# M is multi class, we want to remove those rows.
keep_index = np.where(labels != 2)

labels = labels[keep_index]
M = M[keep_index]


if False:
    for x in describe_cols(M):
        print x

if False:
    plot_correlation_scatter_plot(M)
    plot_correlation_matrix(M)
    plot_kernel_density(M["f0"])  # no designation of col name
    plot_box_plot(M["f0"])  # no designation of col name


if False:
    from eights.generate import val_between, where_all_are_true, append_cols  # val_btwn, where

    # generate a composite rule
    M = where_all_are_true(
        M,
        [
            {"func": val_between, "col_name": "f0", "vals": (3.5, 5.0)},
            {"func": val_between, "col_name": "f1", "vals": (2.7, 3.1)},
        ],
        "a new col_name",
    )
 def test_plot_kernel_density(self):
     np.random.seed(0)
     data = np.random.normal(size=(1000,))
     fig = comm.plot_kernel_density(data, verbose=False)
     self.add_fig_to_report(fig, 'plot_kernel_density')
Beispiel #3
0
M = cast_np_nd_to_sa(M)

#M is multi class, we want to remove those rows.
keep_index = np.where(labels != 2)

labels = labels[keep_index]
M = M[keep_index]

if False:
    for x in describe_cols(M):
        print x

if False:
    plot_correlation_scatter_plot(M)
    plot_correlation_matrix(M)
    plot_kernel_density(M['f0'])  #no designation of col name
    plot_box_plot(M['f0'])  #no designation of col name

if False:
    from eights.generate import val_between, where_all_are_true, append_cols  #val_btwn, where
    #generate a composite rule
    M = where_all_are_true(M, [{
        'func': val_between,
        'col_name': 'f0',
        'vals': (3.5, 5.0)
    }, {
        'func': val_between,
        'col_name': 'f1',
        'vals': (2.7, 3.1)
    }], 'a new col_name')
Beispiel #4
0
 def test_plot_kernel_density(self):
     np.random.seed(0)
     data = np.random.normal(size=(1000, ))
     fig = comm.plot_kernel_density(data, verbose=False)
     self.add_fig_to_report(fig, 'plot_kernel_density')
Beispiel #5
0
#make this problem binary
labels = np.array([0 if x < np.average(labels) else 1 for x in labels])
dtype = np.dtype({'names':  col_names,'formats': [float] * (len(col_names)+1)})
M = cast_np_nd_to_sa(np.array([x[:-1] for x in data[1:]],dtype='float'), dtype)



import pdb; pdb.set_trace()
if False:
    for x in describe_cols(M):
        print x

if False:
   plot_correlation_scatter_plot(M) 
   plot_correlation_matrix(M)
   plot_kernel_density(M['f0']) #no designation of col name
   plot_box_plot(M['f0']) #no designation of col name




exp = run_std_classifiers(M,labels)
exp.make_csv()

import pdb; pdb.set_trace()