Exemplo n.º 1
0
 def test_make_cascading_boolean_array(self):
     check_arrays(
         make_cascading_boolean_array((3, 3)),
         array(
             [[True,   True, False],
              [True,  False, False],
              [False, False, False]]
         ),
     )
     check_arrays(
         make_cascading_boolean_array((3, 3), first_value=False),
         array(
             [[False, False, True],
              [False,  True, True],
              [True,   True, True]]
         ),
     )
     check_arrays(
         make_cascading_boolean_array((1, 3)),
         array([[True, True, False]]),
     )
     check_arrays(
         make_cascading_boolean_array((3, 1)),
         array([[False], [False], [False]]),
     )
     check_arrays(
         make_cascading_boolean_array((3, 0)),
         empty((3, 0), dtype=bool_dtype),
     )
Exemplo n.º 2
0
 def test_make_cascading_boolean_array(self):
     check_arrays(
         make_cascading_boolean_array((3, 3)),
         array(
             [[True,   True, False],
              [True,  False, False],
              [False, False, False]]
         ),
     )
     check_arrays(
         make_cascading_boolean_array((3, 3), first_value=False),
         array(
             [[False, False, True],
              [False,  True, True],
              [True,   True, True]]
         ),
     )
     check_arrays(
         make_cascading_boolean_array((1, 3)),
         array([[True, True, False]]),
     )
     check_arrays(
         make_cascading_boolean_array((3, 1)),
         array([[False], [False], [False]]),
     )
     check_arrays(
         make_cascading_boolean_array((3, 0)),
         empty((3, 0), dtype=bool_dtype),
     )
Exemplo n.º 3
0
    def init_class_fixtures(cls):
        super(StatisticalMethodsTestCase, cls).init_class_fixtures()

        # Using these start and end dates because they are a contigous span of
        # 5 days (Monday - Friday) and they allow for plenty of days to look
        # back on when computing correlations and regressions.
        cls.dates = dates = cls.trading_days
        cls.start_date_index = start_date_index = 14
        cls.end_date_index = end_date_index = 18
        cls.pipeline_start_date = cls.trading_days[start_date_index]
        cls.pipeline_end_date = cls.trading_days[end_date_index]

        sids = cls.sids
        cls.assets = assets = cls.asset_finder.retrieve_all(sids)
        cls.my_asset_column = my_asset_column = 0
        cls.my_asset = assets[my_asset_column]
        cls.num_days = num_days = end_date_index - start_date_index + 1
        cls.num_assets = num_assets = len(assets)

        cls.cascading_mask = \
            AssetIDPlusDay() < (sids[-1] + dates[start_date_index].day)
        cls.expected_cascading_mask_result = make_cascading_boolean_array(
            shape=(num_days, num_assets), )
        cls.alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        cls.expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_days, num_assets), )
        cls.expected_no_mask_result = full(
            shape=(num_days, num_assets),
            fill_value=True,
            dtype=bool_dtype,
        )

        # Random input for factors.
        cls.col = TestingDataSet.float_col
    def init_class_fixtures(cls):
        super(StatisticalMethodsTestCase, cls).init_class_fixtures()

        # Using these start and end dates because they are a contigous span of
        # 5 days (Monday - Friday) and they allow for plenty of days to look
        # back on when computing correlations and regressions.
        cls.dates = dates = cls.trading_days
        cls.start_date_index = start_date_index = 14
        cls.end_date_index = end_date_index = 18
        cls.pipeline_start_date = cls.trading_days[start_date_index]
        cls.pipeline_end_date = cls.trading_days[end_date_index]

        sids = cls.sids
        cls.assets = assets = cls.asset_finder.retrieve_all(sids)
        cls.my_asset_column = my_asset_column = 0
        cls.my_asset = assets[my_asset_column]
        cls.num_days = num_days = end_date_index - start_date_index + 1
        cls.num_assets = num_assets = len(assets)

        cls.cascading_mask = \
            AssetIDPlusDay() < (sids[-1] + dates[start_date_index].day)
        cls.expected_cascading_mask_result = make_cascading_boolean_array(
            shape=(num_days, num_assets),
        )
        cls.alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        cls.expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_days, num_assets),
        )
        cls.expected_no_mask_result = full(
            shape=(num_days, num_assets), fill_value=True, dtype=bool_dtype,
        )

