Black formatting changes

Added tests for Series class

fincal/core.py

@@ -2,7 +2,7 @@ import datetime
 from collections import UserDict, UserList
 from dataclasses import dataclass
 from numbers import Number
-from typing import Iterable, List, Literal, Mapping, Sequence, Tuple, Type, Union
+from typing import Iterable, List, Literal, Mapping, Sequence, Tuple, Union
 
 
 @dataclass
@@ -138,20 +138,36 @@ class Series(UserList):
     def __init__(
         self,
         data,
-        data_type: Union[Type[bool], Type[float], Type[str], Type[datetime.datetime]],
+        data_type: Literal['date', 'number', 'bool'],
         date_format: str = None,
     ):
-        self.dtype = data_type
+        types_dict = {
+            '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():
+            raise ValueError("Unsupported value for data type")
+
         if not isinstance(data, Sequence):
             raise TypeError("Series object can only be created using Sequence types")
 
-        for i in data:
-            if not isinstance(i, data_type):
-                raise Exception("All arguments must be of the same type")
-
-        if data_type == str:
+        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):
@@ -159,7 +175,7 @@ class Series(UserList):
 
     def __getitem__(self, i):
         if isinstance(i, slice):
-            return self.__class__(self.data[i], self.dtype)
+            return self.__class__(self.data[i], str(self.dtype.__name__))
         else:
             return self.data[i]
 
@@ -171,25 +187,58 @@ 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__}")
 
         return gt
 
+    def __ge__(self, other):
+        if self.dtype == bool:
+            raise TypeError(">= not supported for boolean series")
+
+        if isinstance(other, (str, datetime.datetime, datetime.date)):
+            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')
+        else:
+            raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
+
+        return ge
+
     def __lt__(self, other):
         if self.dtype == bool:
             raise TypeError("< not supported for boolean series")
 
+        if isinstance(other, (str, datetime.datetime, datetime.date)):
+            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
 
+    def __le__(self, other):
+        if self.dtype == bool:
+            raise TypeError("<= not supported for boolean series")
+
+        if isinstance(other, (str, datetime.datetime, datetime.date)):
+            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')
+        else:
+            raise Exception(f"Cannot compare type {self.dtype.__name__} to {type(other).__name__}")
+        return le
+
     def __eq__(self, other):
+        if isinstance(other, (str, datetime.datetime, datetime.date)):
+            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
@@ -237,14 +286,14 @@ 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, datetime.datetime)
+        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, float)
+        return Series(self._values, 'number')
 
     @property
     def start_date(self):
@@ -304,7 +353,8 @@ class TimeSeriesCore(UserDict):
             elif len(key) != len(self.dates):
                 raise Exception(f"Length of Series: {len(key)} did not match length of object: {len(self.dates)}")
             else:
-                dates_to_return = [self.dates[i] for i, j in enumerate(key) if j]
+                dates = self.dates
+                dates_to_return = [dates[i] for i, j in enumerate(key) if j]
                 data_to_return = [(key, self.data[key]) for key in dates_to_return]
                 return self.__class__(data_to_return, frequency=self.frequency.symbol)
 

