def test_intcolumn():
dm = DataMatrix(length=2)
# Test assignment
dm.col = IntColumn
dm.col = 1
check_col(dm.col, [1, 1])
dm.col = 2, 3
check_col(dm.col, [2, 3])
dm.col[:-1] = 4
check_col(dm.col, [4, 3])
@raises(TypeError)
def _():
dm.col[0] = "test"
_()
@raises(TypeError)
def _():
dm.col[:] = "test"
_()
# Test shortening and lengthening
dm.length = 0
dm.length = 4
# Check uniqueness
dm.col = 1, 2, 1, 2
ok_(sorted(dm.col.unique) == [1, 2])
# Check dtype
ok_(dm.col._seq.dtype == np.int64)
check_integrity(dm)
def check_desc_stats(col_type, invalid, assert_invalid): dm = DataMatrix(length=4, default_col_type=col_type) # Even lengths dm.col = 1, 2, 3, 10 check_even(dm) if col_type is not IntColumn: dm.length = 5 dm.col = 1, 2, 3, 10, invalid check_even(dm) # Odd lengths (and even with one invalid) dm.length = 3 dm.col = 1, 2, 10 check_odd(dm) if col_type is not IntColumn: dm.length = 4 dm.col[3] = invalid check_odd(dm) # One lengths dm.length = 1 dm.col = 1 eq_(dm.col.mean, 1) eq_(dm.col.median, 1) assert_invalid(dm.col.std) eq_(dm.col.min, 1) eq_(dm.col.max, 1) eq_(dm.col.sum, 1) # Zero lengths dm.length = 0 assert_invalid(dm.col.mean) assert_invalid(dm.col.median) assert_invalid(dm.col.std) assert_invalid(dm.col.min) assert_invalid(dm.col.max) assert_invalid(dm.col.sum)
def test_seriescolumn(): dm = DataMatrix(length=2) dm.col = SeriesColumn(depth=2) dm.col[0] = 1, 2 dm.col[1] = 3, 4 dm.col += 1 check_series(dm.col, [[2,3], [4,5]]) dm.col += 1, 2 check_series(dm.col, [[3,4], [6,7]]) dm.col -= 1 check_series(dm.col, [[2,3], [5,6]]) dm.col -= 1, 2 check_series(dm.col, [[1,2], [3,4]]) dm.col *= 2 check_series(dm.col, [[2,4], [6,8]]) dm.col *= 1.5, 3 check_series(dm.col, [[3,6], [18,24]]) dm.col /= 3 check_series(dm.col, [[1,2], [6,8]]) dm.col /= 1, 2 check_series(dm.col, [[1,2], [3,4]]) dm.col //= 1.5, 2.5 check_series(dm.col, [[0,1], [1,1]]) dm.col += np.array([ [0,0], [10, 10] ]) check_series(dm.col, [[0,1], [11,11]])
def check_str_operations(): dm = DataMatrix(length=2, default_col_type=MixedColumn) dm.col = 'a', 'b' check_col(dm.col, ['a', 'b']) dm.col += 'c', 'd' check_col(dm.col, ['ac', 'bd']) check_integrity(dm)
def check_int_operations(): dm = DataMatrix(length=2, default_col_type=IntColumn) dm.col = 1.5, 2.5 check_col(dm.col, [1, 2]) dm.col *= 1.5 check_col(dm.col, [1, 3]) check_integrity(dm)
def test_mixedcolumn():
dm = DataMatrix(length=2)
# Test assignment
dm.col = 1
check_col(dm.col, [1, 1])
dm.col = 2, 3
check_col(dm.col, [2, 3])
dm.col[:-1] = 4
check_col(dm.col, [4, 3])
dm.col[:] = "test"
check_col(dm.col, ["test", "test"])
# Test shortening and lengthening
dm.length = 0
dm.length = 4
