[param_to_array] deprecated and removed param_to_array from code, use param.values instead

GPy/examples/dimensionality_reduction.py

@@ -23,9 +23,6 @@ def bgplvm_test_model(optimize=False, verbose=1, plot=False, output_dim=200, nan
     X = _np.random.rand(num_inputs, input_dim)
     lengthscales = _np.random.rand(input_dim)
     k = GPy.kern.RBF(input_dim, .5, lengthscales, ARD=True)
-         ##+ GPy.kern.white(input_dim, 0.01)
-         #)
-    #k = GPy.kern.Linear(input_dim, ARD=1)# + GPy.kern.bias(input_dim) + GPy.kern.white(input_dim, 0.00001)
     K = k.K(X)
     Y = _np.random.multivariate_normal(_np.zeros(num_inputs), K, (output_dim,)).T
 
@@ -159,7 +156,6 @@ def swiss_roll(optimize=True, verbose=1, plot=True, N=1000, num_inducing=25, Q=4
 def bgplvm_oil(optimize=True, verbose=1, plot=True, N=200, Q=7, num_inducing=40, max_iters=1000, **k):
     import GPy
     from matplotlib import pyplot as plt
-    from ..util.misc import param_to_array
     import numpy as np
 
     _np.random.seed(0)
@@ -177,7 +173,7 @@ def bgplvm_oil(optimize=True, verbose=1, plot=True, N=200, Q=7, num_inducing=40,
         fig, (latent_axes, sense_axes) = plt.subplots(1, 2)
         m.plot_latent(ax=latent_axes, labels=m.data_labels)
         data_show = GPy.plotting.matplot_dep.visualize.vector_show((m.Y[0,:]))
-        lvm_visualizer = GPy.plotting.matplot_dep.visualize.lvm_dimselect(param_to_array(m.X.mean)[0:1,:], # @UnusedVariable
+        lvm_visualizer = GPy.plotting.matplot_dep.visualize.lvm_dimselect(m.X.mean.values[0:1,:], # @UnusedVariable
             m, data_show, latent_axes=latent_axes, sense_axes=sense_axes, labels=m.data_labels)
         raw_input('Press enter to finish')
         plt.close(fig)
@@ -186,8 +182,6 @@ def bgplvm_oil(optimize=True, verbose=1, plot=True, N=200, Q=7, num_inducing=40,
 def ssgplvm_oil(optimize=True, verbose=1, plot=True, N=200, Q=7, num_inducing=40, max_iters=1000, **k):
     import GPy
     from matplotlib import pyplot as plt
-    from ..util.misc import param_to_array
-    import numpy as np
 
     _np.random.seed(0)
     data = GPy.util.datasets.oil()
@@ -204,7 +198,7 @@ def ssgplvm_oil(optimize=True, verbose=1, plot=True, N=200, Q=7, num_inducing=40
         fig, (latent_axes, sense_axes) = plt.subplots(1, 2)
         m.plot_latent(ax=latent_axes, labels=m.data_labels)
         data_show = GPy.plotting.matplot_dep.visualize.vector_show((m.Y[0,:]))
-        lvm_visualizer = GPy.plotting.matplot_dep.visualize.lvm_dimselect(param_to_array(m.X.mean)[0:1,:], # @UnusedVariable
+        lvm_visualizer = GPy.plotting.matplot_dep.visualize.lvm_dimselect(m.X.mean.values[0:1,:], # @UnusedVariable
             m, data_show, latent_axes=latent_axes, sense_axes=sense_axes, labels=m.data_labels)
         raw_input('Press enter to finish')
         plt.close(fig)
@@ -228,10 +222,10 @@ def _simulate_matern(D1, D2, D3, N, num_inducing, plot_sim=False):
     Ylist = [Y1, Y2, Y3]
 
     if plot_sim:
-        import pylab
+        from matplotlib import pyplot as plt
         import matplotlib.cm as cm
         import itertools
-        fig = pylab.figure("MRD Simulation Data", figsize=(8, 6))
+        fig = plt.figure("MRD Simulation Data", figsize=(8, 6))
         fig.clf()
         ax = fig.add_subplot(2, 1, 1)
         labls = slist_names
@@ -242,29 +236,11 @@ def _simulate_matern(D1, D2, D3, N, num_inducing, plot_sim=False):
             ax = fig.add_subplot(2, len(Ylist), len(Ylist) + 1 + i)
             ax.imshow(Y, aspect='auto', cmap=cm.gray) # @UndefinedVariable
             ax.set_title("Y{}".format(i + 1))
-        pylab.draw()
+        plt.draw()
-        pylab.tight_layout()
+        plt.tight_layout()
 
