ampli/py/clustering.py

from util import getQuery, pickleQuery
import pandas as p
import matplotlib.pyplot as plt
import seaborn as sns


# 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()

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('2017-04-01 00:30:00'::timestamp, '2017-05-01 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'
            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_april
) AS tall_timestamp 
ON comb.read_time = tall_timestamp.read_time AND comb.icp_id = tall_timestamp.icp_id;
"""

pickleQuery(query, "April.pkl")