# Check uniqueness
dm.col = 1, 2, 1, 2
ok_(sorted(dm.col.unique) == [1, 2])
check_integrity(dm)
def test_seriescolumn():
dm = DataMatrix(length=2)
dm.col = SeriesColumn(depth=3)
# Set all rows to a single value
dm.col = 1
check_series(dm.col, [[1, 1, 1], [1, 1, 1]])
# Set rows to different single values
dm.col = 2, 3
check_series(dm.col, [[2, 2, 2], [3, 3, 3]])
# Set one row to a single value
dm.col[0] = 4
check_series(dm.col, [[4, 4, 4], [3, 3, 3]])
# Set one row to different single values
dm.col[1] = 5, 6, 7
check_series(dm.col, [[4, 4, 4], [5, 6, 7]])
# Set all rows to different single values
dm.col.setallrows([8, 9, 10])
check_series(dm.col, [[8, 9, 10], [8, 9, 10]])
# Set the first value in all rows
dm.col[:, 0] = 1
check_series(dm.col, [[1, 9, 10], [1, 9, 10]])
# Set all values in the first row
dm.col[0, :] = 2
check_series(dm.col, [[2, 2, 2], [1, 9, 10]])
# Set all values
dm.col[:, :] = 3
check_series(dm.col, [[3, 3, 3], [3, 3, 3]])
# Test shortening and lengthening
dm.length = 0
check_series(dm.col, [])
dm.length = 3
dm.col = 1, 2, 3
dm.col.depth = 1
check_series(dm.col, [[1], [2], [3]])
dm.col.depth = 3
check_series(dm.col, [[1, 0, 0], [2, 0, 0], [3, 0, 0]])
check_integrity(dm)
def test_floatcolumn():
dm = DataMatrix(length=2)
# Test assignment
dm.col = FloatColumn
dm.col = 1
check_col(dm.col, [1, 1])
dm.col = 2, 3
check_col(dm.col, [2, 3])
dm.col[:-1] = 4
check_col(dm.col, [4, 3])
dm.col[:] = "test"
for value in dm.col:
ok_(np.isnan(value))
# Test shortening and lengthening
dm.length = 0
dm.length = 4
# Check uniqueness
dm.col = 1, 2, 1, 2
ok_(sorted(dm.col.unique) == [1, 2])
# Check dtype
ok_(dm.col._seq.dtype == np.float64)
check_integrity(dm)
def check_select(col_type): dm = DataMatrix(length=2, default_col_type=col_type) dm.col = 1, 2 dm_ = dm.col < 2 check_col(dm_.col, [1]) dm_ = dm.col == 2 check_col(dm_.col, [2]) dm_ = (dm.col == 1) | (dm.col == 2) check_col(dm_.col, [1,2]) dm_ = (dm.col == 1) & (dm.col == 2) check_col(dm_.col, []) dm_ = (dm.col == 1) ^ (dm.col == 2) check_col(dm_.col, [1,2]) check_integrity(dm)
def test_seriescolumn(): dm = DataMatrix(length=3) dm.col = SeriesColumn(depth=3) dm.col[0] = [1,2,3] dm.col[1] = [3,3,3] dm.col[2] = [4,4,4] ok_(all(dm.col.mean == [8./3, 9./3, 10/3.])) ok_(all(dm.col.median == [3,3,3])) ok_(all(dm.col.max == [4,4,4])) ok_(all(dm.col.min == [1,2,3])) ok_(all(dm.col.std == [ np.std([4,3,1], ddof=1), np.std([4,3,2], ddof=1), np.std([4,3,3], ddof=1) ]))