testing.ipynb

@@ -19,35 +19,50 @@
    "execution_count": 2,
    "id": "4b8ccd5f-dfff-4202-82c4-f66a30c122b6",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[(datetime.datetime(2022, 1, 31, 0, 0), 310.980011),\n",
+       " (datetime.datetime(2021, 5, 28, 0, 0), 249.679993)]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "dfd = pd.read_csv('test_files/nav_history_daily - copy.csv')\n",
-    "dfd = dfd[dfd['amfi_code'] == 118825].reset_index(drop=True)"
+    "dfd = pd.read_csv('test_files/msft.csv')\n",
+    "# dfd = dfd[dfd['amfi_code'] == 118825].reset_index(drop=True)\n",
+    "ts = TimeSeries([(i.date, i.nav) for i in dfd.itertuples()], frequency='D')\n",
+    "repr(ts)\n",
+    "ts[['2022-01-31', '2021-05-28']]"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "c52b0c2c-dd01-48dd-9ffa-3147ec9571ef",
+   "id": "086d4377-d1b1-4e51-84c0-39dee28ef75e",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Warning: The input data contains duplicate dates which have been ignored.\n"
+      "Wall time: 17 ms\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "TimeSeries([(datetime.datetime(2013, 1, 2, 0, 0), 18.972),\n",
-       "\t    (datetime.datetime(2013, 1, 3, 0, 0), 19.011),\n",
-       "\t    (datetime.datetime(2013, 1, 4, 0, 0), 19.008)\n",
+       "TimeSeries([(datetime.datetime(2022, 1, 3, 0, 0), 334.75),\n",
+       "\t    (datetime.datetime(2022, 1, 4, 0, 0), 329.01001),\n",
+       "\t    (datetime.datetime(2022, 1, 5, 0, 0), 316.380005)\n",
        "\t    ...\n",
-       "\t    (datetime.datetime(2022, 2, 10, 0, 0), 86.5),\n",
-       "\t    (datetime.datetime(2022, 2, 11, 0, 0), 85.226),\n",
-       "\t    (datetime.datetime(2022, 2, 14, 0, 0), 82.53299999999999)], frequency='D')"
+       "\t    (datetime.datetime(2022, 2, 16, 0, 0), 299.5),\n",
+       "\t    (datetime.datetime(2022, 2, 17, 0, 0), 290.730011),\n",
+       "\t    (datetime.datetime(2022, 2, 18, 0, 0), 287.929993)], frequency='D')"
       ]
      },
      "execution_count": 3,
@@ -56,21 +71,37 @@
     }
    ],
    "source": [
-    "ts = TimeSeries([(i.date, i.nav) for i in dfd.itertuples()], frequency='D')\n",
-    "ts"
+    "%%time\n",
+    "s = ts.dates >= '2022-01-01'\n",
+    "ts[s]"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "9e8ff6c6-3a36-435a-ba87-5b9844c18779",
+   "id": "e815edc9-3746-4192-814e-bd27b2771a0c",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Wall time: 5.97 ms\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "[(datetime.datetime(2022, 1, 31, 0, 0), 85.18),\n",
-       " (datetime.datetime(2021, 5, 31, 0, 0), 74.85)]"
+       "[(datetime.datetime(1992, 2, 19, 0, 0), 2.398438),\n",
+       " (datetime.datetime(1992, 2, 20, 0, 0), 2.447917),\n",
+       " (datetime.datetime(1992, 2, 21, 0, 0), 2.385417),\n",
+       " (datetime.datetime(1992, 2, 24, 0, 0), 2.393229),\n",
+       " (datetime.datetime(1992, 2, 25, 0, 0), 2.411458),\n",
+       " (datetime.datetime(1992, 2, 26, 0, 0), 2.541667),\n",
+       " (datetime.datetime(1992, 2, 27, 0, 0), 2.601563),\n",
+       " (datetime.datetime(1992, 2, 28, 0, 0), 2.572917),\n",
+       " (datetime.datetime(1992, 3, 2, 0, 0), 2.5625),\n",
+       " (datetime.datetime(1992, 3, 3, 0, 0), 2.567708)]"
       ]
      },
      "execution_count": 4,
@@ -79,126 +110,82 @@
     }
    ],
    "source": [
-    "ts[['2022-01-31', '2021-05-31']]"
+    "%%time\n",
+    "ts.iloc[:10]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
-   "id": "086d4377-d1b1-4e51-84c0-39dee28ef75e",
-   "metadata": {},
+   "execution_count": 5,
+   "id": "dc469722-c816-4b57-8d91-7a3b865f86be",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "TimeSeries([(datetime.datetime(2021, 2, 15, 0, 0), 73.483),\n",
