ignore intellij idea folder

replace statistics.coariance in statistics file

.gitignore

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

Check3.py

@@ -0,0 +1,21 @@
+import datetime
+import math
+import random
+import time
+from typing import List
+
+from dateutil.relativedelta import relativedelta
+
+import pyfacts as pft
+
+data = [
+    ("2021-01-01", 10),
+    ("2021-02-01", 12),
+    ("2021-03-01", 14),
+    ("2021-04-01", 16),
+    ("2021-05-01", 18),
+    ("2021-06-01", 20),
+]
+
+ts = pft.TimeSeries(data)
+print(repr(ts))

check.py

@@ -0,0 +1,118 @@
+import datetime
+import math
+import random
+
+# import time
+from typing import List
+
+from dateutil.relativedelta import relativedelta
+
+import pyfacts as pft
+
+
+def create_prices(s0: float, mu: float, sigma: float, num_prices: int) -> list:
+    """Generates a price following a geometric brownian motion process based on the input of the arguments.
+
+        Since this function is used only to generate data for tests, the seed is fixed as 1234.
+        Many of the tests rely on exact values generated using this seed.
+        If the seed is changed, those tests will fail.
+
+    Parameters:
+    ------------
+    s0: float
+        Asset inital price.
+
+    mu: float
+        Interest rate expressed annual terms.
+
+    sigma: float
+        Volatility expressed annual terms.
+
+    num_prices: int
+        number of prices to generate
+
+    Returns:
+    --------
+        Returns a list of values generated using GBM algorithm
+    """
+
+    random.seed(1234)  # WARNING! Changing the seed will cause most tests to fail
+    all_values = []
+    for _ in range(num_prices):
+        s0 *= math.exp(
+            (mu - 0.5 * sigma**2) * (1.0 / 365.0) + sigma * math.sqrt(1.0 / 365.0) * random.gauss(mu=0, sigma=1)
+        )
+        all_values.append(round(s0, 2))
+
+    return all_values
+
+
+def sample_data_generator(
+    frequency: pft.Frequency,
+    num: int = 1000,
+    skip_weekends: bool = False,
+    mu: float = 0.1,
+    sigma: float = 0.05,
+    eomonth: bool = False,
+) -> List[tuple]:
+    """Creates TimeSeries data
+
+    Parameters:
+    -----------
+    frequency: Frequency
+        The frequency of the time series data to be generated.
+
+    num: int
+        Number of date: value pairs to be generated.
+
+    skip_weekends: bool
+        Whether weekends (saturday, sunday) should be skipped.
+        Gets used only if the frequency is daily.
+
+    mu: float
+        Mean return for the values.
+
+    sigma: float
+        standard deviation of the values.
+
+    Returns:
+    --------
+        Returns a TimeSeries object
+    """
+
+    start_date = datetime.datetime(2017, 1, 1)
+    timedelta_dict = {
+        frequency.freq_type: int(
+            frequency.value * num * (7 / 5 if frequency == pft.AllFrequencies.D and skip_weekends else 1)
+        )
+    }
+    end_date = start_date + relativedelta(**timedelta_dict)
+    dates = pft.create_date_series(start_date, end_date, frequency.symbol, skip_weekends=skip_weekends, eomonth=eomonth)
+    values = create_prices(1000, mu, sigma, num)
+    ts = list(zip(dates, values))
+    return ts
+
+
+market_data = sample_data_generator(num=3600, frequency=pft.AllFrequencies.D, skip_weekends=False)
+mts = pft.TimeSeries(market_data, "D")
+print(mts)
+
+# print("Datediff=", (mts.end_date - mts.start_date).days)
+# stock_data = sample_data_generator(num=3600, frequency=pft.AllFrequencies.D, skip_weekends=False, mu=0.12, sigma=0.15)
+# sts = pft.TimeSeries(stock_data, "D")
+# print(sts)
+
+# start = time.time()
+# alpha = pft.jensens_alpha(
+#     asset_data=sts, market_data=mts, risk_free_rate=0.052, return_period_unit="months", return_period_value=1
+# )
+
+# print(alpha)
+
+# print("Alpha calculation took", time.time() - start, "seconds")
+
+# print("Correlation=", pft.correlation(sts, mts))
+
+rr = mts.calculate_rolling_returns(frequency="D")
+
+print(117, rr[rr.values < 0.1])

