returns
-        return self.rolling_returns
+        rolling_returns.sort()
+        return rolling_returns
 
 
 if __name__ == "__main__":

my_test.py

@@ -0,0 +1,23 @@
+import time
+
+import pandas
+
+from fincal.fincal import AllFrequencies, Frequency, TimeSeries, create_date_series
+
+dfd = pandas.read_csv('test_files/nav_history_daily - Copy.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()}
+
+tsd = TimeSeries(data_d, frequency='D')
+tsm = TimeSeries(data_m, frequency='M', date_format='%d-%m-%Y')
+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()
+# rr = tsd.calculate_rolling_returns(datetime.datetime(2022, 1, 1), datetime.datetime(2022, 2, 1), years=1)
+print(time.time() - start)

test_files/nav_history_daily.csv

@@ -0,0 +1,139 @@
+amfi_code,date,nav
+118825,01-11-2021,87.925
+119528,02-11-2021,378.51
+118825,02-11-2021,87.885
+119528,03-11-2021,377.79
+118825,03-11-2021,87.553
+119528,08-11-2021,383.13
+118825,08-11-2021,88.743
+119528,09-11-2021,383.06
+118825,09-11-2021,88.793
+119528,10-11-2021,382.71
+118825,10-11-2021,88.723
+118825,10-11-2021,88.78
+119528,11-11-2021,379.28
+118825,11-11-2021,88.205
+119528,12-11-2021,383.94
+118825,12-11-2021,89.025
+119528,15-11-2021,383.31
+118825,15-11-2021,89.182
+119528,16-11-2021,381.08
+118825,16-11-2021,88.569
+119528,17-11-2021,379.17
+118825,17-11-2021,88.09
+119528,18-11-2021,375.09
+118825,18-11-2021,87.202
+119528,22-11-2021,368.16
+118825,22-11-2021,85.382
+119528,23-11-2021,370.64
+118825,23-11-2021,85.978
+119528,24-11-2021,369.91
+118825,24-11-2021,85.635
+119528,25-11-2021,371.33
+118825,25-11-2021,86.212
+119528,26-11-2021,360.66
+118825,26-11-2021,83.748
+119528,29-11-2021,360.05
+118825,29-11-2021,83.523
+119528,30-11-2021,359.8
+118825,30-11-2021,83.475
+119528,01-12-2021,362.35
+118825,01-12-2021,84.269
+119528,02-12-2021,366.09
+118825,02-12-2021,85.105
+119528,03-12-2021,363.11
+118825,03-12-2021,84.507
+119528,06-12-2021,357.21
+118825,06-12-2021,83.113
+119528,07-12-2021,362.63
+118825,07-12-2021,84.429
+119528,08-12-2021,368.73
+118825,08-12-2021,85.935
+119528,09-12-2021,369.49
+118825,09-12-2021,86.045
+119528,10-12-2021,369.44
+118825,10-12-2021,86.058
+119528,13-12-2021,367.6
+118825,13-12-2021,85.632
+119528,14-12-2021,366.36
+118825,14-12-2021,85.502
+119528,15-12-2021,364.34
+118825,15-12-2021,84.989
+119528,16-12-2021,363.73
+118825,16-12-2021,84.972
+119528,17-12-2021,358.17
+118825,17-12-2021,83.83
+119528,20-12-2021,349.98
+118825,20-12-2021,81.817
+119528,21-12-2021,353.71
+118825,21-12-2021,82.746
+119528,22-12-2021,357.93
+118825,22-12-2021,83.776
+119528,23-12-2021,360.68
+118825,23-12-2021,84.297
+119528,24-12-2021,359.11
+118825,24-12-2021,83.903
+119528,27-12-2021,360.71
+118825,27-12-2021,84.227
+119528,28-12-2021,363.81
+118825,28-12-2021,85.044
+119528,29-12-2021,363.2
+118825,29-12-2021,85.03
+119528,30-12-2021,363.31
+118825,30-12-2021,85.047
+119528,31-12-2021,366.98
+118825,31-12-2021,85.759
+119528,03-01-2022,371.76
+118825,03-01-2022,87.111
+119528,04-01-2022,374.22
+118825,04-01-2022,87.804
+119528,05-01-2022,376.31
+118825,05-01-2022,88.162
+119528,06-01-2022,373.64
+118825,06-01-2022,87.541
+119528,07-01-2022,374.68
+118825,07-01-2022,87.818
+119528,10-01-2022,378.47
+118825,10-01-2022,88.622
+119528,11-01-2022,379.34
+118825,11-01-2022,88.678
+119528,12-01-2022,382.86
+118825,12-01-2022,89.332
+119528,13-01-2022,383.68
+118825,13-01-2022,89.553
+119528,14-01-2022,384.02
+118825,14-01-2022,89.729
+119528,17-01-2022,384.36
+118825,17-01-2022,89.733
+119528,18-01-2022,380
+118825,18-01-2022,88.781
+119528,19-01-2022,377.24
+118825,19-01-2022,88.059
+119528,20-01-2022,374.45
+118825,20-01-2022,87.361
+119528,21-01-2022,369.86
+118825,21-01-2022,86.22
+119528,24-01-2022,361.01
+118825,24-01-2022,83.907
+119528,25-01-2022,364.63
+118825,25-01-2022,84.763
+119528,27-01-2022,361.95
+118825,27-01-2022,83.876
+119528,28-01-2022,361.91
+118825,28-01-2022,83.829
+119528,31-01-2022,367.31
+118825,31-01-2022,85.18
+119528,04-02-2022,371.01
+118825,04-02-2022,86.079
+119528,07-02-2022,365.04
+118825,07-02-2022,84.867
+119528,08-02-2022,365.74
+118825,08-02-2022,84.945
+119528,09-02-2022,369.85
+118825,09-02-2022,85.977
+119528,10-02-2022,372.29
+118825,10-02-2022,86.5
+119528,11-02-2022,366.91
+118825,11-02-2022,85.226
+119528,14-02-2022,355.47
+118825,14-02-2022,82.533

