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()

df = p.read_pickle('../data/April.pkl')

print(df)
print(df.info())