     return slist, [S1, S2, S3], Ylist
 
-def _generate_high_dimensional_output(D1, D2, D3, s1, s2, s3, sS):
-    S1 = _np.hstack([s1, sS])
-    S2 = _np.hstack([s2, s3, sS])
-    S3 = _np.hstack([s3, sS])
-    Y1 = S1.dot(_np.random.randn(S1.shape[1], D1))
-    Y2 = S2.dot(_np.random.randn(S2.shape[1], D2))
-    Y3 = S3.dot(_np.random.randn(S3.shape[1], D3))
-    Y1 += .3 * _np.random.randn(*Y1.shape)
-    Y2 += .2 * _np.random.randn(*Y2.shape)
-    Y3 += .25 * _np.random.randn(*Y3.shape)
-    Y1 -= Y1.mean(0)
-    Y2 -= Y2.mean(0)
-    Y3 -= Y3.mean(0)
-    Y1 /= Y1.std(0)
-    Y2 /= Y2.std(0)
-    Y3 /= Y3.std(0)
-    return Y1, Y2, Y3, S1, S2, S3
-
 def _simulate_sincos(D1, D2, D3, N, num_inducing, plot_sim=False):
     _np.random.seed(1234)
 
@@ -291,10 +267,10 @@ def _simulate_sincos(D1, D2, D3, N, num_inducing, plot_sim=False):
     Ylist = [Y1, Y2, Y3]
 
     if plot_sim:
-        import pylab
+        from matplotlib import pyplot as plt
         import matplotlib.cm as cm
         import itertools
-        fig = pylab.figure("MRD Simulation Data", figsize=(8, 6))
+        fig = plt.figure("MRD Simulation Data", figsize=(8, 6))
         fig.clf()
         ax = fig.add_subplot(2, 1, 1)
         labls = slist_names
@@ -305,28 +281,28 @@ def _simulate_sincos(D1, D2, D3, N, num_inducing, plot_sim=False):
             ax = fig.add_subplot(2, len(Ylist), len(Ylist) + 1 + i)
             ax.imshow(Y, aspect='auto', cmap=cm.gray) # @UndefinedVariable
             ax.set_title("Y{}".format(i + 1))
-        pylab.draw()
+        plt.draw()
-        pylab.tight_layout()
+        plt.tight_layout()
 
     return slist, [S1, S2, S3], Ylist
 
-# def bgplvm_simulation_matlab_compare():
+def _generate_high_dimensional_output(D1, D2, D3, s1, s2, s3, sS):
-#     from GPy.util.datasets import simulation_BGPLVM
+    S1 = _np.hstack([s1, sS])
-#     from GPy import kern
+    S2 = _np.hstack([s2, s3, sS])
-#     from GPy.models import BayesianGPLVM
+    S3 = _np.hstack([s3, sS])
-#
+    Y1 = S1.dot(_np.random.randn(S1.shape[1], D1))
-#     sim_data = simulation_BGPLVM()
+    Y2 = S2.dot(_np.random.randn(S2.shape[1], D2))
-#     Y = sim_data['Y']
+    Y3 = S3.dot(_np.random.randn(S3.shape[1], D3))
-#     mu = sim_data['mu']
+    Y1 += .3 * _np.random.randn(*Y1.shape)
-#     num_inducing, [_, Q] = 3, mu.shape
+    Y2 += .2 * _np.random.randn(*Y2.shape)
-#
+    Y3 += .25 * _np.random.randn(*Y3.shape)
-#     k = kern.linear(Q, ARD=True) + kern.bias(Q, _np.exp(-2)) + kern.white(Q, _np.exp(-2))
+    Y1 -= Y1.mean(0)
-#     m = BayesianGPLVM(Y, Q, init="PCA", num_inducing=num_inducing, kernel=k,
+    Y2 -= Y2.mean(0)
-#                        _debug=False)
+    Y3 -= Y3.mean(0)
-#     m.auto_scale_factor = True
+    Y1 /= Y1.std(0)
-#     m['noise'] = Y.var() / 100.
+    Y2 /= Y2.std(0)
-#     m['linear_variance'] = .01
+    Y3 /= Y3.std(0)
-#     return m
+    return Y1, Y2, Y3, S1, S2, S3
 
 def bgplvm_simulation(optimize=True, verbose=1,
                       plot=True, plot_sim=False,

