Python numpy.genfromtxt方法代码示例

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def load_results(file):
    if not os.path.exists(file):
        return None
    with open(file, 'r') as f:
        lines = [line for line in f]
    if len(lines) < 2:
        return None
    keys = [name.strip() for name in lines[0].split(',')]
    data = np.genfromtxt(file, delimiter=',', skip_header=1, filling_values=0.)
    if data.ndim == 1:
        data = data.reshape(1, -1)
    assert data.ndim == 2
    assert data.shape[-1] == len(keys)
    result = {}
    for idx, key in enumerate(keys):
        result[key] = data[:, idx]
    return result 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def read_data(labelsname, distancename):
    ## Extract labels
    rawlabels = np.genfromtxt(labelsname, delimiter=',', dtype=None)
    labelmap = {}
    row_len = 0
    for row in rawlabels:
        row_len = max(row_len, len(row)-1)
        name = row[0]
        labelmap[name] = list(row)[1:]

    ## Extract distances
    rawdistances = np.genfromtxt(distancename, delimiter=',', dtype=None)
    names = rawdistances[0][1:]
    distances = np.array(rawdistances[1:, 1:], dtype=float)
    labels = np.zeros((len(names), row_len))
    
    for i, name in enumerate(names):
        labels[i, 0:(len(row))] = labelmap[name]

    del labelmap
    return distances, labels, names 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def load_edges(fpath, delimiter=None, has_header=False):
    """Load edges in CSV format as numpy ndarray of strings.

    Args:
        fpath (str): edges file
        delimiter (str): alternative argument name for sep (default=None)
        has_header (bool): True if has header row

    Returns:
        np.ndarray: array of edges
    """
    if PANDAS_INSTALLED:
        header = 'infer' if has_header else None
        df = pd.read_csv(fpath, delimiter=delimiter, header=header)
        edges = df.values
    else:
        logger.warning("Pandas not installed. Using numpy to load csv, which "
                       "is slower.")
        header = 1 if has_header else 0
        edges = np.genfromtxt(fpath, delimiter=delimiter, skip_header=header,
                              dtype=object)
    return edges.astype('str') 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_skip_footer_with_invalid(self):
        with suppress_warnings() as sup:
            sup.filter(ConversionWarning)
            basestr = '1 1\n2 2\n3 3\n4 4\n5  \n6  \n7  \n'
            # Footer too small to get rid of all invalid values
            assert_raises(ValueError, np.genfromtxt,
                          TextIO(basestr), skip_footer=1)
    #        except ValueError:
    #            pass
            a = np.genfromtxt(
                TextIO(basestr), skip_footer=1, invalid_raise=False)
            assert_equal(a, np.array([[1., 1.], [2., 2.], [3., 3.], [4., 4.]]))
            #
            a = np.genfromtxt(TextIO(basestr), skip_footer=3)
            assert_equal(a, np.array([[1., 1.], [2., 2.], [3., 3.], [4., 4.]]))
            #
            basestr = '1 1\n2  \n3 3\n4 4\n5  \n6 6\n7 7\n'
            a = np.genfromtxt(
                TextIO(basestr), skip_footer=1, invalid_raise=False)
            assert_equal(a, np.array([[1., 1.], [3., 3.], [4., 4.], [6., 6.]]))
            a = np.genfromtxt(
                TextIO(basestr), skip_footer=3, invalid_raise=False)
            assert_equal(a, np.array([[1., 1.], [3., 3.], [4., 4.]])) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_dtype_with_object(self):
        # Test using an explicit dtype with an object
        data = """ 1; 2001-01-01
                   2; 2002-01-31 """
        ndtype = [('idx', int), ('code', object)]
        func = lambda s: strptime(s.strip(), "%Y-%m-%d")
        converters = {1: func}
        test = np.genfromtxt(TextIO(data), delimiter=";", dtype=ndtype,
                             converters=converters)
        control = np.array(
            [(1, datetime(2001, 1, 1)), (2, datetime(2002, 1, 31))],
            dtype=ndtype)
        assert_equal(test, control)

