Kaggle--泰坦尼克号失踪者生死情况预测源码(附Titanic数据集)

数据可视化分析

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np

titanic=pd.read_csv('train.csv')
#print(titanic.head())
#设置某一列为索引
#print(titanic.set_index('PassengerId').head())

# =============================================================================
# #绘制一个展示男女乘客比例的扇形图
# #sum the instances of males and females
# males=(titanic['Sex']=='male').sum()
# females=(titanic['Sex']=='female').sum()
# #put them into a list called proportions
# proportions=[males,females]
# #Create a pie chart
# plt.pie(
# #        using proportions
#         proportions,
# #        with the labels being officer names
#         labels=['Males','Females'],
# #        with no shadows
#         shadow=False,
# #        with colors
#         colors=['blue','red'],
#         explode=(0.15,0),
#         startangle=90,
#         autopct='%1.1f%%'
#         )
# plt.axis('equal')
# plt.title("Sex Proportion")
# plt.tight_layout()
# plt.show()
# =============================================================================


# =============================================================================
# #绘制一个展示船票Fare,与乘客年龄和性别的散点图
# #creates the plot using
# lm=sns.lmplot(x='Age',y='Fare',data=titanic,hue='Survived',fit_reg=False)
# #set title
# lm.set(title='Fare x Age')
# #get the axes object and tweak it
# axes=lm.axes
# axes[0,0].set_ylim(-5,)
# axes[0,0].set_xlim(-5,85)
# =============================================================================

# =============================================================================
# #绘制一个展示船票价格的直方图
# #sort the values from the top to least value and slice the first 5 items
# df=titanic.Fare.sort_values(ascending=False)
# #create bins interval using numpy
# binsVal=np.arange(0,600,10)
# #create the plot
# plt.hist(df,bins=binsVal)
# plt.xlabel('Fare')
# plt.ylabel('Frequency')
# plt.title('Fare Payed Histrogram')
# plt.show()
# =============================================================================

#哪个性别的年龄的平均值更大
#print(titanic.groupby('Sex').Age.mean())
#打印出不同性别的年龄的描述性统计信息
#print(titanic.groupby('Sex').Age.describe())
#print(titanic.groupby(['Sex','Survived']).Fare.describe())
#先对Survived再Fare进行排序
#a=titanic.sort_values(['Survived','Fare'],ascending=False)
#print(a)
#选取名字以字母A开头的数据
#b=titanic[titanic.Name.str.startswith('A')]
#print(b)
#找到其中三个人的存活情况
#c=titanic.loc[titanic.Name.isin(['Youseff, Mr. Gerious','Saad, Mr. Amin','Yousif, Mr. Wazli'])\
#              ,['Name','Survived']]
#print(c)
# =============================================================================
# ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
# ts = ts.cumsum()
# ts.plot()
# plt.show()
# 
# df = pd.DataFrame(np.random.randn(1000, 4),index=ts.index,columns=['A', 'B', 'C', 'D'])
# df=df.cumsum()
# plt.figure()
# df.plot()
# plt.legend(loc='best')
# plt.show()
# =============================================================================
#对应每一个location,一共有多少数据值缺失
#print(titanic.isnull().sum())
#对应每一个location,一共有多少数据值完整
#print(titanic.shape[0]-titanic.isnull().sum())
#查看每个列的数据类型
#print(titanic.info())
#print(titanic.dtypes)

主程序
# -*- coding: utf-8 -*-
"""
Created on Tue Apr 10 17:21:16 2018


@author: CSH
"""


import pandas as pd
titanic=pd.read_csv("train.csv")
#print(titanic.describe())


titanic["Age"]=titanic["Age"].fillna(titanic["Age"].median())
#print(titanic.describe())


#print(titanic["Sex"].unique())
titanic.loc[titanic["Sex"]=="male","Sex"]=0
titanic.loc[titanic["Sex"]=="female","Sex"]=1


