Newer
Older
from typing import Optional, List
from pandas import DataFrame
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
def __init__(self, c:Optional[float] = None, cv:Optional[List] = None, t:Optional[List] = None, method = 'regression')-> DataFrame:
phase = [c, cv, t]
index = np.array(["train", "cv", "test"])
notnone = [i for i in range(3) if phase[i] != None]
met_index = index[notnone]
methods = ['regression', 'classification']
perf = {}
for i in notnone:
if method == 'regression':
perf[index[i]] = metrics.reg_(phase[i][0], phase[i][1])
elif method == 'classification':
perf[index[i]] = metrics.class_(phase[i][0], phase[i][1])
if notnone == 1:
self.ret = perf.T
else:
self.ret = DataFrame(perf).T
@staticmethod
def reg_(meas, pred):
meas = np.array(meas)
pred = np.array(pred)
xbar = np.mean(meas) # the average of measured values
e = np.subtract(meas , pred)
e2 = e**2# the squared error
# Sum of squared:
# TOTAL
sst = np.sum((meas - xbar)**2)
# RESIDUAL
ssr = np.sum(e2)
# REGRESSION OR MODEL
ssm = np.sum(pred - xbar)
# Compute statistical metrics
metr = {}
metr['r'] = np.corrcoef(meas, pred)[0, 1]
metr['r2'] = 1-ssr/sst
metr['rmse'] = np.sqrt(np.mean(e2))
metr['mae'] = np.mean(np.abs(e2))
metr['rpd'] = np.std(meas)/np.sqrt(np.mean(e2))
metr['rpiq'] = (np.quantile(meas, .75) - np.quantile(meas, .25))/np.sqrt(np.mean(e2))
return metr
@staticmethod
def class_(meas, pred):
pass
@property
def scores_(self):
return self.ret