def test_meta_from_recarray():
x = np.array([(i, i * 10) for i in range(10)],
dtype=[('a', np.float64), ('b', np.int64)])
res = _meta_from_array(x)
assert isinstance(res, pd.DataFrame)
assert res['a'].dtype == np.float64
assert res['b'].dtype == np.int64
tm.assert_index_equal(res.columns, pd.Index(['a', 'b']))
res = _meta_from_array(x, columns=['b', 'a'])
assert isinstance(res, pd.DataFrame)
assert res['a'].dtype == np.float64
assert res['b'].dtype == np.int64
tm.assert_index_equal(res.columns, pd.Index(['b', 'a']))
with pytest.raises(ValueError):
_meta_from_array(x, columns=['a', 'b', 'c'])
def test_meta_from_recarray():
x = np.array([(i, i * 10) for i in range(10)],
dtype=[('a', np.float64), ('b', np.int64)])
res = _meta_from_array(x)
assert isinstance(res, pd.DataFrame)
assert res['a'].dtype == np.float64
assert res['b'].dtype == np.int64
tm.assert_index_equal(res.columns, pd.Index(['a', 'b']))
res = _meta_from_array(x, columns=['b', 'a'])
assert isinstance(res, pd.DataFrame)
assert res['a'].dtype == np.float64
assert res['b'].dtype == np.int64
tm.assert_index_equal(res.columns, pd.Index(['b', 'a']))
with pytest.raises(ValueError):
_meta_from_array(x, columns=['a', 'b', 'c'])
def test_meta_from_1darray():
x = np.array([1., 2., 3.], dtype=np.float64)
res = _meta_from_array(x)
assert isinstance(res, pd.Series)
assert res.dtype == np.float64
x = np.array([1, 2, 3], dtype=np.object_)
res = _meta_from_array(x, columns='x')
assert isinstance(res, pd.Series)
assert res.name == 'x'
assert res.dtype == np.object_
x = np.array([1, 2, 3], dtype=np.object_)
res = _meta_from_array(x, columns=['x'])
assert isinstance(res, pd.DataFrame)
assert res['x'].dtype == np.object_
tm.assert_index_equal(res.columns, pd.Index(['x']))
with pytest.raises(ValueError):
_meta_from_array(x, columns=['a', 'b'])
def test_meta_from_1darray():
x = np.array([1., 2., 3.], dtype=np.float64)
res = _meta_from_array(x)
assert isinstance(res, pd.Series)
assert res.dtype == np.float64
x = np.array([1, 2, 3], dtype=np.object_)
res = _meta_from_array(x, columns='x')
assert isinstance(res, pd.Series)
assert res.name == 'x'
assert res.dtype == np.object_
x = np.array([1, 2, 3], dtype=np.object_)
res = _meta_from_array(x, columns=['x'])
assert isinstance(res, pd.DataFrame)
assert res['x'].dtype == np.object_
tm.assert_index_equal(res.columns, pd.Index(['x']))
with pytest.raises(ValueError):
_meta_from_array(x, columns=['a', 'b'])
def test_meta_from_1darray():
x = np.array([1.0, 2.0, 3.0], dtype=np.float64)
res = _meta_from_array(x)
assert isinstance(res, pd.Series)
assert res.dtype == np.float64
x = np.array([1, 2, 3], dtype=np.object_)
res = _meta_from_array(x, columns="x")
assert isinstance(res, pd.Series)
assert res.name == "x"
assert res.dtype == np.object_
x = np.array([1, 2, 3], dtype=np.object_)
res = _meta_from_array(x, columns=["x"])
assert isinstance(res, pd.DataFrame)
assert res["x"].dtype == np.object_
tm.assert_index_equal(res.columns, pd.Index(["x"]))
with pytest.raises(ValueError):
_meta_from_array(x, columns=["a", "b"])
def test_meta_from_array():
x = np.array([[1, 2], [3, 4]], dtype=np.int64)
res = _meta_from_array(x)
assert isinstance(res, pd.DataFrame)
assert res[0].dtype == np.int64
assert res[1].dtype == np.int64
tm.assert_index_equal(res.columns, pd.Index([0, 1]))
x = np.array([[1., 2.], [3., 4.]], dtype=np.float64)
res = _meta_from_array(x, columns=['a', 'b'])
assert isinstance(res, pd.DataFrame)
assert res['a'].dtype == np.float64
assert res['b'].dtype == np.float64
tm.assert_index_equal(res.columns, pd.Index(['a', 'b']))
with pytest.raises(ValueError):
_meta_from_array(x, columns=['a', 'b', 'c'])
np.random.seed(42)
x = np.random.rand(201, 2)
x = dd.from_array(x, chunksize=50, columns=['a', 'b'])
assert len(x.divisions) == 6 # Should be 5 partitions and the end
def test_meta_from_array():
x = np.array([[1, 2], [3, 4]], dtype=np.int64)
res = _meta_from_array(x)
assert isinstance(res, pd.DataFrame)
assert res[0].dtype == np.int64
assert res[1].dtype == np.int64
tm.assert_index_equal(res.columns, pd.Index([0, 1]))
x = np.array([[1., 2.], [3., 4.]], dtype=np.float64)
res = _meta_from_array(x, columns=['a', 'b'])
assert isinstance(res, pd.DataFrame)
assert res['a'].dtype == np.float64
assert res['b'].dtype == np.float64
tm.assert_index_equal(res.columns, pd.Index(['a', 'b']))
with pytest.raises(ValueError):
_meta_from_array(x, columns=['a', 'b', 'c'])
np.random.seed(42)
x = np.random.rand(201, 2)
x = dd.from_array(x, chunksize=50, columns=['a', 'b'])
assert len(x.divisions) == 6 # Should be 5 partitions and the end