#print(titanic["Embarked"].value_counts())
titanic["Embarked"]=titanic["Embarked"].fillna("S")
titanic.loc[titanic["Embarked"]=="S","Embarked"]=0
titanic.loc[titanic["Embarked"]=="C","Embarked"]=1
titanic.loc[titanic["Embarked"]=="Q","Embarked"]=2
#线性回归
# =============================================================================
# from sklearn.linear_model import LinearRegression
# from sklearn.cross_validation import KFold
# predictors=["Pclass","Sex","Age","SibSp","Parch","Fare","Embarked"]
# alg=LinearRegression()
# kf=KFold(titanic.shape[0],n_folds=3,random_state=1)
# predictions=[]
# for train,test in kf:
#     train_predictors=(titanic[predictors].iloc[train,:])
#     train_target=titanic["Survived"].iloc[train]
#     alg.fit(train_predictors,train_target)
#     test_predictions=alg.predict(titanic[predictors].iloc[test,:])
#     predictions.append(test_predictions)
# 
# 
# import numpy as np
# predictions=np.concatenate(predictions,axis=0)
# predictions[predictions>.5]=1
# predictions[predictions<=.5]=0
# accuracy=sum(predictions==titanic["Survived"])/len(predictions)
# print(accuracy)
# =============================================================================
#逻辑回归
# =============================================================================
from sklearn.linear_model import LogisticRegression
from sklearn import cross_validation
# predictors=["Pclass","Sex","Age","SibSp","Parch","Fare","Embarked"]
# alg=LogisticRegression(random_state=1)
# scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic["Survived"],cv=3)
# print(scores.mean())
# =============================================================================
#随机森林
# =============================================================================
# from sklearn import cross_validation
# from sklearn.ensemble import RandomForestClassifier
# predictors=["Pclass","Sex","Age","SibSp","Parch","Fare","Embarked"]
# alg=RandomForestClassifier(random_state=1,n_estimators=150,min_samples_split=12,min_samples_leaf=1)
# kf=cross_validation.KFold(titanic.shape[0],n_folds=3,random_state=1)
# scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic["Survived"],cv=kf)
# print(scores.mean())
# =============================================================================


titanic["FamilySize"]=titanic["SibSp"]+titanic["Parch"]
titanic["NameLength"]=titanic["Name"].apply(lambda x:len(x))


#提取名字信息
import re
def get_title(name):
    title_search=re.search('([A-Za-z]+)\.',name)
    if title_search:
        return title_search.group(1)
    return ""


titles=titanic["Name"].apply(get_title)
#print(pd.value_counts(titles))


title_mapping={"Mr":1,"Miss":2,"Mrs":3,"Master":4,"Dr":5,"Rev":6,"Mlle":7,"Major":8,"Col":9,"Ms":10,"Mme":11,"Lady":12,"Sir":13,"Capt":14,"Don":15,"Jonkheer":16,"Countess":17}
for k,v in title_mapping.items():
    titles[titles==k]=v
#print(pd.value_counts(titles))
titanic["Title"]=titles
#特征选择
# =============================================================================
# import numpy as np
# from sklearn.feature_selection import SelectKBest,f_classif
# import matplotlib.pyplot as plt
# predictors=["Pclass","Sex","Age","SibSp","Parch","Fare","Embarked","FamilySize","Title","NameLength"]
# selector=SelectKBest(f_classif,k=5)
# selector.fit(titanic[predictors],titanic["Survived"])
# scores=-np.log10(selector.pvalues_)
# 
# plt.bar(range(len(predictors)),scores)
# plt.xticks(range(len(predictors)),predictors,rotation='vertical')
# plt.show()
# =============================================================================


# =============================================================================
# from sklearn import cross_validation
# from sklearn.ensemble import RandomForestClassifier
# predictors=["Pclass","Sex","Fare","Title","NameLength"]
# alg=RandomForestClassifier(random_state=1,n_estimators=50,min_samples_split=12,min_samples_leaf=1)
# kf=cross_validation.KFold(titanic.shape[0],n_folds=3,random_state=1)
# scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic["Survived"],cv=kf)
# print(scores.mean())
# =============================================================================


#集成学习
from sklearn.cross_validation import KFold
from sklearn.ensemble import GradientBoostingClassifier
import numpy as np
algorithms=[
        [GradientBoostingClassifier(random_state=1,n_estimators=25,max_depth=3),["Pclass","Sex","Fare","Title","NameLength"]],
        [LogisticRegression(random_state=1),["Pclass","Sex","Fare","Title","NameLength"]]]


kf=KFold(titanic.shape[0],n_folds=3,random_state=1)
predictions=[]
for train,test in kf:
    train_target=titanic["Survived"].iloc[train]
    full_test_predictions=[]
    for alg,predictors in algorithms:
        alg.fit(titanic[predictors].iloc[train,:],train_target)
        test_predictions=alg.predict_proba(titanic[predictors].iloc[test,:].astype(float))[:,1]
        full_test_predictions.append(test_predictions)
    test_predictions=(full_test_predictions[0]+full_test_predictions[1])/2
    test_predictions[test_predictions<=.5]=0
    test_predictions[test_predictions>.5]=1
    predictions.append(test_predictions)








predictions=np.concatenate(predictions,axis=0)
accuracy=sum(predictions==titanic["Survived"])/len(predictions)
print(accuracy)

附:链接:https://pan.baidu.com/s/1K1USWVQQOEM9OLr3M1pniw 密码:n8wz
已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 大白 设计师:CSDN官方博客 返回首页