#1、 获取数据
#2、 数据基本处理
#2.1、确定特征值,目标值
#2.2、缺失值处理
#2.3、数据划分
#3、 特征工程(字典特征抽取)
#4、 机器学习(决策树)
#5、模型评估
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier
from tensorflow.keras import estimator
#1、 获取数据
train_data = pd.read_csv("train.csv")
test_data = pd.read_csv("test.csv")
data = train_data.append( test_data , ignore_index = True )
#2、 数据基本处理
#2.1、确定特征值,目标值
#2.2、缺失值处理
data["Age"].fillna(value=data["Age"].mean(), inplace=True)
data["Survived"].fillna(value=0, inplace=True)
data = data.replace(to_replace="?", value=np.NaN)#值替换
data = data.replace(to_replace="NaN", value=np.NaN)#值替换
data.dropna()#nan的值所在行都删除
x = data[["Pclass","Sex","Age"]]#特别注意:区分大小写,查了我半天问题
y = data["Survived"]#特别注意:区分大小写,查了我半天问题
y = y.replace(to_replace="?", value=np.NaN)#值替换
y.dropna()#nan的值所在行都删除
print('\n===x各列的缺失值情况如下:===',x.isnull().sum())
print('\n===y各列的缺失值情况如下:===',y.isnull().sum())
#print(x)
#2.3、数据划分
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22,test_size=0.2)
#3、 特征工程(字典特征抽取)
x_train = x_train.to_dict(orient="records")
x_test = x_test.to_dict(orient="records")
#3、 特征工程 标准化
#print("看看x_train",x_train)
#print("看看y_train",y_train)
#print('\n===y_train各列的缺失值情况如下:===',y_train.isnull().sum())
transfer = DictVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.fit_transform(x_test)
#print(x_train)
#4、 机器学习(决策树)
estimator = DecisionTreeClassifier()
estimator.fit(x_train,y_train)
#5、模型评估
#5.模型评估
#5.1预测值和准确值
y_pre = estimator.predict(x_test)
print("预测值是:\n",y_pre)
score = estimator.score(x_test,y_test)
print("准确率是:\n",score)
#print(x.head())
#print(x_train)
运行结果