-       "\t    (datetime.datetime(2021, 2, 16, 0, 0), 73.237),\n",
-       "\t    (datetime.datetime(2021, 2, 17, 0, 0), 72.98)\n",
-       "\t    ...\n",
-       "\t    (datetime.datetime(2022, 2, 10, 0, 0), 86.5),\n",
-       "\t    (datetime.datetime(2022, 2, 11, 0, 0), 85.226),\n",
-       "\t    (datetime.datetime(2022, 2, 14, 0, 0), 82.53299999999999)], frequency='D')"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Wall time: 311 ms\n"
+     ]
     }
    ],
    "source": [
-    "ts[ts.dates>'2021-02-14']"
+    "%%time\n",
+    "from_date = datetime.date(1994, 1, 1)\n",
+    "to_date = datetime.date(2022, 1, 1)\n",
+    "# print(ts.calculate_returns(to_date, years=7))\n",
+    "rr = ts.calculate_rolling_returns(from_date, to_date)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "6f1226a3-2327-435b-88e7-fd0fdcc8cc1c",
+   "execution_count": 6,
+   "id": "e5d357b4-4fe5-4a0a-8107-0ab6828d7c41",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "TimeSeries([(datetime.datetime(2020, 1, 2, 0, 0), 58.285),\n",
-       "\t    (datetime.datetime(2020, 1, 3, 0, 0), 58.056999999999995),\n",
-       "\t    (datetime.datetime(2020, 1, 6, 0, 0), 56.938)\n",
+       "TimeSeries([(datetime.datetime(1994, 1, 3, 0, 0), -0.06149359306648605),\n",
+       "\t    (datetime.datetime(1994, 1, 4, 0, 0), -0.05433177603118022),\n",
+       "\t    (datetime.datetime(1994, 1, 5, 0, 0), -0.04913276300578029)\n",
        "\t    ...\n",
-       "\t    (datetime.datetime(2022, 2, 10, 0, 0), 86.5),\n",
-       "\t    (datetime.datetime(2022, 2, 11, 0, 0), 85.226),\n",
-       "\t    (datetime.datetime(2022, 2, 14, 0, 0), 82.53299999999999)], frequency='D')"
+       "\t    (datetime.datetime(2021, 12, 29, 0, 0), 0.5255410267822715),\n",
+       "\t    (datetime.datetime(2021, 12, 30, 0, 0), 0.5306749265370103),\n",
+       "\t    (datetime.datetime(2021, 12, 31, 0, 0), 0.5120942811985818)], frequency='D')"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "s = ts.dates > '2020-01-01'\n",
-    "ts[s]"
+    "rr"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "e815edc9-3746-4192-814e-bd27b2771a0c",
+   "execution_count": 7,
+   "id": "4bad2efa",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[(datetime.datetime(2013, 1, 2, 0, 0), 18.972),\n",
-       " (datetime.datetime(2013, 1, 3, 0, 0), 19.011),\n",
-       " (datetime.datetime(2013, 1, 4, 0, 0), 19.008),\n",
-       " (datetime.datetime(2013, 1, 7, 0, 0), 18.95),\n",
-       " (datetime.datetime(2013, 1, 8, 0, 0), 18.954),\n",
-       " (datetime.datetime(2013, 1, 9, 0, 0), 18.94),\n",
-       " (datetime.datetime(2013, 1, 10, 0, 0), 18.957),\n",
-       " (datetime.datetime(2013, 1, 11, 0, 0), 18.948),\n",
-       " (datetime.datetime(2013, 1, 14, 0, 0), 19.177),\n",
-       " (datetime.datetime(2013, 1, 15, 0, 0), 19.272000000000002)]"
+       "Series([1.0, 2.0, 3.0, 4.0, 5.0])"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "ts.iloc[:10]"
+    "sr = Series([1, 2, 3, 4, 5], 'number')\n",
+    "sr"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "dc469722-c816-4b57-8d91-7a3b865f86be",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: total: 15.6 ms\n",
-      "Wall time: 14 ms\n"
-     ]
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "from_date = datetime.date(2020, 1, 1)\n",
-    "to_date = datetime.date(2021, 1, 1)\n",
-    "# print(ts.calculate_returns(to_date, years=7))\n",
-    "rr = ts.calculate_rolling_returns(from_date, to_date)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e5d357b4-4fe5-4a0a-8107-0ab6828d7c41",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -217,7 +204,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.3"
+   "version": "3.9.2"
   }
  },
  "nbformat": 4,

