!pip install catboost

import xgboost
import lightgbm
from sklearn.svm import SVC
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from catboost import CatBoostClassifier

# 训练决策树分类器
clf = DecisionTreeClassifier(random_state=1024)
clf.fit(X_train, y_train)
accuracy_list = []

# test数据集预测
y_pred = clf.predict(X_test)

from sklearn.metrics import accuracy_score
# 评估精度
accuracy = accuracy_score(y_test, y_pred)
print("精度: %.4f%%" % (accuracy * 100.0))
accuracy_list.append(accuracy*100)

精度: 76.2585%

from sklearn.ensemble import RandomForestClassifier
r_clf = RandomForestClassifier(max_features=0.5, max_depth=15, random_state=1)
r_clf.fit(X_train, y_train)
r_pred = r_clf.predict(X_test)
r_acc = accuracy_score(y_test, r_pred)
print(r_acc)
accuracy_list.append(100*r_acc)

0.8279972416510688

log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
log_reg_pred = log_reg.predict(X_test)
log_reg_acc = accuracy_score(y_test, log_reg_pred)
print(log_reg_acc)
accuracy_list.append(100*log_reg_acc)

0.8344990641316127

sv_clf = SVC()
sv_clf.fit(X_train, y_train)
sv_clf_pred = sv_clf.predict(X_test)
sv_clf_acc = accuracy_score(y_test, sv_clf_pred)
print(sv_clf_acc)
accuracy_list.append(100* sv_clf_acc)

0.8360752635208354

kn_clf = KNeighborsClassifier(n_neighbors=6)
kn_clf.fit(X_train, y_train)
kn_pred = kn_clf.predict(X_test)
kn_acc = accuracy_score(y_test, kn_pred)
print(kn_acc)
accuracy_list.append(100*kn_acc)

0.8304600531967293

gradientboost_clf = GradientBoostingClassifier(max_depth=2, random_state=1)
gradientboost_clf.fit(X_train,y_train)
gradientboost_pred = gradientboost_clf.predict(X_test)
gradientboost_acc = accuracy_score(y_test, gradientboost_pred)
print(gradientboost_acc)
accuracy_list.append(100*gradientboost_acc)

0.8364693133681411

xgb_clf = xgboost.XGBRFClassifier(max_depth=3, random_state=1)
xgb_clf.fit(X_train,y_train)
xgb_pred = xgb_clf.predict(X_test)
xgb_acc = accuracy_score(y_test, xgb_pred)
accuracy_list.append(100*xgb_acc)
print(xgb_acc)

[23:09:17] WARNING: ../src/learner.cc:1061: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'multi:softprob' was changed from 'merror' to 'mlogloss'. Explicitly set eval_metric if you'd like to restore the old behavior.
0.8360752635208354

lgb_clf = lightgbm.LGBMClassifier(max_depth=2, random_state=4)
lgb_clf.fit(X_train,y_train)
lgb_pred = lgb_clf.predict(X_test)
lgb_acc = accuracy_score(y_test, lgb_pred)
print(lgb_acc)
accuracy_list.append(100*lgb_acc)

0.8363708009063147

cat_clf = CatBoostClassifier()
cat_clf.fit(X_train,y_train)
cat_pred = cat_clf.predict(X_test)
cat_acc = accuracy_score(y_test, cat_pred)
print(cat_acc)
accuracy_list.append(100*cat_acc)

989:  learn: 0.4191992  total: 12.3s  remaining: 124ms
990:  learn: 0.4190779  total: 12.3s  remaining: 112ms
991:  learn: 0.4189944  total: 12.3s  remaining: 99.5ms
992:  learn: 0.4189137  total: 12.3s  remaining: 87ms
993:  learn: 0.4188195  total: 12.4s  remaining: 74.6ms
994:  learn: 0.4187774  total: 12.4s  remaining: 62.2ms
995:  learn: 0.4187095  total: 12.4s  remaining: 49.7ms
996:  learn: 0.4186093  total: 12.4s  remaining: 37.3ms
997:  learn: 0.4185544  total: 12.4s  remaining: 24.9ms
998:  learn: 0.4184855  total: 12.4s  remaining: 12.4ms
999:  learn: 0.4183650  total: 12.4s  remaining: 0us
0.8307555905822086

print(accuracy_list)

[76.25849669983253, 82.79972416510688, 83.44990641316127, 83.60752635208354, 83.04600531967293, 83.6469313368141, 83.60752635208354, 83.63708009063147, 83.07555905822086]

model_list = ['DecisionTree', 'RandomForest', 'Logistic Regression', 'SVC','KNearestNeighbours',  
              'GradientBooster', 'XGBRF','LGBM', 'CatBoostClassifier']

plt.rcParams['figure.figsize']=20,8
sns.set_style('darkgrid')
ax = sns.barplot(x=model_list, y=accuracy_list, palette = "husl", saturation =2.0)
plt.xlabel('Classifier Models', fontsize = 20 )
plt.ylabel('% of Accuracy', fontsize = 20)
plt.title('Accuracy of different Classifier Models', fontsize = 20)
plt.xticks(fontsize = 12, horizontalalignment = 'center', rotation = 8)
plt.yticks(fontsize = 12)
for i in ax.patches:
    width, height = i.get_width(), i.get_height()
    x, y = i.get_xy() 
    ax.annotate(f'{round(height,2)}%', (x + width/2, y + height*1.02), ha='center', fontsize = 'x-large')
plt.show()