check2.py

@@ -0,0 +1,100 @@
+import datetime
+import math
+import random
+import time
+from typing import List
+
+from dateutil.relativedelta import relativedelta
+
+import pyfacts as pft
+
+
+def create_prices(s0: float, mu: float, sigma: float, num_prices: int) -> list:
+    """Generates a price following a geometric brownian motion process based on the input of the arguments.
+
+        Since this function is used only to generate data for tests, the seed is fixed as 1234.
+        Many of the tests rely on exact values generated using this seed.
+        If the seed is changed, those tests will fail.
+
+    Parameters:
+    ------------
+    s0: float
+        Asset inital price.
+
+    mu: float
+        Interest rate expressed annual terms.
+
+    sigma: float
+        Volatility expressed annual terms.
+
+    num_prices: int
+        number of prices to generate
+
+    Returns:
+    --------
+        Returns a list of values generated using GBM algorithm
+    """
+
+    random.seed(1234)  # WARNING! Changing the seed will cause most tests to fail
+    all_values = []
+    for _ in range(num_prices):
+        s0 *= math.exp(
+            (mu - 0.5 * sigma**2) * (1.0 / 365.0) + sigma * math.sqrt(1.0 / 365.0) * random.gauss(mu=0, sigma=1)
+        )
+        all_values.append(round(s0, 2))
+
+    return all_values
+
+
+def sample_data_generator(
+    frequency: pft.Frequency,
+    num: int = 1000,
+    skip_weekends: bool = False,
+    mu: float = 0.1,
+    sigma: float = 0.05,
+    eomonth: bool = False,
+) -> List[tuple]:
+    """Creates TimeSeries data
+
+    Parameters:
+    -----------
+    frequency: Frequency
+        The frequency of the time series data to be generated.
+
+    num: int
+        Number of date: value pairs to be generated.
+
+    skip_weekends: bool
+        Whether weekends (saturday, sunday) should be skipped.
+        Gets used only if the frequency is daily.
+
+    mu: float
+        Mean return for the values.
+
+    sigma: float
+        standard deviation of the values.
+
+    Returns:
+    --------
+        Returns a TimeSeries object
+    """
+
+    start_date = datetime.datetime(2017, 1, 1)
+    timedelta_dict = {
+        frequency.freq_type: int(
+            frequency.value * num * (7 / 5 if frequency == pft.AllFrequencies.D and skip_weekends else 1)
+        )
+    }
+    end_date = start_date + relativedelta(**timedelta_dict)
+    dates = pft.create_date_series(start_date, end_date, frequency.symbol, skip_weekends=skip_weekends, eomonth=eomonth)
+    values = create_prices(1000, mu, sigma, num)
+    ts = list(zip(dates, values))
+    return ts
+
+
+market_data = sample_data_generator(num=3600, frequency=pft.AllFrequencies.D, skip_weekends=False)
+mts = pft.TimeSeries(market_data, "D")
+print(mts)
+
+sortino = pft.sortino_ratio(mts, risk_free_rate=0.05)
+print(sortino)

my_checks.py

@@ -0,0 +1,26 @@
+import datetime
+import time
+import timeit
+
+import pandas
+
+from pyfacts.pyfacts import AllFrequencies, TimeSeries, create_date_series
+
+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")
+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)
+bdata = tsq.bfill()
+# rr = tsd.calculate_rolling_returns(datetime.datetime(2022, 1, 1), datetime.datetime(2022, 2, 1), years=1)
+print(time.time() - start)

my_test.py

@@ -1,26 +0,0 @@
-import datetime
-import time
-import timeit
-
-import pandas
-
-from fincal.fincal import AllFrequencies, TimeSeries, create_date_series
-
-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')
-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)
-bdata = tsq.bfill()
-# rr = tsd.calculate_rolling_returns(datetime.datetime(2022, 1, 1), datetime.datetime(2022, 2, 1), years=1)
-print(time.time() - start)

pyfacts/exceptions.py

@@ -13,9 +13,9 @@ class DateNotFoundError(Exception):
 class DateOutOfRangeError(Exception):
     """Exception to be raised when provided date is outside the range of dates in the time series"""
 
