Python numpy.ones() 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 test_one_hot():
    """Check if one_hot returns correct label matrices."""
    # Generate label vector
    y = np.hstack((np.ones((10,))*0,
                   np.ones((10,))*1,
                   np.ones((10,))*2))

    # Map to matrix
    Y, labels = one_hot(y)

    # Check for only 0's and 1's
    assert len(np.setdiff1d(np.unique(Y), [0, 1])) == 0

    # Check for correct labels
    assert np.all(labels == np.unique(y))

    # Check correct shape of matrix
    assert Y.shape[0] == y.shape[0]
    assert Y.shape[1] == len(labels) 

def test_cross_phase_2d(self, dask):
        Ny, Nx = (32, 16)
        x = np.linspace(0, 1, num=Nx, endpoint=False)
        y = np.ones(Ny)
        f = 6
        phase_offset = np.pi/2
        signal1 = np.cos(2*np.pi*f*x)  # frequency = 1/(2*pi)
        signal2 = np.cos(2*np.pi*f*x - phase_offset)
        da1 = xr.DataArray(data=signal1*y[:,np.newaxis], name='a',
                          dims=['y','x'], coords={'y':y, 'x':x})
        da2 = xr.DataArray(data=signal2*y[:,np.newaxis], name='b',
                          dims=['y','x'], coords={'y':y, 'x':x})
        with pytest.raises(ValueError):
            xrft.cross_phase(da1, da2, dim=['y','x'])

        if dask:
            da1 = da1.chunk({'x': 16})
            da2 = da2.chunk({'x': 16})
        cp = xrft.cross_phase(da1, da2, dim=['x'])
        actual_phase_offset = cp.sel(freq_x=f).values
        npt.assert_almost_equal(actual_phase_offset, phase_offset) 

def synthetic_field_xr(N, dL, amp, s,
                    other_dim_sizes=None, dim_order=True,
                    chunks=None):

    theta = xr.DataArray(synthetic_field(N, dL, amp, s),
                        dims=['y', 'x'],
                        coords={'y':range(N), 'x':range(N)}
                        )

    if other_dim_sizes:
        _da = xr.DataArray(np.ones(other_dim_sizes),
                           dims=['d%d'%i for i in range(len(other_dim_sizes))])
        if dim_order:
            theta = theta + _da
        else:
            theta = _da + theta

    if chunks:
        theta = theta.chunk(chunks)

    return theta 

def classical_mds(self, D):
        ''' 
        Classical multidimensional scaling

        Parameters
        ----------
        D : square 2D ndarray
            Euclidean Distance Matrix (matrix containing squared distances between points
        '''

        # Apply MDS algorithm for denoising
        n = D.shape[0]
        J = np.eye(n) - np.ones((n,n))/float(n)
        G = -0.5*np.dot(J, np.dot(D, J))

        s, U = np.linalg.eig(G)

        # we need to sort the eigenvalues in decreasing order
        s = np.real(s)
        o = np.argsort(s)
        s = s[o[::-1]]
        U = U[:,o[::-1]]

        S = np.diag(s)[0:self.dim,:]
        self.X = np.dot(np.sqrt(S),U.T) 

def wrap_variable(self, var):
        """wrap layer.w into variables"""
        val = self.lay.w.get(var, None)
        if val is None:
            shape = self.lay.wshape[var]
            args = [0., 1e-2, shape]
            if 'moving_mean' in var:
                val = np.zeros(shape)
            elif 'moving_variance' in var:
                val = np.ones(shape)
            else:
                val = np.random.normal(*args)
            self.lay.w[var] = val.astype(np.float32)
            self.act = 'Init '
        if not self.var: return

        val = self.lay.w[var]
        self.lay.w[var] = tf.constant_initializer(val)
        if var in self._SLIM: return
        with tf.variable_scope(self.scope):
            self.lay.w[var] = tf.get_variable(var,
                shape = self.lay.wshape[var],
                dtype = tf.float32,
                initializer = self.lay.w[var]) 

def _add_default_meta_keys(self, results):
        """Add default meta keys.

