Python numpy.log1p方法代码示例

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def generate_data():

    generated = False

    def _generate_data():

        if not generated:
            assert N_CAT_FEATURE > 1
            assert N_NUM_FEATURE > 3
            np.random.seed(RANDOM_SEED)

            X_num = np.random.normal(size=(N_OBS, N_NUM_FEATURE))
            X_cat = np.random.randint(0, N_CATEGORY, size=(N_OBS, N_CAT_FEATURE))
            df = pd.DataFrame(
                np.hstack((X_num, X_cat)),
                columns=['num_{}'.format(x) for x in range(N_NUM_FEATURE)]
                + ['cat_{}'.format(x) for x in range(N_CAT_FEATURE)]
            )
            df[TARGET_COL] = (1 + X_num[:, 0] * X_num[:, 1] - np.log1p(np.exp(X_num[:, 1] + X_num[:, 2]))
                              + 10 * (X_cat[:, 0] == 0).astype(int)
                              + np.random.normal(scale=.01, size=N_OBS))

        return df

    yield _generate_data 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def load_names(data_names, norm=True, log1p=False, verbose=True):
    # Load datasets.
    datasets = []
    genes_list = []
    n_cells = 0
    for name in data_names:
        X_i, genes_i = load_data(name)
        if norm:
            X_i = normalize(X_i, axis=1)
        if log1p:
            X_i = np.log1p(X_i)
        X_i = csr_matrix(X_i)
            
        datasets.append(X_i)
        genes_list.append(genes_i)
        n_cells += X_i.shape[0]
        if verbose:
            print('Loaded {} with {} genes and {} cells'.
                  format(name, X_i.shape[1], X_i.shape[0]))
    if verbose:
        print('Found {} cells among all datasets'
              .format(n_cells))

    return datasets, genes_list, n_cells 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def log_loss_value(Z, weights, total_weights, rho):
    """
    computes the value and slope of the logistic loss in a numerically stable way
    supports sample non-negative weights for each example in the training data
    see http://stackoverflow.com/questions/20085768/

    Parameters
    ----------
    Z               numpy.array containing training data with shape = (n_rows, n_cols)
    rho             numpy.array of coefficients with shape = (n_cols,)
    total_weights   numpy.sum(total_weights) (only included to reduce computation)
    weights         numpy.array of sample weights with shape (n_rows,)

    Returns
    -------
    loss_value  scalar = 1/n_rows * sum(log( 1 .+ exp(-Z*rho))

    """
    scores = Z.dot(rho)
    pos_idx = scores > 0
    loss_value = np.empty_like(scores)
    loss_value[pos_idx] = np.log1p(np.exp(-scores[pos_idx]))
    loss_value[~pos_idx] = -scores[~pos_idx] + np.log1p(np.exp(scores[~pos_idx]))
    loss_value = loss_value.dot(weights) / total_weights
    return loss_value 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def log_loss_value(Z, rho):
    """
    computes the value and slope of the logistic loss in a numerically stable way
    see also: http://stackoverflow.com/questions/20085768/

    Parameters
    ----------
    Z           numpy.array containing training data with shape = (n_rows, n_cols)
    rho         numpy.array of coefficients with shape = (n_cols,)

    Returns
    -------
    loss_value  scalar = 1/n_rows * sum(log( 1 .+ exp(-Z*rho))

    """
    scores = Z.dot(rho)
    pos_idx = scores > 0
    loss_value = np.empty_like(scores)
    loss_value[pos_idx] = np.log1p(np.exp(-scores[pos_idx]))
    loss_value[~pos_idx] = -scores[~pos_idx] + np.log1p(np.exp(scores[~pos_idx]))
    loss_value = loss_value.mean()
    return loss_value 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def test_branch_cuts(self):
        # check branch cuts and continuity on them
        _check_branch_cut(np.log,   -0.5, 1j, 1, -1, True)
        _check_branch_cut(np.log2,  -0.5, 1j, 1, -1, True)
        _check_branch_cut(np.log10, -0.5, 1j, 1, -1, True)
        _check_branch_cut(np.log1p, -1.5, 1j, 1, -1, True)
        _check_branch_cut(np.sqrt,  -0.5, 1j, 1, -1, True)