test_files/nav_history_monthly - Copy.csv

@@ -0,0 +1,219 @@
+"amfi_code","date","nav"
+118825,2013-01-31,18.913
+118825,2013-02-28,17.723
+118825,2013-03-28,17.563
+118825,2013-04-30,18.272
+118825,2013-05-31,18.383
+118825,2013-06-28,17.802
+118825,2013-07-31,17.588
+118825,2013-08-30,16.993
+118825,2013-09-30,17.732
+118825,2013-10-31,19.665
+118825,2013-11-29,19.787
+118825,2013-12-31,20.499
+118825,2014-01-31,19.994
+118825,2014-02-28,20.942
+118825,2014-03-31,22.339
+118825,2014-04-30,22.599
+118825,2014-05-30,24.937
+118825,2014-06-30,27.011
+118825,2014-07-31,27.219
+118825,2014-08-28,28.625
+118825,2014-09-30,29.493
+118825,2014-10-31,30.685
+118825,2014-11-28,31.956
+118825,2014-12-31,31.646
+118825,2015-01-30,33.653
+118825,2015-02-27,33.581
+118825,2015-03-31,33.14
+118825,2015-04-30,32.181
+118825,2015-05-29,33.256
+118825,2015-06-30,33.227
+118825,2015-07-31,34.697
+118825,2015-08-31,32.833
+118825,2015-09-30,32.94
+118825,2015-10-30,33.071
+118825,2015-11-30,33.024
+118825,2015-12-31,33.267
+118825,2016-01-29,31.389
+118825,2016-02-29,28.751
+118825,2016-03-31,32.034
+118825,2016-04-29,32.848
+118825,2016-05-31,34.135
+118825,2016-06-30,35.006
+118825,2016-07-29,37.148
+118825,2016-08-31,38.005
+118825,2016-09-30,37.724
+118825,2016-10-28,38.722
+118825,2016-11-30,36.689
+118825,2016-12-30,36.239
+118825,2017-01-31,38.195
+118825,2017-02-28,39.873
+118825,2017-03-31,41.421
+118825,2017-04-28,42.525
+118825,2017-05-31,43.977
+118825,2017-06-30,43.979
+118825,2017-07-31,46.554
+118825,2017-08-31,46.383
+118825,2017-09-29,46.085
+118825,2017-10-31,48.668
+118825,2017-11-30,48.824
+118825,2017-12-29,50.579
+118825,2018-01-31,51.799
+118825,2018-02-28,49.041
+118825,2018-03-28,46.858
+118825,2018-04-30,49.636
+118825,2018-05-31,49.169
+118825,2018-06-29,48.716
+118825,2018-07-31,51.455
+118825,2018-08-31,53.494
+118825,2018-09-28,49.863
+118825,2018-10-31,48.538
+118825,2018-11-30,50.597
+118825,2018-12-31,50.691
+118825,2019-01-31,50.517
+118825,2019-02-28,50.176
+118825,2019-03-31,54.017
+118825,2019-04-30,54.402
+118825,2019-05-31,55.334
+118825,2019-06-28,55.181
+118825,2019-07-31,52.388
+118825,2019-08-30,52.214
+118825,2019-09-30,54.058
+118825,2019-10-31,56.514
+118825,2019-11-29,57.42
+118825,2019-12-31,57.771
+118825,2020-01-31,57.135
+118825,2020-02-28,54.034
+118825,2020-03-31,41.452
+118825,2020-04-30,47.326
+118825,2020-05-29,45.845
+118825,2020-06-30,49.526
+118825,2020-07-31,53.306000000000004
+118825,2020-08-19,55.747
+118825,2020-10-30,56.387
+118825,2020-11-27,62.001000000000005
+118825,2020-12-31,66.415
+118825,2021-01-29,65.655
+118825,2021-02-26,70.317
+118825,2021-03-31,70.69
+118825,2021-04-30,70.39
+118825,2021-05-31,74.85
+118825,2021-06-30,77.109
+118825,2021-07-30,78.335
+118825,2021-08-31,83.691
+118825,2021-09-30,86.128
+118825,2021-10-29,86.612
+118825,2021-11-30,83.475
+118825,2021-12-31,85.759
