Python numpy.nan_to_num() Examples

def observe(self) -> np.array:
        """Returns the rows to be observed by the agent."""
        rows = self.rows.copy()

        if len(rows) < self.window_size:
            size = self.window_size - len(rows)
            padding = np.zeros((size, rows.shape[1]))
            padding = pd.DataFrame(padding, columns=self.rows.columns)
            rows = pd.concat([padding, rows], ignore_index=True, sort=False)

        if isinstance(rows, pd.DataFrame):
            rows = rows.fillna(0, axis=1)
            rows = rows.values

        rows = np.nan_to_num(rows)

        return rows 

def tfIdf(dtm):
  nDoc = dtm.shape[0]
  nTerm = dtm.shape[1]
  dtmNorm = dtm/dtm.sum(axis=1, keepdims=True) # Normalize tf to unit weight, tf/line word count
  dtmNorm = np.nan_to_num(dtmNorm)
  tfIdfMat = np.zeros((nDoc,nTerm))
  
  for j in range(nTerm):
    tfVect = dtmNorm[:, j]
    nExist = np.sum(tfVect > 0.0) # if tfVect is 0.0, word is not in current doc
    idf = 0.0
    # int32
    if (nExist > 0):
      idf = np.log(nDoc/nExist)/np.log(2) # log2()
    else:
      idf = 0.0
    tfIdfMat[:,j] = tfVect * idf
  
  return tfIdfMat 

def pagerank(nDim, adjMat, d, K):
    '''
    Args:
    d: damping factor, 
    K: iteration Number
    '''
    P = np.ones((nDim, 1)) * (1/nDim)
    
    # normalize adjacency Matrix
    B = adjMat/adjMat.sum(axis=1, keepdims=True)
    B = np.nan_to_num(B)
    
    U = np.ones((nDim, nDim)) * (1/nDim)
    
    M = d * B + (1-d) * U
    
    for i in range(K):
        P = np.dot(M.T, P)
    score = P.tolist()
    return P 

def lf_overlaps(L, normalize_by_coverage=False):
    """Return the **fraction of items each LF labels that are also labeled by at
     least one other LF.**

    Note that the maximum possible overlap fraction for an LF is the LF's
    coverage, unless `normalize_by_coverage=True`, in which case it is 1.

    Args:
        L: an n x m scipy.sparse matrix where L_{i,j} is the label given by the
            jth LF to the ith candidate
        normalize_by_coverage: Normalize by coverage of the LF, so that it
            returns the percent of LF labels that have overlaps.
    """
    overlaps = (L != 0).T @ _overlapped_data_points(L) / L.shape[0]
    if normalize_by_coverage:
        overlaps /= lf_coverages(L)
    return np.nan_to_num(overlaps) 

def lf_conflicts(L, normalize_by_overlaps=False):
    """Return the **fraction of items each LF labels that are also given a
    different (non-abstain) label by at least one other LF.**

    Note that the maximum possible conflict fraction for an LF is the LF's
        overlaps fraction, unless `normalize_by_overlaps=True`, in which case it
        is 1.

    Args:
        L: an n x m scipy.sparse matrix where L_{i,j} is the label given by the
            jth LF to the ith candidate
        normalize_by_overlaps: Normalize by overlaps of the LF, so that it
            returns the percent of LF overlaps that have conflicts.
    """
    conflicts = (L != 0).T @ _conflicted_data_points(L) / L.shape[0]
    if normalize_by_overlaps:
        conflicts /= lf_overlaps(L)
    return np.nan_to_num(conflicts) 

def __init__(self, data, hpc_p, costs):
        self.data_x = data.iloc[:, 0:-1].astype('float32').values
        self.data_n = np.isnan(self.data_x)
        self.data_x = np.nan_to_num(self.data_x)

        self.data_y = data.iloc[:,   -1].astype('int32').values

        self.data_len = len(data)

        self.hpc_p = hpc_p.values
        self.costs = costs.values

        self.mask = np.zeros( (config.AGENTS, config.FEATURE_DIM), dtype=np.float32 )
        self.x    = np.zeros( (config.AGENTS, config.FEATURE_DIM), dtype=np.float32 )
        self.y    = np.zeros( config.AGENTS, dtype=np.int64 )
        self.p    = np.zeros( config.AGENTS, dtype=np.int32 )
        self.n    = np.zeros( (config.AGENTS, config.FEATURE_DIM), dtype=np.bool ) 

def nan_dot(A, B):
    """
    Returns np.dot(left_matrix, right_matrix) with the convention that
    nan * 0 = 0 and nan * x = nan if x != 0.