        _check_branch_cut(np.arcsin, [ -2, 2],   [1j, 1j], 1, -1, True)
        _check_branch_cut(np.arccos, [ -2, 2],   [1j, 1j], 1, -1, True)
        _check_branch_cut(np.arctan, [0-2j, 2j],  [1,  1], -1, 1, True)

        _check_branch_cut(np.arcsinh, [0-2j,  2j], [1,   1], -1, 1, True)
        _check_branch_cut(np.arccosh, [ -1, 0.5], [1j,  1j], 1, -1, True)
        _check_branch_cut(np.arctanh, [ -2,   2], [1j, 1j], 1, -1, True)

        # check against bogus branch cuts: assert continuity between quadrants
        _check_branch_cut(np.arcsin, [0-2j, 2j], [ 1,  1], 1, 1)
        _check_branch_cut(np.arccos, [0-2j, 2j], [ 1,  1], 1, 1)
        _check_branch_cut(np.arctan, [ -2,  2], [1j, 1j], 1, 1)

        _check_branch_cut(np.arcsinh, [ -2,  2, 0], [1j, 1j, 1], 1, 1)
        _check_branch_cut(np.arccosh, [0-2j, 2j, 2], [1,  1,  1j], 1, 1)
        _check_branch_cut(np.arctanh, [0-2j, 2j, 0], [1,  1,  1j], 1, 1) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def test_branch_cuts_complex64(self):
        # check branch cuts and continuity on them
        _check_branch_cut(np.log,   -0.5, 1j, 1, -1, True, np.complex64)
        _check_branch_cut(np.log2,  -0.5, 1j, 1, -1, True, np.complex64)
        _check_branch_cut(np.log10, -0.5, 1j, 1, -1, True, np.complex64)
        _check_branch_cut(np.log1p, -1.5, 1j, 1, -1, True, np.complex64)
        _check_branch_cut(np.sqrt,  -0.5, 1j, 1, -1, True, np.complex64)

        _check_branch_cut(np.arcsin, [ -2, 2],   [1j, 1j], 1, -1, True, np.complex64)
        _check_branch_cut(np.arccos, [ -2, 2],   [1j, 1j], 1, -1, True, np.complex64)
        _check_branch_cut(np.arctan, [0-2j, 2j],  [1,  1], -1, 1, True, np.complex64)

        _check_branch_cut(np.arcsinh, [0-2j,  2j], [1,   1], -1, 1, True, np.complex64)
        _check_branch_cut(np.arccosh, [ -1, 0.5], [1j,  1j], 1, -1, True, np.complex64)
        _check_branch_cut(np.arctanh, [ -2,   2], [1j, 1j], 1, -1, True, np.complex64)

        # check against bogus branch cuts: assert continuity between quadrants
        _check_branch_cut(np.arcsin, [0-2j, 2j], [ 1,  1], 1, 1, False, np.complex64)
        _check_branch_cut(np.arccos, [0-2j, 2j], [ 1,  1], 1, 1, False, np.complex64)
        _check_branch_cut(np.arctan, [ -2,  2], [1j, 1j], 1, 1, False, np.complex64)