GPy/inference/latent_function_inference/expectation_propagation_dtc.py

@@ -1,7 +1,6 @@
 import numpy as np
 from ...util import diag
 from ...util.linalg import mdot, jitchol, backsub_both_sides, tdot, dtrtrs, dtrtri, dpotri, dpotrs, symmetrify, DSYR
-from ...util.misc import param_to_array
 from ...core.parameterization.variational import VariationalPosterior
 from . import LatentFunctionInference
 from posterior import Posterior
@@ -23,7 +22,7 @@ class EPDTC(LatentFunctionInference):
         self.get_YYTfactor.limit = limit
 
     def _get_trYYT(self, Y):
-        return param_to_array(np.sum(np.square(Y)))
+        return np.sum(np.square(Y))
 
     def __getstate__(self):
         # has to be overridden, as Cacher objects cannot be pickled.
@@ -44,7 +43,7 @@ class EPDTC(LatentFunctionInference):
         """
         N, D = Y.shape
         if (N>=D):
-            return param_to_array(Y)
+            return Y
         else:
             return jitchol(tdot(Y))
 

GPy/inference/latent_function_inference/laplace.py

@@ -12,7 +12,6 @@
 
 import numpy as np
 from ...util.linalg import mdot, jitchol, dpotrs, dtrtrs, dpotri, symmetrify, pdinv
-from ...util.misc import param_to_array
 from posterior import Posterior
 import warnings
 from scipy import optimize
@@ -39,9 +38,6 @@ class Laplace(LatentFunctionInference):
         Returns a Posterior class containing essential quantities of the posterior
         """
 
-        #make Y a normal array!
-        Y = param_to_array(Y)
-
         # Compute K
         K = kern.K(X)
 

GPy/inference/latent_function_inference/var_dtc.py

@@ -6,7 +6,6 @@ from ...util.linalg import mdot, jitchol, backsub_both_sides, tdot, dtrtrs, dtrt
 from ...util import diag
 from ...core.parameterization.variational import VariationalPosterior
 import numpy as np
-from ...util.misc import param_to_array
 from . import LatentFunctionInference
 log_2_pi = np.log(2*np.pi)
 import logging, itertools
@@ -35,7 +34,7 @@ class VarDTC(LatentFunctionInference):
         self.get_YYTfactor.limit = limit
 
     def _get_trYYT(self, Y):
-        return param_to_array(np.sum(np.square(Y)))
+        return np.sum(np.square(Y))
 
     def __getstate__(self):
         # has to be overridden, as Cacher objects cannot be pickled.
@@ -56,7 +55,7 @@ class VarDTC(LatentFunctionInference):
         """
         N, D = Y.shape
         if (N>=D):
-            return param_to_array(Y)
+            return Y.view(np.ndarray)
         else:
             return jitchol(tdot(Y))
 

GPy/inference/latent_function_inference/var_dtc_gpu.py

@@ -6,7 +6,6 @@ from ...util.linalg import jitchol, backsub_both_sides, tdot, dtrtrs
 from ...util import diag
 from ...core.parameterization.variational import VariationalPosterior
 import numpy as np
-from ...util.misc import param_to_array
 from . import LatentFunctionInference
 log_2_pi = np.log(2*np.pi)
 
@@ -117,7 +116,7 @@ class VarDTC_GPU(LatentFunctionInference):
         """
         N, D = Y.shape
         if (N>=D):
-            return param_to_array(Y)
+            return Y.view(np.ndarray)
         else:
             return jitchol(tdot(Y))
 

GPy/inference/latent_function_inference/var_dtc_parallel.py

@@ -6,7 +6,6 @@ from ...util.linalg import jitchol, backsub_both_sides, tdot, dtrtrs, dtrtri,pdi
 from ...util import diag
 from ...core.parameterization.variational import VariationalPosterior
 import numpy as np
-from ...util.misc import param_to_array
 from . import LatentFunctionInference
 log_2_pi = np.log(2*np.pi)
 