    Parameters
    ----------
    A, B : np.ndarrays
    """
    # Find out who should be nan due to nan * nonzero
    should_be_nan_1 = np.dot(np.isnan(A), (B != 0))
    should_be_nan_2 = np.dot((A != 0), np.isnan(B))
    should_be_nan = should_be_nan_1 + should_be_nan_2

    # Multiply after setting all nan to 0
    # This is what happens if there were no nan * nonzero conflicts
    C = np.dot(np.nan_to_num(A), np.nan_to_num(B))

    C[should_be_nan] = np.nan

    return C 

def _average_precision(self, rec, prec):
        """
        calculate average precision, override the default one,
        special 11-point metric

        Params:
        ----------
        rec : numpy.array
            cumulated recall
        prec : numpy.array
            cumulated precision
        Returns:
        ----------
        ap as float
        """
        if rec is None or prec is None:
            return np.nan
        ap = 0.
        for t in np.arange(0., 1.1, 0.1):
            if np.sum(rec >= t) == 0:
                p = 0
            else:
                p = np.max(np.nan_to_num(prec)[rec >= t])
            ap += p / 11.
        return ap 

def Transform(self, data_container, store_folder='', store_key=''):
        if data_container.IsEmpty():
            return data_container

        new_data_container = deepcopy(data_container)
        array = new_data_container.GetArray()
        array -= self._interception
        array /= self._slop
        array = np.nan_to_num(array)

        new_data_container.SetArray(array)
        new_data_container.UpdateFrameByData()

        if store_folder:
            assert(len(store_key) > 0)
            self.SaveNormalDataContainer(data_container, store_folder, store_key)

        return new_data_container 

def macro_accuracy(P, Y, n_classes, bg_class=None, return_all=False, **kwargs):
    def macro_(P, Y, n_classes=None, bg_class=None, return_all=False):
        conf_matrix = sm.confusion_matrix(Y, P, labels=np.arange(n_classes))
        conf_matrix = conf_matrix / (conf_matrix.sum(0)[:, None] + 1e-5)
        conf_matrix = np.nan_to_num(conf_matrix)
        diag = conf_matrix.diagonal() * 100.

        # Remove background score
        if bg_class is not None:
            diag = np.array([diag[i] for i in range(n_classes) if i != bg_class])

        macro = diag.mean()
        if return_all:
            return macro, diag
        else:
            return macro

    if type(P) == list:
        out = [macro_(P[i], Y[i], n_classes=n_classes, bg_class=bg_class, return_all=return_all) for i in range(len(P))]
        if return_all:
            return (np.mean([o[0] for o in out]), np.mean([o[1] for o in out], 0))
        else:
            return np.mean(out)
    else:
        return macro_(P, Y, n_classes=n_classes, bg_class=bg_class, return_all=return_all) 

def rotate_around_axis(coords, Q, origin='empty'):
    '''Uses standard quaternion to rotate a vector. Q requires
    a 4-dimensional vector. coords is the 3d location of the point.
    coords can also be an N x 3 array of vectors. Happens to work
    with Q as a tuple or a np array shape 4'''
    if origin == 'empty':    
        vcV = np.cross(Q[1:], coords)
        RV = np.nan_to_num(coords + vcV * (2*Q[0]) + np.cross(Q[1:],vcV)*2)
    else:
        coords -= origin
        vcV = np.cross(Q[1:],coords)
        RV = (np.nan_to_num(coords + vcV * (2*Q[0]) + np.cross(Q[1:],vcV)*2)) + origin       
        coords += origin #undo in-place offset
    return RV 

def barycentric_generate(hits, tris):
    '''Create scalars to be used by points and triangles'''
    # where the hit lands on the two tri vecs
    tv = tris[:, 1] - tris[:, 0]
    hv = hits - tris[:, 0]
    d1a = np.einsum('ij, ij->i', hv, tv)
    d1b = np.einsum('ij, ij->i', tv, tv)
    scalar1 = np.nan_to_num(d1a / d1b)

    t2v = tris[:, 2] - tris[:, 0]
    d2a = np.einsum('ij, ij->i', hv, t2v)
    d2b = np.einsum('ij, ij->i', t2v, t2v)
    scalar2 = np.nan_to_num(d2a / d2b)
    