        # Random input for factors.
        cls.col = TestingDataSet.float_col
    def init_class_fixtures(cls):
        super(StatisticalBuiltInsTestCase, cls).init_class_fixtures()

        day = cls.trading_calendar.day
        cls.dates = dates = date_range(
            '2015-02-01', '2015-02-28', freq=day, tz='UTC',
        )

        # Using these start and end dates because they are a contigous span of
        # 5 days (Monday - Friday) and they allow for plenty of days to look
        # back on when computing correlations and regressions.
        cls.start_date_index = start_date_index = 14
        cls.end_date_index = end_date_index = 18
        cls.pipeline_start_date = dates[start_date_index]
        cls.pipeline_end_date = dates[end_date_index]
        cls.num_days = num_days = end_date_index - start_date_index + 1

        sids = cls.sids
        cls.assets = assets = cls.asset_finder.retrieve_all(sids)
        cls.my_asset_column = my_asset_column = 0
        cls.my_asset = assets[my_asset_column]
        cls.num_assets = num_assets = len(assets)

        cls.raw_data = raw_data = DataFrame(
            data=arange(len(dates) * len(sids), dtype=float64_dtype).reshape(
                len(dates), len(sids),
            ),
            index=dates,
            columns=assets,
        )

        # Using mock 'close' data here because the correlation and regression
        # built-ins use USEquityPricing.close as the input to their `Returns`
        # factors. Since there is no way to change that when constructing an
        # instance of these built-ins, we need to test with mock 'close' data
        # to most accurately reflect their true behavior and results.
        close_loader = DataFrameLoader(USEquityPricing.close, raw_data)

        cls.run_pipeline = SimplePipelineEngine(
            {USEquityPricing.close: close_loader}.__getitem__,
            dates,
            cls.asset_finder,
        ).run_pipeline

        cls.cascading_mask = \
            AssetIDPlusDay() < (sids[-1] + dates[start_date_index].day)
        cls.expected_cascading_mask_result = make_cascading_boolean_array(
            shape=(num_days, num_assets),
        )
        cls.alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        cls.expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_days, num_assets),
        )
        cls.expected_no_mask_result = full(
            shape=(num_days, num_assets), fill_value=True, dtype=bool_dtype,
        )
    def init_class_fixtures(cls):
        super(StatisticalBuiltInsTestCase, cls).init_class_fixtures()

        day = cls.trading_calendar.day
        cls.dates = dates = date_range(
            '2015-02-01', '2015-02-28', freq=day, tz='UTC',
        )

        # Using these start and end dates because they are a contigous span of
        # 5 days (Monday - Friday) and they allow for plenty of days to look
        # back on when computing correlations and regressions.
        cls.start_date_index = start_date_index = 14
        cls.end_date_index = end_date_index = 18
        cls.pipeline_start_date = dates[start_date_index]
        cls.pipeline_end_date = dates[end_date_index]
        cls.num_days = num_days = end_date_index - start_date_index + 1

        sids = cls.sids
        cls.assets = assets = cls.asset_finder.retrieve_all(sids)
        cls.my_asset_column = my_asset_column = 0
        cls.my_asset = assets[my_asset_column]
        cls.num_assets = num_assets = len(assets)

        cls.raw_data = raw_data = DataFrame(
            data=arange(len(dates) * len(sids), dtype=float64_dtype).reshape(
                len(dates), len(sids),
            ),
            index=dates,
            columns=assets,
        )