@@ -60,7 +59,7 @@ class VarDTC_minibatch(LatentFunctionInference):
         self.get_YYTfactor.limit = limit
 
     def _get_trYYT(self, Y):
-        return param_to_array(np.sum(np.square(Y)))
+        return np.sum(np.square(Y))
 
     def _get_YYTfactor(self, Y):
         """
@@ -70,7 +69,7 @@ class VarDTC_minibatch(LatentFunctionInference):
         """
         N, D = Y.shape
         if (N>=D):
-            return param_to_array(Y)
+            return Y.view(np.ndarray)
         else:
             return jitchol(tdot(Y))
 

GPy/kern/_src/poly.py

@@ -3,7 +3,6 @@
 
 import numpy as np
 from kern import Kern
-from ...util.misc import param_to_array
 from ...core.parameterization import Param
 from ...core.parameterization.transformations import Logexp
 class Poly(Kern):

GPy/models/sparse_gp_regression.py

@@ -7,7 +7,6 @@ from ..core import SparseGP
 from .. import likelihoods
 from .. import kern
 from ..inference.latent_function_inference import VarDTC
-from ..util.misc import param_to_array
 from ..core.parameterization.variational import NormalPosterior
 
 class SparseGPRegression(SparseGP):
@@ -40,7 +39,7 @@ class SparseGPRegression(SparseGP):
         # Z defaults to a subset of the data
         if Z is None:
             i = np.random.permutation(num_data)[:min(num_inducing, num_data)]
-            Z = param_to_array(X)[i].copy()
+            Z = X.view(np.ndarray)[i].copy()
         else:
             assert Z.shape[1] == input_dim
 

GPy/plotting/matplot_dep/dim_reduction_plots.py

@@ -1,7 +1,6 @@
 
 import numpy as np
 from latent_space_visualizations.controllers.imshow_controller import ImshowController,ImAnnotateController
-from ...util.misc import param_to_array
 from ...core.parameterization.variational import VariationalPosterior
 from .base_plots import x_frame2D
 import itertools
@@ -55,9 +54,9 @@ def plot_latent(model, labels=None, which_indices=None,
     #fethch the data points X that we'd like to plot
     X = model.X
     if isinstance(X, VariationalPosterior):
-        X = param_to_array(X.mean)
+        X = X.mean
     else:
-        X = param_to_array(X)
+        X = X
 
 
     if X.shape[0] > 1000:
@@ -175,7 +174,7 @@ def plot_latent(model, labels=None, which_indices=None,
     ax.set_aspect('auto') # set a nice aspect ratio
 
     if plot_inducing:
-        Z = param_to_array(model.Z)
+        Z = model.Z
         ax.plot(Z[:, input_1], Z[:, input_2], '^w')
 
     ax.set_xlim((xmin, xmax))

GPy/plotting/matplot_dep/kernel_plots.py

@@ -35,8 +35,7 @@ def add_bar_labels(fig, ax, bars, bottom=0):
 
 
 def plot_bars(fig, ax, x, ard_params, color, name, bottom=0):
-    from ...util.misc import param_to_array
+    return ax.bar(left=x, height=ard_params.view(np.ndarray), width=.8,
-    return ax.bar(left=x, height=param_to_array(ard_params), width=.8,
                   bottom=bottom, align='center',
                   color=color, edgecolor='k', linewidth=1.2,
                   label=name.replace("_"," "))

GPy/plotting/matplot_dep/models_plots.py

@@ -8,7 +8,6 @@ except:
     pass
 import numpy as np
 from base_plots import gpplot, x_frame1D, x_frame2D
-from ...util.misc import param_to_array
 from ...models.gp_coregionalized_regression import GPCoregionalizedRegression
 from ...models.sparse_gp_coregionalized_regression import SparseGPCoregionalizedRegression
 from scipy import sparse
@@ -67,7 +66,6 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
         X_variance = model.X.variance
     else:
         X = model.X
-    #X, Y = param_to_array(X, model.Y)
     Y = model.Y
     if sparse.issparse(Y): Y = Y.todense().view(np.ndarray)
 

GPy/plotting/matplot_dep/variational_plots.py

@@ -1,5 +1,4 @@
 import pylab as pb, numpy as np
-from ...util.misc import param_to_array
 
 def plot(parameterized, fignum=None, ax=None, colors=None):
     """
@@ -21,7 +20,7 @@ def plot(parameterized, fignum=None, ax=None, colors=None):
     else:
         colors = iter(colors)
     plots = []
-    means, variances = param_to_array(parameterized.mean, parameterized.variance)
+    means, variances = parameterized.mean, parameterized.variance
     x = np.arange(means.shape[0])
     for i in range(means.shape[1]):
         if ax is None:
@@ -68,7 +67,7 @@ def plot_SpikeSlab(parameterized, fignum=None, ax=None, colors=None, side_by_sid
     else:
         colors = iter(colors)
     plots = []
-    means, variances, gamma = param_to_array(parameterized.mean, parameterized.variance, parameterized.binary_prob)
+    means, variances, gamma = parameterized.mean, parameterized.variance, parameterized.binary_prob
     x = np.arange(means.shape[0])
     for i in range(means.shape[1]):
         if side_by_side:

