Fix matplotlib errors; download the sample data

py/clustering.py

@@ -1,6 +1,8 @@
 from util import getQuery, pickleQuery
 import numpy as np
 import pandas as p
+import matplotlib
+matplotlib.use('agg')
 import matplotlib.pyplot as plt
 import seaborn as sns
 from scipy.spatial.distance import squareform

py/downkwh.py

@@ -1,47 +1,13 @@
 from util import getQuery, pickleQuery, getkwh
 import pandas as p
-import matplotlib.pyplot as plt
-import seaborn as sns
+# import matplotlib
+# matplotlib.use('agg')
+# import matplotlib.pyplot as plt
+# import seaborn as sns
 
-# query = """
-# SELECT comb.icp_id, comb.read_time, COALESCE(kwh_tot, 0) AS kwh_tot
-# FROM
-# (
-#     SELECT read_time, icp_id
-#     FROM
-#     (
-#         SELECT read_time 
-#         FROM GENERATE_SERIES('2017-01-01 00:30:00'::timestamp, '2017-02-01 00:00:00'::timestamp, 
-#             '30 minutes'::interval) read_time
-#     ) AS tsdata CROSS JOIN
-#     (
-#         SELECT *
-#         FROM
-#         (
-#             SELECT icp_id, COUNT(DISTINCT read_date) AS data_days 
-#             FROM coup_prd.coupdatamaster
-#             WHERE read_date >= to_date('01/01/2017','dd/mm/yyyy')
-#                 AND read_date <  to_date('01/01/2018','dd/mm/yyyy')
-#                 AND content_code = 'UN'
-#                 AND icp_id LIKE '%%19'
-#             GROUP BY icp_id
-#         ) AS cir 
-#         WHERE data_days >= 360
-#     ) AS qual_icp
-# ) AS comb
-# LEFT JOIN
-# (
-#     SELECT *, read_date + CONCAT(period / 2, ':', period %% 2 * 30, ':00')::time AS read_time
-#     FROM public.coup_tall_jan
-# ) AS tall_timestamp 
-# ON comb.read_time = tall_timestamp.read_time AND comb.icp_id = tall_timestamp.icp_id;
-# """
-# 
-# pickleQuery(query, "../data/jan19s.pkl")
-
-kwhdata = getkwh('2018-01-01', '2018-04-01', '2018-01-01 00:30:00', '2018-04-01 00:00:00', '%%1')
+kwhdata = getkwh('2017-01-01', '2018-01-01', '2017-01-01 00:30:00', '2018-01-01 00:00:00', '%%1')
 
 print(kwhdata.info())
 
 print("Pickling")
-kwhdata.to_pickle("../data/2018-proj-sample.pkl")
+kwhdata.to_pickle("../data/2017-sample.pkl")