[Add] Paddle 代码 CI 中引入 xdoctest 检查

python/paddle/distribution/bernoulli.py

@@ -72,23 +72,23 @@ class Bernoulli(exponential_family.ExponentialFamily):
 
         .. code-block:: python
 
-            import paddle
-            from paddle.distribution import Bernoulli
+            >>> import paddle
+            >>> from paddle.distribution import Bernoulli
 
-            # init `probs` with a float
-            rv = Bernoulli(probs=0.3)
+            >>> # init `probs` with a float
+            >>> rv = Bernoulli(probs=0.3)
 
-            print(rv.mean)
-            # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-            #        0.30000001)
+            >>> print(rv.mean)
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+            0.30000001)
 
-            print(rv.variance)
-            # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-            #        0.21000001)
+            >>> print(rv.variance)
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+            0.21000001)
 
-            print(rv.entropy())
-            # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-            #        0.61086434)
+            >>> print(rv.entropy())
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+            0.61086434)
     """
 
     def __init__(self, probs, name=None):
@@ -156,24 +156,24 @@ def sample(self, shape):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
 
-                rv = Bernoulli(paddle.full((), 0.3))
-                print(rv.sample([100]).shape)
-                # [100]
+                >>> rv = Bernoulli(paddle.full((1), 0.3))
+                >>> print(rv.sample([100]).shape)
+                [100, 1]
 
-                rv = Bernoulli(paddle.to_tensor(0.3))
-                print(rv.sample([100]).shape)
-                # [100, 1]
+                >>> rv = Bernoulli(paddle.to_tensor(0.3))
+                >>> print(rv.sample([100]).shape)
+                [100]
 
-                rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
-                print(rv.sample([100]).shape)
-                # [100, 2]
+                >>> rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
+                >>> print(rv.sample([100]).shape)
+                [100, 2]
 
-                rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
-                print(rv.sample([100, 2]).shape)
-                # [100, 2, 2]
+                >>> rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
+                >>> print(rv.sample([100, 2]).shape)
+                [100, 2, 2]
         """
         name = self.name + '_sample'
         if not in_dynamic_mode():
@@ -211,48 +211,48 @@ def rsample(self, shape, temperature=1.0):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
-
-                paddle.seed(2023)
-
-                rv = Bernoulli(paddle.full((), 0.3))
-                print(rv.sample([100]).shape)
-                # [100]
-
-                rv = Bernoulli(0.3)
-                print(rv.rsample([100]).shape)
-                # [100, 1]
-
-                rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
-                print(rv.rsample([100]).shape)
-                # [100, 2]
-
-                rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
-                print(rv.rsample([100, 2]).shape)
-                # [100, 2, 2]
-
-                # `rsample` has to be followed by a `sigmoid`
-                rv = Bernoulli(0.3)
-                rsample = rv.rsample([3, ])
-                rsample_sigmoid = paddle.nn.functional.sigmoid(rsample)
-                print(rsample, rsample_sigmoid)
-                # Tensor(shape=[3, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        [[-0.88315082],
-                #         [-0.62347704],
-                #         [-0.31513220]]) Tensor(shape=[3, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        [[0.29252526],
-                #         [0.34899110],
-                #         [0.42186251]])
-
-                # The smaller the `temperature`, the distribution of `rsample` closer to `sample`, with `probs` of 0.3.
-                print(paddle.nn.functional.sigmoid(rv.rsample([1000, ], temperature=1.0)).sum())
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        361.06829834)
-
-                print(paddle.nn.functional.sigmoid(rv.rsample([1000, ], temperature=0.1)).sum())
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        288.66418457)
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
+
+                >>> rv = Bernoulli(paddle.full((1), 0.3))
+                >>> print(rv.sample([100]).shape)
+                [100, 1]
+
+                >>> rv = Bernoulli(0.3)
+                >>> print(rv.rsample([100]).shape)
+                [100]
+
+                >>> rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
+                >>> print(rv.rsample([100]).shape)
+                [100, 2]
+
+                >>> rv = Bernoulli(paddle.to_tensor([0.3, 0.5]))
+                >>> print(rv.rsample([100, 2]).shape)
+                [100, 2, 2]
+
+                >>> # `rsample` has to be followed by a `sigmoid`
+                >>> # doctest: +SKIP
+                >>> rv = Bernoulli(0.3)
+                >>> rsample = rv.rsample([3, ])
+                >>> rsample_sigmoid = paddle.nn.functional.sigmoid(rsample)
+                >>> print(rsample, rsample_sigmoid)
+                Tensor(shape=[3, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                [[-0.88315082],
+                [-0.62347704],
+                [-0.31513220]])
+                Tensor(shape=[3, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                [[0.29252526],
+                [0.34899110],
+                [0.42186251]])
+
+                >>> # The smaller the `temperature`, the distribution of `rsample` closer to `sample`, with `probs` of 0.3.
+                >>> print(paddle.nn.functional.sigmoid(rv.rsample([1000, ], temperature=1.0)).sum())
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                361.06829834)
+
+                >>> print(paddle.nn.functional.sigmoid(rv.rsample([1000, ], temperature=0.1)).sum())
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                288.66418457)
         """
         name = self.name + '_rsample'
         if not in_dynamic_mode():
@@ -308,13 +308,13 @@ def cdf(self, value):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
 
