python类chararray()的实例源码

def setUp(self):
        TestComparisons.setUp(self)
        self.B = np.array([['efg', '123  '],
                           ['051', 'tuv']], np.unicode_).view(np.chararray)

def setUp(self):
        self.A = np.array([[' abc ', ''],
                           ['12345', 'MixedCase'],
                           ['123 \t 345 \0 ', 'UPPER']]).view(np.chararray)
        self.B = np.array([[sixu(' \u03a3 '), sixu('')],
                           [sixu('12345'), sixu('MixedCase')],
                           [sixu('123 \t 345 \0 '), sixu('UPPER')]]).view(np.chararray)

def setUp(self):
        self.A = np.array([[' abc ', ''],
                           ['12345', 'MixedCase'],
                           ['123 \t 345 \0 ', 'UPPER']],
                          dtype='S').view(np.chararray)
        self.B = np.array([[sixu(' \u03a3 '), sixu('')],
                           [sixu('12345'), sixu('MixedCase')],
                           [sixu('123 \t 345 \0 '), sixu('UPPER')]]).view(np.chararray)

def setUp(self):
        self.A = np.array([['abc', '123'],
                           ['789', 'xyz']]).view(np.chararray)
        self.B = np.array([['efg', '456'],
                           ['051', 'tuv']]).view(np.chararray)

def test_add(self):
        AB = np.array([['abcefg', '123456'],
                       ['789051', 'xyztuv']]).view(np.chararray)
        assert_array_equal(AB, (self.A + self.B))
        assert_(len((self.A + self.B)[0][0]) == 6)

def test_radd(self):
        QA = np.array([['qabc', 'q123'],
                       ['q789', 'qxyz']]).view(np.chararray)
        assert_array_equal(QA, ('q' + self.A))

def test_rmul(self):
        A = self.A
        for r in (2, 3, 5, 7, 197):
            Ar = np.array([[A[0, 0]*r, A[0, 1]*r],
                           [A[1, 0]*r, A[1, 1]*r]]).view(np.chararray)
            assert_array_equal(Ar, (r * self.A))

        for ob in [object(), 'qrs']:
            try:
                ob * A
            except ValueError:
                pass
            else:
                self.fail("chararray can only be multiplied by integers")

def test_mod(self):
        """Ticket #856"""
        F = np.array([['%d', '%f'], ['%s', '%r']]).view(np.chararray)
        C = np.array([[3, 7], [19, 1]])
        FC = np.array([['3', '7.000000'],
                       ['19', '1']]).view(np.chararray)
        assert_array_equal(FC, F % C)

        A = np.array([['%.3f', '%d'], ['%s', '%r']]).view(np.chararray)
        A1 = np.array([['1.000', '1'], ['1', '1']]).view(np.chararray)
        assert_array_equal(A1, (A % 1))

        A2 = np.array([['1.000', '2'], ['3', '4']]).view(np.chararray)
        assert_array_equal(A2, (A % [[1, 2], [3, 4]]))

def test_rmod(self):
        assert_(("%s" % self.A) == str(self.A))
        assert_(("%r" % self.A) == repr(self.A))

        for ob in [42, object()]:
            try:
                ob % self.A
            except TypeError:
                pass
            else:
                self.fail("chararray __rmod__ should fail with "
                          "non-string objects")

def test_empty_indexing():
    """Regression test for ticket 1948."""
    # Check that indexing a chararray with an empty list/array returns an
    # empty chararray instead of a chararray with a single empty string in it.
    s = np.chararray((4,))
    assert_(s[[]].size == 0)

def __init__(self, filename):
        self.filename = filename
        self.xyzfile = open(self.filename, 'r')
        self.offsets = []
        self.n_atoms = self._n_atoms()
        self.n_frames = self._n_frames()
        self.box_size = np.empty([self.n_frames, 3], dtype=np.float)
        self.atom_names = np.chararray([self.n_frames, self.n_atoms, 1], itemsize=3)
        self.coords = np.empty([self.n_frames, self.n_atoms, 3], dtype=np.float)
        self.read_all_frames()

def echantillonnage (fichier):

    data = np.genfromtxt(fichier,delimiter=',')

    clen, rlen = data.shape   
    new_tab=np.chararray([clen,rlen],itemsize=25)

    for c in range(0,rlen):
        petit=str(c)+'_1'
        moyen=str(c)+'_2'
        grand=str(c)+'_3'

