Python numpy.sum() Examples

def add_intercept(self, X):
        """Add 1's to data as last features."""
        # Data shape
        N, D = X.shape

        # Check if there's not already an intercept column
        if np.any(np.sum(X, axis=0) == N):

            # Report
            print('Intercept is not the last feature. Swapping..')

            # Find which column contains the intercept
            intercept_index = np.argwhere(np.sum(X, axis=0) == N)

            # Swap intercept to last
            X = X[:, np.setdiff1d(np.arange(D), intercept_index)]

        # Add intercept as last column
        X = np.hstack((X, np.ones((N, 1))))

        # Append column of 1's to data, and increment dimensionality
        return X, D+1 

def cost(params, input_size, hidden_size, num_labels, X, y, learning_rate):
    m = X.shape[0]
    X = np.matrix(X)
    y = np.matrix(y)
    
    # reshape the parameter array into parameter matrices for each layer
    theta1 = np.matrix(np.reshape(params[:hidden_size * (input_size + 1)], (hidden_size, (input_size + 1))))
    theta2 = np.matrix(np.reshape(params[hidden_size * (input_size + 1):], (num_labels, (hidden_size + 1))))
    
    # run the feed-forward pass
    a1, z2, a2, z3, h = forward_propagate(X, theta1, theta2)
    
    # compute the cost
    J = 0
    for i in range(m):
        first_term = np.multiply(-y[i,:], np.log(h[i,:]))
        second_term = np.multiply((1 - y[i,:]), np.log(1 - h[i,:]))
        J += np.sum(first_term - second_term)
    
    J = J / m
    
    # add the cost regularization term
    J += (float(learning_rate) / (2 * m)) * (np.sum(np.power(theta1[:,1:], 2)) + np.sum(np.power(theta2[:,1:], 2)))
    
    return J 

def gradientReg(theta, X, y, learningRate):
    theta = np.matrix(theta)
    X = np.matrix(X)
    y = np.matrix(y)
    
    parameters = int(theta.ravel().shape[1])
    grad = np.zeros(parameters)
    
    error = sigmoid(X * theta.T) - y
    
    for i in range(parameters):
        term = np.multiply(error, X[:,i])
        
        if (i == 0):
            grad[i] = np.sum(term) / len(X)
        else:
            grad[i] = (np.sum(term) / len(X)) + ((learningRate / len(X)) * theta[:,i])
    
    return grad 

def cost(params, Y, R, num_features):
    Y = np.matrix(Y)  # (1682, 943)
    R = np.matrix(R)  # (1682, 943)
    num_movies = Y.shape[0]
    num_users = Y.shape[1]
    
    # reshape the parameter array into parameter matrices
    X = np.matrix(np.reshape(params[:num_movies * num_features], (num_movies, num_features)))  # (1682, 10)
    Theta = np.matrix(np.reshape(params[num_movies * num_features:], (num_users, num_features)))  # (943, 10)
    
    # initializations
    J = 0
    
    # compute the cost
    error = np.multiply((X * Theta.T) - Y, R)  # (1682, 943)
    squared_error = np.power(error, 2)  # (1682, 943)
    J = (1. / 2) * np.sum(squared_error)
    
    return J 

def test_bounds(self):
        """
        Test that out-of-bounds coordinates return NaN reddening, and that
        in-bounds coordinates do not return NaN reddening.
        """

        for mode in (['random_sample', 'random_sample_per_pix',
                      'median', 'samples', 'mean']):
            # Draw random coordinates, both above and below dec = -30 degree line
            n_pix = 1000
            ra = -180. + 360.*np.random.random(n_pix)
            dec = -75. + 90.*np.random.random(n_pix)    # 45 degrees above/below
            c = coords.SkyCoord(ra, dec, frame='icrs', unit='deg')

            ebv_calc = self._bayestar(c, mode=mode)

            nan_below = np.isnan(ebv_calc[dec < -35.])
            nan_above = np.isnan(ebv_calc[dec > -25.])
            pct_nan_above = np.sum(nan_above) / float(nan_above.size)

