Python testing.check_arrays函数代码示例

 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),
     )

    def test_setitem_array(self):
        arr = LabelArray(self.strs, missing_value=None)
        orig_arr = arr.copy()

        # Write a row.
        self.assertFalse(
            (arr[0] == arr[1]).all(),
            "This test doesn't test anything because rows 0"
            " and 1 are already equal!"
        )
        arr[0] = arr[1]
        for i in range(arr.shape[1]):
            self.assertEqual(arr[0, i], arr[1, i])

        # Write a column.
        self.assertFalse(
            (arr[:, 0] == arr[:, 1]).all(),
            "This test doesn't test anything because columns 0"
            " and 1 are already equal!"
        )
        arr[:, 0] = arr[:, 1]
        for i in range(arr.shape[0]):
            self.assertEqual(arr[i, 0], arr[i, 1])

        # Write the whole array.
        arr[:] = orig_arr
        check_arrays(arr, orig_arr)

    def test_masked_rankdata_2d(self,
                                seed_value,
                                method,
                                use_mask,
                                set_missing,
                                ascending):
        eyemask = ~eye(5, dtype=bool)
        nomask = ones((5, 5), dtype=bool)

        seed(seed_value)
        asfloat = (randn(5, 5) * seed_value)
        asdatetime = (asfloat).copy().view('datetime64[ns]')

        mask = eyemask if use_mask else nomask
        if set_missing:
            asfloat[:, 2] = nan
            asdatetime[:, 2] = NaTns

        float_result = masked_rankdata_2d(
            data=asfloat,
            mask=mask,
            missing_value=nan,
            method=method,
            ascending=True,
        )
        datetime_result = masked_rankdata_2d(
            data=asdatetime,
            mask=mask,
            missing_value=NaTns,
            method=method,
            ascending=True,
        )

        check_arrays(float_result, datetime_result)

    def test_rolling_and_nonrolling(self):
        open_ = USEquityPricing.open
        close = USEquityPricing.close
        volume = USEquityPricing.volume

        # Test for thirty days up to the last day that we think all
        # the assets existed.
        dates_to_test = self.dates[-30:]

        constants = {open_: 1, close: 2, volume: 3}
        loader = PrecomputedLoader(constants=constants, dates=self.dates, sids=self.asset_ids)
        engine = SimplePipelineEngine(lambda column: loader, self.dates, self.asset_finder)

        sumdiff = RollingSumDifference()

        result = engine.run_pipeline(
            Pipeline(
                columns={"sumdiff": sumdiff, "open": open_.latest, "close": close.latest, "volume": volume.latest}
            ),
            dates_to_test[0],
            dates_to_test[-1],
        )
        self.assertIsNotNone(result)
        self.assertEqual({"sumdiff", "open", "close", "volume"}, set(result.columns))

        result_index = self.asset_ids * len(dates_to_test)
        result_shape = (len(result_index),)
        check_arrays(result["sumdiff"], Series(index=result_index, data=full(result_shape, -3, dtype=float)))

        for name, const in [("open", 1), ("close", 2), ("volume", 3)]:
            check_arrays(result[name], Series(index=result_index, data=full(result_shape, const, dtype=float)))

    def test_isnull_datetime_dtype(self):
        class DatetimeFactor(Factor):
            dtype = datetime64ns_dtype
            window_length = 0
            inputs = ()

        factor = DatetimeFactor()

        data = arange(25).reshape(5, 5).astype('datetime64[ns]')
        data[eye(5, dtype=bool)] = NaTns

        graph = TermGraph(
            {
                'isnull': factor.isnull(),
                'notnull': factor.notnull(),
            }
        )

        results = self.run_graph(
            graph,
            initial_workspace={factor: data},
            mask=self.build_mask(ones((5, 5))),
        )
        check_arrays(results['isnull'], eye(5, dtype=bool))
        check_arrays(results['notnull'], ~eye(5, dtype=bool))

    def test_percentile_nasty_partitions(self):
        # Test percentile with nasty partitions: divide up 5 assets into
        # quartiles.
        # There isn't a nice mathematical definition of correct behavior here,
        # so for now we guarantee the behavior of numpy.nanpercentile.  This is
        # mostly for regression testing in case we write our own specialized
        # percentile calculation at some point in the future.

        data = arange(25, dtype=float).reshape(5, 5) % 4
        quartiles = range(4)
        filter_names = ['pct_' + str(q) for q in quartiles]

        graph = TermGraph(
            {
                name: self.f.percentile_between(q * 25.0, (q + 1) * 25.0)
                for name, q in zip(filter_names, quartiles)
            }
        )
        results = self.run_graph(
            graph,
            initial_workspace={self.f: data},
            mask=self.build_mask(ones((5, 5))),
        )

        for name, quartile in zip(filter_names, quartiles):
            result = results[name]
            lower = quartile * 25.0
            upper = (quartile + 1) * 25.0
            expected = and_(
                nanpercentile(data, lower, axis=1, keepdims=True) <= data,
                data <= nanpercentile(data, upper, axis=1, keepdims=True),
            )
            check_arrays(result, expected)

    def test_isnull_int_dtype(self, custom_missing_value):

        class CustomMissingValue(Factor):
            dtype = int64_dtype
            window_length = 0
            missing_value = custom_missing_value
            inputs = ()

        factor = CustomMissingValue()

        data = arange(25).reshape(5, 5)
        data[eye(5, dtype=bool)] = custom_missing_value

        graph = TermGraph(
            {
                'isnull': factor.isnull(),
                'notnull': factor.notnull(),
            }
        )

