ampli/py/clusAssign.py

# An algorithm for assigning a dataset to pre-existing clusters
import pandas as p

# Pre-existing aggregated clusters
clusfile = '../data/9-clusters.agg.pkl'

# A new dataset
ndsfile = '../data/2016-17-sample.pkl'


clusdf = p.read_pickle(clusfile)
clusdf = clusdf.pivot(index = 'read_time', columns = 'cluster', values = 'kwh_tot_mean')
del clusdf.columns.name
print(clusdf.info())



newdf = p.read_pickle(ndsfile).pivot(index = 'read_time', 
                                     columns = 'icp_id', 
                                     values = 'kwh_tot').loc[clusdf.index, :]
print(newdf)
print(newdf.info())