        We set default meta keys including `pad_shape`, `scale_factor` and
        `img_norm_cfg` to avoid the case where no `Resize`, `Normalize` and
        `Pad` are implemented during the whole pipeline.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            results (dict): Updated result dict contains the data to convert.
        """
        img = results['img']
        results.setdefault('pad_shape', img.shape)
        results.setdefault('scale_factor', 1.0)
        num_channels = 1 if len(img.shape) < 3 else img.shape[2]
        results.setdefault(
            'img_norm_cfg',
            dict(
                mean=np.zeros(num_channels, dtype=np.float32),
                std=np.ones(num_channels, dtype=np.float32),
                to_rgb=False))
        return results 

def __init__(self, wave_len=254, wave_dif=64, buffer_size=5, loop_num=5, window=np.hanning(254)):
        self.wave_len = wave_len
        self.wave_dif = wave_dif
        self.buffer_size = buffer_size
        self.loop_num = loop_num
        self.window = window

        self.wave_buf = np.zeros(wave_len+wave_dif, dtype=float)
        self.overwrap_buf = np.zeros(wave_dif*buffer_size+(wave_len-wave_dif), dtype=float)
        self.spectrum_buffer = np.ones((self.buffer_size, self.wave_len), dtype=complex)
        self.absolute_buffer = np.ones((self.buffer_size, self.wave_len), dtype=complex)
        
        self.phase = np.zeros(self.wave_len, dtype=complex)
        self.phase += np.random.random(self.wave_len)-0.5 + np.random.random(self.wave_len)*1j - 0.5j
        self.phase[self.phase == 0] = 1
        self.phase /= np.abs(self.phase) 

def predict_all(X, all_theta):
    rows = X.shape[0]
    params = X.shape[1]
    num_labels = all_theta.shape[0]
    
    # same as before, insert ones to match the shape
    X = np.insert(X, 0, values=np.ones(rows), axis=1)
    
    # convert to matrices
    X = np.matrix(X)
    all_theta = np.matrix(all_theta)
    
    # compute the class probability for each class on each training instance
    h = sigmoid(X * all_theta.T)
    
    # create array of the index with the maximum probability
    h_argmax = np.argmax(h, axis=1)
    
    # because our array was zero-indexed we need to add one for the true label prediction
    h_argmax = h_argmax + 1
    
    return h_argmax 

def prepare_poly_data(*args, power):
    """
    args: keep feeding in X, Xval, or Xtest
        will return in the same order
    """
    def prepare(x):
        # expand feature
        df = poly_features(x, power=power)

        # normalization
        ndarr = normalize_feature(df).as_matrix()

        # add intercept term
        return np.insert(ndarr, 0, np.ones(ndarr.shape[0]), axis=1)

    return [prepare(x) for x in args] 

def create_sprite_image(images):
    if isinstance(images, list):
        images = np.array(images)
    img_h = images.shape[1]
    img_w = images.shape[2]
    # sprite 可以理解为所有小图片拼成的大正方形矩阵
    m = int(np.ceil(np.sqrt(images.shape[0])))

    # 使用全 1 来初始化最终的大图片
    sprite_image = np.ones((img_h*m, img_w*m))

    for i in range(m):
        for j in range(m):
            # 计算当前图片编号
            cur = i * m + j
            if cur < images.shape[0]:
                # 将小图片的内容复制到最终的 sprite 图像
                sprite_image[i*img_h:(i+1)*img_h,
                             j*img_w:(j+1)*img_w] = images[cur]
    return sprite_image