        # Using mock 'close' data here because the correlation and regression
        # built-ins use USEquityPricing.close as the input to their `Returns`
        # factors. Since there is no way to change that when constructing an
        # instance of these built-ins, we need to test with mock 'close' data
        # to most accurately reflect their true behavior and results.
        close_loader = DataFrameLoader(USEquityPricing.close, raw_data)

        cls.run_pipeline = SimplePipelineEngine(
            {USEquityPricing.close: close_loader}.__getitem__,
            dates,
            cls.asset_finder,
        ).run_pipeline

        cls.cascading_mask = \
            AssetIDPlusDay() < (sids[-1] + dates[start_date_index].day)
        cls.expected_cascading_mask_result = make_cascading_boolean_array(
            shape=(num_days, num_assets),
        )
        cls.alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        cls.expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_days, num_assets),
        )
        cls.expected_no_mask_result = full(
            shape=(num_days, num_assets), fill_value=True, dtype=bool_dtype,
        )
Exemplo n.º 7
0
    def test_factor_with_multiple_outputs(self):
        dates = self.dates[5:10]
        assets = self.assets
        asset_ids = self.asset_ids
        constants = self.constants
        num_dates = len(dates)
        num_assets = len(assets)
        open = USEquityPricing.open
        close = USEquityPricing.close
        engine = SimplePipelineEngine(
            lambda column: self.loader, self.dates, self.asset_finder,
        )

        def create_expected_results(expected_value, mask):
            expected_values = where(mask, expected_value, nan)
            return DataFrame(expected_values, index=dates, columns=assets)

        cascading_mask = AssetIDPlusDay() < (asset_ids[-1] + dates[0].day)
        expected_cascading_mask_result = make_cascading_boolean_array(
            shape=(num_dates, num_assets),
        )

        alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_dates, num_assets), first_value=False,
        )

        expected_no_mask_result = full(
            shape=(num_dates, num_assets), fill_value=True, dtype=bool_dtype,
        )

        masks = cascading_mask, alternating_mask, NotSpecified
        expected_mask_results = (
            expected_cascading_mask_result,
            expected_alternating_mask_result,
            expected_no_mask_result,
        )
        for mask, expected_mask in zip(masks, expected_mask_results):
            open_price, close_price = MultipleOutputs(mask=mask)
            pipeline = Pipeline(
                columns={'open_price': open_price, 'close_price': close_price},
            )
            if mask is not NotSpecified:
                pipeline.add(mask, 'mask')

            results = engine.run_pipeline(pipeline, dates[0], dates[-1])
            for colname, case_column in (('open_price', open),
                                         ('close_price', close)):
                if mask is not NotSpecified:
                    mask_results = results['mask'].unstack()
                    check_arrays(mask_results.values, expected_mask)
                output_results = results[colname].unstack()
                output_expected = create_expected_results(
                    constants[case_column], expected_mask,
                )
                assert_frame_equal(output_results, output_expected)
Exemplo n.º 8
0
    def test_masked_factor(self):
        """
        Test that a Custom Factor computes the correct values when passed a
        mask. The mask/filter should be applied prior to computing any values,
        as opposed to computing the factor across the entire universe of
        assets. Any assets that are filtered out should be filled with missing
        values.
        """
        loader = self.loader
        dates = self.dates[5:8]
        assets = self.assets
        asset_ids = self.asset_ids
        constants = self.constants
        num_dates = len(dates)
        num_assets = len(assets)
        open = USEquityPricing.open
        close = USEquityPricing.close
        engine = SimplePipelineEngine(lambda column: loader, self.dates, self.asset_finder)

        factor1_value = constants[open]
        factor2_value = 3.0 * (constants[open] - constants[close])

        def create_expected_results(expected_value, mask):
            expected_values = where(mask, expected_value, nan)
            return DataFrame(expected_values, index=dates, columns=assets)

        cascading_mask = AssetIDPlusDay() < (asset_ids[-1] + dates[0].day)
        expected_cascading_mask_result = make_cascading_boolean_array(shape=(num_dates, num_assets))

        alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_dates, num_assets), first_value=False
        )

        masks = cascading_mask, alternating_mask
        expected_mask_results = (expected_cascading_mask_result, expected_alternating_mask_result)
        for mask, expected_mask in zip(masks, expected_mask_results):
            # Test running a pipeline with a single masked factor.
            columns = {"factor1": OpenPrice(mask=mask), "mask": mask}
            pipeline = Pipeline(columns=columns)
            results = engine.run_pipeline(pipeline, dates[0], dates[-1])

            mask_results = results["mask"].unstack()
            check_arrays(mask_results.values, expected_mask)

            factor1_results = results["factor1"].unstack()
            factor1_expected = create_expected_results(factor1_value, mask_results)
            assert_frame_equal(factor1_results, factor1_expected)