        ndtype = [('nest', [('idx', int), ('code', object)])]
        with assert_raises_regex(NotImplementedError,
                                 'Nested fields.* not supported.*'):
            test = np.genfromtxt(TextIO(data), delimiter=";",
                                 dtype=ndtype, converters=converters) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_replace_space(self):
        # Test the 'replace_space' option
        txt = "A.A, B (B), C:C\n1, 2, 3.14"
        # Test default: replace ' ' by '_' and delete non-alphanum chars
        test = np.genfromtxt(TextIO(txt),
                             delimiter=",", names=True, dtype=None)
        ctrl_dtype = [("AA", int), ("B_B", int), ("CC", float)]
        ctrl = np.array((1, 2, 3.14), dtype=ctrl_dtype)
        assert_equal(test, ctrl)
        # Test: no replace, no delete
        test = np.genfromtxt(TextIO(txt),
                             delimiter=",", names=True, dtype=None,
                             replace_space='', deletechars='')
        ctrl_dtype = [("A.A", int), ("B (B)", int), ("C:C", float)]
        ctrl = np.array((1, 2, 3.14), dtype=ctrl_dtype)
        assert_equal(test, ctrl)
        # Test: no delete (spaces are replaced by _)
        test = np.genfromtxt(TextIO(txt),
                             delimiter=",", names=True, dtype=None,
                             deletechars='')
        ctrl_dtype = [("A.A", int), ("B_(B)", int), ("C:C", float)]
        ctrl = np.array((1, 2, 3.14), dtype=ctrl_dtype)
        assert_equal(test, ctrl) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_replace_space_known_dtype(self):
        # Test the 'replace_space' (and related) options when dtype != None
        txt = "A.A, B (B), C:C\n1, 2, 3"
        # Test default: replace ' ' by '_' and delete non-alphanum chars
        test = np.genfromtxt(TextIO(txt),
                             delimiter=",", names=True, dtype=int)
        ctrl_dtype = [("AA", int), ("B_B", int), ("CC", int)]
        ctrl = np.array((1, 2, 3), dtype=ctrl_dtype)
        assert_equal(test, ctrl)
        # Test: no replace, no delete
        test = np.genfromtxt(TextIO(txt),
                             delimiter=",", names=True, dtype=int,
                             replace_space='', deletechars='')
        ctrl_dtype = [("A.A", int), ("B (B)", int), ("C:C", int)]
        ctrl = np.array((1, 2, 3), dtype=ctrl_dtype)
        assert_equal(test, ctrl)
        # Test: no delete (spaces are replaced by _)
        test = np.genfromtxt(TextIO(txt),
                             delimiter=",", names=True, dtype=int,
                             deletechars='')
        ctrl_dtype = [("A.A", int), ("B_(B)", int), ("C:C", int)]
        ctrl = np.array((1, 2, 3), dtype=ctrl_dtype)
        assert_equal(test, ctrl) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_names_with_usecols_bug1636(self):
        # Make sure we pick up the right names w/ usecols
        data = "A,B,C,D,E\n0,1,2,3,4\n0,1,2,3,4\n0,1,2,3,4"
        ctrl_names = ("A", "C", "E")
        test = np.genfromtxt(TextIO(data),
                             dtype=(int, int, int), delimiter=",",
                             usecols=(0, 2, 4), names=True)
        assert_equal(test.dtype.names, ctrl_names)
        #
        test = np.genfromtxt(TextIO(data),
                             dtype=(int, int, int), delimiter=",",
                             usecols=("A", "C", "E"), names=True)
        assert_equal(test.dtype.names, ctrl_names)
        #
        test = np.genfromtxt(TextIO(data),
                             dtype=int, delimiter=",",
                             usecols=("A", "C", "E"), names=True)
        assert_equal(test.dtype.names, ctrl_names) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_utf8_file(self):
        utf8 = b"\xcf\x96"
        with temppath() as path:
            with open(path, "wb") as f:
                f.write((b"test1,testNonethe" + utf8 + b",test3\n") * 2)
            test = np.genfromtxt(path, dtype=None, comments=None,
                                 delimiter=',', encoding="UTF-8")
            ctl = np.array([
                     ["test1", "testNonethe" + utf8.decode("UTF-8"), "test3"],
                     ["test1", "testNonethe" + utf8.decode("UTF-8"), "test3"]],
                     dtype=np.unicode)
            assert_array_equal(test, ctl)

            # test a mixed dtype
            with open(path, "wb") as f:
                f.write(b"0,testNonethe" + utf8)
            test = np.genfromtxt(path, dtype=None, comments=None,
                                 delimiter=',', encoding="UTF-8")
            assert_equal(test['f0'], 0)
            assert_equal(test['f1'], "testNonethe" + utf8.decode("UTF-8")) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def read_emission_spectra_text(filename):
    """
    Read text-formatted emission spectra.

    Parameters
    ----------
    filename : str
       The Tecan Infinite output filen to be read.

    Returns
    -------
    SRC_280 : numpy.array
    SRC_280_x : numpy.array
    SRC_280_x_num : numpy.array

    Examples
    --------

    """