# 加载 mnist 数据，制定 one_hot=False，得到的 labels 就是一个数字，而不是一个向量 

def color_overlap(color1, *args):
    '''
    color_overlap(color1, color2...) yields the rgba value associated with overlaying color2 on top
      of color1 followed by any additional colors (overlaid left to right). This respects alpha
      values when calculating the results.
    Note that colors may be lists of colors, in which case a matrix of RGBA values is yielded.
    '''
    args = list(args)
    args.insert(0, color1)
    rgba = np.asarray([0.5,0.5,0.5,0])
    for c in args:
        c = to_rgba(c)
        a = c[...,3]
        a0 = rgba[...,3]
        if   np.isclose(a0, 0).all(): rgba = np.ones(rgba.shape) * c
        elif np.isclose(a,  0).all(): continue
        else:                         rgba = times(a, c) + times(1-a, rgba)
    return rgba 

def image_reslice(image, spec, method=None, fill=0, dtype=None, weights=None, image_type=None):
    '''
    image_reslice(image, spec) yields a duplicate of the given image resliced to have the voxels
      indicated by the given image spec. Note that spec may be an image itself.

    Optional arguments that can be passed to image_interpolate() (asside from affine) are allowed
    here and are passed through.
    '''
    if image_type is None and is_image(image): image_type = to_image_type(image)
    spec = to_image_spec(spec)
    image = to_image(image)
    # we make a big mesh and interpolate at these points...
    imsh = spec['image_shape']
    (args, kw) = ([np.arange(n) for n in imsh[:3]], {'indexing': 'ij'})
    ijk = np.asarray([u.flatten() for u in np.meshgrid(*args, **kw)])
    ijk = np.dot(spec['affine'], np.vstack([ijk, np.ones([1,ijk.shape[1]])]))[:3]
    # interpolate here...
    u = image_interpolate(image, ijk, method=method, fill=fill, dtype=dtype, weights=weights)
    return to_image((np.reshape(u, imsh), spec), image_type=image_type) 

def jacobian(self, p, into=None):
        # transpose to be 3 x 2 x n
        p = np.transpose(np.reshape(p, (-1, 3, 2)), (1,2,0))
        # First, get the two legs...
        (dx_ab, dy_ab) = p[1] - p[0]
        (dx_ac, dy_ac) = p[2] - p[0]
        (dx_bc, dy_bc) = p[2] - p[1]
        # now, the area is half the z-value of the cross-product...
        sarea0 = 0.5 * (dx_ab*dy_ac - dx_ac*dy_ab)
        # but we want to abs it
        dsarea0 = np.sign(sarea0)
        z = np.transpose([[-dy_bc,dx_bc], [dy_ac,-dx_ac], [-dy_ab,dx_ab]], (2,0,1))
        z = times(0.5*dsarea0, z)
        m = numel(p)
        n = p.shape[2]
        ii = (np.arange(n) * np.ones([6, n])).T.flatten()
        z = sps.csr_matrix((z.flatten(), (ii, np.arange(len(ii)))), shape=(n, m))
        return safe_into(into, z) 

def apply_affine(aff, coords):
    '''
    apply_affine(affine, coords) yields the result of applying the given affine transformation to
      the given coordinate or coordinates.

    This function expects coords to be a (dims X n) matrix but if the first dimension is neither 2
    nor 3, coords.T is used; i.e.:
      apply_affine(affine3x3, coords2xN) ==> newcoords2xN
      apply_affine(affine4x4, coords3xN) ==> newcoords3xN
      apply_affine(affine3x3, coordsNx2) ==> newcoordsNx2 (for N != 2)
      apply_affine(affine4x4, coordsNx3) ==> newcoordsNx3 (for N != 3)
    '''
    if aff is None: return coords
    (coords,tr) = (np.asanyarray(coords), False)
    if len(coords.shape) == 1: return np.squeeze(apply_affine(np.reshape(coords, (-1,1)), aff))
    elif len(coords.shape) > 2: raise ValueError('cannot apply affine to ND-array for N > 2')
    if   len(coords) == 2: aff = to_affine(aff, 2)
    elif len(coords) == 3: aff = to_affine(aff, 3)
    else: (coords,aff,tr) = (coords.T, to_affine(aff, coords.shape[1]), True)
    r = np.dot(aff, np.vstack([coords, np.ones([1,coords.shape[1]])]))[:-1]
    return r.T if tr else r 