            # print r'{:s}: {:.5f}% nan above dec=-25 deg.'.format(mode, 100.*pct_nan_above)

            self.assertTrue(np.all(nan_below))
            self.assertTrue(pct_nan_above < 0.05) 

def select_threshold(pval, yval):
    best_epsilon = 0
    best_f1 = 0
    f1 = 0
    
    step = (pval.max() - pval.min()) / 1000
    
    for epsilon in np.arange(pval.min(), pval.max(), step):
        preds = pval < epsilon
        
        tp = np.sum(np.logical_and(preds == 1, yval == 1)).astype(float)
        fp = np.sum(np.logical_and(preds == 1, yval == 0)).astype(float)
        fn = np.sum(np.logical_and(preds == 0, yval == 1)).astype(float)
        
        precision = tp / (tp + fp)
        recall = tp / (tp + fn)
        f1 = (2 * precision * recall) / (precision + recall)
        
        if f1 > best_f1:
            best_f1 = f1
            best_epsilon = epsilon
    
    return best_epsilon, best_f1 

def find_match(self, pred, gt):
    '''
    Match component to balls.
    '''
    batch_size, n_frames_input, n_components, _ = pred.shape
    diff = pred.reshape(batch_size, n_frames_input, n_components, 1, 2) - \
               gt.reshape(batch_size, n_frames_input, 1, n_components, 2)
    diff = np.sum(np.sum(diff ** 2, axis=-1), axis=1)
    # Direct indices
    indices = np.argmin(diff, axis=2)
    ambiguous = np.zeros(batch_size, dtype=np.int8)
    for i in range(batch_size):
      _, counts = np.unique(indices[i], return_counts=True)
      if not np.all(counts == 1):
        ambiguous[i] = 1
    return indices, ambiguous 

def cost0(params, input_size, hidden_size, num_labels, X, y, learning_rate):
    m = X.shape[0]
    X = np.matrix(X)
    y = np.matrix(y)
    
    # reshape the parameter array into parameter matrices for each layer
    theta1 = np.matrix(np.reshape(params[:hidden_size * (input_size + 1)], (hidden_size, (input_size + 1))))
    theta2 = np.matrix(np.reshape(params[hidden_size * (input_size + 1):], (num_labels, (hidden_size + 1))))
    
    # run the feed-forward pass
    a1, z2, a2, z3, h = forward_propagate(X, theta1, theta2)
    
    # compute the cost
    J = 0
    for i in range(m):
        first_term = np.multiply(-y[i,:], np.log(h[i,:]))
        second_term = np.multiply((1 - y[i,:]), np.log(1 - h[i,:]))
        J += np.sum(first_term - second_term)
    
    J = J / m
    
    return J 

def test_bounds(self):
        """
        Test that out-of-bounds coordinates return NaN reddening, and that
        in-bounds coordinates do not return NaN reddening.
        """

        for mode in (['random_sample', 'random_sample_per_pix',
                      'median', 'samples', 'mean']):
            # Draw random coordinates on the sphere
            n_pix = 10000
            u, v = np.random.random((2,n_pix))
            l = 360. * u
            b = 90. - np.degrees(np.arccos(2.*v - 1.))
            c = coords.SkyCoord(l, b, frame='galactic', unit='deg')

            A_calc = self._iphas(c, mode=mode)

            in_bounds = (l > 32.) & (l < 213.) & (b < 4.5) & (b > -4.5)
            out_of_bounds = (l < 28.) | (l > 217.) | (b > 7.) | (b < -7.)

