用决策树使用train.csv作为训练集完成模型的建立,再将训练好的模型在test.csv上进行测试。
时间: 2024-02-23 17:58:26 浏览: 20
好的,以下是使用决策树进行训练和测试的 Python 代码示例:
``` python
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
# 读取训练集和测试集数据
train_data = pd.read_csv('train.csv')
test_data = pd.read_csv('test.csv')
# 筛选特征和标签
features = train_data.drop(['Survived'], axis=1)
labels = train_data['Survived']
# 划分训练集和验证集
train_features, val_features, train_labels, val_labels = train_test_split(features, labels, test_size=0.2)
# 创建决策树模型并进行训练
clf = DecisionTreeClassifier()
clf.fit(train_features, train_labels)
# 在验证集上进行测试
val_pred = clf.predict(val_features)
val_acc = accuracy_score(val_labels, val_pred)
print('Validation accuracy:', val_acc)
# 在测试集上进行测试
test_features = test_data.drop(['Survived'], axis=1)
test_labels = test_data['Survived']
test_pred = clf.predict(test_features)
test_acc = accuracy_score(test_labels, test_pred)
print('Test accuracy:', test_acc)
```
其中,train.csv 是训练集数据,test.csv 是测试集数据。我们首先读取数据,并对训练集进行特征和标签的筛选,然后使用 `train_test_split` 函数划分训练集和验证集。接着,我们创建决策树模型并对训练集进行训练,然后在验证集上进行测试,计算验证集上的准确率。最后,我们在测试集上进行测试,计算测试集上的准确率。