数据分析学习——第五天

数据分析学习：泰坦尼克号实战

模型搭建

特征工程

#缺失值的处理
data['Cabin'] = data['Cabin'].fillna('NA')
data['Embarked'] = data['Embarked'].fillna('S')
print(data.info())
data['Age'] = data['Age'].fillna(data['Age'].mean())

datax = data[['Pclass','Sex','Age','SibSp','Parch','Fare', 'Embarked']]
# 进行虚拟变量转换
datae = pd.get_dummies(datax)

模型搭建

切割训练集和测试集

from sklearn.model_selection import train_test_split
X = datae
y = data['Survived']
# 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)

模型创建

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
lr = LogisticRegression()
lr.fit(X_train, y_train)
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,penalty='l2', random_state=None, solver='liblinear', tol=0.0001,verbose=0, warm_start=False)
print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr.score(X_test, y_test)))

结果：

通过调整参数改变

lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)

LogisticRegression(C=100, class_weight=None, dual=False, fit_intercept=True,intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,penalty='l2', random_state=None, solver='liblinear', tol=0.0001,verbose=0, warm_start=False)
print("Training set score: {:.2f}".format(lr2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr2.score(X_test, y_test)))

输出模型预测结果

# 预测标签
pred = lr.predict(X_train)
# 此时我们可以看到0和1的数组
pred[:10] 12345

模型评估

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)
print("Average cross-validation score: {:.2f}".format(scores.mean()))

混淆矩阵

from sklearn.metrics import confusion_matrix
# 训练模型
lr = LogisticRegression(C=100)
lr.fit(X_train, y_train)
LogisticRegression(C=100, class_weight=None, dual=False, fit_intercept=True,
 intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
 penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
 verbose=0, warm_start=False)
 # 模型预测结果
pred = lr.predict(X_train)
# 混淆矩阵
confusion_matrix(y_train, pred)

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)