GPy/plotting/matplot_dep/visualize.py

@@ -4,7 +4,6 @@ import GPy
 import numpy as np
 import matplotlib as mpl
 import time
-from ...util.misc import param_to_array
 from GPy.core.parameterization.variational import VariationalPosterior
 try:
     import visual

GPy/util/data_resources.json

@@ -523,6 +523,23 @@
             "http://staffwww.dcs.shef.ac.uk/people/N.Lawrence/dataset_mirror/singlecell/"
         ]
     },
+    "singlecell_islam": {
+        "citation": "Single-Cell RNA-Seq Reveals Dynamic, Random Monoallelic Gene Expression in Mammalian Cells Qiaolin Deng, Daniel Ramskoeld, Bjoern Reinius, and Rickard Sandberg Science 10 January 2014: 343 (6167), 193-196. [DOI:10.1126/science.1245316]",
+        "details" : "92 single cells (48 mouse ES cells, 44 mouse embryonic fibroblasts and 4 negative controls) were analyzed by single-cell tagged reverse transcription (STRT)",
+        "files"   : [["GSE29087_L139_expression_tab.txt.gz"], ["GSE29087_family.soft.gz"]],
+        "license" : "Gene Expression Omnibus: http://www.ncbi.nlm.nih.gov/geo/info/disclaimer.html",
+        "size"    : 1159449,
+        "urls"    : ["ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE29nnn/GSE29087/suppl/", "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE29nnn/GSE29087/soft/"]
+    },
+    "singlecell_deng": {
+        "citation": "Deng Q, Ramsköld D, Reinius B, Sandberg R. Single-cell RNA-seq reveals dynamic, random monoallelic gene expression in mammalian cells. Science 2014 Jan 10;343(6167):193-6. PMID: 24408435",
+        "details" : "First generation mouse strain crosses were used to study monoallelic expression on the single cell level",
+        "files"   : [["?acc=GSE45719&format=file"], ["GSE45719_series_matrix.txt.gz"]],
+        "license" : "Gene Expression Omnibus: http://www.ncbi.nlm.nih.gov/geo/info/disclaimer.html",
+        "size"    : 1159449,
+        "save_names": [["GSE45719_Raw.tar"], [null]],
+        "urls"    : ["http://www.ncbi.nlm.nih.gov/geo/download/", "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE45nnn/GSE45719/matrix/"]
+    },
     "sod1_mouse": {
         "citation": "Transcriptomic indices of fast and slow disease progression in two mouse models of amyotrophic lateral sclerosis' Nardo G1, Iennaco R, Fusi N, Heath PR, Marino M, Trolese MC, Ferraiuolo L, Lawrence N, Shaw PJ, Bendotti C Brain. 2013 Nov;136(Pt 11):3305-32. doi: 10.1093/brain/awt250. Epub 2013 Sep 24.",
         "details": "Gene expression data from two separate strains of mice: C57 and 129Sv in wild type and SOD1 mutant strains.",

GPy/util/datasets.py

@@ -82,9 +82,16 @@ def prompt_user(prompt):
 
 def data_available(dataset_name=None):
     """Check if the data set is available on the local machine already."""
-    for file_list in data_resources[dataset_name]['files']:
+    from itertools import izip_longest
-        for file in file_list:
+    dr = data_resources[dataset_name]
-            if not os.path.exists(os.path.join(data_path, dataset_name, file)):
+    zip_urls = (dr['files'], )
+    if dr.has_key('save_names'): zip_urls += (dr['save_names'], )
+    else: zip_urls += ([],)
+
+    for file_list, save_list in izip_longest(*zip_urls, fillvalue=[]):
+        for f, s in izip_longest(file_list, save_list, fillvalue=None):
+            if s is not None: f=s # If there is a save_name given, use that one
+            if not os.path.exists(os.path.join(data_path, dataset_name, f)):
                 return False
     return True
 