    # closest point on edge segment between the two points created above
    cp1 = tv * np.expand_dims(scalar1, axis=1)
    cp2 = t2v * np.expand_dims(scalar2, axis=1)
    cpvec = cp2 - cp1
    cp1_at = tris[:,0] + cp1
    hcp = hits - cp1_at # this is cp3 above. Not sure what's it's for yet
    dhcp = np.einsum('ij, ij->i', hcp, cpvec)
    d3b = np.einsum('ij, ij->i', cpvec, cpvec)
    hcp_scalar = np.nan_to_num(dhcp / d3b)
    hcp_vec = cpvec * np.expand_dims(hcp_scalar, axis=1)    
    
    # base of tri on edge between first two points
    d3 = np.einsum('ij, ij->i', -cp1, cpvec)
    scalar3 = np.nan_to_num(d3 / d3b)
    base_cp_vec = cpvec * np.expand_dims(scalar3, axis=1)
    base_on_span = cp1_at + base_cp_vec

    # Where the point occurs on the edge between the base of the triangle
    #   and the cpoe of the base of the triangle on the cpvec    
    base_vec = base_on_span - tris[:,0]
    dba = np.einsum('ij, ij->i', hv, base_vec)
    dbb = np.einsum('ij, ij->i', base_vec, base_vec)
    scalar_final = np.nan_to_num(dba / dbb)
    p_on_bv = base_vec * np.expand_dims(scalar_final, axis=1)
    perp = (p_on_bv) - (cp1 + base_cp_vec)
    return scalar1, scalar2, hcp_scalar, scalar3, scalar_final 

def project_points(points, tri_coords):
    '''Using this to get the points off the surface
    Takes the average length of two vecs off triangles
    and applies it to the length of the normals.
    This way the normal scales with the mesh and with
    changes to the individual triangle vectors'''
    t0 = tri_coords[:, 0]
    t1 = tri_coords[:, 1]
    t2 = tri_coords[:, 2]
    tv1 = t1 - t0
    tv2 = t2 - t0
    cross = np.cross(tv1, tv2)
    
    # get the average length of the two vectors and apply it to the cross product
    sq = np.sqrt(np.einsum('ij,ij->i', cross, cross))
    x1 = np.einsum('ij,ij->i', tv1, tv1)
    x2 = np.einsum('ij,ij->i', tv2, tv2)
    av_root = np.sqrt((x1 + x2) / 2)
    cr_root = (cross / np.expand_dims(sq, axis=1)) * np.expand_dims(av_root, axis=1)    
     
    v1 = points - t0
    v1_dots = np.einsum('ij,ij->i', cr_root, v1)
    n_dots = np.einsum('ij,ij->i', cr_root, cr_root)
    scale = np.nan_to_num(v1_dots / n_dots)
    offset = cr_root * np.expand_dims(scale, axis=1)
    drop = points - offset # The drop is used by the barycentric generator as points in the triangles
    return drop, scale 

def decayCoefObjectiveFn(x, Y, EX2):
	"""
	Computes the objective function for terms involving lambda in the M-step.
	Checked.
	Input:
	x: value of lambda
	Y: the matrix of observed values
	EX2: the matrix of values of EX2 estimated in the E-step.
	Returns:
	obj: value of objective function
	grad: gradient
	"""
	with warnings.catch_warnings():
		warnings.simplefilter("ignore")

		y_squared = Y ** 2
		Y_is_zero = np.abs(Y) < 1e-6
		exp_Y_squared = np.exp(-x * y_squared)
		log_exp_Y = np.nan_to_num(np.log(1 - exp_Y_squared))
		exp_ratio = np.nan_to_num(exp_Y_squared / (1 - exp_Y_squared))
		obj = sum(sum(Y_is_zero * (-EX2 * x) + (1 - Y_is_zero) * log_exp_Y))
		grad = sum(sum(Y_is_zero * (-EX2) + (1 - Y_is_zero) * y_squared * exp_ratio))

		if (type(obj) is not np.float64) or (type(grad) is not np.float64):
			raise Exception("Unexpected behavior in optimizing decay coefficient lambda. Please contact emmap1@cs.stanford.edu.")
		if type(obj) is np.float64:
			obj = -np.array([obj])
		if type(grad) is np.float64:
			grad = -np.array([grad])

		return obj, grad 

def forward(y_hat, y):
        y_hat = _cutoff(y_hat)
        y = _cutoff(y)
        return -np.mean(np.sum(np.nan_to_num(y * np.log(y_hat) + (1 - y) * np.log(1 - y_hat)), axis=1)) 

def forward(y_hat, y):
        assert (np.abs(np.sum(y_hat, axis=1) - 1.) < cutoff).all()
        assert (np.abs(np.sum(y, axis=1) - 1.) < cutoff).all()
        y_hat = _cutoff(y_hat)
        y = _cutoff(y)
        return -np.mean(np.sum(np.nan_to_num(y * np.log(y_hat)), axis=1)) 

