Start agg py

py/agg.py

@@ -0,0 +1,23 @@
+# Aggregrate given clusters
+import pandas as p
+
+def aggregator(widedf, clusdf):
+    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
+        subdf = widedf[icps]
+        agged = subdf.agg('median', 'mean', qlow, qhigh)
+        print(agged)
+
+
+def main():
+    wd = p.read_pickle()
+    cd = p.read_pickle()
+
+
+if __name__ == "__main__":
+    main()