            # Test running a pipeline with a second factor. This ensures that
            # adding another factor to the pipeline with a different window
            # length does not cause any unexpected behavior, especially when
            # both factors share the same mask.
            columns["factor2"] = RollingSumDifference(mask=mask)
            pipeline = Pipeline(columns=columns)
            results = engine.run_pipeline(pipeline, dates[0], dates[-1])

            mask_results = results["mask"].unstack()
            check_arrays(mask_results.values, expected_mask)

            factor1_results = results["factor1"].unstack()
            factor2_results = results["factor2"].unstack()
            factor1_expected = create_expected_results(factor1_value, mask_results)
            factor2_expected = create_expected_results(factor2_value, mask_results)
            assert_frame_equal(factor1_results, factor1_expected)
            assert_frame_equal(factor2_results, factor2_expected)
Exemplo n.º 9
0
    def test_masked_factor(self):
        """
        Test that a Custom Factor computes the correct values when passed a
        mask. The mask/filter should be applied prior to computing any values,
        as opposed to computing the factor across the entire universe of
        assets. Any assets that are filtered out should be filled with missing
        values.
        """
        loader = self.loader
        dates = self.dates[5:8]
        assets = self.assets
        asset_ids = self.asset_ids
        constants = self.constants
        num_dates = len(dates)
        num_assets = len(assets)
        open = USEquityPricing.open
        close = USEquityPricing.close
        engine = SimplePipelineEngine(
            lambda column: loader, self.dates, self.asset_finder,
        )

        factor1_value = constants[open]
        factor2_value = 3.0 * (constants[open] - constants[close])

        def create_expected_results(expected_value, mask):
            expected_values = where(mask, expected_value, nan)
            return DataFrame(expected_values, index=dates, columns=assets)

        cascading_mask = AssetIDPlusDay() < (asset_ids[-1] + dates[0].day)
        expected_cascading_mask_result = make_cascading_boolean_array(
            shape=(num_dates, num_assets),
        )

        alternating_mask = (AssetIDPlusDay() % 2).eq(0)
        expected_alternating_mask_result = make_alternating_boolean_array(
            shape=(num_dates, num_assets), first_value=False,
        )

        masks = cascading_mask, alternating_mask
        expected_mask_results = (
            expected_cascading_mask_result,
            expected_alternating_mask_result,
        )
        for mask, expected_mask in zip(masks, expected_mask_results):
            # Test running a pipeline with a single masked factor.
            columns = {'factor1': OpenPrice(mask=mask), 'mask': mask}
            pipeline = Pipeline(columns=columns)
            results = engine.run_pipeline(pipeline, dates[0], dates[-1])

            mask_results = results['mask'].unstack()
            check_arrays(mask_results.values, expected_mask)

            factor1_results = results['factor1'].unstack()
            factor1_expected = create_expected_results(factor1_value,
                                                       mask_results)
            assert_frame_equal(factor1_results, factor1_expected)

            # Test running a pipeline with a second factor. This ensures that
            # adding another factor to the pipeline with a different window
            # length does not cause any unexpected behavior, especially when
            # both factors share the same mask.
            columns['factor2'] = RollingSumDifference(mask=mask)
            pipeline = Pipeline(columns=columns)
            results = engine.run_pipeline(pipeline, dates[0], dates[-1])

            mask_results = results['mask'].unstack()
            check_arrays(mask_results.values, expected_mask)

            factor1_results = results['factor1'].unstack()
            factor2_results = results['factor2'].unstack()
            factor1_expected = create_expected_results(factor1_value,
                                                       mask_results)
            factor2_expected = create_expected_results(factor2_value,
                                                       mask_results)
            assert_frame_equal(factor1_results, factor1_expected)
            assert_frame_equal(factor2_results, factor2_expected)