基于机器学习的临床决策支持

#导入依赖库
#!/usr/bin/python3

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
import matplotlib.gridspec as gridspec 
import seaborn as sns
import time
%matplotlib inline 

#Import models from scikit learn module:
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.cross_validation import KFold  
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC

from sklearn import metrics

#载入数据

data = pd.read_csv("data.csv")
data.head()

#数据预处理
data.drop('id',axis=1,inplace=True) #移除id
data.drop('Unnamed: 32',axis=1,inplace=True)
print("Row, Col", data.shape)# (row,col)

#数据标记，M：恶性，B：良性

data['diagnosis'] = data['diagnosis'].map({'M':1,'B':0})
data.head()

#挖掘数据
data.describe()

data.plot(kind='density', subplots=True, layout=(5,7), sharex=False, legend=False, fontsize=1)
plt.show()

print(data.groupby('diagnosis').size())
sns.countplot(data['diagnosis'],label="Count")
plt.show()

#划分训练集和测试集

traindf, testdf = train_test_split(data, test_size = 0.3)
labels = 'Train', 'Test'
plt.pie([70, 30], labels=labels, autopct='%1.1f%%', shadow=True)
plt.show()
print("Train set", traindf.shape)
print("Test set", testdf.shape)

features_mean= list(data.columns[1:11])
corr = data[features_mean].corr() 
plt.figure(figsize=(14,14))
sns.heatmap(corr, cbar = True,  square = True, annot=True, fmt= '.2f',annot_kws={'size': 15},
           xticklabels= features_mean, yticklabels= features_mean,
           cmap= 'coolwarm') 
plt.show()

#用于模型分类和访问性能的通用函数。
Y = data['diagnosis'].values
X = data.drop('diagnosis', axis=1).values
X_train, X_test, Y_train, Y_test = train_test_split (X, Y, test_size = 0.30, random_state=21)
def classification_model(model, data, predictors, outcome):

    #拟合模型
    model.fit(data[predictors],data[outcome])

    #对训练集进行预测
    predictions = model.predict(data[predictors])

    #输出准确性
    accuracy = metrics.accuracy_score(predictions,data[outcome])
    print("Accuracy : %s" % "{0:.3%}".format(accuracy))

  #Perform k-fold cross-validation with 5 folds
    kfold = KFold(data.shape[0], n_folds=5)
    error = []
    for train, test in kfold:

         #过滤数据
        train_predictors = (data[predictors].iloc[train,:])

        # 目的在于训练算法
        train_target = data[outcome].iloc[train]

       # 使用预测变量和目标训练算法。
        model.fit(train_predictors, train_target)

       #记录每次交叉验证运行的错误
        error.append(model.score(data[predictors].iloc[test,:], data[outcome].iloc[test]))
        cv_results = cross_val_score(model, X_train, Y_train, cv=kfold, scoring='accuracy')

    print("Cross-Validation Score : %s" % "{0:.3%}".format(np.mean(error)))

  #Fit the model again so that it can be refered outside the function:
    model.fit(data[predictors],data[outcome])

predictor_var = ['texture_mean','perimeter_mean','smoothness_mean','compactness_mean','symmetry_mean']
outcome_var='diagnosis'
model=LogisticRegression()
classification_model(model,traindf,predictor_var,outcome_var)

Accuracy : 91.206%
Cross-Validation Score : 90.206%

predictor_var = ['texture_mean','perimeter_mean','smoothness_mean','compactness_mean','symmetry_mean']
model = DecisionTreeClassifier()
classification_model(model,traindf,predictor_var,outcome_var)

Accuracy : 100.000%
Cross-Validation Score : 87.446%

predictor_var = ['texture_mean']
model = DecisionTreeClassifier()
classification_model(model,traindf,predictor_var,outcome_var)

Accuracy : 96.231%
Cross-Validation Score : 66.329%

predictor_var = ['texture_mean','perimeter_mean','smoothness_mean','compactness_mean','symmetry_mean']
model= KNeighborsClassifier()
classification_model(model,traindf,predictor_var,outcome_var)

Accuracy : 92.462%
Cross-Validation Score : 89.456%

predictor_var = ['texture_mean','perimeter_mean','smoothness_mean','compactness_mean','symmetry_mean']
model= SVC()
classification_model(model,traindf,predictor_var,outcome_var)

Accuracy : 94.472%
Cross-Validation Score : 87.937%

#几种机器学习模型的性能比较

Y = data['diagnosis'].values
X = data.drop('diagnosis', axis=1).values
X_train, X_test, Y_train, Y_test = train_test_split (X, Y, test_size = 0.30, random_state=21)
models_list = []
models_list.append(('LR', LogisticRegression()))
models_list.append(('DT', DecisionTreeClassifier()))
models_list.append(('SVM', SVC())) 
models_list.append(('KNN', KNeighborsClassifier()))
num_folds = 10
results = []
names = []
for name, model in models_list:
    start = time.time()
    cv_results = cross_val_score(model, X_train, Y_train, cv=num_folds, scoring='accuracy')
    end = time.time()
    results.append(cv_results)
    names.append(name)
    print( "%s:(run time: %f)"% (name, end-start))

LR:(run time: 0.069959)
DT:(run time: 0.047665)
SVM:(run time: 0.156240)
KNN:(run time: 0.029838)