Machine-Learning-and-Data-Science-with-Python-A-Complete-Beginners-Guide/algorithm_evaluation_metric_confusion.py at master · Frank88cc/Machine-Learning-and-Data-Science-with-Python-A-Complete-Beginners-Guide · GitHub

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
# -*- coding: utf-8 -*-
"""
@author: abhilash
"""
#load the csv file using read_csv function of pandas library
from pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.linear_model import LogisticRegression

filename = 'pima-indians-diabetes.csv'
#url = 'https://myfilecsv.com/test.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(filename, names=names)

array = dataframe.values

#splitting the array to input and output
X = array[:,0:8]
Y = array[:,8]
test_size = 0.33


seed = 7
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,random_state=seed)
model = LogisticRegression(solver='liblinear')

model.fit(X_train, Y_train)
predicted = model.predict(X_test)

matrix = confusion_matrix(Y_test, predicted)
print(matrix)