tests/test_core.py

@@ -0,0 +1,49 @@
+import datetime
+
+from fincal.core import AllFrequencies, Frequency, Series
+from fincal.fincal import create_date_series
+
+
+class TestFrequency:
+    def test_creation(self):
+        D = Frequency('daily', 'days', 1, 1, 'D')
+        assert D.days == 1
+        assert D.symbol == 'D'
+        assert D.name == 'daily'
+        assert D.value == 1
+        assert D.freq_type == 'days'
+
+
+class TestAllFrequencies:
+    def test_attributes(self):
+        assert hasattr(AllFrequencies, 'D')
+        assert hasattr(AllFrequencies, 'M')
+        assert hasattr(AllFrequencies, 'Q')
+
+    def test_days(self):
+        assert AllFrequencies.D.days == 1
+        assert AllFrequencies.M.days == 30
+        assert AllFrequencies.Q.days == 91
+
+    def test_symbol(self):
+        assert AllFrequencies.H.symbol == 'H'
+        assert AllFrequencies.W.symbol == 'W'
+
+    def test_values(self):
+        assert AllFrequencies.H.value == 6
+        assert AllFrequencies.Y.value == 1
+
+    def test_type(self):
+        assert AllFrequencies.Q.freq_type == 'months'
+        assert AllFrequencies.W.freq_type == 'days'
+
+
+class TestSeries:
+    def test_creation(self):
+        series = Series([1, 2, 3, 4, 5, 6, 7], data_type=int)
+        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

tests/test_fincal.py

@@ -4,7 +4,7 @@ import random
 from typing import Literal, Sequence
 
 import pytest
-from fincal.core import Frequency
+from fincal.core import Frequency, Series
 from fincal.fincal import TimeSeries, create_date_series
 
 THIS_DIR = os.path.dirname(os.path.abspath(__file__))
@@ -18,8 +18,8 @@ def create_test_data(
     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'
+    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),
@@ -35,19 +35,19 @@ def create_test_data(
         for i in to_remove:
             dates.remove(i)
     if date_as_str:
-        dates = [i.strftime('%Y-%m-%d') for i in dates]
+        dates = [i.strftime("%Y-%m-%d") for i in dates]
 
-    values = [random.randint(8000, 90000)/100 for _ 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':
+    if as_outer_type == "list":
+        if as_inner_type == "list":
             data = [list(i) for i in data]
-        elif as_inner_type == 'dict[1]':
+        elif as_inner_type == "dict[1]":
             data = [dict((i,)) for i in data]
-        elif as_inner_type == 'dict[2]':
+        elif as_inner_type == "dict[2]":
             data = [dict(date=i, value=j) for i, j in data]
-    elif as_outer_type == 'dict':
+    elif as_outer_type == "dict":
         data = dict(data)
 
     return data
@@ -117,7 +117,7 @@ class TestDateSeries:
 
 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)
+        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)
@@ -126,26 +126,36 @@ class TestFincal:
         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)
+        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)
+        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
+        assert len(ffill_data) >= 498
 
         ffill_data = time_series.ffill(inplace=True)
         assert ffill_data is None
-        assert len(time_series) > 498
+        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)
+    def test_iloc_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
+        assert time_series.iloc[0] is not None
+        assert time_series.iloc[:3] is not None
+        assert time_series.iloc[5:7] is not None
+        assert isinstance(time_series.iloc[0], tuple)
+        assert isinstance(time_series.iloc[10:20], list)
+        assert len(time_series.iloc[10:20]) == 10
+
+    def test_key_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")
+        available_date = time_series.iloc[5][0]
+        assert time_series[available_date] is not None
+        assert isinstance(time_series["dates"], Series)
+        assert isinstance(time_series["values"], Series)
+        assert len(time_series.dates) == 50
+        assert len(time_series.values) == 50