sklearn实战-乳腺癌细胞数据挖掘（博主亲自录制视频）
https://study.163.com/course/introduction.htm?courseId=1005269003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share
医药统计项目可联系
QQ：231469242
randomForest.py
调参后，预测最高准确性也达到了89%
随机森林的参数
# -*- coding: utf-8 -*-
"""
Created on Sat Mar 31 09:30:24 2018
@author: Administrator
随机森林不需要预处理数据
"""
#导入数据预处理，包括标准化处理或正则处理
from sklearn import preprocessing
from sklearn.preprocessing import Imputer
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
import pandas as pd
#中文字体设置
from matplotlib.font_manager import FontProperties
font=FontProperties(fname=r"c:windowsfontssimsun.ttc",size=14)
#读取变量名文件
varibleFileName="titantic.xlsx"
#读取目标文件
targetFileName="target.xlsx"
#读取excel
data=pd.read_excel(varibleFileName)
data_dummies=pd.get_dummies(data)
print('features after one-hot encoding:
',list(data_dummies.columns))
features=data_dummies.ix[:,"Pclass":'Embarked_S']
x=features.values
#数据预处理
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)
imp.fit(x)
x=imp.transform(x)
target=pd.read_excel(targetFileName)
y=target.values
x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=0)
names=features.columns
trees=1000
max_depth=10
#n_estimators表示树的个数，测试中100颗树足够
forest=RandomForestClassifier(n_estimators=trees,random_state=0,max_depth=max_depth)
forest.fit(x_train,y_train)
print("random forest with %d trees:"%trees)
print("accuracy on the training subset:{:.3f}".format(forest.score(x_train,y_train)))
print("accuracy on the test subset:{:.3f}".format(forest.score(x_test,y_test)))
#print('Feature importances:{}'.format(forest.feature_importances_))
names=features.columns
importance=forest.feature_importances_
zipped = zip(importance,names)
list1=list(zipped)
list1.sort(reverse=True)
#print(list1)
n_features=data_dummies.shape[1]
plt.barh(range(n_features),forest.feature_importances_,align='center')
plt.yticks(np.arange(n_features),features)
plt.title("random forest with %d trees,%dmax_depth:"%(trees,max_depth))
plt.xlabel('Feature Importance')
plt.ylabel('Feature')
plt.show()
'''
random forest with 1000 trees:
accuracy on the training subset:0.983
accuracy on the test subset:0.878
random forest with 1000 trees,max_depth=4:
accuracy on the training subset:0.854
accuracy on the test subset:0.884
random forest with 1000 trees,max_depth=5:
accuracy on the training subset:0.853
accuracy on the test subset:0.887
random forest with 1000 trees,max_depth=9
accuracy on the training subset:0.871
accuracy on the test subset:0.890
'''
去掉覆盖率低的变量后，随机森林准确性反而下降，看了随机森林不需要去计算变量覆盖率
训练数据准确性0.983
测试数据准确性0.878
'''
random forest with 1000 trees:
accuracy on the training subset:0.983
accuracy on the test subset:0.878
'''
重要因子来看，性别第一，占据40%重要性，
年龄重要性18%左右，
票价重要性17%左右
logistic.py
# -*- coding: utf-8 -*-
"""
Created on Sun Apr 29 22:39:35 2018
@author: Administrator
"""
# -*- coding: utf-8 -*-
"""
Created on Sat Mar 31 09:30:24 2018
@author: Administrator
随机森林不需要预处理数据
"""
from sklearn.linear_model import LogisticRegression
#导入数据预处理，包括标准化处理或正则处理
from sklearn import preprocessing
from sklearn.preprocessing import Imputer
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import pandas as pd
#中文字体设置
from matplotlib.font_manager import FontProperties
font=FontProperties(fname=r"c:windowsfontssimsun.ttc",size=14)
#读取变量名文件
varibleFileName="titantic.xlsx"
#读取目标文件
targetFileName="target.xlsx"
#读取excel
data=pd.read_excel(varibleFileName)
data_dummies=pd.get_dummies(data)
print('features after one-hot encoding:
',list(data_dummies.columns))
features=data_dummies.ix[:,"Pclass":'Embarked_S']
x=features.values
#数据预处理
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)
imp.fit(x)
x=imp.transform(x)