@@ -94,8 +101,13 @@ def download_url(url, store_directory, save_name = None, messages = True, suffix
     file = url[i+1:]
     print file
     dir_name = os.path.join(data_path, store_directory)
-    save_name = os.path.join(dir_name, file)
+
-    print "Downloading ", url, "->", os.path.join(store_directory, file)
+    if save_name is None: save_name = os.path.join(dir_name, file)
+    else: save_name = os.path.join(dir_name, save_name)
+
+    if suffix is None: suffix=''
+
+    print "Downloading ", url, "->", save_name
     if not os.path.exists(dir_name):
         os.makedirs(dir_name)
     try:
@@ -178,19 +190,24 @@ def authorize_download(dataset_name=None):
 
 def download_data(dataset_name=None):
     """Check with the user that the are happy with terms and conditions for the data set, then download it."""
+    import itertools
 
     dr = data_resources[dataset_name]
     if not authorize_download(dataset_name):
         raise Exception("Permission to download data set denied.")
 
-    if dr.has_key('suffices'):
+    zip_urls = (dr['urls'], dr['files'])
-        for url, files, suffices in zip(dr['urls'], dr['files'], dr['suffices']):
+
-            for file, suffix in zip(files, suffices):
+    if dr.has_key('save_names'): zip_urls += (dr['save_names'], )
-                download_url(os.path.join(url,file), dataset_name, dataset_name, suffix=suffix)
+    else: zip_urls += ([],)
-    else:
+
-        for url, files in zip(dr['urls'], dr['files']):
+    if dr.has_key('suffices'): zip_urls += (dr['suffices'], )
-            for file in files:
+    else: zip_urls += ([],)
-                download_url(os.path.join(url,file), dataset_name, dataset_name)
+
+    for url, files, save_names, suffices in itertools.izip_longest(*zip_urls, fillvalue=[]):
+        for f, save_name, suffix in itertools.izip_longest(files, save_names, suffices, fillvalue=None):
+            download_url(os.path.join(url,f), dataset_name, save_name, suffix=suffix)
+
     return True
 
 def data_details_return(data, data_set):
@@ -895,6 +912,128 @@ def singlecell(data_set='singlecell'):
                                 'genes': genes, 'labels':labels,
                                 }, data_set)
 
