Kaggle竞赛之Titanic存活预测2

提高代码规范性，基于上一个 baseline 的提高

import pandas as pd
from sklearn.preprocessing import LabelBinarizer
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split#数据划分方法
from sklearn.ensemble import RandomForestClassifier#随机森林
from sklearn.model_selection import GridSearchCV #网格交叉搜索交叉验证# data = pd.read_csv("file_path")打印出来看def data_clean(file_path):""""数据处理函数parameters:file_path:数据文件路径""""data = pd.read_csv(file_path)#删除不需要的列data.drop("PassengerId",axis=1,inplace=True)data.drop(["Name","Ticket","Cabin"],axis=1,inplace=True)#对空值进行填充data["Age"].fillna(data["Age"].mean(),inplace=True)#对字符的东西进行一个空值填充data["Embarked"].fillna(data["Embarked"].mode[0],inplace=True)#数据preprocessingdata["Sex"]=LabelBinarizer().fit_transform(data["Sex"])data = pd.get_dummied(data)#缩放，减少计算量data["Fare"] = StandardScaler().fit_transform(data["Fare"].values.reshape(-1,1))return (data)# 数据划分
def data_split(data):""""数据划分函数parameters:data:要划分的数据""""x = data.drop(["Survived"],axis=1)y = data["Survived"]x_train,x_test,y_train,y_test = train_test.split(x,y,test_size=0.2)return (x_train,x_test,y_train,y_test)# 模型搭建
def model_fit(x,y):"""模型训练函数parameters:x:特征y:标签"""#定义好参数Para_grid = [{"n_estimators":[3,10,30],"max_features":[2,4,6,8]},{"bootstrap",[False],"n_estimators":[3,10],"max_features":[2,4,6]}]#模型实例化model = RandomForestClassifier()#模型和交叉验证次数gird_search = GridSearchCV(model,Para_grid,cv=5)#模型训练grid_search.fit(x,y)return(grid_search.best_params_,grid_search.best_estimator_)data = data_clean("data/train.csv")
x_train,x_test,y_train,y_test = data_split(data)
model_fit(x_train,y_train)
# 上一行得到最优的模型和参数
model = RandomForestClassifier(n_estimators=30,max_features=2,max_depth=100)
model.fit(x_train,y_train)
model.score(x_test,y_test)#程序入口
if __name__ == '__main__':ABC