target=pd.read_excel(targetFileName)
y=target.values
x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=0)
names=features.columns
#n_estimators表示树的个数，测试中100颗树足够
logistic=LogisticRegression()
logistic.fit(x_train,y_train)
print("logistic:")
print("accuracy on the training subset:{:.3f}".format(logistic.score(x_train,y_train)))
print("accuracy on the test subset:{:.3f}".format(logistic.score(x_test,y_test)))
'''
logistic:
accuracy on the training subset:0.850
accuracy on the test subset:0.875
'''
目前效果最好的是去掉低覆盖率的变量后，SVM准确率最高0.89
# -*- coding: utf-8 -*-
"""
Created on Sat Mar 31 09:30:24 2018
@author: Administrator
随机森林不需要预处理数据
"""
from sklearn.svm import SVC
#导入数据预处理，包括标准化处理或正则处理
from sklearn import preprocessing
from sklearn.preprocessing import Imputer
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import pandas as pd
#中文字体设置
from matplotlib.font_manager import FontProperties
font=FontProperties(fname=r"c:windowsfontssimsun.ttc",size=14)
#读取变量名文件
varibleFileName="titantic.xlsx"
#读取目标文件
targetFileName="target.xlsx"
#读取excel
data=pd.read_excel(varibleFileName)
data_dummies=pd.get_dummies(data)
print('features after one-hot encoding:
',list(data_dummies.columns))
features=data_dummies.ix[:,"Pclass":'Embarked_S']
x=features.values
#数据预处理
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)
imp.fit(x)
x=imp.transform(x)
target=pd.read_excel(targetFileName)
y=target.values
x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=0)
names=features.columns
svm=SVC()
svm.fit(x_train,y_train)
print("svc:")
print("accuracy on the training subset:{:.3f}".format(svm.score(x_train,y_train)))
print("accuracy on the test subset:{:.3f}".format(svm.score(x_test,y_test)))
'''
svc:
accuracy on the training subset:0.900
accuracy on the test subset:0.726
'''
#标准化数据
X_train_scaled = preprocessing.scale(x_train)
x_test_scaled = preprocessing.scale(x_test)
svm1=SVC()
svm1.fit(X_train_scaled,y_train)
#改变C参数，调优,kernel表示核函数，用于平面转换，probability表示是否需要计算概率
svm1=SVC()
svm1.fit(X_train_scaled,y_train)
print("accuracy on the scaled training subset:{:.3f}".format(svm1.score(X_train_scaled,y_train)))
print("accuracy on the scaled test subset:{:.3f}".format(svm1.score(x_test_scaled,y_test)))
'''
accuracy on the scaled training subset:0.866
accuracy on the scaled test subset:0.881
'''
#改变C参数，调优,kernel表示核函数，用于平面转换，probability表示是否需要计算概率
svm2=SVC(C=10,gamma="auto",kernel='rbf',probability=True)
svm2.fit(X_train_scaled,y_train)
print("after c parameter=10,accuracy on the scaled training subset:{:.3f}".format(svm2.score(X_train_scaled,y_train)))
print("after c parameter=10,accuracy on the scaled test subset:{:.3f}".format(svm2.score(x_test_scaled,y_test)))
'''
after c parameter=10,accuracy on the scaled training subset:0.878
after c parameter=10,accuracy on the scaled test subset:0.890
'''
xgboost1.py
效果也相当好
AUC: 0.9464 ACC: 0.8841 Recall: 0.8716 F1-score: 0.8716 Precesion: 0.8716
# -*- coding: utf-8 -*-
"""
Created on Sat Mar 31 09:30:24 2018
@author: Administrator
随机森林不需要预处理数据
"""
import xgboost as xgb
#导入数据预处理，包括标准化处理或正则处理
from sklearn import preprocessing
from sklearn.preprocessing import Imputer
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import pandas as pd
#中文字体设置
from matplotlib.font_manager import FontProperties
font=FontProperties(fname=r"c:windowsfontssimsun.ttc",size=14)
#读取变量名文件
varibleFileName="titantic.xlsx"
#读取目标文件
targetFileName="target.xlsx"
#读取excel
data=pd.read_excel(varibleFileName)
data_dummies=pd.get_dummies(data)
print('features after one-hot encoding:
',list(data_dummies.columns))
features=data_dummies.ix[:,"Pclass":'Embarked_S']
x=features.values
#数据预处理