            n_nan_in_bounds = np.sum(np.isnan(A_calc[in_bounds]))
            n_finite_out_of_bounds = np.sum(np.isfinite(A_calc[out_of_bounds]))

            self.assertTrue(n_nan_in_bounds == 0)
            self.assertTrue(n_finite_out_of_bounds == 0) 

def solve_modal(model,k:int):
    """
    Solve eigen mode of the MDOF system
    
    params:
        model: FEModel.
        k: number of modes to extract.
    """
    K_,M_=model.K_,model.M_
    if k>model.DOF:
        logger.info('Warning: the modal number to extract is larger than the system DOFs, only %d modes are available'%model.DOF)
        k=model.DOF
    omega2s,modes = sl.eigsh(K_,k,M_,sigma=0,which='LM')
    delta = modes/np.sum(modes,axis=0)
    model.is_solved=True
    model.mode_=delta
    model.omega_=np.sqrt(omega2s).reshape((k,1)) 

def loss(self, x, t):
        """求损失函数
        Parameters
        ----------
        x : 输入数据
        t : 教师标签
        Returns
        -------
        损失函数的值
        """
        y = self.predict(x)

        weight_decay = 0
        for idx in range(1, self.hidden_layer_num + 2):
            W = self.params['W' + str(idx)]
            weight_decay += 0.5 * self.weight_decay_lambda * np.sum(W ** 2)

        return self.last_layer.forward(y, t) + weight_decay 

def _load_data():

    dfTrain = pd.read_csv(config.TRAIN_FILE)
    dfTest = pd.read_csv(config.TEST_FILE)

    def preprocess(df):
        cols = [c for c in df.columns if c not in ["id", "target"]]
        df["missing_feat"] = np.sum((df[cols] == -1).values, axis=1)
        df["ps_car_13_x_ps_reg_03"] = df["ps_car_13"] * df["ps_reg_03"]
        return df

    dfTrain = preprocess(dfTrain)
    dfTest = preprocess(dfTest)

    cols = [c for c in dfTrain.columns if c not in ["id", "target"]]
    cols = [c for c in cols if (not c in config.IGNORE_COLS)]

    X_train = dfTrain[cols].values
    y_train = dfTrain["target"].values
    X_test = dfTest[cols].values
    ids_test = dfTest["id"].values
    cat_features_indices = [i for i,c in enumerate(cols) if c in config.CATEGORICAL_COLS]

    return dfTrain, dfTest, X_train, y_train, X_test, ids_test, cat_features_indices 

def _prepro_cpg(self, states, dists):
        """Preprocess the state and distance of neighboring CpG sites."""
        prepro_states = []
        prepro_dists = []
        for state, dist in zip(states, dists):
            nan = state == dat.CPG_NAN
            if np.any(nan):
                state[nan] = np.random.binomial(1, state[~nan].mean(),
                                                nan.sum())
                dist[nan] = self.cpg_max_dist
            dist = np.minimum(dist, self.cpg_max_dist) / self.cpg_max_dist
            prepro_states.append(np.expand_dims(state, 1))
            prepro_dists.append(np.expand_dims(dist, 1))
        prepro_states = np.concatenate(prepro_states, axis=1)
        prepro_dists = np.concatenate(prepro_dists, axis=1)
        if self.cpg_wlen:
            center = prepro_states.shape[2] // 2
            delta = self.cpg_wlen // 2
            tmp = slice(center - delta, center + delta)
            prepro_states = prepro_states[:, :, tmp]
            prepro_dists = prepro_dists[:, :, tmp]
        return (prepro_states, prepro_dists) 

def _avg_embed(self, embed_dict, words_dict):
        """
        :param embed_dict:
        :param words_dict:
        """
        print("loading pre_train embedding by avg for out of vocabulary.")
        embeddings = np.zeros((int(self.words_count), int(self.dim)))
        inword_list = {}
        for word in words_dict:
            if word in embed_dict:
                embeddings[words_dict[word]] = np.array([float(i) for i in embed_dict[word]], dtype='float32')
                inword_list[words_dict[word]] = 1
                self.exact_count += 1
            elif word.lower() in embed_dict:
                embeddings[words_dict[word]] = np.array([float(i) for i in embed_dict[word.lower()]], dtype='float32')
                inword_list[words_dict[word]] = 1
                self.fuzzy_count += 1
            else:
                self.oov_count += 1
        sum_col = np.sum(embeddings, axis=0) / len(inword_list)  # avg
        for i in range(len(words_dict)):
            if i not in inword_list and i != self.padID:
                embeddings[i] = sum_col
        final_embed = torch.from_numpy(embeddings).float()
        return final_embed 