def dataframe_select(df, *cols, **filters):
    '''
    dataframe_select(df, k1=v1, k2=v2...) yields df after selecting all the columns in which the
      given keys (k1, k2, etc.) have been selected such that the associated columns in the dataframe
      contain only the rows whose cells match the given values.
    dataframe_select(df, col1, col2...) selects the given columns.
    dataframe_select(df, col1, col2..., k1=v1, k2=v2...) selects both.
    
    If a value is a tuple/list of 2 elements, then it is considered a range where cells must fall
    between the values. If value is a tuple/list of more than 2 elements or is a set of any length
    then it is a list of values, any one of which can match the cell.
    '''
    ii = np.ones(len(df), dtype='bool')
    for (k,v) in six.iteritems(filters):
        vals = df[k].values
        if   pimms.is_set(v):                    jj = np.isin(vals, list(v))
        elif pimms.is_vector(v) and len(v) == 2: jj = (v[0] <= vals) & (vals < v[1])
        elif pimms.is_vector(v):                 jj = np.isin(vals, list(v))
        else:                                    jj = (vals == v)
        ii = np.logical_and(ii, jj)
    if len(ii) != np.sum(ii): df = df.loc[ii]
    if len(cols) > 0: df = df[list(cols)]
    return df 

def dotplot2(s1, s2, wordsize=5, overlap=5, verbose=1):
        """ verbose = 0 (no progress), 1 (progress if s1 and s2 are long) or
        2 (progress in any case) """
        doProgress = False
        if verbose > 1 or len(s1)*len(s2) > 1e6:
            doProgress = True

        mat = numpy.ones(((len(s1)-wordsize)/overlap+2, (len(s2)-wordsize)/overlap+2))

        for i in range(0, len(s1)-wordsize, overlap):
            if i % 1000 == 0 and doProgress:
                logging.info("  dotplot progress: {} of {} rows done".format(i, len(s1)-wordsize))
            word1 = s1[i:i+wordsize]

            for j in range(0, len(s2)-wordsize, overlap):
                word2 = s2[j:j+wordsize]

                if word1 == word2 or word1 == word2[::-1]:
                    mat[i/overlap, j/overlap] = 0
        
        imgData = None
        tempDir = tempfile.mkdtemp()
        try:
            path = os.path.join(tempDir, "dotplot.png")
            misc.imsave(path, mat)
            imgData = open(path).read()
        except Exception as e:
            logging.error("Error generating dotplots:'{}'".format(e))
        finally:
            shutil.rmtree(tempDir)
        return imgData 

def one_hot(y, fill_k=False, one_not=False):
    """Map to one-hot encoding."""
    # Check labels
    labels = np.unique(y)

    # Number of classes
    K = len(labels)

    # Number of samples
    N = y.shape[0]

    # Preallocate array
    if one_not:
        Y = -np.ones((N, K))
    else:
        Y = np.zeros((N, K))

    # Set k-th column to 1 for n-th sample
    for n in range(N):

        # Map current class to index label
        y_n = (y[n] == labels)

        if fill_k:
            Y[n, y_n] = y_n
        else:
            Y[n, y_n] = 1

    return Y, labels 

def psi(self, X, theta, w, K=2):
        """
        Compute psi function.