+118825,2022-01-31,85.18
+118825,2022-02-17,84.33
+119528,2013-01-31,101.36
+119528,2013-02-28,95.25
+119528,2013-03-28,94.81
+119528,2013-04-30,99.75
+119528,2013-05-31,99.73
+119528,2013-06-28,97.52
+119528,2013-07-31,95.37
+119528,2013-08-30,92.24
+119528,2013-09-30,97.45
+119528,2013-10-31,107.03
+119528,2013-11-29,105.91
+119528,2013-12-31,109.3
+119528,2014-01-31,105.09
+119528,2014-02-28,108.58
+119528,2014-03-31,117.28
+119528,2014-04-30,118.06
+119528,2014-05-30,131.33
+119528,2014-06-30,139.48
+119528,2014-07-31,140.49
+119528,2014-08-28,145.43
+119528,2014-09-30,147.4
+119528,2014-10-31,154.46
+119528,2014-11-28,161.93
+119528,2014-12-31,159.62
+119528,2015-01-30,170.46
+119528,2015-02-27,171.18
+119528,2015-03-31,166.8
+119528,2015-04-30,161.95
+119528,2015-05-29,166.78
+119528,2015-06-30,166.67
+119528,2015-07-31,172.33
+119528,2015-08-31,161.96
+119528,2015-09-30,162.25
+119528,2015-10-30,164.16
+119528,2015-11-30,162.7
+119528,2015-12-31,162.83
+119528,2016-01-29,155.87
+119528,2016-02-29,144.56
+119528,2016-03-31,159.88
+119528,2016-04-29,163.54
+119528,2016-05-31,170.01
+119528,2016-06-30,174.61
+119528,2016-07-29,184.36
+119528,2016-08-31,189.33
+119528,2016-09-30,187.16
+119528,2016-10-28,189.29
+119528,2016-11-30,178.19
+119528,2016-12-30,176.66
+119528,2017-01-31,185.76
+119528,2017-02-28,193.2
+119528,2017-03-31,200.54
+119528,2017-04-28,205.25
+119528,2017-05-31,208.22
+119528,2017-06-30,209.83
+119528,2017-07-31,221.15
+119528,2017-08-31,219.99
+119528,2017-09-29,217.7
+119528,2017-10-31,226.94
+119528,2017-11-30,225.24
+119528,2017-12-29,233.26
+119528,2018-01-31,237.57
+119528,2018-02-28,226.55
+119528,2018-03-28,219.73
+119528,2018-04-30,232.04
+119528,2018-05-31,228.49
+119528,2018-06-29,225.27
+119528,2018-07-31,237.11
+119528,2018-08-31,243.79
+119528,2018-09-28,223.83
+119528,2018-10-31,218.61
+119528,2018-11-30,226.99
+119528,2018-12-31,228.61
+119528,2019-01-31,224.26
+119528,2019-02-28,222.71
+119528,2019-03-29,240.21
+119528,2019-04-30,240.01
+119528,2019-05-31,243.72
+119528,2019-06-28,241.28
+119528,2019-07-31,229.54
+119528,2019-08-30,226.0
+119528,2019-09-30,234.75
+119528,2019-10-31,242.11
+119528,2019-11-29,246.75
+119528,2019-12-31,247.81
+119528,2020-01-31,246.14
+119528,2020-02-28,231.91
+119528,2020-03-31,175.98
+119528,2020-04-30,200.77
+119528,2020-05-29,196.75
+119528,2020-06-30,210.55
+119528,2020-07-31,224.93
+119528,2020-08-19,233.78
+119528,2020-10-30,235.83
+119528,2020-11-27,264.04
+119528,2020-12-31,285.02
+119528,2021-01-29,280.52
+119528,2021-02-26,300.56
+119528,2021-03-31,301.57
+119528,2021-04-30,301.1
+119528,2021-05-31,320.98
+119528,2021-06-30,327.64
+119528,2021-07-30,336.6
+119528,2021-08-31,360.75
+119528,2021-09-30,369.42
+119528,2021-10-29,372.89
+119528,2021-11-30,359.8
+119528,2021-12-31,366.98
+119528,2022-01-31,367.31
+119528,2022-02-17,363.56