+def singlecell_rna_seq_islam(dataset='singlecell_islam'):
+    if not data_available(dataset):
+        download_data(dataset)
+
+    from pandas import read_csv, DataFrame, concat
+    dir_path = os.path.join(data_path, dataset)
+    filename = os.path.join(dir_path, 'GSE29087_L139_expression_tab.txt.gz')
+    data = read_csv(filename, sep='\t', skiprows=6, compression='gzip', header=None)
+    header1 = read_csv(filename, sep='\t', header=None, skiprows=5, nrows=1, compression='gzip')
+    header2 = read_csv(filename, sep='\t', header=None, skiprows=3, nrows=1, compression='gzip')
+    data.columns = np.concatenate((header1.ix[0, :], header2.ix[0, 7:]))
+    Y = data.set_index("Feature").ix[8:, 6:-4].T.astype(float)
+
+    # read the info .soft
+    filename = os.path.join(dir_path, 'GSE29087_family.soft.gz')
+    info = read_csv(filename, sep='\t', skiprows=0, compression='gzip', header=None)
+    # split at ' = '
+    info = DataFrame(info.ix[:,0].str.split(' = ').tolist())
+    # only take samples:
+    info = info[info[0].str.contains("!Sample")]
+    info[0] = info[0].apply(lambda row: row[len("!Sample_"):])
+
+    groups = info.groupby(0).groups
+    # remove 'GGG' from barcodes
+    barcode = info[1][groups['barcode']].apply(lambda row: row[:-3])
+
+    title = info[1][groups['title']]
+    title.index = barcode
+    title.name = 'title'
+    geo_accession = info[1][groups['geo_accession']]
+    geo_accession.index = barcode
+    geo_accession.name = 'geo_accession'
+    case_id = info[1][groups['source_name_ch1']]
+    case_id.index = barcode
+    case_id.name = 'source_name_ch1'
+
+    info = concat([title, geo_accession, case_id], axis=1)
+    labels = info.join(Y).source_name_ch1[:-4]
+    labels[labels=='Embryonic stem cell'] = "ES"
+    labels[labels=='Embryonic fibroblast'] = "MEF"
+
+    return data_details_return({'Y': Y,
+                                'info': '92 single cells (48 mouse ES cells, 44 mouse embryonic fibroblasts and 4 negative controls) were analyzed by single-cell tagged reverse transcription (STRT)',
+                                'genes': Y.columns,
+                                'labels': labels,
+                                'datadf': data,
+                                'infodf': info}, dataset)
+
+def singlecell_rna_seq_deng(dataset='singlecell_deng'):
+    if not data_available(dataset):
+        download_data(dataset)
+
+    from pandas import read_csv
+    dir_path = os.path.join(data_path, dataset)
+
+    # read the info .soft
+    filename = os.path.join(dir_path, 'GSE45719_series_matrix.txt.gz')
+    info = read_csv(filename, sep='\t', skiprows=0, compression='gzip', header=None, nrows=29, index_col=0)
+    summary = info.loc['!Series_summary'][1]
+    design = info.loc['!Series_overall_design']
+
+    # only take samples:
+    sample_info = read_csv(filename, sep='\t', skiprows=30, compression='gzip', header=0, index_col=0).T
+    sample_info.columns = sample_info.columns.to_series().apply(lambda row: row[len("!Sample_"):])
+    sample_info.columns.name = sample_info.columns.name[len("!Sample_"):]
+    sample_info = sample_info[['geo_accession', 'characteristics_ch1',  'description']]
+    sample_info = sample_info.ix[:, np.r_[0:3, 5:sample_info.shape[1]]]
+    c = sample_info.columns.to_series()
+    c[1:4] = ['strain', 'cross', 'developmental_stage']
+    sample_info.columns = c
+
+    # Extract the tar file
+    filename = os.path.join(dir_path, 'GSE45719_Raw.tar')
+    with tarfile.open(filename, 'r') as files:
+        data = None
+        gene_info = None
+        message = ''
+        members = files.getmembers()
+        overall = len(members)
+        for i, file_info in enumerate(members):
+            f = files.extractfile(file_info)
+            inner = read_csv(f, sep='\t', header=0, compression='gzip', index_col=0)
+            sys.stdout.write(' '*(len(message)+1) + '\r')
+            sys.stdout.flush()
+            message = "{: >7.2%}: Extracting: {}".format(float(i+1)/overall, file_info.name[:20]+"...txt.gz")
+            sys.stdout.write(message)
+            if data is None:
+                data = inner.RPKM.to_frame()
+                data.columns = [file_info.name[:-18]]
+                gene_info = inner.Refseq_IDs.to_frame()
+                gene_info.columns = [file_info.name[:-18]]
+            else:
+                data[file_info.name[:-18]] = inner.RPKM
+                gene_info[file_info.name[:-18]] = inner.Refseq_IDs
+
+    # Strip GSM number off data index
+    rep = re.compile('GSM\d+_')
+    data.columns = data.columns.to_series().apply(lambda row: row[rep.match(row).end():])
+    data = data.T
+
+    # make sure the same index gets used
+    sample_info.index = data.index
+
+    # get the labels from the description
+    rep = re.compile('fibroblast|\d+-cell|embryo|liver|blastocyst|blastomere|zygote', re.IGNORECASE)
+    labels = sample_info.developmental_stage.apply(lambda row: " ".join(rep.findall(row)))
+
+    sys.stdout.write(' '*len(message) + '\r')
+    sys.stdout.flush()
+    print "Read Archive {}".format(files.name)
+
+    return data_details_return({'Y': data,
+                                'series_info': info,
+                                'sample_info': sample_info,
+                                'gene_info': gene_info,
+                                'summary': summary,
+                                'design': design,
+                                'genes': data.columns,
+                                'labels': labels,
+                                }, dataset)
+
+
 def swiss_roll_1000():
     return swiss_roll(num_samples=1000)
 

GPy/util/misc.py

@@ -90,6 +90,8 @@ Convert an arbitrary number of parameters to :class:ndarray class objects. This
 converting parameter objects to numpy arrays, when using scipy.weave.inline routine.
 In scipy.weave.blitz there is no automatic array detection (even when the array inherits
 from :class:ndarray)"""
+    import warnings
+    warnings.warn("Please use param.values, as this function will be deprecated in the next release.", DeprecationWarning)
     assert len(param) > 0, "At least one parameter needed"
     if len(param) == 1:
         return param[0].view(np.ndarray)