/
Multi_class_classification_precision.py
119 lines (93 loc) · 3.64 KB
/
Multi_class_classification_precision.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
import pandas
import argparse
import numpy
from collections import Counter
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn import metrics
#there are 3 Types of precision in case of Multi-class classification.
#1. Macro averaged precision
#2. Micro averaged precision
#3. Weighted precision
def true_positive(y_true, y_pred):
tp = 0
for yt, yp in zip(y_true, y_pred):
if yt == 1 and yp == 1:
tp += 1
return tp
def true_negative(y_true, y_pred):
tn = 0
for yt, yp in zip(y_true, y_pred):
if yt == 0 and yp == 0:
tn += 1
return tn
def false_positive(y_true, y_pred):
fp = 0
for yt, yp in zip(y_true, y_pred):
if yt == 0 and yp == 1:
fp += 1
return fp
def false_negative(y_true, y_pred):
fn = 0
for yt, yp in zip(y_true, y_pred):
if yt == 1 and yp == 0:
fn += 1
return fn
def precision(y_test, y_pred):
tp =true_positive(y_test, y_pred)
fp = false_positive(y_test, y_pred)
try:
return(tp/(tp+fp))
except ZeroDivisionError:
return 0
def Macro_averaged_precision(y_test, predictions):
precisions = []
for i in range(1,5):
temp_ytest = [1 if x == i else 0 for x in y_test]
temp_ypred = [1 if x == i else 0 for x in predictions]
print(temp_ypred)
print(temp_ytest)
prec = precision(temp_ytest, temp_ypred)
precisions.append(prec)
return (sum(precisions)/len(precisions))
def Micro_averaged_precision(y_test, predictions):
tp = 0
fp = 0
for i in range(1,5):
temp_ytest = [1 if x == i else 0 for x in y_test]
temp_ypred = [1 if x == i else 0 for x in predictions]
tp += true_positive(temp_ytest, temp_ypred)
fp += false_positive(temp_ytest, temp_ypred)
precisions = tp / (tp + fp)
return precisions
def weighted_precision(y_test, predictions):
num_classes = len(numpy.unique(y_test))
#coutns for every class
precision = 0
for i in range(1, num_classes):
temp_ytest = [1 if x == i else 0 for x in y_test]
temp_ypred = [1 if x == i else 0 for x in predictions]
tp = true_positive(temp_ytest, temp_ypred)
fp = false_positive(temp_ytest, temp_ypred)
try:
preai = tp / (tp+fp)
except ZeroDivisionError:
preai = 0
weighted = preai*sum(temp_ytest)
precision += weighted
precision = precision/len(y_test)
return precision
if __name__ == "__main__":
data = pandas.read_csv("C:\\Users\\iamvi\\OneDrive\\Desktop\\Metrics_in_Machine_Learning\\development-index\\Development Index.csv")
train = data.drop(['Development Index'], axis = 1).values
test = data["Development Index"].values
model = LogisticRegression()
X_train, X_test, y_train, y_test = train_test_split(train, test, stratify = test)
model.fit(X_train, y_train)
predictions = model.predict(X_test)
print("Macro precision is:", Macro_averaged_precision(y_test, predictions))
print("Micro precision is:", Micro_averaged_precision(y_test, predictions))
print("Weighted precision is:", weighted_precision(y_test, predictions))
print("sklearn Macro", metrics.precision_score(y_test, predictions, average = "macro"))
print("sklearn Micro", metrics.precision_score(y_test, predictions, average = "micro"))
print("sklearn weighted", metrics.precision_score(y_test, predictions, average = "weighted"))