diff options
author | zsloan | 2018-02-13 18:03:38 +0000 |
---|---|---|
committer | zsloan | 2018-02-13 18:03:38 +0000 |
commit | 85b8ecc3d6cb44a7a45e942c4ff353add54be7fa (patch) | |
tree | e873fef43ad045ab652c50540520692c46cadc9b | |
parent | 28adaeb4b00cf88b2057e8c4400c4803cd413101 (diff) | |
parent | f44a18ccd4c45ab7fd2179c9000d1bf836e3f654 (diff) | |
download | genenetwork2-85b8ecc3d6cb44a7a45e942c4ff353add54be7fa.tar.gz |
Resolved conflict
-rw-r--r-- | wqflask/wqflask/correlation/show_corr_results.py | 96 |
1 files changed, 73 insertions, 23 deletions
diff --git a/wqflask/wqflask/correlation/show_corr_results.py b/wqflask/wqflask/correlation/show_corr_results.py index bb109f60..c072cf82 100644 --- a/wqflask/wqflask/correlation/show_corr_results.py +++ b/wqflask/wqflask/correlation/show_corr_results.py @@ -75,6 +75,46 @@ def print_mem(stage=""): mem = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss #print("{}: {}".format(stage, mem/1024)) +def is_float(value): + try: + float(value) + return True + except: + return False + +def is_int(value): + try: + int(value) + return True + except: + return False + +def is_str(value): + if value is None: + return False + try: + str(value) + return True + except: + return False + +def get_float(vars,name,default=None): + if name in vars: + if is_float(vars[name]): + return float(vars[name]) + return None + +def get_int(vars,name,default=None): + if name in vars: + if is_int(vars[name]): + return float(vars[name]) + return default + +def get_string(vars,name,default=None): + if name in vars: + if not vars[name] is None: + return str(vars[name]) + return default class AuthException(Exception): pass @@ -96,7 +136,19 @@ class CorrelationResults(object): # get trait list from db (database name) # calculate correlation with Base vector and targets - print("TESTING...") + # Check parameters + assert('corr_type' in start_vars) + assert(is_str(start_vars['corr_type'])) + assert('dataset' in start_vars) + # assert('group' in start_vars) permitted to be empty? + assert('corr_sample_method' in start_vars) + assert('corr_samples_group' in start_vars) + assert('corr_dataset' in start_vars) + assert('min_expr' in start_vars) + assert('corr_return_results' in start_vars) + if 'loc_chr' in start_vars: + assert('min_loc_mb' in start_vars) + assert('max_loc_mb' in start_vars) with Bench("Doing correlations"): if start_vars['dataset'] == "Temp": @@ -115,6 +167,7 @@ class CorrelationResults(object): self.sample_data = {} self.corr_type = start_vars['corr_type'] self.corr_method = start_vars['corr_sample_method'] +<<<<<<< HEAD if 'min_expr' in start_vars: if start_vars['min_expr'] != "": self.min_expr = float(start_vars['min_expr']) @@ -129,20 +182,19 @@ class CorrelationResults(object): self.p_range_upper = float(start_vars['p_range_upper']) except: self.p_range_upper = 1.00 +======= + self.min_expr = get_float(start_vars,'min_expr') + self.p_range_lower = get_float(start_vars,'p_range_lower',-1.0) + self.p_range_upper = get_float(start_vars,'p_range_upper',1.0) +>>>>>>> f44a18ccd4c45ab7fd2179c9000d1bf836e3f654 if ('loc_chr' in start_vars and 'min_loc_mb' in start_vars and 'max_loc_mb' in start_vars): - self.location_chr = start_vars['loc_chr'] - if start_vars['min_loc_mb'].isdigit(): - self.min_location_mb = start_vars['min_loc_mb'] - else: - self.min_location_mb = None - if start_vars['max_loc_mb'].isdigit(): - self.max_location_mb = start_vars['max_loc_mb'] - else: - self.max_location_mb = None + self.location_chr = get_string(start_vars,'loc_chr') + self.min_location_mb = get_int(start_vars,'min_loc_mb') + self.max_location_mb = get_int(start_vars,'max_loc_mb') self.get_formatted_corr_type() self.return_number = int(start_vars['corr_return_results']) @@ -190,7 +242,7 @@ class CorrelationResults(object): else: for trait, values in self.target_dataset.trait_data.iteritems(): self.get_sample_r_and_p_values(trait, values) - + elif self.corr_type == "lit": self.trait_geneid_dict = self.dataset.retrieve_genes("GeneId") lit_corr_data = self.do_lit_correlation_for_all_traits() @@ -571,7 +623,7 @@ class CorrelationResults(object): self.this_trait_vals.append(sample_value) target_vals.append(target_sample_value) - self.this_trait_vals, target_vals, num_overlap = corr_result_helpers.normalize_values(self.this_trait_vals, target_vals) + self.this_trait_vals, target_vals, num_overlap = corr_result_helpers.normalize_values(self.this_trait_vals, target_vals) #ZS: 2015 could add biweight correlation, see http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3465711/ if self.corr_method == 'pearson': @@ -581,8 +633,8 @@ class CorrelationResults(object): if num_overlap > 5: self.correlation_data[trait] = [sample_r, sample_p, num_overlap] - - + + """ correlations = [] @@ -680,8 +732,8 @@ class CorrelationResults(object): method=self.method) return trait_list - """ - + """ + def do_tissue_corr_for_all_traits_2(self): """Comments Possibly Out of Date!!!!! @@ -1096,7 +1148,7 @@ class CorrelationResults(object): totalTraits = len(traits) #XZ, 09/18/2008: total trait number return traits - + def calculate_corr_for_all_tissues(self, tissue_dataset_id=None): symbol_corr_dict = {} @@ -1136,7 +1188,7 @@ class CorrelationResults(object): values_2.append(target_value) correlation = calCorrelation(values_1, values_2) self.correlation_data[trait] = correlation - + def getFileName(self, target_db_name): ### dcrowell August 2008 """Returns the name of the reference database file with which correlations are calculated. Takes argument cursor which is a cursor object of any instance of a subclass of templatePage @@ -1151,7 +1203,7 @@ class CorrelationResults(object): return FileName def do_parallel_correlation(self, db_filename, num_overlap): - + #XZ, 01/14/2009: This method is for parallel computing only. #XZ: It is supposed to be called when "Genetic Correlation, Pearson's r" (method 1) #XZ: or "Genetic Correlation, Spearman's rho" (method 2) is selected @@ -1331,7 +1383,7 @@ class CorrelationResults(object): z_value = z_value*math.sqrt(nOverlap-3) sample_p = 2.0*(1.0 - reaper.normp(abs(z_value))) - correlation_data[traitdataName] = [sample_r, sample_p, nOverlap] + correlation_data[traitdataName] = [sample_r, sample_p, nOverlap] # traitinfo = [traitdataName, sample_r, nOverlap] # allcorrelations.append(traitinfo) @@ -1339,7 +1391,7 @@ class CorrelationResults(object): return correlation_data # return allcorrelations - + datasetFile = open(webqtlConfig.GENERATED_TEXT_DIR+db_filename,'r') print("Invoking parallel computing") @@ -1396,5 +1448,3 @@ class CorrelationResults(object): # for one_result in results: # for one_traitinfo in one_result: # allcorrelations.append( one_traitinfo ) - - |