第三章 模型搭建和评估-评估
根据之前的模型的建模,我们知道如何运用sklearn这个库来完成建模,以及我们知道了的数据集的划分等等操作。那么一个模型我们怎么知道它好不好用呢?以至于我们能不能放心的使用模型给我的结果呢?那么今天的学习的评估,就会很有帮助。
加载下面的库
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import Image
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
%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
任务:加载数据并分割测试集和训练集
#写入代码
X = pd.read_csv("clear_data.csv")
X.head()
PassengerId | Pclass | Age | SibSp | Parch | Fare | Sex_female | Sex_male | Embarked_C | Embarked_Q | Embarked_S | |
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | 22.0 | 1 | 0 | 7.2500 | 0 | 1 | 0 | 0 | 1 |
1 | 1 | 1 | 38.0 | 1 | 0 | 71.2833 | 1 | 0 | 1 | 0 | 0 |
2 | 2 | 3 | 26.0 | 0 | 0 | 7.9250 | 1 | 0 | 0 | 0 | 1 |
3 | 3 | 1 | 35.0 | 1 | 0 | 53.1000 | 1 | 0 | 0 | 0 | 1 |
4 | 4 | 3 | 35.0 | 0 | 0 | 8.0500 | 0 | 1 | 0 | 0 | 1 |
y = pd.read_csv("train.csv")["Survived"]
y.head()
0 0
1 1
2 1
3 1
4 0
Name: Survived, dtype: int64
from sklearn.model_selection import train_test_split
#写入代码
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify = y, random_state = 0)
X_train