    SRC_280 = np.genfromtxt(filename, dtype='str')
    SRC_280_x = SRC_280[0,:]
    SRC_280_x_num = re.findall(r'\d+', str(SRC_280_x )[1:-1])

    return [SRC_280, SRC_280_x, SRC_280_x_num] 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def crawl_folders(self, sequence_length):
        sequence_set = []
        demi_length = (sequence_length-1)//2
        shifts = list(range(-demi_length, demi_length + 1))
        shifts.pop(demi_length)
        for scene in self.scenes:
            intrinsics = np.genfromtxt(scene/'cam.txt').astype(np.float32).reshape((3, 3))
            imgs = sorted(scene.files('*.jpg'))
            if len(imgs) < sequence_length:
                continue
            for i in range(demi_length, len(imgs)-demi_length):
                sample = {'intrinsics': intrinsics, 'tgt': imgs[i], 'ref_imgs': []}
                for j in shifts:
                    sample['ref_imgs'].append(imgs[i+j])
                sequence_set.append(sample)
        random.shuffle(sequence_set)
        self.samples = sequence_set 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def read_scene_data(data_root, sequence_set, seq_length=3, step=1):
    data_root = Path(data_root)
    im_sequences = []
    poses_sequences = []
    indices_sequences = []
    demi_length = (seq_length - 1) // 2
    shift_range = np.array([step*i for i in range(-demi_length, demi_length + 1)]).reshape(1, -1)

    sequences = set()
    for seq in sequence_set:
        corresponding_dirs = set((data_root/'sequences').dirs(seq))
        sequences = sequences | corresponding_dirs

    print('getting test metadata for theses sequences : {}'.format(sequences))
    for sequence in tqdm(sequences):
        poses = np.genfromtxt(data_root/'poses'/'{}.txt'.format(sequence.name)).astype(np.float64).reshape(-1, 3, 4)
        imgs = sorted((sequence/'image_2').files('*.png'))
        # construct 5-snippet sequences
        tgt_indices = np.arange(demi_length, len(imgs) - demi_length).reshape(-1, 1)
        snippet_indices = shift_range + tgt_indices
        im_sequences.append(imgs)
        poses_sequences.append(poses)
        indices_sequences.append(snippet_indices)
    return im_sequences, poses_sequences, indices_sequences 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def get_displacements_from_speed(root, date, scene, indices, tgt_index):
    """get displacement magnitudes by integrating over speed values.
    Might be a good alternative if the GPS is not good enough"""
    if len(indices) == 0:
        return []
    oxts_root = root/date/scene/'oxts'
    with open(oxts_root/'timestamps.txt') as f:
        timestamps = np.array([datetime.datetime.strptime(ts[:-3], "%Y-%m-%d %H:%M:%S.%f").timestamp() for ts in f.read().splitlines()])
    speeds = np.zeros((len(indices), 3))
    for i, index in enumerate(indices):
        oxts_data = np.genfromtxt(oxts_root/'data'/'{:010d}.txt'.format(index))
        speeds[i] = oxts_data[[6,7,10]]
    displacements = np.zeros((len(indices), 3))
    # Perform the integration operation, using trapezoidal method
    for i0, (i1, i2) in enumerate(zip(indices, indices[1:])):
        displacements[i0 + 1] = displacements[i0] + 0.5*(speeds[i0] + speeds[i0 + 1]) * (timestamps[i1] - timestamps[i2])
    # Set the origin of displacements at tgt_index
    displacements -= displacements[tgt_index]
    # Finally, get the displacement magnitude relative to tgt and discard the middle value (which is supposed to be 0)
    displacements_mag = np.linalg.norm(displacements, axis=1)
    return np.concatenate([displacements_mag[:tgt_index], displacements_mag[tgt_index + 1:]]) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_commented_header(self):
        # Check that names can be retrieved even if the line is commented out.
        data = TextIO("""
#gender age weight
M   21  72.100000
F   35  58.330000
M   33  21.99
        """)
        # The # is part of the first name and should be deleted automatically.
        test = np.genfromtxt(data, names=True, dtype=None)
        ctrl = np.array([('M', 21, 72.1), ('F', 35, 58.33), ('M', 33, 21.99)],
                        dtype=[('gender', '|S1'), ('age', int), ('weight', float)])
        assert_equal(test, ctrl)
        # Ditto, but we should get rid of the first element
        data = TextIO(b"""
# gender age weight
M   21  72.100000
F   35  58.330000
M   33  21.99
        """)
        test = np.genfromtxt(data, names=True, dtype=None)
        assert_equal(test, ctrl) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import genfromtxt [as 别名]
def test_dtype_with_object(self):
        # Test using an explicit dtype with an object
        data = """ 1; 2001-01-01
                   2; 2002-01-31 """
        ndtype = [('idx', int), ('code', np.object)]
        func = lambda s: strptime(s.strip(), "%Y-%m-%d")
        converters = {1: func}
        test = np.genfromtxt(TextIO(data), delimiter=";", dtype=ndtype,
                             converters=converters)
        control = np.array(
            [(1, datetime(2001, 1, 1)), (2, datetime(2002, 1, 31))],
            dtype=ndtype)
        assert_equal(test, control)

        ndtype = [('nest', [('idx', int), ('code', np.object)])]
        try:
            test = np.genfromtxt(TextIO(data), delimiter=";",
                                 dtype=ndtype, converters=converters)
        except NotImplementedError:
            pass
        else:
            errmsg = "Nested dtype involving objects should be supported."
            raise AssertionError(errmsg)