Saving clustered datasets

py/clustering.py

@@ -80,6 +80,10 @@ print(mdagg)
 print(mdagg.info())
 print(mdagg.describe())
 # mdf.to_csv('~/windows/Documents/clusters-ward.csv')
+print("Saving")
+mdf.to_pickle('../data/9-clusters.pkl')
+mdagg.to_pickle('../data/9-clusters.agg.pkl')
+print("saved")
 
 # Algorithm via 
 # <https://stackoverflow.com/questions/38153829/custom-cluster-colors-of-scipy-dendrogram-in-python-link-color-func>
@@ -108,14 +112,12 @@ print(mdagg.describe())
 # )
 # plt.show()
 
-sns.set()
-
-f, axes = plt.subplots(3,3)
-print(f)
-print(axes)
-
-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()