kaggle比赛练手之titanic幸存者

感觉处理这种预测题目，数据科学也是一门需要掌握的学科，模型再好，如果喂进去的数据质量很差的话，也不会得到一个优异的评分，这就要求我们对数据保持敏感，从多个维度去思考每个特征之间的直观或者隐藏的关系，要用到的工具很多，慢慢学

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import KFold
from sklearn import preprocessing
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.neighbors import KNeighborsClassifier
data = pd.read_csv('F:/ML/kaggle/titanic/train.csv')
test_data = pd.read_csv('F:/ML/kaggle/titanic/test.csv')

def process(data):
	data['Age'] = data['Age'].fillna(data['Age'].median())
	
	counts = data['Embarked'].value_counts()
	fill = counts.idxmax()
	data['Embarked'] =  data['Embarked'].fillna(fill)

	data.loc[data[&#