def forward(y_hat, y):
        assert (np.abs(np.sum(y_hat, axis=1) - 1.) < cutoff).all()
        assert (np.abs(np.sum(y, axis=1) - 1.) < cutoff).all()
        y_hat = _cutoff(y_hat)
        y = _cutoff(y)
        return -np.mean(np.sum(np.nan_to_num(y * np.power((1 - y_hat), gama) * np.log(y_hat)), axis=1)) 

def compute_importance(pi, mu, x):
    return np.nan_to_num(float(pi.prob(x).array) / float(mu.prob(x).array)) 

def compute_full_importance(pi, mu):
    pimu = pi.all_prob.array / mu.all_prob.array
    # NaN occurs when inf/inf or 0/0
    pimu[np.isnan(pimu)] = 1
    pimu = np.nan_to_num(pimu)
    return pimu 

def get_threshold(model_id):
    trained_models = pd.read_csv(common.DEFAULT_TRAINED_MODELS_FILE, sep='\t')
    model_config = trained_models[trained_models["model_id"] == model_id]
    if model_config.empty:
        raise ValueError("Can't find the model %s in %s" %
                         (model_id, common.DEFAULT_TRAINED_MODELS_FILE))
    model_config = model_config.to_dict(orient="list")
    model_settings=eval(model_config['dataset_settings'][0])

    Y_test = np.load(common.DATASETS_DIR+'/item_factors_test_%s_%s_%s.npy' % (model_settings['fact'],model_settings['dim'],model_settings['dataset']))
    Y_pred = np.load(common.FACTORS_DIR+'/factors_%s.npy' % model_id)

    good_scores = Y_pred[Y_test==1]
    th = good_scores.mean()
    std = good_scores.std()
    print 'Mean th',th
    print 'Std',std

    p, r, thresholds = precision_recall_curve(Y_test.flatten(), Y_pred.flatten())
    f = np.nan_to_num((2 * (p*r) / (p+r)) * (p>r))
    print f
    max_f = np.argmax(f)
    fth = thresholds[max_f]
    print f[max_f],p[max_f],r[max_f]
    print 'F th %.2f' % fth
    plt.plot(r, p, 
             label='Precision-recall curve of class {0}')

    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('Recall')
    plt.ylabel('Precision')
    plt.title('Extension of Precision-Recall curve to multi-class')
    plt.savefig("pr_curve.png") 

def gaussian_curvature(self):
        ''' Calculates the Gaussian curvature at each node

        Returns
        ---------
        nd: NodeData
            NodeData structure with gaussian curvature for each surface node


        Rerefereces
        -------------
        https://computergraphics.stackexchange.com/a/1721
        '''
        nodes_areas = self.nodes_areas()[:]
        triangles_angles = np.deg2rad(
            np.nan_to_num(self.triangle_angles()[self.elm.triangles])
        )
        triangle_nodes = self.elm[self.elm.triangles] - 1
        triangle_nodes = triangle_nodes[:, :3]
        node_angles = np.bincount(
            triangle_nodes.reshape(-1),
            triangles_angles.reshape(-1), self.nodes.nr
        )
        nodes_areas[nodes_areas == 0] = .1
        gaussian_curvature = (2*np.pi - node_angles)/nodes_areas
        return NodeData(gaussian_curvature, 'gaussian_curvature') 

def _assert_allclose(a, b, tol=1e-5):
  if isinstance(a, (tuple, list)) and isinstance(b, (tuple, list)):
    for ia, ib in zip(a, b):
      _assert_allclose(ia, ib, tol)
  else:
    try:
      a = np.nan_to_num(a)
      b = np.nan_to_num(b)
      assert np.allclose(a, b, tol), ('Expected: %s\nGot: %s' % (b, a))
    except TypeError:
      raise TypeError('Could not compare values %s and %s' % (a, b)) 

def partial_transform(self, traj, shuffle=0, verbose=False):
        """Transform a single mdtraj.Trajectory into an array of metric scores.

