Fix a very important error; continue aggregation

py/agg.py

@@ -2,21 +2,23 @@
 import pandas as p
 
 def aggregator(widedf, clusdf):
-    clusters = clusdf.cluster.unique()
+    clusters = clusdf['cluster'].unique()
     clusters.sort()
     aggv = {}
     qlow  = lambda x: x.quantile(0.250)
     qhigh = lambda x: x.quantile(0.750)
     for c in clusters:
-        icps = clusters[clusters.cluster == c].icp_id.values
+        icps = clusdf[clusdf.cluster == c].icp_id.values
         subdf = widedf[icps]
-        agged = subdf.agg('median', 'mean', qlow, qhigh)
+        agged = subdf.agg(func = 'median', axis = 1)
         print(agged)
 
 
 def main():
-    wd = p.read_pickle()
-    cd = p.read_pickle()
+    wd = p.read_pickle("../data/2017-5k-wide.pkl")
+    cd = p.read_pickle("../data/5kclustable.pkl")
+    aggregator(wd, cd)
+
 
 
 if __name__ == "__main__":

py/clustering.py

@@ -72,7 +72,7 @@ def dendro(lobj, clustdf, numclusts, icps, fname):
 def main():
     parser = ArgumentParser(description='Cluster from pre-existing distance correlation matrix in pickled dataframe')
     parser.add_argument("-i", "--input",  dest="input",  help = "input pickle path; default: ../data/5kdcorrmatrix.pkl",  metavar="[PATH]", default = "../data/5kdcorrmatrix.pkl")
-    parser.add_argument("-o", "--output", dest="output", help = "output pickle path; default: ../data/5kdcorrmatrix.pkl",  metavar="[PATH]", default = "../data/5kdcorrmatrix.pkl")
+    parser.add_argument("-o", "--output", dest="output", help = "output pickle path; default: ../data/5kdclustable.pkl",  metavar="[PATH]", default = "../data/5kdclustable.pkl")
     parser.add_argument("--method", dest="method", help = "clustering method; default 'ward'", metavar = "[METHOD]", default = "ward")
     parser.add_argument("--clusters",  dest="numclusters",  help = "number of clusters; default: 9", metavar = "[NUM]", default = 9, type = int)
     parser.add_argument("-d", "--dendrogram", dest = "incdendro", help = "draw dendrogram", action ="store_true")