Logestic Regression
In [18]: import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split df = pd . read_csv ( "framingham_heart_disease.csv" ) df . head () Out[18]: male age education currentSmoker cigsPerDay BPMeds prevalentStroke prevalentHyp diabetes totChol sysBP diaBP BMI heartRate glucose TenYearCHD 0 1 39 4.0 0 0.0 0.0 0 0 0 195.0 106.0 70.0 26.97 80.0 77.0 0 1 0 46 2.0 0 0.0 0.0 0 0 0 250.0 121.0 81.0 28.73 95.0 76.0 0 2 1 48 1.0 1 20.0 0.0 0 0 0 245.0 127.5 80.0 25.34 75.0 70.0 0 3 0 61 3.0 1 30.0 0.0 0 1 0 225.0 150.0 95.0 28.58 65.0 103.0 1 4 0 46 3.0 1 23.0 0.0 0 0 0 285.0 130.0 84.0 23.10 85.0 85.0 0 In [5]: df . describe () Out[5]: male age education currentSmoker cigsPerDay BPMeds prevalentStroke prevalentHyp diabetes totChol sysBP diaBP BMI heartRate glucose TenYearCHD count 4238.000000 4238.000000 4133.000000 4238.000000 4209.000000 4185.000000 4238.000000 4238.000000 4238.000000 4188.000000 423