python打卡day31@浙大疏锦行

DAY 31 文件的规范拆分和写法

知识点回顾

1. 规范的文件命名
2. 规范的文件夹管理
3. 机器学习项目的拆分
4. 编码格式和类型注解

作业：尝试针对之前的心脏病项目，准备拆分的项目文件，思考下哪些部分可以未来复用。

一、导入数据库

import numpy as np
import pandas as pd

二、数据可视化

import matplotlib.pyplot as plt
import seaborn as sns 
 
from sklearn.ensemble import RandomForestClassifier 
 
from sklearn.tree import DecisionTreeClassifier
 
from sklearn.tree import export_graphviz 
 
from sklearn.metrics import roc_curve, auc 
from sklearn.metrics import classification_report 
 
from sklearn.metrics import confusion_matrix 
 
from sklearn.model_selection import train_test_split 
 
 
 
np.random.seed(123) 
pd.options.mode.chained_assignment = None  
 
%matplotlib inline

三、可视化风格的设置

sns.set(palette = 'pastel', rc = {"figure.figsize": (10,5), 
                                  "axes.titlesize" : 14,    
                                  "axes.labelsize" : 12,    
                                  "xtick.labelsize" : 10,   
                                  "ytick.labelsize" : 10 }) 
a = sns.countplot(x = 'target', data = dt)              
a.set_title('Distribution of Presence of Heart Disease') 
a.set_xticklabels(['Absent', 'Present'])                 
plt.xlabel("Presence of Heart Disease")                  
 
plt.show()
g = sns.countplot(x = 'age', data = dt) 
g.set_title('Distribution of Age')      
plt.xlabel('Age')                       
b = sns.countplot(x = 'target', data = dt, hue = 'sex')         
plt.legend(['Female', 'Male'])                                    
b.set_title('Distribution of Presence of Heart Disease by Sex')   
b.set_xticklabels(['Absent', 'Present'])

plt.show()
sns.distplot(dt['chol'].dropna(), kde=True, color='darkblue', bins=40)

四、数据预处理

dt['sex'][dt['sex'] == 0] = 'female'
dt['sex'][dt['sex'] == 1] = 'male'
 
dt['chest_pain_type'][dt['chest_pain_type'] == 1] = 'typical angina'
dt['chest_pain_type'][dt['chest_pain_type'] == 2] = 'atypical angina'
dt['chest_pain_type'][dt['chest_pain_type'] == 3] = 'non-anginal pain'
dt['chest_pain_type'][dt['chest_pain_type'] == 4] = 'asymptomatic'
 
dt['fasting_blood_sugar'][dt['fasting_blood_sugar'] == 0] = 'lower than 120mg/ml'
dt['fasting_blood_sugar'][dt['fasting_blood_sugar'] == 1] = 'greater than 120mg/ml'
 
dt['rest_ecg'][dt['rest_ecg'] == 0] = 'normal'
dt['rest_ecg'][dt['rest_ecg'] == 1] = 'ST-T wave abnormality'
dt['rest_ecg'][dt['rest_ecg'] == 2] = 'left ventricular hypertrophy'
 
dt['exercise_induced_angina'][dt['exercise_induced_angina'] == 0] = 'no'
dt['exercise_induced_angina'][dt['exercise_induced_angina'] == 1] = 'yes'
 
dt['st_slope'][dt['st_slope'] == 1] = 'upsloping'
dt['st_slope'][dt['st_slope'] == 2] = 'flat'
dt['st_slope'][dt['st_slope'] == 3] = 'downsloping'
 
dt['thalassemia'][dt['thalassemia'] == 1] = 'normal'
dt['thalassemia'][dt['thalassemia'] == 2] = 'fixed defect'
dt['thalassemia'][dt['thalassemia'] == 3] = 'reversable defect'

五、创建模型

model = RandomForestClassifier(max_depth=5, n_estimators=10)    
model.fit(X_train, y_train)                                     

六、模型训练

y_predict = model.predict(X_test)
y_pred_quant = model.predict_proba(X_test)[:, 1]
y_pred_bin = model.predict(X_test)

七、模型评估

total=sum(sum(confusion_matrix))
 
sensitivity = confusion_matrix[0,0]/(confusion_matrix[0,0]+confusion_matrix[1,0])
print('灵敏度 : ', sensitivity )
 
specificity = confusion_matrix[1,1]/(confusion_matrix[1,1]+confusion_matrix[0,1])
print('特异度 : ', specificity)