test_files/nav_history_monthly.csv

@@ -0,0 +1,11 @@
+amfi_code,date,nav
+118825,31-03-2021,70.69
+118825,30-04-2021,70.39
+118825,31-05-2021,74.85
+118825,30-07-2021,78.335
+118825,31-08-2021,83.691
+118825,30-09-2021,86.128
+118825,29-10-2021,86.612
+118825,30-11-2021,83.475
+118825,31-01-2022,85.18
+118825,17-02-2022,84.33

test_files/nav_history_quarterly - Copy.csv

@@ -0,0 +1,71 @@
+"amfi_code","date","nav"
+118825,2013-03-28,17.563
+118825,2013-06-28,17.802
+118825,2013-09-30,17.732
+118825,2013-12-31,20.499
+118825,2014-03-31,22.339
+118825,2014-06-30,27.011
+118825,2014-09-30,29.493
+118825,2014-12-31,31.646
+118825,2015-03-31,33.14
+118825,2015-06-30,33.227
+118825,2015-09-30,32.94
+118825,2015-12-31,33.267
+118825,2016-03-31,32.034
+118825,2016-06-30,35.006
+118825,2016-09-30,37.724
+118825,2016-12-30,36.239
+118825,2017-03-31,41.421
+118825,2017-06-30,43.979
+118825,2017-09-29,46.085
+118825,2017-12-29,50.579
+118825,2018-03-28,46.858
+118825,2018-06-29,48.716
+118825,2018-09-28,49.863
+118825,2018-12-31,50.691
+118825,2019-03-31,54.017
+118825,2019-06-28,55.181
+118825,2019-09-30,54.058
+118825,2019-12-31,57.771
+118825,2020-03-31,41.452
+118825,2020-06-30,49.526
+118825,2020-12-31,66.415
+118825,2021-03-31,70.69
+118825,2021-06-30,77.109
+118825,2021-09-30,86.128
+118825,2021-12-31,85.759
+119528,2013-03-28,94.81
+119528,2013-06-28,97.52
+119528,2013-09-30,97.45
+119528,2013-12-31,109.3
+119528,2014-03-31,117.28
+119528,2014-06-30,139.48
+119528,2014-09-30,147.4
+119528,2014-12-31,159.62
+119528,2015-03-31,166.8
+119528,2015-06-30,166.67
+119528,2015-09-30,162.25
+119528,2015-12-31,162.83
+119528,2016-03-31,159.88
+119528,2016-06-30,174.61
+119528,2016-09-30,187.16
+119528,2016-12-30,176.66
+119528,2017-03-31,200.54
+119528,2017-06-30,209.83
+119528,2017-09-29,217.7
+119528,2017-12-29,233.26
+119528,2018-03-28,219.73
+119528,2018-06-29,225.27
+119528,2018-09-28,223.83
+119528,2018-12-31,228.61
+119528,2019-03-29,240.21
+119528,2019-06-28,241.28
+119528,2019-09-30,234.75
+119528,2019-12-31,247.81
+119528,2020-03-31,175.98
+119528,2020-06-30,210.55
+119528,2020-12-31,285.02
+119528,2021-03-31,301.57
+119528,2021-06-30,327.64
+119528,2021-09-30,369.42
+119528,2021-12-31,366.98