        results = self.run_graph(
            graph,
            initial_workspace={factor: data},
            mask=self.build_mask(ones((5, 5))),
        )
        check_arrays(results['isnull'], eye(5, dtype=bool))
        check_arrays(results['notnull'], ~eye(5, dtype=bool))

    def test_single_factor(self):
        loader = self.loader
        assets = self.assets
        engine = SimplePipelineEngine(
            lambda column: loader, self.dates, self.asset_finder,
        )
        result_shape = (num_dates, num_assets) = (5, len(assets))
        dates = self.dates[10:10 + num_dates]

        factor = RollingSumDifference()
        expected_result = -factor.window_length

        # Since every asset will pass the screen, these should be equivalent.
        pipelines = [
            Pipeline(columns={'f': factor}),
            Pipeline(
                columns={'f': factor},
                screen=factor.eq(expected_result),
            ),
        ]

        for p in pipelines:
            result = engine.run_pipeline(p, dates[0], dates[-1])
            self.assertEqual(set(result.columns), {'f'})
            assert_multi_index_is_product(
                self, result.index, dates, assets
            )

            check_arrays(
                result['f'].unstack().values,
                full(result_shape, expected_result, dtype=float),
            )

 def compute(self, today, assets, out, returns, returns_slice):
     # Make sure that our slice is the correct shape (i.e. has only
     # one column) and that it has the same values as the original
     # returns factor from which it is derived.
     assert returns_slice.shape == (self.window_length, 1)
     assert returns.shape == (self.window_length, len(sids))
     check_arrays(returns_slice[:, 0], returns[:, my_asset_column])

    def test_window_safe(self, factor_len):
        # all true data set of (days, securities)
        data = full(self.default_shape, True, dtype=bool)

        class InputFilter(Filter):
            inputs = ()
            window_length = 0

        class TestFactor(CustomFactor):
            dtype = float64_dtype
            inputs = (InputFilter(), )
            window_length = factor_len

            def compute(self, today, assets, out, filter_):
                # sum for each column
                out[:] = np_sum(filter_, axis=0)

        results = self.run_graph(
            TermGraph({'windowsafe': TestFactor()}),
            initial_workspace={InputFilter(): data},
        )

        # number of days in default_shape
        n = self.default_shape[0]

        # shape of output array
        output_shape = ((n - factor_len + 1), self.default_shape[1])
        check_arrays(
            results['windowsafe'],
            full(output_shape, factor_len, dtype=float64)
        )

 def check_output(self, expr, expected):
     result = expr._compute(
         [self.fake_raw_data[input_] for input_ in expr.inputs],
         self.mask.index,
         self.mask.columns,
         self.mask.values,
     )
     check_arrays(result, expected)

    def test_any(self):

        # FUN FACT: The inputs and outputs here are exactly the negation of
        # the inputs and outputs for test_all above. This isn't a coincidence.
        #
        # By de Morgan's Laws, we have::
        #
        #     ~(a & b) == (~a | ~b)
        #
        # negating both sides, we have::
        #
        #      (a & b) == ~(a | ~b)
        #
        # Since all(a, b) is isomorphic to (a & b), and any(a, b) is isomorphic
        # to (a | b), we have::
        #
        #     all(a, b) == ~(any(~a, ~b))
        #
        data = array([[0, 0, 0, 0, 0, 0],
                      [1, 0, 0, 0, 0, 0],
                      [0, 1, 0, 0, 0, 0],
                      [0, 0, 1, 0, 0, 0],
                      [0, 0, 0, 1, 0, 0],
                      [0, 0, 0, 0, 1, 0],
                      [0, 0, 0, 0, 0, 1]], dtype=bool)

        # With a window_length of N, 1's should be "sticky" for the (N - 1)
        # days after the 1 in the base data.

        # Note that, the way ``self.run_graph`` works, we compute the same
        # number of output rows for all inputs, so we only get the last 4
        # outputs for expected_3 even though we have enought input data to
        # compute 5 rows.
        expected_3 = array([[1, 1, 1, 0, 0, 0],
                            [0, 1, 1, 1, 0, 0],
                            [0, 0, 1, 1, 1, 0],
                            [0, 0, 0, 1, 1, 1]], dtype=bool)

        expected_4 = array([[1, 1, 1, 0, 0, 0],
                            [1, 1, 1, 1, 0, 0],
                            [0, 1, 1, 1, 1, 0],
                            [0, 0, 1, 1, 1, 1]], dtype=bool)

        class Input(Filter):
            inputs = ()
            window_length = 0

        results = self.run_graph(
            TermGraph({
                '3': Any(inputs=[Input()], window_length=3),
                '4': Any(inputs=[Input()], window_length=4),
            }),
            initial_workspace={Input(): data},
            mask=self.build_mask(ones(shape=data.shape)),
        )

        check_arrays(results['3'], expected_3)
        check_arrays(results['4'], expected_4)

 def check(terms):
     graph = TermGraph(terms)
     results = self.run_graph(
         graph,
         initial_workspace={f: data},
         mask=self.build_mask(ones((5, 5))),
     )
     for method in terms:
         check_arrays(results[method], expected_ranks[method])

 def check_terms(self, terms, expected, initial_workspace, mask):
     """
     Compile the given terms into a TermGraph, compute it with
     initial_workspace, and compare the results with ``expected``.
     """
     graph = TermGraph(terms)
     results = self.run_graph(graph, initial_workspace, mask)
     for key, (res, exp) in dzip_exact(results, expected).items():
         check_arrays(res, exp)

    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)