-    def __init__(self, date: datetime.datetime, type: Literal['min', 'max']) -> None:
-        if type == 'min':
+    def __init__(self, date: datetime.datetime, type: Literal["min", "max"]) -> None:
+        if type == "min":
             message = f"Provided date {date} is before the first date in the TimeSeries"
-        if type == 'max':
+        if type == "max":
             message = f"Provided date {date} is after the last date in the TimeSeries"
         super().__init__(message)

pyfacts/statistics.py

@@ -8,7 +8,7 @@ from typing import Literal
 from pyfacts.core import date_parser
 
 from .pyfacts import TimeSeries
-from .utils import _interval_to_years
+from .utils import _interval_to_years, covariance
 
 
 @date_parser(3, 4)
@@ -212,7 +212,7 @@ def beta(
     asset_rr = asset_data.calculate_rolling_returns(**common_params)
     market_rr = market_data.calculate_rolling_returns(**common_params)
 
-    cov = statistics.covariance(asset_rr.values, market_rr.values)
+    cov = covariance(asset_rr.values, market_rr.values)
     market_var = statistics.variance(market_rr.values)
 
     beta = cov / market_var

pyfacts/utils.py

@@ -1,4 +1,7 @@
+from __future__ import annotations
+
 import datetime
+import statistics
 from dataclasses import dataclass
 from typing import List, Literal, Mapping, Sequence, Tuple
 
@@ -187,3 +190,36 @@ def _is_eomonth(dates: Sequence[datetime.datetime], threshold: float = 0.7):
     eomonth_dates = [date.month != (date + relativedelta(days=1)).month for date in dates]
     eomonth_proportion = sum(eomonth_dates) / len(dates)
     return eomonth_proportion > threshold
+
+
+def covariance(series1: list, series2: list) -> float:
+    """Returns the covariance of two series
+
+        This is a compatibility function for Python versions prior to 3.10.
+        It will be replaced with statistics.covariance when support is dropped for versions <3.10.
+
+    Parameters
+    ----------
+    series1 : List
+        A list of numbers
+    series2 : list
+        A list of numbers
+
+    Returns
+    -------
+    float
+        Returns the covariance as a float value
+    """
+
+    n = len(series1)
+    if len(series2) != n:
+        raise ValueError("Lenght of both series must be same for covariance calcualtion.")
+    if n < 2:
+        raise ValueError("At least two data poitns are required for covariance calculation.")
+
+    mean1 = statistics.mean(series1)
+    mean2 = statistics.mean(series2)
+
+    xy = sum([(x - mean1) * (y - mean2) for x, y in zip(series1, series2)])
+
+    return xy / n

test.py

@@ -1,34 +0,0 @@
-# from fincal.core import FincalOptions
-import fincal as fc
-
-data = [
-    ("2022-01-01", 150),
-    ("2022-01-02", 152),
-    ("2022-01-03", 151),
-    ("2022-01-04", 154),
-    ("2022-01-05", 150),
-    ("2022-01-06", 157),
-    ("2022-01-07", 155),
-    ("2022-01-08", 158),
-    ("2022-01-09", 162),
-    ("2022-01-10", 160),
-    ("2022-01-11", 156),
-    ("2022-01-12", 162),
-    ("2023-01-01", 164),
-    ("2023-01-02", 161),
-    ("2023-01-03", 167),
-    ("2023-01-04", 168),
-]
-ts = fc.TimeSeries(data, frequency="D", date_format="%Y-%d-%m")
-print(ts)
-
-sharpe = fc.sharpe_ratio(
-    ts,
-    risk_free_rate=(1 + 0.15) ** (1 / 12) - 1,
-    from_date="2022-02-01",
-    to_date="2023-04-01",
-    frequency="M",
-    return_period_unit="months",
-    return_period_value=1,
-)
-print(f"{sharpe=}")

