-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathknn.py
138 lines (105 loc) · 4.84 KB
/
knn.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
import wx
import matplotlib.patches as patches
import pandas as pd
import numpy as np
import utils
k_calc_type = ""
def construct_df(raw):
data = raw
raw['avg'] = raw[['maxC']].mean(axis=1) # NOT USING AVERAGE ANYMORE, WANT TO GET AS WARM AS IT COULD BE.
# FOR THE WORST.
return data
def construct_year_data(df, year):
return df.loc[df['yyyy'] == year]
def get_month_data(data, year, mm): #10oC
df = construct_df(data)
year_data = construct_year_data(df, year)
if year_data.loc[df['mm'] == mm].empty == False:
temp = year_data.loc[df['mm'] == mm].iloc[0]['avg']
else:
temp=0
return temp
def get_month_data_max(data, year, mm): #10oC
df = construct_df(data)
year_data = construct_year_data(df, year)
if year_data.loc[df['mm'] == mm].empty == False:
temp = year_data.loc[df['mm'] == mm].iloc[0]['maxC']
else:
temp = 0
return temp
def get_month_data_min(data, year, mm): #10oC
df = construct_df(data)
year_data = construct_year_data(df, year)
if year_data.loc[df['mm'] == mm].empty == False:
temp = year_data.loc[df['mm'] == mm].iloc[0]['minC']
else:
temp = 0
return temp
def construct_season_avg(data, year, season):
seasons = {
"winter": utils.mean([get_month_data(data, year-1, 12),get_month_data(data, year, 1),get_month_data(data, year, 2)]),
"spring": utils.mean([get_month_data(data, year, 3), get_month_data(data, year, 4), get_month_data(data, year, 5)]),
"summer": utils.mean([get_month_data(data, year, 6), get_month_data(data, year, 7), get_month_data(data, year, 8)]),
"autumn": utils.mean([get_month_data(data, year, 9), get_month_data(data, year, 10), get_month_data(data, year, 11)]),
}
return seasons.get(season) #gets actual value
def construct_season_avg_max(data, year, season):
seasons = {
"winter": utils.mean([get_month_data_max(data, year-1, 12),get_month_data_max(data, year, 1),get_month_data_max(data, year, 2)]),
"spring": utils.mean([get_month_data_max(data, year, 3), get_month_data_max(data, year, 4), get_month_data_max(data, year, 5)]),
"summer": utils.mean([get_month_data_max(data, year, 6), get_month_data_max(data, year, 7), get_month_data_max(data, year, 8)]),
"autumn": utils.mean([get_month_data_max(data, year, 9), get_month_data_max(data, year, 10), get_month_data_max(data, year, 11)]),
}
return seasons.get(season) #gets actual value
def construct_season_avg_min(data, year, season):
seasons = {
"winter": utils.mean([get_month_data_min(data, year-1, 12),get_month_data_min(data, year, 1),get_month_data_min(data, year, 2)]),
"spring": utils.mean([get_month_data_min(data, year, 3), get_month_data_min(data, year, 4), get_month_data_min(data, year, 5)]),
"summer": utils.mean([get_month_data_min(data, year, 6), get_month_data_min(data, year, 7), get_month_data_min(data, year, 8)]),
"autumn": utils.mean([get_month_data_min(data, year, 9), get_month_data_min(data, year, 10), get_month_data_min(data, year, 11)]),
}
return seasons.get(season) #gets actual value
def calculate_knn_mid(data, k, year, season):
k_side = k // 2
k_range=[]
for i in range(k):
if i != k_side:
k_range.append(construct_season_avg(data, year + (i - k_side), season))
return utils.mean(k_range) #gets predicted value
def calculate_knn_forcast(data, k, year, season): #calc future values
k_range=[]
for i in range(k):
k_range.append(construct_season_avg(data, year - (k-i), season))
return utils.mean(k_range) #gets predicted value
def get_max_temperature(data, month, year):
df = construct_df(data)
year_data = construct_year_data(df, year)
if year_data.loc[df['mm'] == month].empty == False:
temp = year_data.loc[df['mm'] == month].iloc[0]['maxC']
else:
temp = 0
return temp
def get_min_temperature(data, month, year):
df = construct_df(data)
year_data = construct_year_data(df, year)
temp=0
if year_data.loc[df['mm'] == month].empty == False:
temp = year_data.loc[df['mm'] == month].iloc[0]['minC']
else:
temp = 0
return temp
def get_average_temperature(data, month, year):
temps = []
temps.append(get_max_temperature(data, month, year))
temps.append(get_min_temperature(data, month, year))
return utils.mean(temps)
def get_average_max(data, years_to_check, year_to_start, season):
avg = 0
for i in range(years_to_check):
avg += construct_season_avg_max(data, year_to_start-i, season)
return avg / years_to_check
def get_average_min(data, years_to_check, year_to_start, season):
avg = 0
for i in range(years_to_check):
avg += construct_season_avg_min(data, year_to_start-i, season)
return avg / years_to_check