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)
imp.fit(x)
x=imp.transform(x)
target=pd.read_excel(targetFileName)
y=target.values
x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=0)
names=features.columns
dtrain=xgb.DMatrix(x_train,label=y_train)
dtest=xgb.DMatrix(x_test)
params={'booster':'gbtree',
#'objective': 'reg:linear',
'objective': 'binary:logistic',
'eval_metric': 'auc',
'max_depth':4,
'lambda':10,
'subsample':0.75,
'colsample_bytree':0.75,
'min_child_weight':2,
'eta': 0.025,
'seed':0,
'nthread':8,
'silent':1}
watchlist = [(dtrain,'train')]
bst=xgb.train(params,dtrain,num_boost_round=100,evals=watchlist)
ypred=bst.predict(dtest)
# 设置阈值, 输出一些评价指标
y_pred = (ypred >= 0.5)*1
#模型校验
print ('AUC: %.4f' % metrics.roc_auc_score(y_test,ypred))
print ('ACC: %.4f' % metrics.accuracy_score(y_test,y_pred))
print ('Recall: %.4f' % metrics.recall_score(y_test,y_pred))
print ('F1-score: %.4f' %metrics.f1_score(y_test,y_pred))
print ('Precesion: %.4f' %metrics.precision_score(y_test,y_pred))
metrics.confusion_matrix(y_test,y_pred)
print("xgboost:")
print('Feature importances:{}'.format(bst.get_fscore()))
'''
AUC: 0.9464
ACC: 0.8841
Recall: 0.8716
F1-score: 0.8716
Precesion: 0.8716
xgboost:
Feature importances:{'f5': 69, 'f1': 178, 'f2': 68, 'f4': 245, 'f6': 25, 'f0': 88, 'f3': 25, 'f194': 4, 'f193': 21, 'f195': 9}
'''
决策树
decisionTree.py
# -*- coding: utf-8 -*-
"""
Created on Mon Apr 30 19:04:10 2018
@author: Administrator
"""
from sklearn.tree import export_graphviz
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import Imputer
import pandas as pd
import numpy as np
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt
#读取变量名文件
varibleFileName="titantic.xlsx"
#读取目标文件
targetFileName="target.xlsx"
#读取excel
data=pd.read_excel(varibleFileName)
data_dummies=pd.get_dummies(data)
print('features after one-hot encoding:
',list(data_dummies.columns))
features=data_dummies.ix[:,"Pclass":'Embarked_S']
x=features.values
#数据预处理
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)
imp.fit(x)
x=imp.transform(x)
target=pd.read_excel(targetFileName)
y=target.values
X_train,x_test,y_train,y_test=train_test_split(x,y,random_state=0)
#变量名
names=features.columns
#调参
list_average_accuracy=[]
depth=range(1,30)
for i in depth:
#max_depth=4限制决策树深度可以降低算法复杂度，获取更精确值
tree= DecisionTreeClassifier(max_depth=i,random_state=0)
tree.fit(X_train,y_train)
accuracy_training=tree.score(X_train,y_train)
accuracy_test=tree.score(x_test,y_test)
average_accuracy=(accuracy_training+accuracy_test)/2.0
#print("average_accuracy:",average_accuracy)
list_average_accuracy.append(average_accuracy)
max_value=max(list_average_accuracy)
#索引是0开头，结果要加1
best_depth=list_average_accuracy.index(max_value)+1
print("best_depth:",best_depth)
best_tree= DecisionTreeClassifier(max_depth=best_depth,random_state=0)
best_tree.fit(X_train,y_train)
accuracy_training=best_tree.score(X_train,y_train)
accuracy_test=best_tree.score(x_test,y_test)
print("decision tree:")
print("accuracy on the training subset:{:.3f}".format(best_tree.score(X_train,y_train)))
print("accuracy on the test subset:{:.3f}".format(best_tree.score(x_test,y_test)))
'''
best_depth: 19
decision tree:
accuracy on the training subset:0.976
accuracy on the test subset:0.860
'''
#绘图，显示因子重要性
n_features=x.shape[1]
plt.barh(range(n_features),best_tree.feature_importances_,align='center')
plt.yticks(np.arange(n_features),features)
plt.title("Decision Tree:")
plt.xlabel('Feature Importance')
plt.ylabel('Feature')
plt.show()
#生成一个dot文件，以后用cmd形式生成图片
export_graphviz(best_tree,out_file="Titanic.dot",class_names=['death','live'],feature_names=names,impurity=False,filled=True)
