def test_continuousMetaAnalysis(self):
# assert result is not None
studies = self.model.get_studies_in_current_order()
data_location = {'experimental_mean': 2, 'effect_size': 18, 'experimental_std_dev': 5, 'experimental_sample_size': 1, 'control_std_dev': 5, 'control_sample_size': 1, 'variance': 19, 'control_mean': 4}
data_type = CONTINUOUS
python_to_R.dataset_to_simple_continuous_robj(model=self.model,
included_studies=studies,
data_location=data_location,
data_type=data_type,
covs_to_include=[])
method = "continuous.random"
params = {'conf.level': 95.0, 'digits': 3, 'fp_col2_str': u'[default]', 'fp_show_col4': False, 'fp_xlabel': u'[default]', 'fp_col4_str': u'Ev/Ctrl', 'fp_xticks': '[default]', 'fp_col3_str': u'Ev/Trt', 'fp_show_col3': False, 'fp_show_col2': True, 'fp_show_col1': True, 'fp_plot_lb': '[default]', 'fp_outpath': u'./r_tmp/forest.png', 'rm.method': 'DL', 'fp_plot_ub': '[default]', 'fp_col1_str': u'Studies', 'measure': 'SMD', 'fp_show_summary_line': True}
result = python_to_R.run_continuous_ma(function_name=method,
params=params)
self.assertIsNotNone(result, "Result is unexpectedly none!")
def populate_cbo_box(self):
print("populating combo box")
self.method_cbo_box.clear()
# we first build an R object with the current data. this is to pass off
# to the R side to check the feasibility of the methods over the current data.
# i.e., we do not display methods that cannot be performed over the
# current data.
tmp_obj_name = "tmp_obj"
covs_to_include = []
#if self.mode==SUBGROUP_MODE:
# covs_to_include = [self.wizard().get_subgroup_variable(),]
covs_to_include = []
if OMA_CONVENTION[self.data_type] == "binary":
python_to_R.dataset_to_simple_binary_robj(self.model,
included_studies = self.get_included_studies_in_proper_order(),
data_location = self.data_location,
var_name = tmp_obj_name,
covs_to_include=covs_to_include,
one_arm=False)
elif OMA_CONVENTION[self.data_type] == "continuous":
python_to_R.dataset_to_simple_continuous_robj(model=self.model,
included_studies=self.get_included_studies_in_proper_order(),
data_location=self.data_location,
data_type=self.data_type,
var_name=tmp_obj_name,
covs_to_include=covs_to_include,
one_arm=False)
self.available_method_d = python_to_R.get_available_methods(
for_data_type=OMA_CONVENTION[self.data_type],
data_obj_name=tmp_obj_name,
metric=self.metric,
funnel_mode=self.funnel_mode)
print "\n\navailable %s methods: %s" % (self.data_type, ", ".join(self.available_method_d.keys()))
method_names = self.available_method_d.keys()
method_names.sort(reverse=True)
for method in method_names:
self.method_cbo_box.addItem(method)
self.current_method = self.available_method_d[str(self.method_cbo_box.currentText())]
self.setup_params()
self.parameter_grp_box.setTitle(self.current_method)
def test_bootstrapped_ma(self):
''' bootstrapped meta analysis '''
studies = self.model.get_studies_in_current_order()
method = "continuous.random"
current_param_vals = {'conf.level': 95.0, 'histogram.xlab': 'Effect Size', 'fp_xticks': '[default]', 'fp_show_col4': False, 'fp_show_col3': False, 'fp_xlabel': u'[default]', 'fp_show_col1': True, 'fp_show_col2': True, 'fp_outpath': u'./r_tmp/forest.png', 'rm.method': 'DL', 'fp_plot_ub': '[default]', 'fp_col1_str': u'Studies', 'measure': 'SMD', 'fp_plot_lb': '[default]', 'bootstrap.plot.path': '/Users/george/git/OpenMEE/r_tmp/bootstrap.png', 'digits': 3, 'fp_col2_str': u'[default]', 'num.bootstrap.replicates': 1000, 'fp_col4_str': u'Ev/Ctrl', 'histogram.title': 'Bootstrap Histogram', 'fp_col3_str': u'Ev/Trt', 'fp_show_summary_line': True, 'bootstrap.type': 'boot.ma'}
data_location = {'experimental_mean': 2, 'effect_size': 18, 'experimental_std_dev': 5, 'experimental_sample_size': 1, 'control_std_dev': 5, 'control_sample_size': 1, 'variance': 19, 'control_mean': 4}
meta_f_str = "bootstrap.continuous"
python_to_R.dataset_to_simple_continuous_robj(model=self.model,
included_studies=studies,
data_location=data_location,
data_type=CONTINUOUS,
covs_to_include=[])
result = python_to_R.run_meta_method(meta_function_name = meta_f_str,
function_name = method,
params = current_param_vals)
# assert result is not None
self.assertIsNotNone(result, "Result is unexpectedly none!")
def test_subgroup(self):
''' subgroup meta analysis '''
studies = self.model.get_studies_in_current_order()
method = "continuous.random"
current_param_vals = {'conf.level': 95.0, 'digits': 3, 'fp_col2_str': u'[default]', 'fp_show_col4': False, 'fp_xlabel': u'[default]', 'fp_col4_str': u'Ev/Ctrl', 'fp_xticks': '[default]', 'fp_col3_str': u'Ev/Trt', 'fp_show_col3': False, 'fp_show_col2': True, 'fp_show_col1': True, 'fp_plot_lb': '[default]', 'fp_outpath': u'./r_tmp/forest.png', 'rm.method': 'DL', 'fp_plot_ub': '[default]', 'fp_col1_str': u'Studies', 'cov_name': 'Gender', 'measure': 'SMD', 'fp_show_summary_line': True}
data_location = {'experimental_mean': 2, 'effect_size': 18, 'experimental_std_dev': 5, 'experimental_sample_size': 1, 'control_std_dev': 5, 'control_sample_size': 1, 'variance': 19, 'control_mean': 4}
meta_f_str = "subgroup.ma.continuous"
cov_names_to_include = ["Gender",]
covs_to_include = get_covs_from_names(cov_names_to_include, model=self.model)
python_to_R.dataset_to_simple_continuous_robj(model=self.model,
included_studies=studies,
data_location=data_location,
data_type=CONTINUOUS,
covs_to_include=covs_to_include)
result = python_to_R.run_meta_method(meta_function_name = meta_f_str,
function_name = method,
params = current_param_vals)
# assert result is not None
self.assertIsNotNone(result, "Result is unexpectedly none!")