def compute_centroids(X, idx, k):
    m, n = X.shape
    centroids = np.zeros((k, n))
    
    for i in range(k):
        indices = np.where(idx == i)
        centroids[i,:] = (np.sum(X[indices,:], axis=1) / len(indices[0])).ravel()
    
    return centroids 

def backward(self, dout):
        FN, C, FH, FW = self.W.shape
        dout = dout.transpose(0, 2, 3, 1).reshape(-1, FN)

        self.db = np.sum(dout, axis=0)
        self.dW = np.dot(self.col.T, dout)
        self.dW = self.dW.transpose(1, 0).reshape(FN, C, FH, FW)

        dcol = np.dot(dout, self.col_W.T)
        dx = col2im(dcol, self.x.shape, FH, FW, self.stride, self.pad)

        return dx 

def __backward(self, dout):
        dbeta = dout.sum(axis=0)
        dgamma = np.sum(self.xn * dout, axis=0)
        dxn = self.gamma * dout
        dxc = dxn / self.std
        dstd = -np.sum((dxn * self.xc) / (self.std * self.std), axis=0)
        dvar = 0.5 * dstd / self.std
        dxc += (2.0 / self.batch_size) * self.xc * dvar
        dmu = np.sum(dxc, axis=0)
        dx = dxc - dmu / self.batch_size

        self.dgamma = dgamma
        self.dbeta = dbeta

        return dx 

def backward(self, dout):
        dx = np.dot(dout, self.W.T)
        self.dW = np.dot(self.x.T, dout)
        self.db = np.sum(dout, axis=0)

        dx = dx.reshape(*self.original_x_shape)  # 还原输入数据的形状（对应张量）
        return dx 

def mean_squared_error(y, t):
    return 0.5 * np.sum((y - t) ** 2) 

def softmax(x):
    if x.ndim == 2:
        x = x.T
        x = x - np.max(x, axis=0)
        y = np.exp(x) / np.sum(np.exp(x), axis=0)
        return y.T

    x = x - np.max(x)  # 溢出对策
    return np.exp(x) / np.sum(np.exp(x)) 

def softmax(a):
    c = np.max(a)
    exp_a = np.exp(a - c) # 溢出对策
    sum_exp_a = np.sum(exp_a)
    y = exp_a / sum_exp_a

    return y 

def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        t = np.argmax(t, axis=1)

        accuracy = np.sum(y==t) / float(x.shape[0])
        return accuracy 

def cifti_split(cii, label=('lh', 'rh', 'rest'), subject=None, hemi=None, null=np.nan):
    '''
    cifti_split(cii, label) yields the rows or columns of the given cifti file that correspond to
      the given label (see below).
    cifti_split(cii) is equivalent to cifti_split(cii, ('lh', 'rh', 'rest')).

    The label argument may be any of the following:
      * a valid CIFTI label name such as 'CIFTI_STRUCTURE_CEREBELLUM' or
        'CIFTI_STRUCTURE_CORTEX_LEFT';
      * an abbreviated name such as 'cerebellum' for 'CIFTI_STRUCTURE_CEREBELLUM'.
      * the abbreviations 'lh' and 'rh' which stand for 'CIFTI_STRUCTURE_CORTEX_LEFT' and 
        'CIFTI_STRUCTURE_CORTEX_RIGHT';
      * the special keyword 'rest', which represents all the rows/columns not collected by any other
        instruction ('rest', by itself, results in the whole matrix being returned); or
      * A tuple of the above, indicating that each of the items listed should be returned
        sequentially in a tuple.