        _check_branch_cut(np.arcsinh, [ -2,  2, 0], [1j, 1j, 1], 1, 1, False, np.complex64)
        _check_branch_cut(np.arccosh, [0-2j, 2j, 2], [1,  1,  1j], 1, 1, False, np.complex64)
        _check_branch_cut(np.arctanh, [0-2j, 2j, 0], [1,  1,  1j], 1, 1, False, np.complex64) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def test_branch_cuts(self):
        # check branch cuts and continuity on them
        yield _check_branch_cut, np.log,   -0.5, 1j, 1, -1, True
        yield _check_branch_cut, np.log2,  -0.5, 1j, 1, -1, True
        yield _check_branch_cut, np.log10, -0.5, 1j, 1, -1, True
        yield _check_branch_cut, np.log1p, -1.5, 1j, 1, -1, True
        yield _check_branch_cut, np.sqrt,  -0.5, 1j, 1, -1, True

        yield _check_branch_cut, np.arcsin, [ -2, 2],   [1j, 1j], 1, -1, True
        yield _check_branch_cut, np.arccos, [ -2, 2],   [1j, 1j], 1, -1, True
        yield _check_branch_cut, np.arctan, [0-2j, 2j],  [1,  1], -1, 1, True

        yield _check_branch_cut, np.arcsinh, [0-2j,  2j], [1,   1], -1, 1, True
        yield _check_branch_cut, np.arccosh, [ -1, 0.5], [1j,  1j], 1, -1, True
        yield _check_branch_cut, np.arctanh, [ -2,   2], [1j, 1j], 1, -1, True

        # check against bogus branch cuts: assert continuity between quadrants
        yield _check_branch_cut, np.arcsin, [0-2j, 2j], [ 1,  1], 1, 1
        yield _check_branch_cut, np.arccos, [0-2j, 2j], [ 1,  1], 1, 1
        yield _check_branch_cut, np.arctan, [ -2,  2], [1j, 1j], 1, 1

        yield _check_branch_cut, np.arcsinh, [ -2,  2, 0], [1j, 1j, 1], 1, 1
        yield _check_branch_cut, np.arccosh, [0-2j, 2j, 2], [1,  1,  1j], 1, 1
        yield _check_branch_cut, np.arctanh, [0-2j, 2j, 0], [1,  1,  1j], 1, 1 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def test_branch_cuts_complex64(self):
        # check branch cuts and continuity on them
        yield _check_branch_cut, np.log,   -0.5, 1j, 1, -1, True, np.complex64
        yield _check_branch_cut, np.log2,  -0.5, 1j, 1, -1, True, np.complex64
        yield _check_branch_cut, np.log10, -0.5, 1j, 1, -1, True, np.complex64
        yield _check_branch_cut, np.log1p, -1.5, 1j, 1, -1, True, np.complex64
        yield _check_branch_cut, np.sqrt,  -0.5, 1j, 1, -1, True, np.complex64

        yield _check_branch_cut, np.arcsin, [ -2, 2],   [1j, 1j], 1, -1, True, np.complex64
        yield _check_branch_cut, np.arccos, [ -2, 2],   [1j, 1j], 1, -1, True, np.complex64
        yield _check_branch_cut, np.arctan, [0-2j, 2j],  [1,  1], -1, 1, True, np.complex64

        yield _check_branch_cut, np.arcsinh, [0-2j,  2j], [1,   1], -1, 1, True, np.complex64
        yield _check_branch_cut, np.arccosh, [ -1, 0.5], [1j,  1j], 1, -1, True, np.complex64
        yield _check_branch_cut, np.arctanh, [ -2,   2], [1j, 1j], 1, -1, True, np.complex64

        # check against bogus branch cuts: assert continuity between quadrants
        yield _check_branch_cut, np.arcsin, [0-2j, 2j], [ 1,  1], 1, 1, False, np.complex64
        yield _check_branch_cut, np.arccos, [0-2j, 2j], [ 1,  1], 1, 1, False, np.complex64
        yield _check_branch_cut, np.arctan, [ -2,  2], [1j, 1j], 1, 1, False, np.complex64

        yield _check_branch_cut, np.arcsinh, [ -2,  2, 0], [1j, 1j, 1], 1, 1, False, np.complex64
        yield _check_branch_cut, np.arccosh, [0-2j, 2j, 2], [1,  1,  1j], 1, 1, False, np.complex64
        yield _check_branch_cut, np.arctanh, [0-2j, 2j, 0], [1,  1,  1j], 1, 1, False, np.complex64 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def c_code(self, node, name, inp, out, sub):
        x, = inp
        z, = out
        # These constants were obtained by looking at the output of
        # python commands like:
        #  for i in xrange(750):
        #      print i, repr(numpy.log1p(numpy.exp(theano._asarray([i,-i], dtype=dt))))
        # the boundary checks prevent us from generating inf

