Task2--模型评估

0.目的

记录7个模型（逻辑回归、SVM、决策树、随机森林、GBDT、XGBoost和LightGBM）关于accuracy、precision，recall和F1-score、auc值的评分表格，并画出ROC曲线。

1.导入，读取，定义

#导入
import pandas as import pd
import matplotlib.pyplot as plt 

from sklearn.metrics import roc_auc_score
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.metrics import f1_score
from sklearn.metrics import roc_score,auc

from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import LinearSVC
from xgboost import XGBClassifier
from lightgbm import LGBMClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import warnings

warnings.filterwarnings("ignore")

#读取
data = pd.read_csv('data_all.csv')
#打印  
print(data.shape)

x = data.drop(['status'],axis = 1)
y = data.['status']
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size = 0.3, random_state = 2018)

sc = StandardScaler()
sc.fit(x_train)
x_train_std = sc.transform(x_train)
x_test_std = sc.transform(x_test)

#定义得分,曲线
def score(y_true, y_predict, y_predict_pro):
    acc_score = accuracy_score(y_true, y_predict)
    pre_score = precision_score(y_true, y_predict)
    recall = recall_score(y_true, y_predict)
    F1 = f1_score(y_true, y_predict)
    acc_score = roc_auc_score(y_true, y_predict_pro)
    fpr, tpr, thresholds = roc_curve(y_test, y_predict_pro)
    plt.plot(fpr, tpr, 'b', label = 'AUC = %0.4f'% auc_score)
    plt.plot([0,1],[0,1],'r--',label= 'Random guess')
    plt.legend(loc='lower right')
    plt.title('ROCcurve')
    plt.xlabel('false positive rate')
    plt.ylabel('true positive rate')
    plt.show()
    #打印得分
    print(acc_score)
    print(pre_score)
    print(recall)
    print(F1)
    print(auc_score)

2. 逻辑回归

#逻辑回归
lr = LogisticRegression(randdom_state = 2018)
lr.fit(x_train_std, y_train)

3. SVM

#SVM
svc = LinearSVC(random_state = 2018)
svc.fit(x_train_std, y_train)
svc.predict = svc.predict(x_test_std)
svc_predict_pro = svc.decision_function(X_test_std)
get_scores(y_test,svc_predict,svc_predict_pro)

4. 决策树

#决策树
clf = DecisionTreeClassifier(random_state = 2018)
clf.fit(x_train_std, y_train)
clf_predict = clf.predict(x_test_std)
clf_predict_proba = clf.predict_proba(X_test_std)[:,1]
get_scores(y_test,clf_predict,clf_predict_proba)

5. 随机森林

#随机森林
rfc = RandomForestClassifier(random_state = 2018)
rfc.fit(x_train_std, y_train)
rfc_predict = rfc.predict(x_test_std)
rfc_predict_proba = rfc.predict_proba(X_test_std)[:,1]
get_scores(y_test,rfc_predict,rfc_predict_proba)

6.GBDT

#GBDT
gdbt = GradientBoostingClassifier(random_state=2018)
gdbt.fit(x_train_std, y_train)
gdbt_predict = gdbt.predict(x_test_std)
gdbt_predict_proba = gdbt.predict_proba(X_test_std)[:,1]
get_scores(y_test,gdbt_predict,gdbt_predict_proba)

7.XGBoost

#XGBoost
xgbs = XGBClassifier(random_state=2018)
xgbs.fit(x_train_std, y_train)
xgbs_predict = xgbs.predict(x_test_std)
xgbs_predict_proba = xgbs.predict_proba(X_test_std)[:,1]
get_scores(y_test,xgbs_predict,xgbs_predict_proba)

8.LightGBM

#LightGBM
lgbm = LGBMClassifier(random_state=2018)
lgbm.fit(x_train_std, y_train)
lgbm_predict = lgbm.predict(x_test_std)
lgbm_predict_proba = lgbm.predict_proba(X_test_std)[:,1]
get_scores(y_test,lgbm_predict,lr_predict_pro)