Python sklearn.decomposition.FactorAnalysis() Examples

def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.decomposition.PCA, decomposition.PCA)
        self.assertIs(df.decomposition.IncrementalPCA,
                      decomposition.IncrementalPCA)
        self.assertIs(df.decomposition.KernelPCA, decomposition.KernelPCA)
        self.assertIs(df.decomposition.FactorAnalysis,
                      decomposition.FactorAnalysis)
        self.assertIs(df.decomposition.FastICA, decomposition.FastICA)
        self.assertIs(df.decomposition.TruncatedSVD, decomposition.TruncatedSVD)
        self.assertIs(df.decomposition.NMF, decomposition.NMF)
        self.assertIs(df.decomposition.SparsePCA, decomposition.SparsePCA)
        self.assertIs(df.decomposition.MiniBatchSparsePCA,
                      decomposition.MiniBatchSparsePCA)
        self.assertIs(df.decomposition.SparseCoder, decomposition.SparseCoder)
        self.assertIs(df.decomposition.DictionaryLearning,
                      decomposition.DictionaryLearning)
        self.assertIs(df.decomposition.MiniBatchDictionaryLearning,
                      decomposition.MiniBatchDictionaryLearning)

        self.assertIs(df.decomposition.LatentDirichletAllocation,
                      decomposition.LatentDirichletAllocation) 

def dim_reduction_method(self):
        """
        select dimensionality reduction method
        """
        if self.dim_reduction=='pca':
            return PCA()
        elif self.dim_reduction=='factor-analysis':
            return FactorAnalysis()
        elif self.dim_reduction=='fast-ica':
            return FastICA()
        elif self.dim_reduction=='kernel-pca':
            return KernelPCA()
        elif self.dim_reduction=='sparse-pca':
            return SparsePCA()
        elif self.dim_reduction=='truncated-svd':
            return TruncatedSVD()
        elif self.dim_reduction!=None:
            raise ValueError('%s is not a supported dimensionality reduction method. Valid inputs are: \
                             "pca","factor-analysis","fast-ica,"kernel-pca","sparse-pca","truncated-svd".' 
                             %(self.dim_reduction)) 

def FA(data, dim):
    fa = FactorAnalysis(n_components=dim)
    fa.fit(data)
    return fa.transform(data) 

def __init__(self, **kwargs):
        super().__init__()
        self.estimator = sk_d.FactorAnalysis(**kwargs) 

def compute_scores(X):
    pca = PCA()
    fa = FactorAnalysis()

    pca_scores, fa_scores = [], []
    for n in n_components:
        pca.n_components = n
        fa.n_components = n
        pca_scores.append(np.mean(cross_val_score(pca, X)))
        fa_scores.append(np.mean(cross_val_score(fa, X)))

    return pca_scores, fa_scores 

def __init__(self, inverse_l2=0.0001, verbose=False):
        self.verbose = verbose
        self.model = pipeline.make_pipeline(
            decomposition.FactorAnalysis(),
            LogisticRegression(
                C=inverse_l2, solver='liblinear', verbose=verbose)
        ) 

def testAlgorithm():
    import matplotlib.pyplot as plt

    random.seed(35)
    np.random.seed(32)

    n = 200
    d = 20
    k = 2
    sigma = .3
    n_clusters = 3
    decay_coef = .1

    X, Y, Z, ids = generateSimulatedDimensionalityReductionData(n_clusters, n, d, k, sigma, decay_coef)

    Zhat, params = block_ZIFA.fitModel(Y, k)
    colors = ['red', 'blue', 'green']
    cluster_ids = sorted(list(set(ids)))
    model = FactorAnalysis(n_components=k)
    factor_analysis_Zhat = model.fit_transform(Y)

    plt.figure(figsize=[15, 5])

    plt.subplot(131)
    for id in cluster_ids:
        plt.scatter(Z[ids == id, 0], Z[ids == id, 1], color=colors[id - 1], s=4)
        plt.title('True Latent Positions\nFraction of Zeros %2.3f' % (Y == 0).mean())
        plt.xlim([-4, 4])
        plt.ylim([-4, 4])

    plt.subplot(132)
    for id in cluster_ids:
        plt.scatter(Zhat[ids == id, 0], Zhat[ids == id, 1], color=colors[id - 1], s=4)
        plt.xlim([-4, 4])
        plt.ylim([-4, 4])
        plt.title('ZIFA Estimated Latent Positions')
        # title(titles[method])

    plt.subplot(133)
    for id in cluster_ids:
        plt.scatter(factor_analysis_Zhat[ids == id, 0], factor_analysis_Zhat[ids == id, 1], color = colors[id - 1], s = 4)
        plt.xlim([-4, 4])
        plt.ylim([-4, 4])
        plt.title('Factor Analysis Estimated Latent Positions')

    plt.show() 

def initializeParams(Y, K, singleSigma=False, makePlot=False):
	"""
	initializes parameters using a standard factor analysis model (on imputed data) + exponential curve fitting.
	Checked.
	Input:
	Y: data matrix, n_samples x n_genes
	K: number of latent components
	singleSigma: uses only a single sigma as opposed to a different sigma for every gene
	makePlot: makes a mu - p_0 plot and shows the decaying exponential fit.
	Returns:
	A, mus, sigmas, decay_coef: initialized model parameters.
	"""

	N, D = Y.shape
	model = FactorAnalysis(n_components=K)
	zeroedY = deepcopy(Y)
	mus = np.zeros([D, 1])

	for j in range(D):
		non_zero_idxs = np.abs(Y[:, j]) > 1e-6
		mus[j] = zeroedY[:, j].mean()
		zeroedY[:, j] = zeroedY[:, j] - mus[j]

	model.fit(zeroedY)

	A = model.components_.transpose()
	sigmas = np.atleast_2d(np.sqrt(model.noise_variance_)).transpose()
	if singleSigma:
		sigmas = np.mean(sigmas) * np.ones(sigmas.shape)

	# Now fit decay coefficient
	means = []
	ps = []
	for j in range(D):
		non_zero_idxs = np.abs(Y[:, j]) > 1e-6
		means.append(Y[non_zero_idxs, j].mean())
		ps.append(1 - non_zero_idxs.mean())

	decay_coef, pcov = curve_fit(exp_decay, means, ps, p0=.05)
	decay_coef = decay_coef[0]

	mse = np.mean(np.abs(ps - np.exp(-decay_coef * (np.array(means) ** 2))))

	if (mse > 0) and makePlot:
		from matplotlib.pyplot import figure, scatter, plot, title, show
		figure()
		scatter(means, ps)
		plot(np.arange(min(means), max(means), .1), np.exp(-decay_coef * (np.arange(min(means), max(means), .1) ** 2)))
		title('Decay Coef is %2.3f; MSE is %2.3f' % (decay_coef, mse))
		show()

	return A, mus, sigmas, decay_coef