        # float16 limits: -17.0, 6.0
        # We use the float32 limits for float16 for now as the
        # computation will happend in float32 anyway.
        if (node.inputs[0].type == scalar.float32 or
                node.inputs[0].type == scalar.float16):
            return """%(z)s = %(x)s < -103.0f ? 0.0 : %(x)s > 14.0f ? %(x)s : log1p(exp(%(x)s));""" % locals()
        elif node.inputs[0].type == scalar.float64:
            return """%(z)s = %(x)s < -745.0 ? 0.0 : %(x)s > 16.0 ? %(x)s : log1p(exp(%(x)s));""" % locals()
        else:
            raise NotImplementedError('only floatingpoint is implemented') 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def tf_log(dtm, log_fn=np.log1p):
    """
    Transform raw count document-term-matrix `dtm` to log-normalized term frequency matrix ``log_fn(dtm)``.

    :param dtm: (sparse) document-term-matrix of size NxM (N docs, M is vocab size) with raw term counts.
    :param log_fn: log function to use; default is NumPy's :func:`numpy.log1p`, which calculates ``log(1 + x)``
    :return: (sparse) log-normalized term frequency matrix of size NxM
    """
    if dtm.ndim != 2:
        raise ValueError('`dtm` must be a 2D array/matrix')

    if log_fn is np.log1p:
        if issparse(dtm):
            return dtm.log1p()
        else:
            return log_fn(dtm)
    else:
        if issparse(dtm):
            dtm = dtm.toarray()

        return log_fn(dtm) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def idf(dtm, smooth_log=1, smooth_df=1):
    """
    Calculate inverse document frequency (idf) vector from raw count document-term-matrix `dtm` with formula
    ``log(smooth_log + N / (smooth_df + df))``, where ``N`` is the number of documents, ``df`` is the document frequency
    (see function :func:`~tmtoolkit.bow.bow_stats.doc_frequencies`), `smooth_log` and `smooth_df` are smoothing
    constants. With default arguments, the formula is thus ``log(1 + N/(1+df))``.

    Note that this may introduce NaN values due to division by zero when a document is of length 0.

    :param dtm: (sparse) document-term-matrix of size NxM (N docs, M is vocab size) with raw term counts.
    :param smooth_log: smoothing constant inside log()
    :param smooth_df: smoothing constant to add to document frequency
    :return: NumPy array of size M (vocab size) with inverse document frequency for each term in the vocab
    """
    if dtm.ndim != 2 or 0 in dtm.shape:
        raise ValueError('`dtm` must be a non-empty 2D array/matrix')

    n_docs = dtm.shape[0]
    df = doc_frequencies(dtm)
    x = n_docs / (smooth_df + df)

    if smooth_log == 1:      # log1p is faster than the equivalent log(1 + x)
        return np.log1p(x)
    else:
        return np.log(smooth_log + x) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def idf_probabilistic(dtm, smooth=1):
    """
    Calculate probabilistic inverse document frequency (idf) vector from raw count document-term-matrix `dtm` with
    formula ``log(smooth + (N - df) / df)``, where ``N`` is the number of documents and ``df`` is the document
    frequency (see function :func:`~tmtoolkit.bow.bow_stats.doc_frequencies`).

