第三章模型建立和评估
输出图片设置
plt.rcParams[‘font.sans-serif’] = [‘SimHei’] # 用来正常显示中文标签
plt.rcParams[‘axes.unicode_minus’] = False # 用来正常显示负号
plt.rcParams[‘figure.figsize’] = (10, 6) # 设置输出图片大小
特征工程
1.缺失值填充
2.编码分类变量
onehot encoding
# 取出所有的输入特征
data = train[['Pclass','Sex','Age','SibSp','Parch','Fare', 'Embarked']]
# 进行虚拟变量转换
data = pd.get_dummies(data)
模型搭建
sklearn模型算法选择路径图
对数据集进行切割
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
逻辑回归
from sklearn.linear_model import LogisticRegression
# 默认参数逻辑回归模型
lr = LogisticRegression()
lr.fit(X_train, y_train)
# 调整参数后的逻辑回归模型
lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)
# 查看训练集和测试集score值
print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr.score(X_test, y_test)))
随机森林
from sklearn.ensemble import RandomForestClassifier
# 默认参数的随机森林分类模型
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
# 调整参数后的随机森林分类模型
rfc2 = RandomForestClassifier(n_estimators=100, max_depth=5)
rfc2.fit(X_train, y_train)
print("Training set score: {:.2f}".format(rfc.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc.score(X_test, y_test)))
输出模型预测结果
1.交叉验证
from sklearn.model_selection import cross_val_score
lr = LogisticRegression(C=100)
scores = cross_val_score(lr, X_train, y_train, cv=10)
# k折交叉验证分数
scores
# 平均交叉验证分数
print("Average cross-validation score: {:.2f}".format(scores.mean()))
2.混淆矩阵
from sklearn.metrics import confusion_matrix
lr = LogisticRegression(C=100)
lr.fit(X_train, y_train)
# 模型预测结果
pred = lr.predict(X_train)
# 混淆矩阵
confusion_matrix(y_train, pred)
3.绘制ROC曲线
from sklearn.metrics import roc_curve
fpr, tpr, thresholds = roc_curve(y_test, lr.decision_function(X_test))
plt.plot(fpr, tpr, label="ROC Curve")
plt.xlabel("FPR")
plt.ylabel("TPR (recall)")
# 找到最接近于0的阈值
close_zero = np.argmin(np.abs(thresholds))
plt.plot(fpr[close_zero], tpr[close_zero], 'o', markersize=10, label="threshold zero", fillstyle="none", c='k', mew=2)
plt.legend(loc=4)