机器学习建模与评估
预处理流程：
1. 导入库
2. 读取数据查看数据信息--理解数据
3. 缺失值处理
4. 异常值处理
5. 离散值处理
6. 删除无用列
7. 划分数据集
8. 特征工程
9. 模型训练
10. 模型评估
11. 模型保存
12. 模型预测
数据集的划分
#数据划分
# 划分训练集和测试集
from sklearn.model_selection import train_test_split
X = data.drop(['target'], axis=1)
y = data['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 训练集和测试集的形状
print(f"训练集形状：{X_train.shape},测试集形状：{X_test.shape}")
#target是标签数据导入相关库
from sklearn.svm import SVC #支持向量机分类器
from sklearn.neighbors import KNeighborsClassifier #K近邻分类器
from sklearn.linear_model import LogisticRegression #逻辑回归分类器
import xgboost as xgb #XGBoost分类器
import lightgbm as lgb #LightGBM分类器
from sklearn.ensemble import RandomForestClassifier #随机森林分类器
from catboost import CatBoostClassifier #CatBoost分类器
from sklearn.tree import DecisionTreeClassifier #决策树分类器
from sklearn.naive_bayes import GaussianNB #高斯朴素贝叶斯分类器
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score # 用于评估分类器性能的指标
from sklearn.metrics import classification_report, confusion_matrix #用于生成分类报告和混淆矩阵
import warnings #用于忽略警告信息
warnings.filterwarnings("ignore") # 忽略所有警告信息
支持向量机SVM
# SVM
svm_model = SVC(random_state=42)
svm_model.fit(X_train, y_train)
svm_pred = svm_model.predict(X_test)
print("\nSVM 分类报告：")
print(classification_report(y_test, svm_pred))
print("SVM 混淆矩阵：")
print(confusion_matrix(y_test, svm_pred))
# 计算 SVM 评估指标，这些指标默认计算正类的性能
svm_accuracy = accuracy_score(y_test, svm_pred)
svm_precision = precision_score(y_test, svm_pred)
svm_recall = recall_score(y_test, svm_pred)
svm_f1 = f1_score(y_test, svm_pred)
print("SVM 模型评估指标：")
print(f"准确率: {svm_accuracy:.4f}")
print(f"精确率: {svm_precision:.4f}")
print(f"召回率: {svm_recall:.4f}")
print(f"F1 值: {svm_f1:.4f}")KNN模型
#KNN
knn_model = KNeighborsClassifier()
knn_model.fit(X_train, y_train)
knn_pred = knn_model.predict(X_test)
print("\nKNN 分类报告：")
print(classification_report(y_test, knn_pred))
print("KNN 混淆矩阵：")
print(confusion_matrix(y_test, knn_pred))
knn_accuracy = accuracy_score(y_test, knn_pred)
knn_precision = precision_score(y_test, knn_pred)
knn_recall = recall_score(y_test, knn_pred)
knn_f1 = f1_score(y_test, knn_pred)
print("KNN 模型评估指标：")
print(f"准确率: {knn_accuracy:.4f}")
print(f"精确率: {knn_precision:.4f}")
print(f"召回率: {knn_recall:.4f}")
print(f"F1 值: {knn_f1:.4f}")逻辑回归
#逻辑回归
logreg_model = LogisticRegression()
logreg_model.fit(X_train, y_train)
logreg_pred = logreg_model.predict(X_test)
print("\n逻辑回归 分类报告：")
print(classification_report(y_test, knn_pred))
print("逻辑回归 混淆矩阵：")
print(confusion_matrix(y_test, knn_pred))
logreg_accuracy = accuracy_score(y_test, knn_pred)
logreg_precision = precision_score(y_test, knn_pred)
logreg_recall = recall_score(y_test, knn_pred)
logreg_f1 = f1_score(y_test, knn_pred)
print("逻辑回归 模型评估指标：")
print(f"准确率: {logreg_accuracy:.4f}")
print(f"精确率: {logreg_precision:.4f}")
print(f"召回率: {logreg_recall:.4f}")
print(f"F1 值: {logreg_f1:.4f}")朴素贝叶斯
#朴素贝叶斯
nb_model = GaussianNB()
nb_model.fit(X_train, y_train)
nb_pred = nb_model.predict(X_test)
print("\n朴素贝叶斯 分类报告：")
print(classification_report(y_test, nb_pred))
print("朴素贝叶斯 混淆矩阵：")
print(confusion_matrix(y_test, nb_pred))
nb_accuracy = accuracy_score(y_test, nb_pred)
nb_precision = precision_score(y_test, nb_pred)
nb_recall = recall_score(y_test, nb_pred)