def check_operations(col_type): dm = DataMatrix(length=2, default_col_type=col_type) dm.col = 1, 2 dm.col += 1 check_col(dm.col, [2, 3]) dm.col += 1, 2 check_col(dm.col, [3, 5]) dm.col -= 1 check_col(dm.col, [2, 4]) dm.col -= 1, 2 check_col(dm.col, [1, 2]) dm.col *= 2 check_col(dm.col, [2, 4]) dm.col *= 1.5, 3 check_col(dm.col, [3, 12]) dm.col /= 3 check_col(dm.col, [1, 4]) dm.col /= 1, 2 check_col(dm.col, [1, 2]) dm.col //= 1.5, 2.5 check_col(dm.col, [0, 0]) check_integrity(dm)
def check_operations(col_type): dm = DataMatrix(length=2, default_col_type=col_type) dm.col = 1, '2' dm.col += 1 check_col(dm.col, [2, 3]) dm.col += 1, '2' check_col(dm.col, [3, 5]) dm.col -= 1 check_col(dm.col, [2, 4]) dm.col -= 1, '2' check_col(dm.col, [1, 2]) dm.col *= 2 check_col(dm.col, [2, 4]) dm.col *= 1, '2' check_col(dm.col, [2, 8]) dm.col /= 2 check_col(dm.col, [1, 4]) dm.col /= 1, '2' check_col(dm.col, [1, 2]) # Right-hand operations dm.col = 1 + dm.col check_col(dm.col, [2, 3]) dm.col = (1, 2) + dm.col check_col(dm.col, [3, 5]) dm.col = 5 - dm.col check_col(dm.col, [2, 0]) dm.col = (3, 1) - dm.col check_col(dm.col, [1, 1]) dm.col = 2 * dm.col check_col(dm.col, [2, 2]) dm.col = (1, 2) * dm.col check_col(dm.col, [2, 4]) dm.col = 4 / dm.col check_col(dm.col, [2, 1]) dm.col = (4, 2) / dm.col check_col(dm.col, [2, 2]) dm.col = 2 ** dm.col check_col(dm.col, [4, 4]) dm.col = (2, 4) ** dm.col check_col(dm.col, [16, 256]) dm.col = 17 % dm.col check_col(dm.col, [1, 17]) dm.col = (2, 16) % dm.col check_col(dm.col, [0, 16]) check_integrity(dm)
def test_seriescolumn(): dm = DataMatrix(length=2) dm.col = SeriesColumn(depth=2) dm.col[0] = 1, 2 dm.col[1] = 3, 4 dm.col += 1 check_series(dm.col, [[2,3], [4,5]]) dm.col += 1, 2 check_series(dm.col, [[3,4], [6,7]]) dm.col -= 1 check_series(dm.col, [[2,3], [5,6]]) dm.col -= 1, 2 check_series(dm.col, [[1,2], [3,4]]) dm.col *= 2 check_series(dm.col, [[2,4], [6,8]]) dm.col *= 1.5, 3 check_series(dm.col, [[3,6], [18,24]]) dm.col /= 3 check_series(dm.col, [[1,2], [6,8]]) dm.col /= 1, 2 check_series(dm.col, [[1,2], [3,4]]) dm.col //= 1.5, 2.5 check_series(dm.col, [[0,1], [1,1]]) dm.col += np.array([ [0,0], [10, 10] ]) check_series(dm.col, [[0,1], [11,11]]) # Right-side operations dm.col[0] = 1, 2 dm.col[1] = 3, 4 dm.col = 1 + dm.col check_series(dm.col, [[2,3], [4,5]]) dm.col = (1, 2) + dm.col check_series(dm.col, [[3,4], [6,7]]) dm.col = 1 - dm.col check_series(dm.col, [[-2,-3], [-5,-6]]) dm.col = (1, 2) - dm.col check_series(dm.col, [[3, 4], [7, 8]]) dm.col = 2 * dm.col check_series(dm.col, [[6, 8], [14, 16]]) dm.col = (1.5, 3) * dm.col check_series(dm.col, [[9, 12], [42, 48]]) dm.col = 3 / dm.col check_series(dm.col, [[1./3, 1./4], [3./42, 1./16]]) dm.col = (1, 2) / dm.col check_series(dm.col, [[3, 4], [28, 32]]) dm.col = (1.5, 2.5) // dm.col check_series(dm.col, [[0, 0], [0, 0]]) dm.col = np.array([ [0, 0], [10, 10] ]) + dm.col check_series(dm.col, [[0, 0], [10, 10]])
