import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import Image
%matplotlib inline
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
# 读取训练数集
train = pd.read_csv('train.csv')
train.shape
1.1 缺失值填充
# 对分类变量进行填充
train['Cabin'] = train['Cabin'].fillna('NA')
train['Embarked'] = train['Embarked'].fillna('S')
# 对连续变量进行填充
train['Age'] = train['Age'].fillna(train['Age'].mean())
# 检查缺失值比例
train.isnull().mean().sort_values(ascending=False)
1.2 编码分类变量
# 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)
2.1 切割训练集和测试集
切割数据集是为了后续能评估模型泛化能力
sklearn中切割数据集的方法为train_test_split
查看函数文档可以在jupyter noteboo里面使用train_test_split?后回车即可看到
分层和随机种子在参数里寻找
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 = 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
2.2 模型创建
逻辑回归不是回归模型而是分类模型,不要与LinearRegression混淆
随机森林其实是决策树集成为了降低决策树过拟合的情况
线性模型所在的模块为sklearn.linear_model
树模型所在的模块为sklearn.ensemble
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
# 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)))
# 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)))
2.3 输出模型预测结果
一般监督模型在sklearn里面有个predict能输出预测标签,predict_proba则可以输出标签概率
# 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]
3.1 交叉验证
交叉验证在sklearn中的模块为sklearn.model_selection
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()))
3.2 混淆矩阵
混淆矩阵的方法在sklearn中的sklearn.metrics模块
混淆矩阵需要输入真实标签和预测标签
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))
3.3 ROC曲线
ROC曲线在sklearn中的模块为sklearn.metrics
ROC曲线下面所包围的面积越大越好
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)