        #----------------- sur le rang --------------------------
        data_sort=np.sort(data[:,c])
        x=len(data_sort)/3.
        tiers=data_sort[int(x)]
        deux_tiers=data_sort[2*int(x)]   
        #-----------------------------------------------------------        


        for l in range(0,clen):
            if data[l,c]<tiers:
                new_tab[l,c]=petit

            elif data[l,c]<deux_tiers:
                new_tab[l,c]=moyen
            else :
                new_tab[l,c]=grand

    return new_tab

def echantillonnage_glucose (fichier):

    data = np.genfromtxt(fichier,delimiter=',')  
    clen, rlen = data.shape   
    rlen=rlen+1
    diab= np.genfromtxt('glucose_a_traiter.csv',delimiter=',')
    new_tab=np.chararray([clen,rlen],itemsize=25)

    for c in range(0,rlen-1):
        petit=str(c)+'_1'
        moyen=str(c)+'_2'
        grand=str(c)+'_3'

        #----------------- sur le rang --------------------------
        data_sort=np.sort(data[:,c])
        x=len(data_sort)/3.
        tiers=data_sort[int(x)]
        deux_tiers=data_sort[2*int(x)]   
        #-----------------------------------------------------------        


        for l in range(0,clen):
            if data[l,c]<tiers:
                new_tab[l,c]=petit

            elif data[l,c]<deux_tiers:
                new_tab[l,c]=moyen
            else :
                new_tab[l,c]=grand

    for l in range (0,clen):        
        if diab[0,l]<6.5:            
            if diab[1,l]==0 and diab[2,l]==0 :
                new_tab[l,-1]=petit               
            else : 
                new_tab[l,-1]=moyen            
        else : new_tab[l,-1]=grand      

    return new_tab

def fill_matrix(matrix, width, value='n/a'):
    if matrix.shape[0] < width:
        nraters = matrix.shape[1]
        nas = np.chararray((1, nraters), itemsize=len(value))
        nas[:] = value
        matrix = np.vstack(tuple([matrix] + [nas] * (width - matrix.shape[0])))
    return matrix

def one_hot_encoding_sequences(seqs):
    CHARS = 'acgt'
    CHARS_COUNT = len(CHARS)

    maxlen = max(map(len, seqs))
    res = numpy.zeros((len(seqs), CHARS_COUNT * maxlen), dtype=numpy.uint8)

    for si, seq in enumerate(seqs):
        seqlen = len(seq)
        arr = numpy.chararray((seqlen,), buffer=seq)
        for ii, char in enumerate(CHARS):
            res[si][ii*seqlen:(ii+1)*seqlen][arr == char] = 1

    return res

def one_hot_encoding_sequences(seqs, sequenceLength):
    """
    input: genome sequences
    output: one_hot encoded sequence array
    """

    le = preprocessing.LabelEncoder()

    one_hot_sequences = []

    le.fit_transform(['a','t','g','c'])
    for si, seq in enumerate(seqs):
        seqlen = len(seq)
        arr = np.chararray((seqlen,), buffer=seq)
        a = le.transform(arr)

        a = np.array(a)

        b = np.zeros((len(a), 4))
        b[np.arange(len(a)), a] = 1

        #b = np.array(b)
        b = b.transpose()

        if b.shape[1] == sequenceLength:
            one_hot_sequences.append(b)

    return one_hot_sequences

#print one_hot_encoding_sequences(['atgctgc','gctatgc'])

#print numpy.arange(8).reshape((4,8/4), order = 'F')

def write_kmers(kmers, filename):
    char_kmers = np.chararray(kmers.shape)
    for _char, _int in six.iteritems(ALPHABET):
        char_kmers[kmers == _int] = _char

    with open(filename, 'w') as fh:
        for i, kmer in enumerate(char_kmers):
            print('>%d' % i, file=fh)
            print(kmer.tostring().decode(), file=fh)

def test_chararray_rstrip(self,level=rlevel):
        # Ticket #222
        x = np.chararray((1,), 5)
        x[0] = asbytes('a   ')
        x = x.rstrip()
        assert_equal(x[0], asbytes('a'))

def setUp(self):
        self.A = np.array([['abc ', '123  '],
                           ['789 ', 'xyz ']]).view(np.chararray)
        self.B = np.array([['abc', '123'],
                           ['789', 'xyz']]).view(np.chararray)

def setUp(self):
        self.A = np.array('abc1', dtype='c').view(np.chararray)