机器学习基础练习之ttnkh

#导入基本的库
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
import missingno as msno
#读取数据集
train_data=pd.read_csv(r"C:\Users\24306\Desktop\datasets\ttnkh_dataset\train.csv")
test_data=pd.read_csv(r"C:\Users\24306\Desktop\datasets\ttnkh_dataset\test.csv")
#查看女性的存活率
women=train_data.loc[train_data.Sex=='female']['Survived']
rate_women=sum(women)/len(women)
print(f'女性的存活率是{rate_women}')
#查看男性的存活率
men=train_data.loc[train_data.Sex=='male']['Survived']
rate_men=sum(men)/len(men)
print(f'男性的存活率为{rate_men}')
#y是活着的，即要求预测的结果--标签
y=train_data['Survived']

#用feature的特征来进行预测
features=["Pclass","Sex","SibSp","Parch"]
X = pd.get_dummies(train_data[features])
#测试集与训练集要一样的模式
X_test = pd.get_dummies(test_data[features])
#模型使用为随机森林
model = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)
model.fit(X, y)
#预测结果
predictions = model.predict(X_test)
print(predictions)
#输入的结果
output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})
output.to_csv('submission.csv', index=False)
print("Your submission was successfully saved!")