        Parameters
        ----------
        traj : mdtraj.Trajectory
            Trajectory to transform
        shuffle : int
            Number of shuffle iterations (default: 0)
        verbose : bool
            Whether to display performance

        Returns
        -------
        result : np.ndarray
            Scoring matrix
        """
        self._before_exec(traj)
        result = self._floored_exec()
        correction = np.zeros_like(result)
        for i in range(shuffle):
            with Timing(i, verbose=verbose):
                self._shuffle()
                correction += self._floored_exec()

        return floor_threshold(result - np.nan_to_num(correction / shuffle)) 

def getLap(self):
        degree_mat = np.diagflat(np.sum(self.adj_mat, axis=1))
        deg_trans = np.diagflat(np.reciprocal(np.sqrt(np.sum(self.adj_mat, axis=1))))
        deg_trans = np.nan_to_num(deg_trans)
        L = degree_mat-self.adj_mat

        # eye = np.eye(self.node_size)
        norm_lap_mat = np.matmul(np.matmul(deg_trans, L), deg_trans)
        return norm_lap_mat 

def test_vec2ang(vectors, lonlat, ndim):
    vectors = np.broadcast_to(vectors, (2,) * ndim + (3,))
    theta1, phi1 = hp_compat.vec2ang(vectors, lonlat=lonlat)
    theta2, phi2 = hp.vec2ang(vectors, lonlat=lonlat)
    # Healpy sometimes returns NaNs for phi (somewhat incorrectly)
    phi2 = np.nan_to_num(phi2)
    assert_allclose(theta1, theta1, atol=1e-10)
    assert_allclose(phi1, phi2, atol=1e-10) 

def getdataset(datasetname, onehot_encode_strings=True):
    # load
    dataset = fetch_openml(datasetname)
    # get X and y
    X = dshape(dataset.data)
    try:
        target = dshape(dataset.target)
    except:
        print("WARNING: No target found. Taking last column of data matrix as target")
        target = X[:, -1]
        X = X[:, :-1]
    if (
        len(target.shape) > 1 and target.shape[1] > X.shape[1]
    ):  # some mldata sets are mixed up...
        X = target
        target = dshape(dataset.data)
    if len(X.shape) == 1 or X.shape[1] <= 1:
        for k in dataset.keys():
            if k != "data" and k != "target" and len(dataset[k]) == X.shape[1]:
                X = np.hstack((X, dshape(dataset[k])))
    # one-hot for categorical values
    if onehot_encode_strings:
        cat_ft = [
            i
            for i in range(X.shape[1])
            if "str" in str(type(unpack(X[0, i])))
            or "unicode" in str(type(unpack(X[0, i])))
        ]
        if len(cat_ft):
            for i in cat_ft:
                X[:, i] = tonumeric(X[:, i])
            X = OneHotEncoder(categorical_features=cat_ft).fit_transform(X)
    # if sparse, make dense
    try:
        X = X.toarray()
    except:
        pass
    # convert y to monotonically increasing ints
    y = tonumeric(target).astype(int)
    return np.nan_to_num(X.astype(float)), y 

def bollinger_bands(stock_price, window_size, num_of_std):
    rolling_mean = stock_price.rolling(window=window_size).mean()
    rolling_std = stock_price.rolling(window=window_size).std()
    lower_band = rolling_mean - (rolling_std * num_of_std)
    return np.nan_to_num(rolling_mean), np.nan_to_num(lower_band) 

def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
        mid, lower = bollinger_bands(dataframe['close'], window_size=40, num_of_std=2)
        dataframe['mid'] = np.nan_to_num(mid)
        dataframe['lower'] = np.nan_to_num(lower)
        dataframe['bbdelta'] = (dataframe['mid'] - dataframe['lower']).abs()
        dataframe['pricedelta'] = (dataframe['open'] - dataframe['close']).abs()
        dataframe['closedelta'] = (dataframe['close'] - dataframe['close'].shift()).abs()
        dataframe['tail'] = (dataframe['close'] - dataframe['low']).abs()
        return dataframe 

def transform_array(self, X, y, w):
    """Transform the data in a set of (X, y, w) arrays."""
    if self.transform_X:
      X = np.nan_to_num((X - self.X_min) / (self.X_max - self.X_min))
    elif self.transform_y:
      y = np.nan_to_num((y - self.y_min) / (self.y_max - self.y_min))
    return (X, y, w) 

def transform_array(self, X, y, w):
    """Transform the data in a set of (X, y, w) arrays."""
    if self.transform_X:
      if not hasattr(self, 'move_mean') or self.move_mean:
        X = np.nan_to_num((X - self.X_means) / self.X_stds)
      else:
        X = np.nan_to_num(X / self.X_stds)
    if self.transform_y:
      if not hasattr(self, 'move_mean') or self.move_mean:
        y = np.nan_to_num((y - self.y_means) / self.y_stds)
      else:
        y = np.nan_to_num(y / self.y_stds)
    return (X, y, w)