        Parameters
        ----------
        X : array
            data set (N samples by D features)
        theta : array
            classifier parameters (D features by 1)
        w : array
            importance-weights (N samples by 1)
        K : int
            number of classes (def: 2)

        Returns
        -------
        psi : array
            array with psi function values (N samples by K classes)

        """
        # Number of samples
        N = X.shape[0]

        # Preallocate psi array
        psi = np.zeros((N, K))

        # Loop over classes
        for k in range(K):
            # Compute feature statistics
            Xk = self.feature_stats(X, k*np.ones((N, 1)))

            # Compute psi function
            psi[:, k] = (w*np.dot(Xk, theta))[:, 0]

        return psi 

def predict_proba(self, Z):
        """
        Compute posteriors on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples by D features)

        Returns
        -------
        preds : array
            label predictions (M samples by 1)

        """
        # Data shape
        M, D = Z.shape

        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == D:
                raise ValueError('''Test data is of different dimensionality
                                 than training data.''')

        # Calculate psi function for target samples
        psi = self.psi(Z, self.theta.T, np.ones((M, 1)), K=self.K)

        # Compute posteriors for target samples
        return self.posterior(psi) 

def test_regularization():
    """Test for fitting the model."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = ImportanceWeightedClassifier(loss_function='lr',
                                       l2_regularization=None)
    assert isinstance(clf.clf, LogisticRegressionCV)
    clf = ImportanceWeightedClassifier(loss_function='lr',
                                       l2_regularization=1.0)
    assert isinstance(clf.clf, LogisticRegression) 

def test_fit():
    """Test for fitting the model."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = ImportanceWeightedClassifier(loss_function='lr')
    clf.fit(X, y, Z)
    assert clf.is_trained
    clf = ImportanceWeightedClassifier(loss_function='qd')
    clf.fit(X, y, Z)
    assert clf.is_trained
    clf = ImportanceWeightedClassifier(loss_function='hinge')
    clf.fit(X, y, Z)
    assert clf.is_trained 

def test_predict():
    """Test for making predictions."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = ImportanceWeightedClassifier()
    clf.fit(X, y, Z)
    u_pred = clf.predict(Z)
    labels = np.unique(y)
    assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0 

def test_predict():
    """Test for making predictions."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = TransferComponentClassifier()
    clf.fit(X, y, Z)
    u_pred = clf.predict(Z)
    labels = np.unique(y)
    assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0 

def test_fit():
    """Test for fitting the model."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = SubspaceAlignedClassifier()
    clf.fit(X, y, Z)
    assert clf.is_trained 

def test_fit_semi():
    """Test for fitting the model."""
    X = rnd.randn(10, 2)
    y = np.hstack((np.zeros((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    u = np.array([[0, 0], [9, 1]])
    clf = SemiSubspaceAlignedClassifier()
    clf.fit(X, y, Z, u)
    assert clf.is_trained 

def test_predict():
    """Test for making predictions."""
    X = rnd.randn(10, 2)
    y = np.hstack((-np.ones((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = SubspaceAlignedClassifier()
    clf.fit(X, y, Z)
    u_pred = clf.predict(Z)
    labels = np.unique(y)
    assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0 

def test_predict_semi():
    """Test for making predictions."""
    X = rnd.randn(10, 2)
    y = np.hstack((np.zeros((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    u = np.array([[0, 0], [9, 1]])
    clf = SemiSubspaceAlignedClassifier()
    clf.fit(X, y, Z, u)
    u_pred = clf.predict(Z)
    labels = np.unique(y)
    assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0 

def test_predict():
    """Test for making predictions."""
    X = rnd.randn(10, 2)
    y = np.hstack((np.zeros((5,)), np.ones((5,))))
    Z = rnd.randn(10, 2) + 1
    clf = RobustBiasAwareClassifier()
    clf.fit(X, y, Z)
    u_pred = clf.predict(Z)
    labels = np.unique(y)
    assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0 

def test_fit():
    """Test for fitting the model."""
    X = np.vstack((rnd.randn(5, 2), rnd.randn(5, 2)+1))
    y = np.hstack((np.zeros((5,)), np.ones((5,))))
    Z = np.vstack((rnd.randn(5, 2)-1, rnd.randn(5, 2)+2))
    clf = TargetContrastivePessimisticClassifier(l2=0.1)
    clf.fit(X, y, Z)
    assert clf.is_trained