    The following optional arguments may be given:
      * subject (default: None) may specify the subject
      * hemi (default: None) can specify the hemisphere object that 
    '''
    dat = np.asanyarray(cii.dataobj if is_image(cii) else cii)
    n = dat.shape[-1]
    atlas = cifti_split._size_data.get(n, None)
    if atlas is None: raise ValueError('cannot split cifti with size %d' % n)
    if atlas not in cifti_split._atlas_cache:
        patt = os.path.join('data', 'fs_LR', '%s.atlasroi.%dk_fs_LR.shape.gii')
        lgii = nib.load(os.path.join(library_path(), patt % ('lh', atlas)))
        rgii = nib.load(os.path.join(library_path(), patt % ('rh', atlas)))
        cifti_split._atlas_cache[atlas] = tuple([pimms.imm_array(gii.darrays[0].data.astype('bool'))
                                                 for gii in (lgii, rgii)])
    (lroi,rroi) = cifti_split._atlas_cache[atlas]
    (ln,lN) = (np.sum(lroi), len(lroi))
    (rn,rN) = (np.sum(rroi), len(rroi))
    (ldat,rdat,sdat) = [np.full(dat.shape[:-1] + (k,), null) for k in [lN, rN, n - ln - rn]]
    ldat[..., lroi] = dat[..., :ln]
    rdat[..., rroi] = dat[..., ln:(ln+rn)]
    sdat[...] = dat[..., (ln+rn):]
    if ln + rn >= n: sdat = None
    return (ldat, rdat, sdat) 

def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        if t.ndim != 1: t = np.argmax(t, axis=1)

        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy 

def normalize(u):
    '''
    normalize(u) yields a vetor with the same direction as u but unit length, or, if u has zero
    length, yields u.
    '''
    u = np.asarray(u)
    unorm = np.sqrt(np.sum(u**2, axis=0))
    z = np.isclose(unorm, 0)
    c = np.logical_not(z) / (unorm + z)
    return u * c 

def evaluate(self, points):
        points = atleast_2d(points)

        d, m = points.shape
        if d != self.d:
            if d == 1 and m == self.d:
                # points was passed in as a row vector
                points = reshape(points, (self.d, 1))
                m = 1
            else:
                msg = "points have dimension %s, dataset has dimension %s" % (d,
                    self.d)
                raise ValueError(msg)

        result = zeros((m,), dtype=np.float)

        if m >= self.n:
            # there are more points than data, so loop over data
            for i in range(self.n):
                diff = self.dataset[:, i, newaxis] - points
                tdiff = dot(self.inv_cov, diff)
                energy = sum(diff*tdiff,axis=0) / 2.0
                result = result + exp(-energy)
        else:
            # loop over points
            for i in range(m):
                diff = self.dataset - points[:, i, newaxis]
                tdiff = dot(self.inv_cov, diff)
                energy = sum(diff * tdiff, axis=0) / 2.0
                result[i] = sum(exp(-energy), axis=0)

        result = result / self._norm_factor

        return result 

def mean_squared_error(y, t):
    return 0.5 * np.sum((y-t)**2)


# 交叉熵误差
# 支持单个和 batch 

def OR(x1, x2):
    x = np.array([x1, x2])
    w = np.array([0.5, 0.5])
    b = -0.2
    tmp = np.sum(w * x) + b
    if tmp <= 0:
        return 0
    return 1


# 异或门 

def NAND(x1, x2):
    x = np.array([x1, x2])
    w = np.array([-0.5, -0.5])
    b = -0.7
    tmp = np.sum(w * x) + b
    if tmp <= 0:
        return 0
    return 1


# 或门 

def accuracy(self, X, T):
        Y = self.predict(X, train_flg=False)
        Y = np.argmax(Y, axis=1)
        if T.ndim != 1: T = np.argmax(T, axis=1)

        accuracy = np.sum(Y == T) / float(X.shape[0])
        return accuracy