def execute_binFeatures(self,analysis_id_I,features_I=[],n_bins_I=[]):
'''bin features of continuous data
INPUT:
analysis_id_I = string,
features_I = [] of string, e.g. ['mutation_position','mutation_frequency']
n_bins_I = int, the number of bins per feature (if bins is empty, bins will be calculated)
OUTPUT:
'''
data_O = [];
calculatehistogram = calculate_histogram();
#get the analysis information
experiment_ids,sample_names = [],[];
experiment_ids,sample_names = self.get_experimentIDAndSampleName_analysisID_dataStage01ResequencingAnalysis(analysis_id_I);
#bin each feature
for features_cnt,features in enumerate(features_I):
n_bins = 50;
calc_bins_I = True;
if n_bins_I and n_bins_I[features_cnt]:
n_bins = n_bins_I[features_cnt];
calc_bins_I = False;
if features == 'mutation_position':
data_hist = [];
#get all the data for the analysis
for sn_cnt,sn in enumerate(sample_names):
data_tmp = [];
data_tmp = self.get_AllMutationPositions_experimentIDAndSampleName_dataStage01ResequencingMutationsAnnotated(experiment_ids[sn_cnt],sn);
if data_tmp:
data_hist.extend(data_tmp);
#make the bins for the histogram
x_O,dx_O,y_O = calculatehistogram.histogram(data_I=data_hist,n_bins_I=n_bins,calc_bins_I=calc_bins_I);
tmp = self.record_histogram(analysis_id_I,features,'',x_O,dx_O,y_O);
data_O.extend(tmp);
elif features == 'mutation_frequency':
data_hist = [];
#get all the data for the analysis
for sn_cnt,sn in enumerate(sample_names):
data_tmp = [];
data_tmp = self.get_AllMutationFrequencies_experimentIDAndSampleName_dataStage01ResequencingMutationsAnnotated(experiment_ids[sn_cnt],sn);
if data_tmp:
data_hist.extend(data_tmp);
#make the bins for the histogram
x_O,dx_O,y_O = calculatehistogram.histogram(data_I=data_hist,n_bins_I=n_bins,calc_bins_I=calc_bins_I);
tmp = self.record_histogram(analysis_id_I,features,'',x_O,dx_O,y_O);
data_O.extend(tmp);
else:
print('feature not recongnized');
#add the data to the database
self.add_dataStage01ResequencingHistogram(data_O);
def export_dataStage02PhysiologySampledPoints_js(self,
analysis_id_I,
simulation_ids_I = [],
rxn_ids_I = [],
query_I={},
data_dir_I='tmp'
):
'''Visualize the sampling distribution
DESCRIPTION:
tile1=filtermenu
tile2=sampling distribution
tile3=table
'''
calculatehistogram = calculate_histogram();
physiology_analysis_query = stage02_physiology_analysis_query(self.session,self.engine,self.settings);
data_sampledPoints_O = [];
data_O = [];
#get the analysis info
simulation_ids = physiology_analysis_query.get_simulationID_analysisID_dataStage02PhysiologyAnalysis(analysis_id_I);
if simulation_ids_I:
simulation_ids = [s for s in simulation_ids if s in simulation_ids_I];
for simulation_id in simulation_ids:
#get the data_dirs for the simulations and read in the points
sampledPoints = self.get_rows_simulationID_dataStage02PhysiologySampledPoints(simulation_id);
sampledPoints = sampledPoints[0];
data_sampledPoints_O.append(sampledPoints);
# get simulation information
simulation_info_all = [];
simulation_info_all = self.get_rows_simulationIDAndSimulationType_dataStage02PhysiologySimulation(simulation_id,'sampling');
if not simulation_info_all:
print('simulation not found!')
return;
simulation_info = simulation_info_all[0]; # unique constraint guarantees only 1 row will be returned
# get simulation parameters
simulation_parameters_all = [];
simulation_parameters_all = self.get_rows_simulationID_dataStage02PhysiologySamplingParameters(simulation_id);
if not simulation_parameters_all:
print('simulation not found!')
return;
simulation_parameters = simulation_parameters_all[0]; # unique constraint guarantees only 1 row will be returned
#fill the sampledData with the actual points
sampling = cobra_sampling(model_I=None,data_dir_I = sampledPoints['data_dir'],loops_I=sampledPoints['infeasible_loops']);
if simulation_parameters['sampler_id']=='gpSampler':
# load the results of sampling
sampling.get_points_matlab(matlab_data=None,sampler_model_name='sampler_out');
sampling.remove_loopsFromPoints();
elif simulation_parameters['sampler_id']=='optGpSampler':
sampling.get_points_json();
sampling.remove_loopsFromPoints();
else:
print('sampler_id not recognized');
#store the sampledPoints
for k,v in sampling.points.items():
if rxn_ids_I:
if not k in rxn_ids_I:
continue;
n_bins = 100;
calc_bins_I = False;
x_O,dx_O,y_O = calculatehistogram.histogram(data_I=v,n_bins_I=n_bins,calc_bins_I=calc_bins_I);
for i,b in enumerate(x_O):
tmp = {
'simulation_id':simulation_id,
'rxn_id':k,
#'feature_units':feature_units,
'bin':b,
'bin_width':dx_O[i],
'frequency':int(y_O[i]),
'used_':True,
'comment_':None};
data_O.append(tmp);
#data_listDict = listDict();
#data_listDict.set_dictList(sampling.points);
#data_listDict.convert_dictList2DataFrame();
#points, rxn_ids = data_listDict.get_flattenedDataAndColumnLabels();
#data_listDict.clear_allData();
#data_listDict.add_column2DataFrame('rxn_id',rxn_ids);
#data_listDict.add_column2DataFrame('points',points);
#data_listDict.add_column2DataFrame('simulation_id',simulation_id);
#data_listDict.convert_dataFrame2ListDict();
#data_O.extend(data_listDict.get_listDict());
#make the DDT histograms
# visualization parameters
data1_keys = ['simulation_id',
'rxn_id',
'bin',
];
data1_nestkeys = [
'bin'
];
data1_keymap = {
'xdata':'bin',
'ydata':'frequency',
'serieslabel':'simulation_id',
'featureslabel':'bin',
'tooltiplabel':'rxn_id',
'ydatalb':None,
'ydataub':None};
nsvgtable = ddt_container_filterMenuAndChart2dAndTable();
nsvgtable.make_filterMenuAndChart2dAndTable(
data_filtermenu=data_O,
data_filtermenu_keys=data1_keys,
data_filtermenu_nestkeys=data1_nestkeys,
data_filtermenu_keymap=data1_keymap,
data_svg_keys=None,
data_svg_nestkeys=None,
data_svg_keymap=None,
data_table_keys=None,
data_table_nestkeys=None,
data_table_keymap=None,
data_svg=None,
data_table=None,
svgtype='verticalbarschart2d_01',
tabletype='responsivetable_01',
svgx1axislabel='',
svgy1axislabel='',
tablekeymap = [data1_keymap],
svgkeymap = [data1_keymap],
formtile2datamap=[0],
tabletile2datamap=[0],
svgtile2datamap=[0], #calculated on the fly
svgfilters=None,
svgtileheader='Sampled points',
tablefilters=None,
tableheaders=None
);
if data_dir_I=='tmp':
filename_str = self.settings['visualization_data'] + '/tmp/ddt_data.js'
elif data_dir_I=='data_json':
data_json_O = nsvgtable.get_allObjects_js();
return data_json_O;
with open(filename_str,'w') as file:
file.write(nsvgtable.get_allObjects());