import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
diabetes = pd.read_csv('diabetes.csv')
diabetes.head(5)
Pregnanciesint64
Glucoseint64
0
6
148
1
1
85
2
8
183
3
1
89
4
0
137
diabetes.shape
feature_cols = ['Pregnancies','Insulin','BMI', 'Age', 'Glucose', 'BloodPressure', 'DiabetesPedigreeFunction']
x = diabetes[feature_cols]
y = diabetes.Outcome
X_train, X_test, Y_train, Y_test = train_test_split(x, y, test_size=0.25, random_state=0)
logreg = LogisticRegression(max_iter=len(X_train))
logreg.fit(X_train,Y_train)
y_pred = logreg.predict(X_test)
y_pred
from sklearn import metrics
cnf_matrix = metrics.confusion_matrix(Y_test, y_pred)
cnf_matrix
class_names = [0,1]
fig, ax = plt.subplots()
tick_marks = np. arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
sns.heatmap(pd.DataFrame(cnf_matrix), annot = True , cmap = 'Blues_r', fmt = 'g')
ax.xaxis.set_label_position('top')
plt.tight_layout()
plt.title('Matriz de confusión',y =1.1)
plt.ylabel('Etiqueta actual')
plt.xlabel('Etiqueta de predicción')
print("Exactitud",metrics.accuracy_score(Y_test, y_pred))
Exactitud 0.8020833333333334