def _get_coefficients_and_current_regressors_tickers(self, regressors_tickers: List[Ticker], positions_tickers: List[Ticker],
positions_allocation: QFSeries, from_date: datetime,
to_date: datetime):
tickers = [*positions_tickers, *regressors_tickers]
data = self._data_provider.get_price(tickers, PriceField.Close, from_date, to_date).to_simple_returns()
dc = DataCleaner(data, 0.1)
clean_data = dc.proxy_using_value(0)
positions_returns = clean_data.reindex(columns=positions_tickers,
fill_value=0) # we expect the same dim as positions_allocation series
regressors_returns = clean_data.reindex(columns=regressors_tickers).dropna(axis=1,
how='all') # missing regressors should be removed
portfolio_returns = positions_returns.dot(positions_allocation.values)
return self._get_coefficients(regressors_returns, portfolio_returns), regressors_returns.columns
def _preprocess_data(self, analysed_tms, regressors_df):
"""
Cleans the data before they are processed (e.g. removes regressors containing too many missing data,
proxies missing data).
"""
self.logger.debug("Length of input timeseries: {:d} \n".format(len(analysed_tms)))
data_cleaner = DataCleaner(regressors_df)
common_regressors_df = data_cleaner.proxy_using_regression(analysed_tms, columns_type=SimpleReturnsSeries)
common_regressors_df, common_analysed_tms = get_values_for_common_dates(common_regressors_df, analysed_tms)
self.logger.debug("Length of preprocessed timeseries: {:d}".format(common_analysed_tms.size))
self.logger.debug("Number of regressors: {:d}".format(common_regressors_df.shape[1]))
return common_regressors_df, common_analysed_tms
def setUp(self):
self.test_dataframe = self._create_test_dataframe()
self.test_benchmark = self._create_test_benchmark()
self.data_cleaner = DataCleaner(self.test_dataframe)
class TestDataCleaner(TestCase):
def setUp(self):
self.test_dataframe = self._create_test_dataframe()
self.test_benchmark = self._create_test_benchmark()
self.data_cleaner = DataCleaner(self.test_dataframe)
@classmethod
def _create_test_dataframe(cls):
values = [[np.nan, 0.0, 0.0, 0.0, 0.0], [1.0, np.nan, 1.0, 1.0, 1.0],
[2.0, np.nan, np.nan, 2.0, 2.0],
[3.0, 3.0, 3.0, np.nan, 3.0], [4.0, 4.0, 4.0, 4.0, 4.0],
[5.0, 5.0, 5.0, 5.0, 5.0]]
index = pd.date_range(start='2015-01-01', periods=6)
columns = ['a', 'b', 'c', 'd', 'e']
dataframe = SimpleReturnsDataFrame(data=values,
index=index,
columns=columns)
return dataframe
@classmethod
def _create_test_benchmark(cls):
values = [1.0, 2.0, 3.0, 4.0, 5.0, 6.0]
index = pd.date_range(start='2015-01-02', periods=6)
return SimpleReturnsSeries(data=values,
index=index,
name='Test prices')
def test_proxy_using_values(self):
expected_values = [[0.0, 0.0, 0.0, 0.0], [1.0, 1.0, 1.0, 1.0],
[2.0, 0.0, 2.0, 2.0], [3.0, 3.0, 0.0, 3.0],
[4.0, 4.0, 4.0, 4.0], [5.0, 5.0, 5.0, 5.0]]
expected_columns = ['a', 'c', 'd', 'e']
expected_dates = self.test_dataframe.index.copy()
expected_dataframe = SimpleReturnsDataFrame(data=expected_values,
columns=expected_columns,
index=expected_dates)
self.data_cleaner.threshold = 0.2
actual_dataframe = self.data_cleaner.proxy_using_value(proxy_value=0.0)
assert_dataframes_equal(expected_dataframe, actual_dataframe)
def test_proxy_using_regression(self):
expected_values = [[np.nan, 0.0, 0.0, 0.0], [1.0, 1.0, 1.0, 1.0],
[2.0, 2.0, 2.0, 2.0], [3.0, 3.0, 3.0, 3.0],
[4.0, 4.0, 4.0, 4.0], [5.0, 5.0, 5.0, 5.0]]
expected_columns = ['a', 'c', 'd', 'e']
expected_dates = self.test_dataframe.index.copy()
expected_dataframe = SimpleReturnsDataFrame(data=expected_values,
columns=expected_columns,
index=expected_dates)
self.data_cleaner.threshold = 0.2
actual_dataframe = self.data_cleaner.proxy_using_regression(
benchmark_tms=self.test_benchmark,
columns_type=SimpleReturnsSeries)
assert_dataframes_equal(expected_dataframe, actual_dataframe)