def test_seriescolumn():
_test_copying(SeriesColumn(depth=1))
dm = DataMatrix(length=2)
dm.col = SeriesColumn(depth=3)
# Set all rows to a single value
dm.col = 1
check_series(dm.col, [[1, 1, 1], [1, 1, 1]])
# Set rows to different single values
dm.col = 2, 3
check_series(dm.col, [[2, 2, 2], [3, 3, 3]])
# Set one row to a single value
dm.col[0] = 4
check_series(dm.col, [[4, 4, 4], [3, 3, 3]])
# Set one row to different single values
dm.col[1] = 5, 6, 7
check_series(dm.col, [[4, 4, 4], [5, 6, 7]])
# Set all rows to different single values
dm.col.setallrows([8, 9, 10])
check_series(dm.col, [[8, 9, 10], [8, 9, 10]])
# Set the first value in all rows
dm.col[:, 0] = 1
check_series(dm.col, [[1, 9, 10], [1, 9, 10]])
# Set all values in the first row
dm.col[0, :] = 2
check_series(dm.col, [[2, 2, 2], [1, 9, 10]])
# Set all values
dm.col[:, :] = 3
check_series(dm.col, [[3, 3, 3], [3, 3, 3]])
# Test shortening and lengthening
dm.length = 0
check_series(dm.col, [])
dm.length = 3
dm.col = 1, 2, 3
dm.col.depth = 1
check_series(dm.col, [[1], [2], [3]])
dm.col.depth = 3
check_series(dm.col, [[1, NAN, NAN], [2, NAN, NAN], [3, NAN, NAN]])
check_integrity(dm)
# Test
dm = DataMatrix(length=2)
dm.col = SeriesColumn(depth=3)
dm.col = 1, 2
check_series(dm.col, [[1, 1, 1], [2, 2, 2]])
dm.col = 3, 4, 5
check_series(dm.col, [[3, 4, 5]] * 2)
dm.col.depth = 2
dm.col[:] = 1, 2
check_series(dm.col, [[1, 1], [2, 2]])
dm.col[:, :] = 3, 4
check_series(dm.col, [[3, 4], [3, 4]])
# Check if series return right type
dm = DataMatrix(length=4)
dm.col = SeriesColumn(depth=5)
dm.col = [[1, 2, 3, 4, 5], [6, 7, 8, 9, 10], [11, 12, 13, 14, 15],
[16, 17, 18, 19, 20]]
# (int, int) -> float
val = dm.col[2, 2]
eq_(val, 13)
eq_(type(val), float)
# (int) -> array
val = dm.col[2]
ok_(all(val == np.array([11, 12, 13, 14, 15])))
eq_(type(val), np.ndarray)
# (int, slice) -> array
val = dm.col[2, 1:-1]
ok_(all(val == np.array([12, 13, 14])))
eq_(type(val), np.ndarray)
# (int, (int, int)) -> array
val = dm.col[2, (1, 3)]
ok_(all(val == np.array([12, 14])))
eq_(type(val), np.ndarray)
# (slice) -> SeriesColumn
val = dm.col[1:-1]
check_series(val, [
[6, 7, 8, 9, 10],
[11, 12, 13, 14, 15],
])
# (slice, int) -> FloatColumn
val = dm.col[1:-1, 2]
ok_(isinstance(val, FloatColumn))
check_col(val, [8, 13])
# ((int, int), int) -> FloatColumn
val = dm.col[(1, 3), 2]
ok_(isinstance(val, FloatColumn))
check_col(val, [8, 18])
# (slice, slice) -> SeriesColumn
val = dm.col[1:-1, 1:-1]
ok_(isinstance(val, _SeriesColumn))
check_series(val, [
[7, 8, 9],
[12, 13, 14],
])
# ((int, int), slice) -> SeriesColumn
val = dm.col[(1, 3), 1:-1]