test_files/nav_history_quarterly.csv

@@ -0,0 +1,9 @@
+amfi_code,date,nav
+118825,31-03-2019,54.017
+118825,28-06-2019,55.181
+118825,31-12-2019,57.771
+118825,31-03-2020,41.452
+118825,30-06-2020,49.526
+118825,30-06-2021,77.109
+118825,30-09-2021,86.128
+118825,31-12-2021,85.759

tests/test_fincal.py

@@ -1,21 +1,151 @@
+import datetime
+import os
+import random
+from typing import Literal, Sequence
 
-import unittest
+import pytest
+from fincal.core import Frequency
+from fincal.fincal import TimeSeries, create_date_series
 
-from fincal.fincal import TimeSeries
+THIS_DIR = os.path.dirname(os.path.abspath(__file__))
+sample_data_path = os.path.join(THIS_DIR, "data")
 
 
-class TestFincal(unittest.TestCase):
-    def test_ts(self):
-        data = [
-            ('2020-01-01',  23),
-            ('2020-01-02',  24),
-            ('2020-01-03',  25),
-            ('2020-01-06',  26),
-            ('2020-01-07',  27),
-            ('2020-01-08',  28),
-            ('2020-01-10',  29),
-            ('2020-01-11',  30)
-        ]
-        time_series = TimeSeries(data)
-        time_series.ffill(inplace=True)
-        self.assertEqual(len(time_series.time_series), 11)
+def create_test_data(
+    frequency: str,
+    eomonth: bool,
+    n: int,
+    gaps: float,
+    month_position: Literal["start", "middle", "end"],
+    date_as_str: bool,
+    as_outer_type: Literal['dict', 'list'] = 'list',
+    as_inner_type: Literal['dict', 'list', 'tuple'] = 'tuple'
+) -> Sequence[tuple]:
+    start_dates = {
+        "start": datetime.datetime(2016, 1, 1),
+        "middle": datetime.datetime(2016, 1, 15),
+        "end": datetime.datetime(2016, 1, 31),
+    }
+    end_date = datetime.datetime(2021, 12, 31)
+    dates = create_date_series(start_dates[month_position], end_date, frequency=frequency, eomonth=eomonth)
+    dates = dates[:n]
+    if gaps:
+        num_gaps = int(len(dates) * gaps)
+        to_remove = random.sample(dates, num_gaps)
+        for i in to_remove:
+            dates.remove(i)
+    if date_as_str:
+        dates = [i.strftime('%Y-%m-%d') for i in dates]
+
+    values = [random.randint(8000, 90000)/100 for _ in dates]
+
+    data = list(zip(dates, values))
+    if as_outer_type == 'list':
+        if as_inner_type == 'list':
+            data = [list(i) for i in data]
+        elif as_inner_type == 'dict[1]':
+            data = [dict((i,)) for i in data]
+        elif as_inner_type == 'dict[2]':
+            data = [dict(date=i, value=j) for i, j in data]
+    elif as_outer_type == 'dict':
+        data = dict(data)
+
+    return data
+
+
+class TestDateSeries:
+    def test_daily(self):
+        start_date = datetime.datetime(2020, 1, 1)
+        end_date = datetime.datetime(2020, 12, 31)
+        d = create_date_series(start_date, end_date, frequency="D")
+        assert len(d) == 366
+
+        start_date = datetime.datetime(2017, 1, 1)
+        end_date = datetime.datetime(2017, 12, 31)
+        d = create_date_series(start_date, end_date, frequency="D")
+        assert len(d) == 365
+
+        with pytest.raises(ValueError):
+            create_date_series(start_date, end_date, frequency="D", eomonth=True)
+
+    def test_monthly(self):
+        start_date = datetime.datetime(2020, 1, 1)
+        end_date = datetime.datetime(2020, 12, 31)
+        d = create_date_series(start_date, end_date, frequency="M")
