Linear model: used[kW] = -15.787539178999925 * (Humidity) + 42.2943941122893 The MSE is:1.7615477909956858 and the RMSE is: 1.3272331336263745 The F-Score is: 0.015432098765432096 Washer at Day: 10.092497203000006 and Washer at Night: 43.63436277900002 Cellar Lights at Day: 71.80866663400005 and Cellar Lights at Night: 121.43663938300006 We see that the energy readings for both these devices are much greater than their daylight counter
parts. While it seems more obvious that lights for the cellar are used more towards the night, it s
eems that even the washers are used more in the night time. We can assume the schedules of people a
re more aligned to use these devices towards the night time. In [1]:
from
PIL import
Image from
statistics import
*
import
pandas as
pd import
numpy as
np import
matplotlib.pyplot as
plt In [2]:
import
as
file In [3]:
weather_file =
pd
.
read_csv
(
"weather_data.csv"
)
#We import the weather_data file
In [4]:
energy_file =
pd
.
read_csv
(
"energy_data.csv"
) #We import the energy_data file
In [5]:
dates =
file
.
generate
(
energy_file
,
weather_file
) #here we process the two files, merge the weather_data with energy_data file
#and create dataForDecember file that has only the collected data for December
In [6]:
mergedData =
pd
.
read_csv
(
"mergedData.csv"
) #We read our created file for the merged data
In [7]:
dataForDecember =
pd
.
read_csv
(
"dataForDecember.csv"
) #We read our created file for the data of December
In [8]:
file
.
generateHeatMap
(
dataForDecember
) In [9]:
file
.
LReg
(
dataForDecember
)
In [10]:
file
.
decData
(
dataForDecember
,
dates
) In [11]:
file
.
handleData
(
energy_file
) #We take into account Washer and Cellar Lights Energy
In [ ]:
