def get_patient_set(self, filters): f1 = list(filters) filter_df = pd.concat(f1, axis=1) clinical_filter = filter_df.dropna().sum(1) == 0 keepers_o = H.true_index(clinical_filter) keepers_o = keepers_o.intersection(self.mut_df.columns) keepers_o = keepers_o.intersection(self.cna_df.columns) return keepers_o
def get_patient_set(self, filters): f1 = list(filters) filter_df = pd.concat(f1, axis=1) clinical_filter = filter_df.dropna().sum(1) == 0 keepers_o = H.true_index(clinical_filter) keepers_o = keepers_o.intersection(self.mut_df.columns) keepers_o = keepers_o.intersection(self.cna_df.columns) keepers_o = keepers_o.intersection(self.surv.unstack().index) keepers_o = keepers_o.intersection(self.rna_df.columns) keepers_o = keepers_o.intersection(self.mirna_df.columns) return keepers_o
def mut_filter(df, rate, binary_cutoff=12): ''' Filter out mutation features, ensuring that a feature is not entirely an artifact of mutation rate. ''' df = df[df.sum(1) >= binary_cutoff] cc = H.screen_feature(rate, rev_kruskal, df) fc_apply = lambda s: fc(s, rate) direction = df.apply(fc_apply, axis=1) direction.name = 'direction' cc = cc.join(direction) cc = cc[cc.direction==False] df = df.ix[H.true_index(cc.p > .01)] df = df.dropna(axis=1) return df
def mut_filter(df, rate, binary_cutoff=12): """ Filter out mutation features, ensuring that a feature is not entirely an artifact of mutation rate. """ get_min_count = lambda s: s.value_counts().min() if len(s.unique()) > 1 else -1 df = df[df.apply(get_min_count, axis=1) > binary_cutoff] cc = H.screen_feature(rate, rev_kruskal, df) fc_apply = lambda s: fc(s, rate) direction = df.apply(fc_apply, axis=1) direction.name = 'direction' cc = cc.join(direction) #cc = cc[cc.direction == False] #return cc df = df.ix[H.true_index((cc.p > .01) | (cc.direction == True))] df = df.dropna(axis=1) return df
def mut_filter(df, rate, binary_cutoff=12): """ Filter out mutation features, ensuring that a feature is not entirely an artifact of mutation rate. """ get_min_count = lambda s: s.value_counts().min() if len(s.unique() ) > 1 else -1 df = df[df.apply(get_min_count, axis=1) > binary_cutoff] cc = H.screen_feature(rate, rev_kruskal, df) fc_apply = lambda s: fc(s, rate) direction = df.apply(fc_apply, axis=1) direction.name = 'direction' cc = cc.join(direction) #cc = cc[cc.direction == False] #return cc df = df.ix[H.true_index((cc.p > .01) | (cc.direction == True))] df = df.dropna(axis=1) return df