+        assert len(d) == 12
+
+        d = create_date_series(start_date, end_date, frequency="M", eomonth=True)
+        assert datetime.datetime(2020, 2, 29) in d
+
+        start_date = datetime.datetime(2020, 1, 31)
+        d = create_date_series(start_date, end_date, frequency="M")
+        assert datetime.datetime(2020, 2, 29) in d
+        assert datetime.datetime(2020, 8, 31) in d
+        assert datetime.datetime(2020, 10, 30) not in d
+
+        start_date = datetime.datetime(2020, 2, 29)
+        d = create_date_series(start_date, end_date, frequency="M")
+        assert len(d) == 11
+        assert datetime.datetime(2020, 2, 29) in d
+        assert datetime.datetime(2020, 8, 31) not in d
+        assert datetime.datetime(2020, 10, 29) in d
+
+    def test_quarterly(self):
+        start_date = datetime.datetime(2018, 1, 1)
+        end_date = datetime.datetime(2020, 12, 31)
+        d = create_date_series(start_date, end_date, frequency="Q")
+        assert len(d) == 12
+
+        d = create_date_series(start_date, end_date, frequency="Q", eomonth=True)
+        assert datetime.datetime(2020, 4, 30) in d
+
+        start_date = datetime.datetime(2020, 1, 31)
+        d = create_date_series(start_date, end_date, frequency="Q")
+        assert len(d) == 4
+        assert datetime.datetime(2020, 2, 29) not in d
+        assert max(d) == datetime.datetime(2020, 10, 31)
+
+        start_date = datetime.datetime(2020, 2, 29)
+        d = create_date_series(start_date, end_date, frequency="Q")
+        assert datetime.datetime(2020, 2, 29) in d
+        assert datetime.datetime(2020, 8, 31) not in d
+        assert datetime.datetime(2020, 11, 29) in d
+
+        d = create_date_series(start_date, end_date, frequency="Q", eomonth=True)
+        assert datetime.datetime(2020, 11, 30) in d
+
+
+class TestFincal:
+    def test_creation(self):
+        data = create_test_data(frequency='D', eomonth=False, n=50, gaps=0, month_position='start', date_as_str=True)
+        time_series = TimeSeries(data, frequency="D")
+        assert len(time_series) == 50
+        assert isinstance(time_series.frequency, Frequency)
+        assert time_series.frequency.days == 1
+
+        ffill_data = time_series.ffill()
+        assert len(ffill_data) == 50
+
+        data = create_test_data(frequency='D', eomonth=False, n=500, gaps=0.1, month_position='start', date_as_str=True)
+        time_series = TimeSeries(data, frequency="D")
+        assert len(time_series) == 450
+
+    def test_ffill(self):
+        data = create_test_data(frequency='D', eomonth=False, n=500, gaps=0.1, month_position='start', date_as_str=True)
+        time_series = TimeSeries(data, frequency="D")
+        ffill_data = time_series.ffill()
+        assert len(ffill_data) > 498
+
+        ffill_data = time_series.ffill(inplace=True)
+        assert ffill_data is None
+        assert len(time_series) > 498
+
+    def test_slicing(self):
+        data = create_test_data(frequency='D', eomonth=False, n=50, gaps=0, month_position='start', date_as_str=True)
+        time_series = TimeSeries(data, frequency="D")
+        assert time_series[0] is not None
+        assert time_series[:3] is not None
+        assert time_series[5:7] is not None
+        assert isinstance(time_series[0], tuple)
+        assert isinstance(time_series[10:20], list)
+        assert len(time_series[10:20]) == 10