11. Class reference¶

This is a list of modules, classes, and functions available in astroML. For more details, please refer to the user guide or the text book. Examples of the use of astroML can also be found in the code examples, the text book figures and the paper figures.

11.1. Plotting Functions: astroML.plotting¶

11.1.1. Functions¶

 plotting.hist(x[, bins, range]) Deprecated since version 0.4. plotting.scatter_contour(x, y[, levels, …]) Scatter plot with contour over dense regions

11.1.2. Classes¶

 plotting.MultiAxes(ndim[, inner_labels, …]) Visualize Multiple-dimensional data

11.2. Density Estimation & Histograms: astroML.density_estimation¶

11.2.1. Histogram Tools¶

 density_estimation.histogram(a[, bins, range]) Deprecated since version 0.4. density_estimation.bayesian_blocks(t[, x, …]) Deprecated since version 0.4. density_estimation.knuth_bin_width(data[, …]) Deprecated since version 0.4. density_estimation.scotts_bin_width(data[, …]) Deprecated since version 0.4. Deprecated since version 0.4.

11.2.2. Density Estimation¶

 density_estimation.XDGMM(n_components[, …]) Extreme Deconvolution K-neighbors density estimation Empirically learn a distribution from one-dimensional data Generate random variables distributed according to an arbitrary function

11.3. Linear Regression & Fitting: astroML.linear_model¶

11.3.1. Linear Regression¶

 Simple Linear Regression with errors in y linear_model.PolynomialRegression([degree, …]) Polynomial Regression with errors in y Basis Function with errors in y linear_model.NadarayaWatson([kernel, h]) Nadaraya-Watson Kernel Regression

11.3.2. Functions¶

 linear_model.TLS_logL(v, X, dX) Compute the total least squares log-likelihood

11.5. Time Series Analysis: astroML.time_series¶

11.5.1. Periodic Time Series¶

 time_series.lomb_scargle(t, y, dy, omega[, …]) Deprecated since version 0.4. time_series.lomb_scargle_bootstrap(t, y, dy, …) Deprecated since version 0.4. time_series.multiterm_periodogram(t, y, dy, …) Deprecated since version 0.4. time_series.search_frequencies(t, y, dy[, …]) Utility Routine to find the best frequencies
 time_series.MultiTermFit(omega, n_terms) Multi-term Fourier fit to a light curve

11.5.2. Aperiodic Time Series¶

 time_series.ACF_scargle(t, y, dy[, n_omega, …]) Compute the Auto-correlation function via Scargle’s method time_series.ACF_EK(t, y, dy[, bins]) Auto-correlation function via the Edelson-Krolik method time_series.generate_power_law(N, dt, beta) Generate a power-law light curve time_series.generate_damped_RW(t_rest[, …]) Generate a damped random walk light curve

11.6. Statistical Functions: astroML.stats¶

 stats.binned_statistic(x, values[, …]) Compute a binned statistic for a set of data. stats.binned_statistic_2d(x, y, values[, …]) Compute a bidimensional binned statistic for a set of data. stats.binned_statistic_dd(sample, values[, …]) Compute a multidimensional binned statistic for a set of data. stats.sigmaG(a[, axis, overwrite_input, …]) Compute the rank-based estimate of the standard deviation stats.median_sigmaG(a[, axis, …]) Compute median and rank-based estimate of the standard deviation stats.mean_sigma(a[, axis, dtype, ddof, …]) Compute mean and standard deviation for an array stats.fit_bivariate_normal(x, y[, robust]) Fit bivariate normal parameters to a 2D distribution of points stats.bivariate_normal([mu, sigma_1, …]) Sample points from a 2D normal distribution stats.trunc_exp A truncated positive exponential continuous random variable. stats.linear A truncated positive exponential continuous random variable.

11.7. Dimensionality Reduction: astroML.dimensionality¶

 dimensionality.iterative_pca(X, M[, n_ev, …]) Parameters

11.8. Correlation Functions: astroML.correlation¶

Tools for computing two-point correlation functions.

 correlation.two_point(data, bins[, method, …]) Two-point correlation function correlation.two_point_angular(ra, dec, bins) Angular two-point correlation function correlation.bootstrap_two_point(data, bins) Bootstrapped two-point correlation function Angular two-point correlation function

11.9. Filters: astroML.filters¶

 filters.savitzky_golay(y, window_size, order) Smooth (and optionally differentiate) data with a Savitzky-Golay filter filters.wiener_filter(t, h[, signal, noise, …]) Compute a Wiener-filtered time-series filters.min_component_filter(x, y, feature_mask) Minimum component filtering

11.10. Fourier and Wavelet Transforms: astroML.fourier¶

 fourier.FT_continuous(t, h[, axis, method]) Approximate a continuous 1D Fourier Transform with sampled data. fourier.IFT_continuous(f, H[, axis, method]) Approximate a continuous 1D Inverse Fourier Transform with sampled data. fourier.PSD_continuous(t, h[, axis, method]) Approximate a continuous 1D Power Spectral Density of sampled data. fourier.wavelet_PSD(t, h, f0[, Q]) Compute the wavelet PSD as a function of f0 and t fourier.sinegauss(t, t0, f0, Q) Sine-gaussian wavelet fourier.sinegauss_FT(f, t0, f0, Q) Fourier transform of the sine-gaussian wavelet. fourier.sinegauss_PSD(f, t0, f0, Q) Compute the PSD of the sine-gaussian function at frequency f

11.11. Luminosity Functions: astroML.lumfunc¶

 lumfunc.Cminus(x, y, xmax, ymax) Lynden-Bell’s C-minus method lumfunc.binned_Cminus(x, y, xmax, ymax, …) Compute the binned distributions using the Cminus method lumfunc.bootstrap_Cminus(x, y, xmax, ymax, …) Compute the binned distributions using the Cminus method, with bootstrapped estimates of the errors

11.12. Classification: astroML.classification¶

 classification.GMMBayes([n_components]) GaussianMixture Bayes Classifier

11.13. Resampling: astroML.resample¶

 resample.bootstrap(data, n_bootstraps, …) Compute bootstraped statistics of a dataset. resample.jackknife(data, user_statistic[, …]) Compute first-order jackknife statistics of the data.