Save figure instead of showing; download all data

py/clustering.py

@@ -92,7 +92,8 @@ dendrogram(
     link_color_func = lambda x: link_cols[x],
     color_threshold = None
 )
-plt.show()
+# plt.show()
+plt.savefig("../img/sample-9-dendro.png")
 
 sns.set()
 
@@ -102,4 +103,5 @@ 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()
+# plt.show()
+plt.savefig("../img/sample-9-panedtrends.png")

py/downkwh.py

@@ -10,4 +10,4 @@ kwhdata = getkwh('2017-01-01', '2018-01-01', '2017-01-01 00:30:00', '2018-01-01
 print(kwhdata.info())
 
 print("Pickling")
-kwhdata.to_pickle("../data/2017-sample.pkl")
+kwhdata.to_pickle("../data/2017-all.pkl")

py/util.py

@@ -79,7 +79,7 @@ def getkwh(datestart, dateend, timestart, timeend, subset):
             SELECT read_time 
             FROM GENERATE_SERIES(%(tsstart)s::timestamp, %(tsend)s::timestamp, 
                 '30 minutes'::interval) read_time
-        ) AS tsdata CROSS JOIN public.icp_sample
+        ) AS tsdata CROSS JOIN public.best_icp
     ) AS comb
     LEFT JOIN
     (
@@ -97,7 +97,7 @@ def getkwh(datestart, dateend, timestart, timeend, subset):
              and   a.read_date <  to_date(%(dateend)s,'yyyy-mm-dd')
              and   a.content_code  ~ ('UN|CN|EG')
              AND   a.icp_id IN (
-                SELECT icp_id FROM public.icp_sample
+                SELECT icp_id FROM public.best_icp
              )
             GROUP BY 1, 2, 3
         ) AS coup_tall