def _get_meta_features(self, gene_sets, filter_down):
gs = extract_geneset_pcs(self.df, gene_sets, filter_down)
self.loadings, self.pct_var, pathways = gs
if hasattr(self.global_vars, 'background'):
r = screen_feature(self.global_vars.background, pearson_pandas,
pathways)
pathways = pathways.ix[r.p > 10e-5]
pathways = ((pathways.T - pathways.mean(1)) / pathways.std(1)).T
U, S, pc = frame_svd(pathways)
self.pathways = pathways
self.features['pathways'] = pathways
self.global_vars['pathway_pc1'] = pc[0]
self.global_vars['pathway_pc2'] = pc[1]
self.global_loadings['pathway_pc1'] = U[0]
self.global_loadings['pathway_pc2'] = U[1]
def _get_meta_features(self, gene_sets, filter_down):
gs = extract_geneset_pcs(self.df, gene_sets, filter_down)
self.loadings, self.pct_var, pathways = gs
if hasattr(self.global_vars, 'background'):
r = screen_feature(self.global_vars.background, pearson_pandas,
pathways)
pathways = pathways.ix[r.p > 10e-5]
pathways = ((pathways.T - pathways.mean(1)) / pathways.std(1)).T
U, S, pc = frame_svd(pathways)
self.pathways = pathways
self.features['pathways'] = pathways
self.global_vars['pathway_pc1'] = pc[0]
self.global_vars['pathway_pc2'] = pc[1]
self.global_loadings['pathway_pc1'] = U[0]
self.global_loadings['pathway_pc2'] = U[1]
def _get_real_features(self):
binary, singles, real = extract_features(self.df)
background_df = real.ix[real.index.diff(singles.index)].dropna()
background = extract_pc(background_df, 0)
ss = screen_feature(background['pat_vec'], pearson_pandas, singles)
singles = singles.ix[ss.p > 10e-5]
singles = ((singles.T - singles.mean(1)) / singles.std(1)).T
U, S, pc = frame_svd(singles)
self.features['binary'] = binary
self.features['real'] = singles
self.global_vars['background'] = background['pat_vec']
self.global_vars['filtered_pc1'] = pc[0]
self.global_vars['filtered_pc2'] = pc[1]
self.global_loadings['background'] = background['gene_vec']
self.global_loadings['filtered_pc1'] = U[0]
self.global_loadings['filtered_pc2'] = U[1]
def _get_real_features(self):
binary, singles, real = extract_features(self.df)
background_df = real.ix[real.index.diff(singles.index)].dropna()
background = extract_pc(background_df, 0)
ss = screen_feature(background['pat_vec'], pearson_pandas, singles)
singles = singles.ix[ss.p > 10e-5]
singles = ((singles.T - singles.mean(1)) / singles.std(1)).T
U, S, pc = frame_svd(singles)
self.features['binary'] = binary
self.features['real'] = singles
self.global_vars['background'] = background['pat_vec']
self.global_vars['filtered_pc1'] = pc[0]
self.global_vars['filtered_pc2'] = pc[1]
self.global_loadings['background'] = background['gene_vec']
self.global_loadings['filtered_pc1'] = U[0]
self.global_loadings['filtered_pc2'] = U[1]
def SVC_fill_old(feature, df):
gg = df.apply(lambda s: to_quants(s, std=1) > 0)
diff = screen_feature(feature, chi2_cont_test, gg)
dd = diff[diff.p < .05]
pats = gg.columns.intersection(feature.index)
mat = gg.ix[dd.index]
X = mat.ix[:, pats].T.as_matrix()
Y = (feature)
Y = np.array(Y.ix[pats])
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size=0.35, random_state=5796543)
params = [{'kernel': ['rbf'], 'gamma': [0, .1, .05, .01, 1e-3, 1e-4, 1e-5],
'C': [.1, 1, 10, 100, 1000], 'class_weight': ['auto']},
{'kernel': ['linear'], 'C': [1, 10, 100, 1000],
'class_weight': ['auto']},
{'kernel': ['poly'], 'C': [1, 10, 100, 1000],
'class_weight': ['auto']}]
clf = GridSearchCV(SVC(C=1), params, score_func=auc_score)
clf.fit(X_train, y_train, cv=5);
best = clf.best_estimator_
auc = clf.score(X, Y)
mat_all = gg.ix[mat.index].T.as_matrix()
inferred = best.predict(mat_all)
inferred = pd.Series(inferred, index=gg.columns)
fun = pd.Series(best.decision_function(mat_all)[:, 0], mat.columns)
f = feature.copy()
f = f.ix[inferred.index]
f[f.isnull()] = inferred[f.isnull()]
filled_feature = f.astype(float)
return {'auc': auc, 'model': best, 'decision_function': fun,
'inferred_values': inferred, 'filled_feature': filled_feature}