test2.py

@@ -1,52 +0,0 @@
-import time
-
-from fincal.fincal import TimeSeries
-
-# start = time.time()
-# dfd = pd.read_csv("test_files/msft.csv")  # , dtype=dict(nav=str))
-# # dfd = dfd[dfd["amfi_code"] == 118825].reset_index(drop=True)
-# print("instantiation took", round((time.time() - start) * 1000, 2), "ms")
-# ts = TimeSeries([(i.date, i.nav) for i in dfd.itertuples()], frequency="D")
-# print(repr(ts))
-
-start = time.time()
-# mdd = ts.max_drawdown()
-# print(mdd)
-# print("max drawdown calc took", round((time.time() - start) * 1000, 2), "ms")
-# # print(ts[['2022-01-31', '2021-05-28']])
-
-# rr = ts.calculate_rolling_returns(
-#           from_date='2021-01-01',
-#           to_date='2022-01-01',
-#           frequency='D',
-#           interval_type='days',
-#           interval_value=30,
-#           compounding=False
-#       )
-
-
-data = [
-    ("2022-01-01", 10),
-    # ("2022-01-08", 12),
-    ("2022-01-15", 14),
-    ("2022-01-22", 16)
-    # ("2020-02-07", 18),
-    # ("2020-02-14", 20),
-    # ("2020-02-21", 22),
-    # ("2020-02-28", 24),
-    # ("2020-03-01", 26),
-    # ("2020-03-01", 28),
-    # ("2020-03-01", 30),
-    # ("2020-03-01", 32),
-    # ("2021-03-01", 34),
-]
-
-ts = TimeSeries(data, "W")
-# ts_expanded = ts.expand("D", "ffill", skip_weekends=True)
-
-# for i in ts_expanded:
-#     print(i)
-
-print(ts.get("2022-01-01"))
-
-print(ts.ffill())

tests/test_stats.py

@@ -169,7 +169,7 @@ class TestBeta:
         sts = pft.TimeSeries(stock_data, "D")
         mts = pft.TimeSeries(market_data, "D")
         beta = pft.beta(sts, mts, frequency="D", return_period_unit="days", return_period_value=1)
-        assert round(beta, 4) == 1.6001
+        assert round(beta, 4) == 1.5997
 
     def test_beta_daily_freq_daily_returns(self, create_test_data):
         market_data = create_test_data(num=3600, frequency=pft.AllFrequencies.D)
@@ -177,7 +177,7 @@ class TestBeta:
         sts = pft.TimeSeries(stock_data, "D")
         mts = pft.TimeSeries(market_data, "D")
         beta = pft.beta(sts, mts)
-        assert round(beta, 4) == 1.6292
+        assert round(beta, 4) == 1.6287
 
     def test_beta_monthly_freq(self, create_test_data):
         market_data = create_test_data(num=3600, frequency=pft.AllFrequencies.D)
@@ -185,7 +185,7 @@ class TestBeta:
         sts = pft.TimeSeries(stock_data, "D")
         mts = pft.TimeSeries(market_data, "D")
         beta = pft.beta(sts, mts, frequency="M")
-        assert round(beta, 4) == 1.629
+        assert round(beta, 4) == 1.6137
 
     def test_beta_monthly_freq_monthly_returns(self, create_test_data):
         market_data = create_test_data(num=3600, frequency=pft.AllFrequencies.D)
@@ -193,4 +193,4 @@ class TestBeta:
         sts = pft.TimeSeries(stock_data, "D")
         mts = pft.TimeSeries(market_data, "D")
         beta = pft.beta(sts, mts, frequency="M", return_period_unit="months", return_period_value=1)
-        assert round(beta, 4) == 1.6023
+        assert round(beta, 4) == 1.5887

tox.ini

@@ -1,6 +1,10 @@
 [tox]
-envlist = py39
+minversion = 3.8.0
+envlist = py38,py39,py310
 
 [testenv]
 deps = pytest
 commands = pytest
+
+[flake8]
+max-line-length=125