动手学数据分析 Task05--数据建模&测评

数据建模

• 选择模型
  sklearn选择算法选择路径图：
  

任务一 切割训练集和测试集

from sklearn.model_selection import train_test_split
# 一般先取出X和y后再切割，有些情况会使用到未切割的，这时候X和y就可以用,x是清洗好的数据，y是我们要预测的存活数据'Survived'
X = data
y = train['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)
# 查看数据形状
X_train.shape, X_test.shape

任务二 构建模型

#逻辑回归模型（分类）
from sklearn.linear_model import LogisticRegression
# 默认参数逻辑回归模型
lr = LogisticRegression()
lr.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)))
# 调整参数后的逻辑回归模型
lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)
print("Training set score: {:.2f}".format(lr2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr2.score(X_test, y_test)))

#随机森林模型
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)
print("Training set score: {:.2f}".format(rfc.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc.score(X_test, y_test)))
# 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(rfc2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc2.score(X_test, y_test)))

任务三 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]
# 预测标签概率
pred_proba = lr.predict_proba(X_train)
pred_proba[:10]

模型评估

任务一 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()))

任务二 混淆矩阵

from sklearn.metrics import confusion_matrix
# 训练模型
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)
from sklearn.metrics import classification_report
# 精确率、召回率以及f1-score
print(classification_report(y_train, pred))

任务三 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)