-                rv = Bernoulli(0.3)
-                print(rv.cdf(paddle.to_tensor([1.0])))
-                # Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        [1.])
+                >>> rv = Bernoulli(0.3)
+                >>> print(rv.cdf(paddle.to_tensor([1.0])))
+                Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                [1.])
         """
         name = self.name + '_cdf'
         if not in_dynamic_mode():
@@ -346,13 +346,13 @@ def log_prob(self, value):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
 
-                rv = Bernoulli(0.3)
-                print(rv.log_prob(paddle.to_tensor([1.0])))
-                # Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        [-1.20397282])
+                >>> rv = Bernoulli(0.3)
+                >>> print(rv.log_prob(paddle.to_tensor([1.0])))
+                Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                [-1.20397282])
         """
         name = self.name + '_log_prob'
         if not in_dynamic_mode():
@@ -385,13 +385,13 @@ def prob(self, value):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
 
-                rv = Bernoulli(0.3)
-                print(rv.prob(paddle.to_tensor([1.0])))
-                # Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        [0.29999998])
+                >>> rv = Bernoulli(0.3)
+                >>> print(rv.prob(paddle.to_tensor([1.0])))
+                Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                [0.29999998])
         """
         name = self.name + '_prob'
         if not in_dynamic_mode():
@@ -415,13 +415,13 @@ def entropy(self):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
 
-                rv = Bernoulli(0.3)
-                print(rv.entropy())
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        0.61086434)
+                >>> rv = Bernoulli(0.3)
+                >>> print(rv.entropy())
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                0.61086434)
         """
         name = self.name + '_entropy'
 
@@ -448,15 +448,15 @@ def kl_divergence(self, other):
 
             .. code-block:: python
 
-                import paddle
-                from paddle.distribution import Bernoulli
+                >>> import paddle
+                >>> from paddle.distribution import Bernoulli
 
-                rv = Bernoulli(0.3)
-                rv_other = Bernoulli(0.7)
+                >>> rv = Bernoulli(0.3)
+                >>> rv_other = Bernoulli(0.7)
 
-                print(rv.kl_divergence(rv_other))
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        0.33891910)
+                >>> print(rv.kl_divergence(rv_other))
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                0.33891910)
         """
         name = self.name + '_kl_divergence'
         if not in_dynamic_mode():

python/paddle/distribution/beta.py

@@ -55,31 +55,35 @@ class Beta(exponential_family.ExponentialFamily):
 
         .. code-block:: python
 
-            import paddle
-
-            # scale input
-            beta = paddle.distribution.Beta(alpha=0.5, beta=0.5)
-            print(beta.mean)
-            # Tensor(shape=[], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        0.50000000)
-            print(beta.variance)
-            # Tensor(shape=[], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        0.12500000)
-            print(beta.entropy())
-            # Tensor(shape=[], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        0.12500000)
-
-            # tensor input with broadcast
-            beta = paddle.distribution.Beta(alpha=paddle.to_tensor([0.2, 0.4]), beta=0.6)
-            print(beta.mean)
-            # Tensor(shape=[2], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        [0.25000000, 0.40000001])
-            print(beta.variance)
-            # Tensor(shape=[2], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        [0.10416666, 0.12000000])
-            print(beta.entropy())
-            # Tensor(shape=[2], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        [-1.91923141, -0.38095069])
+            >>> import paddle
+
+            >>> # scale input
+            >>> beta = paddle.distribution.Beta(alpha=0.5, beta=0.5)
+            >>> print(beta.mean)
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+            0.50000000)
+
+            >>> print(beta.variance)
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+            0.12500000)
+
+            >>> print(beta.entropy())
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+            -0.24156499)
+
+            >>> # tensor input with broadcast
+            >>> beta = paddle.distribution.Beta(alpha=paddle.to_tensor([0.2, 0.4]), beta=0.6)
+            >>> print(beta.mean)
+            Tensor(shape=[2], dtype=float32, place=Place(cpu), stop_gradient=True,
+            [0.25000000, 0.40000001])
+
+            >>> print(beta.variance)
+            Tensor(shape=[2], dtype=float32, place=Place(cpu), stop_gradient=True,
+            [0.10416666, 0.12000000])
+
+            >>> print(beta.entropy())
+            Tensor(shape=[2], dtype=float32, place=Place(cpu), stop_gradient=True,
+            [-1.91923141, -0.38095081])
     """
 
     def __init__(self, alpha, beta):