ok_(isinstance(val, _SeriesColumn))
check_series(val, [
[7, 8, 9],
[17, 18, 19],
])
# ((int, int), (int int)) -> SeriesColumn
val = dm.col[(1, 3), (1, 3)]
ok_(isinstance(val, _SeriesColumn))
check_series(val, [
[7, 9],
[17, 19],
])
def test_floatcolumn():
_test_numericcolumn(FloatColumn)
_test_copying(FloatColumn)
# Test automatic conversion to float
dm = DataMatrix(length=2)
dm.col = FloatColumn
dm.col = 1.9, '2.9'
check_col(dm.col, [1.9, 2.9])
# Test nans
dm.col = 'nan'
check_col(dm.col, [np.nan, np.nan])
dm.col = None
check_col(dm.col, [np.nan, np.nan])
dm.col = np.nan
check_col(dm.col, [np.nan, np.nan])
dm.col = 'x'
check_col(dm.col, [np.nan, np.nan])
# Test infs
dm.col = 'inf'
check_col(dm.col, [np.inf, np.inf])
dm.col = np.inf
check_col(dm.col, [np.inf, np.inf])
# Test nans and infs
dm.col = 'nan', 'inf'
check_col(dm.col, [np.nan, np.inf])
dm.col = np.inf, np.nan
check_col(dm.col, [np.inf, np.nan])
dm.col = 'x', None
check_col(dm.col, [np.nan, np.nan])
# Check dtype
ok_(dm.col._seq.dtype == np.float64)
check_integrity(dm)
def _test_numericcolumn(cls):
# Test init and change by single value
dm = DataMatrix(length=2)
dm.col = cls
dm.col = 1
check_col(dm.col, [1, 1])
dm.col = 2
check_col(dm.col, [2, 2])
# Test init and change by sequence
dm = DataMatrix(length=2)
dm.col = cls
dm.col = 1, 2
check_col(dm.col, [1, 2])
dm.col = 3, 4
check_col(dm.col, [3, 4])
# Test setting by slice
dm = DataMatrix(length=3)
dm.col = cls
dm.col = 1
dm.col[1:] = 2
check_col(dm.col, [1, 2, 2])
dm.col[:-1] = 4, 3
check_col(dm.col, [4, 3, 2])
# Test setting by DataMatrix
dm = DataMatrix(length=10)
dm.x = range(10)
dm.y = FloatColumn
dm = dm.x != {3, 6}
dm.y[dm.x > 3] = 10
dm.y[dm.x >= 8] = 11
check_col(dm.y, [np.nan] * 3 + [10] * 3 + [11] * 2)
# Test shortening and lengthening
dm = DataMatrix(length=4)
dm.length = 0
dm.length = 4
# Check uniqueness
dm.col = 1, 2, 1, 2
assert sorted(dm.col.unique) == [1,2]
dm.col[dm.col == 2] = 0, 0
check_col(dm.col, [1, 0, 1, 0])
check_integrity(dm)
# Check if numericcolumns return right type
dm = DataMatrix(length=5)
dm.col = cls
dm.col = 1, 2, 3, 4, 5
# int -> float
val = dm.col[2]
assert isinstance(val, (int, float))
assert val == 3
# (int, int) -> FloatColumn
val = dm.col[1, 3]
assert isinstance(val, cls)
check_col(val, [2, 4])
# slice -> FloatColumn
val = dm.col[1:-1]
assert isinstance(val, cls)
check_col(val, [2, 3, 4])
# Check array setting and getting
if cls != MixedColumn:
a = dm.col.array
assert isinstance(a, np.ndarray)
assert a.shape == (5,)
assert all(a == [1, 2, 3, 4, 5])
def test_where():
dm = DataMatrix(length=4)
dm.col = 1, 2, 3, 4
assert dm[dm.col == {2, 4}] == [1, 3]