    :param dtm: (sparse) document-term-matrix of size NxM (N docs, M is vocab size) with raw term counts.
    :param smooth: smoothing constant (setting this to 0 can lead to -inf results)
    :return: NumPy array of size M (vocab size) with probabilistic inverse document frequency for each term in the vocab
    """
    if dtm.ndim != 2 or 0 in dtm.shape:
        raise ValueError('`dtm` must be a non-empty 2D array/matrix')

    n_docs = dtm.shape[0]
    df = doc_frequencies(dtm)
    x = (n_docs - df) / df

    if smooth == 1:      # log1p is faster than the equivalent log(1 + x)
        return np.log1p(x)
    else:
        return np.log(smooth + x) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def bm25_weight(X, K1=100, B=0.8):
    """ Weighs each row of a sparse matrix X  by BM25 weighting """
    # calculate idf per term (user)
    X = coo_matrix(X)

    N = float(X.shape[0])
    idf = log(N) - log1p(bincount(X.col))

    # calculate length_norm per document (artist)
    row_sums = numpy.ravel(X.sum(axis=1))
    average_length = row_sums.mean()
    length_norm = (1.0 - B) + B * row_sums / average_length

    # weight matrix rows by bm25
    X.data = X.data * (K1 + 1.0) / (K1 * length_norm[X.row] + X.data) * idf[X.col]
    return X 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def mu_law_encode(audio):
    '''Quantizes waveform amplitudes.
    Mostly adaped from
    https://github.com/ibab/tensorflow-wavenet/blob/master/wavenet/ops.py#L64-L75

    Args:
      audio: Raw wave signal. float32.
    '''
    mu = float(hp.Q - 1)
    # Perform mu-law companding transformation (ITU-T, 1988).
    # Minimum operation is here to deal with rare large amplitudes caused
    # by resampling.
    magnitude = np.log1p(mu * np.abs(audio)) / np.log1p(mu)
    signal = np.sign(audio) * magnitude
    # Quantize signal to the specified number of levels.
    return ((signal + 1) / 2 * mu + 0.5).astype(np.int32) 

# 需要导入模块: import numpy [as 别名]
# 或者: from numpy import log1p [as 别名]
def test_branch_cuts(self):
        # check branch cuts and continuity on them
        yield _check_branch_cut, np.log,   -0.5, 1j, 1, -1
        yield _check_branch_cut, np.log2,  -0.5, 1j, 1, -1
        yield _check_branch_cut, np.log10, -0.5, 1j, 1, -1
        yield _check_branch_cut, np.log1p, -1.5, 1j, 1, -1
        yield _check_branch_cut, np.sqrt,  -0.5, 1j, 1, -1

        yield _check_branch_cut, np.arcsin, [ -2, 2],   [1j, -1j], 1, -1
        yield _check_branch_cut, np.arccos, [ -2, 2],   [1j, -1j], 1, -1
        yield _check_branch_cut, np.arctan, [-2j, 2j],  [1,  -1 ], -1, 1

        yield _check_branch_cut, np.arcsinh, [-2j,  2j], [-1,   1], -1, 1
        yield _check_branch_cut, np.arccosh, [ -1, 0.5], [1j,  1j], 1, -1
        yield _check_branch_cut, np.arctanh, [ -2,   2], [1j, -1j], 1, -1

        # check against bogus branch cuts: assert continuity between quadrants
        yield _check_branch_cut, np.arcsin, [-2j, 2j], [ 1,  1], 1, 1
        yield _check_branch_cut, np.arccos, [-2j, 2j], [ 1,  1], 1, 1
        yield _check_branch_cut, np.arctan, [ -2,  2], [1j, 1j], 1, 1

        yield _check_branch_cut, np.arcsinh, [ -2,  2, 0], [1j, 1j, 1 ], 1, 1
        yield _check_branch_cut, np.arccosh, [-2j, 2j, 2], [1,  1,  1j], 1, 1
        yield _check_branch_cut, np.arctanh, [-2j, 2j, 0], [1,  1,  1j], 1, 1