心脏病题目（1）数据可视化

数据集：

https://www.kaggle.com/ronitf/heart-disease-uci

 

• 检查目标值

print(data.target.value_counts())

1    165
0    138
Name: target, dtype: int64

• 画出图像

sns.countplot(x='target',data=data)

 

• 求百分比

target1 = len(data[data['target']==1])
target0 = len(data[data['target']==0])
NoHD = target0/len(data['target'])
IsHD = target1/len(data['target'])

 0.45544554455445546 0.5445544554455446

• 年龄跟心脏病的分布 

pd.crosstab(data.age,data.target).plot(kind='bar',figsize=(18,6))
plt.title('Age distribution for heart attack')
plt.xticks(fontsize=20,rotation=45)
plt.xlabel('Age')
plt.ylabel('Frequency')
plt.savefig('Heartdisease.eps')#eps可以到AI里改美观一点&#