nb_f1 = f1_score(y_test, nb_pred)
print("朴素贝叶斯 模型评估指标：")
print(f"准确率: {nb_accuracy:.4f}")
print(f"精确率: {nb_precision:.4f}")
print(f"召回率: {nb_recall:.4f}")
print(f"F1 值: {nb_f1:.4f}")决策树
#决策树
dt_model = DecisionTreeClassifier(random_state=42)
dt_model.fit(X_train, y_train)
dt_pred = dt_model.predict(X_test)
print("\n决策树 分类报告：")
print(classification_report(y_test, dt_pred))
print("决策树 混淆矩阵：")
print(confusion_matrix(y_test, dt_pred))
dt_accuracy = accuracy_score(y_test, dt_pred)
dt_precision = precision_score(y_test, dt_pred)
dt_recall = recall_score(y_test, dt_pred)
dt_f1 = f1_score(y_test, dt_pred)
print("决策树 模型评估指标：")
print(f"准确率: {dt_accuracy:.4f}")
print(f"精确率: {dt_precision:.4f}")
print(f"召回率: {dt_recall:.4f}")
print(f"F1 值: {dt_f1:.4f}")决策森林
#决策森林
rf_model = RandomForestClassifier(random_state=42)
rf_model.fit(X_train, y_train)
rf_pred = rf_model.predict(X_test)
print("\n随机森林 分类报告：")
print(classification_report(y_test, rf_pred))
print("随机森林 混淆矩阵：")
print(confusion_matrix(y_test, rf_pred))
rf_accuracy = accuracy_score(y_test, rf_pred)
rf_precision = precision_score(y_test, rf_pred)
rf_recall = recall_score(y_test, rf_pred)
rf_f1 = f1_score(y_test, rf_pred)
print("随机森林 模型评估指标：")
print(f"准确率: {rf_accuracy:.4f}")
print(f"精确率: {rf_precision:.4f}")
print(f"召回率: {rf_recall:.4f}")
print(f"F1 值: {rf_f1:.4f}")XGBoost
#XGBoost
xgb_model = xgb.XGBClassifier(random_state=42)
xgb_model.fit(X_train, y_train)
xgb_pred = xgb_model.predict(X_test)
print("\nXGBoost 分类报告：")
print(classification_report(y_test, xgb_pred))
print("XGBoost 混淆矩阵：")
print(confusion_matrix(y_test, xgb_pred))
xgb_accuracy = accuracy_score(y_test, xgb_pred)
xgb_precision = precision_score(y_test, xgb_pred)
xgb_recall = recall_score(y_test, xgb_pred)
xgb_f1 = f1_score(y_test, xgb_pred)
print("XGBoost 模型评估指标：")
print(f"准确率: {xgb_accuracy:.4f}")
print(f"精确率: {xgb_precision:.4f}")
print(f"召回率: {xgb_recall:.4f}")
print(f"F1 值: {xgb_f1:.4f}")LightGBM
#LightGBM
lgb_model = lgb.LGBMClassifier(random_state=42)
lgb_model.fit(X_train, y_train)
lgb_pred = lgb_model.predict(X_test)
print("\nLightGBM 分类报告：")
print(classification_report(y_test, lgb_pred))
print("LightGBM 混淆矩阵：")
print(confusion_matrix(y_test, lgb_pred))
lgb_accuracy = accuracy_score(y_test, lgb_pred)
lgb_precision = precision_score(y_test, lgb_pred)
lgb_recall = recall_score(y_test, lgb_pred)
lgb_f1 = f1_score(y_test, lgb_pred)
print("LightGBM 模型评估指标：")
print(f"准确率: {lgb_accuracy:.4f}")
print(f"精确率: {lgb_precision:.4f}")
print(f"召回率: {lgb_recall:.4f}")
print(f"F1 值: {lgb_f1:.4f}")结果汇总：
import pandas as pd
from tabulate import tabulate
results = {
"Model": ["SVM", "KNN", "逻辑回归", "朴素贝叶斯", "决策树", "随机森林", "XGBoost", "LightGBM"],
"Accuracy": [0.70, 0.69, 0.89, 0.87, 0.75, 0.84, 0.82, 0.84],
"Precision": [0.67, 0.69, 0.88, 0.90, 0.84, 0.84, 0.86, 0.87],
"Recall": [0.88, 0.75, 0.91, 0.84, 0.66, 0.84, 0.78, 0.81],
"F1-Score": [0.76, 0.72, 0.89, 0.87, 0.74, 0.84, 0.82, 0.84]
}
# 将结果存储为 DataFrame
results_df = pd.DataFrame(results)
# 使用 tabulate 以表格形式输出，居中显示
table = tabulate(results_df, headers='keys', tablefmt='pretty', floatfmt=".2f", stralign='center')
print(table)
# 如果需要保存为 CSV 文件
results_df.to_csv("model_comparison.csv", index=False)
