Refactor out filenames for data pickles

py/clustering.py

@@ -6,37 +6,13 @@ import seaborn as sns
 from scipy.spatial.distance import squareform
 from scipy.cluster.hierarchy import dendrogram, linkage, cophenet, fcluster
 
-
-# query = """
-# SELECT *, read_date + CONCAT(period / 2, ':', period %% 2 * 30, ':00')::time AS read_time
-# FROM public.coup_tall_april WHERE icp_id LIKE (%s) AND read_date = to_date(%s, 'dd/mm/yyyy') 
-# ORDER BY icp_id, read_time;
-# """
-# 
-# qparams = ['%%1117', '20/04/2017']
-
-# query = """
-# SELECT read_date, period, AVG(kwh_tot) AS average
-# FROM public.coup_tall_april
-# GROUP BY read_date, period
-# ORDER BY read_date, period;
-# """
-# 
-# qparams = []
-# 
-# df = getQuery(query, qparams)
-# 
-# print(df.info())
-# 
-# sns.set()
-# 
-# #sns.lineplot(x = 'read_time', y = 'kwh_tot', hue = 'icp_id', data = df)
-# sns.lineplot(x = 'period', y = 'average', hue = 'read_date', data = df)
-# 
-# plt.show()
+Sourcedata =   '../data/2017-sample.pkl'
+lableddata =   '../data/9-clusters.pkl'
+aggdata =      '../data/9-clusters.agg.pkl'
+clustertable = '../data/9-clusters-sample-table.pkl'
 
 numclusts = 9
-df = p.read_pickle('../data/2016-17-sample.pkl')
+df = p.read_pickle(Sourcedata)
 dforig = df
 
 # print(df)
@@ -68,6 +44,7 @@ print(clusts)
 print(cmat.index.values)
 clustdf = p.DataFrame({'icp_id' : cmat.index.values, 'cluster' : clusts})
 print(clustdf)
+clustdf.to_pickle(clustertable)
 mdf = p.merge(clustdf, dforig, on = 'icp_id', how = 'left')
 print(mdf)
 print(mdf.info())
@@ -84,8 +61,8 @@ print(mdagg.info())
 print(mdagg.describe())
 # mdf.to_csv('~/windows/Documents/clusters-ward.csv')
 print("Saving")
-mdf.to_pickle('../data/9-clusters-1617.pkl')
-mdagg.to_pickle('../data/9-clusters-1617.agg.pkl')
+mdf.to_pickle(lableddata)
+mdagg.to_pickle(aggdata)
 print("saved")
 
 # Algorithm via 
@@ -115,12 +92,12 @@ dendrogram(
 )
 plt.show()
 
-# sns.set()
-# 
-# f, axes = plt.subplots(3,3)
-# 
-# for i, c in enumerate(clabs):
-#     fds = mdagg[mdagg.cluster == c]
-#     sns.lineplot(x = 'read_time', y = 'kwh_tot_mean', color = cpal[c], ax = axes[i//3][i%3], data = fds)
-#     axes[i//3][i%3].fill_between(fds.read_time.dt.to_pydatetime(), fds.kwh_tot_CI_low, fds.kwh_tot_CI_high, alpha = 0.1, color = cpal[c])
-# plt.show()
+sns.set()
+
+f, axes = plt.subplots(3,3)
+
+for i, c in enumerate(clabs):
+    fds = mdagg[mdagg.cluster == c]
+    sns.lineplot(x = 'read_time', y = 'kwh_tot_mean', color = cpal[c], ax = axes[i//3][i%3], data = fds)
+    axes[i//3][i%3].fill_between(fds.read_time.dt.to_pydatetime(), fds.kwh_tot_CI_low, fds.kwh_tot_CI_high, alpha = 0.1, color = cpal[c])
+plt.show()