美文网首页
04泰坦尼克数据分析

04泰坦尼克数据分析

作者: Jachin111 | 来源:发表于2022-12-23 17:56 被阅读0次

数据探索

# 导入库
import pandas as pd
import numpy as np
import random as rnd

import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC,LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier

import warnings
warnings.filterwarnings("ignore")

# 导入数据
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
train.shape
image.png 
test.shape
image.png 
combine = [train,test]

# 字段信息
train.columns
image.png 
# 字段分类
train.dtypes
image.png 
# 缺失值
train.isnull().sum()
image.png 
test.isnull().sum()
image.png 
train.info()
image.png

数据假设

删除字段
本项目主要是考察其他字段和Survival字段的关系
重点关注字段：Age、Embarked
删除字段：对数据分析没有作用，直接删除的字段：Ticket（票号）、Cabin（客舱号）、PassengerId（乘客号）、Name（姓名）

修改、增加字段
增加Family：根据Parch（船上的兄弟姐妹个数） 和 SibSp（船上的父母小孩个数）
从Name字段中提取Title作为新特征
将年龄Age字段转成有序的分类特征
创建一个基于票价Fare 范围的特征

猜想
女人（Sex=female）更容易生还
小孩（Age>？）更容易生还
船舱等级高的乘客更容易生还（Pclass=1）

统计分析

# 1.船舱等级(1-头等，2-二等，3-三等)
train[["Pclass","Survived"]].groupby(["Pclass"],as_index=False).mean().sort_values(by="Survived",ascending=False)
image.png 
# 2.性别
train[["Sex","Survived"]].groupby(["Sex"],as_index=False).mean().sort_values(by="Survived",ascending=False)
image.png 
# 3.兄弟姐妹/配偶数
train[["SibSp","Survived"]].groupby(["SibSp"],as_index=False).mean().sort_values(by="Survived",ascending=False)
image.png 
# 4.父母/孩子数
train[["Parch","Survived"]].groupby("Parch",as_index=False).mean().sort_values(by="Survived",ascending=False)
image.png

可视化分析

# 年龄与生还
g = sns.FacetGrid(train,col="Survived")
g.map(plt.hist,"Age",bins=20)

plt.show()
image.png 
# 舱位与生还
grid = sns.FacetGrid(train,col="Survived",row="Pclass",aspect=1.6)
grid.map(plt.hist,"Age",alpha=0.5,bins=20)
grid.add_legend()

plt.show()
image.png 
# 登船低点、性别与生还关系
grid = sns.FacetGrid(train,row="Embarked",aspect=1.6)
grid.map(sns.pointplot,"Pclass","Survived","Sex",palette="deep")
grid.add_legend()

plt.show()
image.png 
# 票价、舱位与生还
grid = sns.FacetGrid(train,row="Embarked",col="Survived",aspect=1.6)
grid.map(sns.barplot,"Sex","Fare",alpha=.5,ci=None)
grid.add_legend()

plt.show()
image.png

删除无效字段

print("Before",train.shape,test.shape,combine[0].shape,combine[1].shape)
image.png 
train = train.drop(["Ticket","Cabin"],axis=1)
test = test.drop(["Ticket","Cabin"],axis=1)
combine = [train,test]

print("After",train.shape,test.shape,combine[0].shape,combine[1].shape)
image.png

生成新特征

# 字段Name处理
for dataset in combine:
    dataset["Title"] = dataset.Name.str.extract('([A-Za-z]+)\.',expand=False)
    
train.groupby(["Sex","Title"]).size().reset_index()
image.png 
pd.crosstab(train["Title"],train["Sex"])
image.png 
for dataset in combine:
    dataset["Title"] = dataset["Title"].replace(["Lady","Countess","Capt","Col","Don","Dr","Major","Rev","Sir","Jonkheer","Dona"],"Rare")
    dataset["Title"] = dataset["Title"].replace("Mlle","Miss")
    dataset["Title"] = dataset["Title"].replace("Ms","Miss")
    dataset["Title"] = dataset["Title"].replace("Mme","Mrs")
    
train[["Title","Survived"]].groupby("Title",as_index=False).mean()
image.png 
title_mapping = {"Mr":1,"Miss":2,"Mrs":3,"Master":4,"Rare":5}

for dataset in combine:
    dataset["Title"] = dataset["Title"].map(title_mapping)
    dataset["Title"] = dataset["Title"].fillna(0)
    
train.head()
image.png 
train = train.drop(["Name","PassengerId"],axis=1)
test = test.drop(["Name"],axis=1)

combine = [train,test]
print(train.shape,test.shape)
image.png 
# 字段Sex
for dataset in combine:
    dataset["Sex"] = dataset["Sex"].map({"female":1,"male":0}).astype(int)

grid = sns.FacetGrid(train,row="Pclass",col="Sex",aspect=1.6)
grid.map(plt.hist,"Age",alpha=.5,bins=20)
grid.add_legend()

plt.show()
image.png 
# 字段Age
# 1.字段的缺失值处理
train.isnull().sum()
image.png 
guess_ages = np.zeros((2,3))

for dataset in combine:
    for i in range(0,2):
        for j in range(0,3):
            guess_df = dataset[(dataset["Sex"]==i)&(dataset["Pclass"]==j+1)]["Age"].dropna()
            age_guess = guess_df.median()
            guess_ages[i,j] = int(age_guess/0.5 + 0.5)*0.5
            
    for i in range(0,2):
        for j in range(0,3):
            dataset.loc[(dataset.Age.isnull())&(dataset.Sex==i)&(dataset.Pclass==j+1),"Age"] = guess_ages[i,j]
    dataset["Age"] = dataset["Age"].astype(int)
    
train.isnull().sum()
image.png 
# 2.年龄分段分箱
train["AgeBand"] = pd.cut(train["Age"],5)
train.head()
image.png 
train[["AgeBand","Survived"]].groupby(["AgeBand"],as_index=False).mean().sort_values(by="AgeBand",ascending=True)
image.png 
# 3.转成数值类型
for dataset in combine:
    dataset.loc[dataset["Age"]<=16,"Age"] = 0
    dataset.loc[(dataset["Age"]>16) & (dataset["Age"]<=32),"Age"] = 1
    dataset.loc[(dataset["Age"]>32) & (dataset["Age"]<=48),"Age"] = 2
    dataset.loc[(dataset["Age"]>48) & (dataset["Age"]<=64),"Age"] = 3
    dataset.loc[dataset["Age"]>64,"Age"] = 4
    
train = train.drop(["AgeBand"],axis=1)
combine = [train,test]

字段处理

# 生成新字段1
for dataset in combine:
    dataset["FamilySize"] = dataset["SibSp"] + dataset["Parch"] + 1
    
train[["FamilySize","Survived"]].groupby(["FamilySize"],as_index=False).mean().sort_values(by="Survived",ascending=False)
image.png 
for dataset in combine:
    dataset["IsAlone"] = 0
    dataset.loc[dataset["FamilySize"]==1,"IsAlone"] = 1
    
train[["IsAlone","Survived"]].groupby(["IsAlone"],as_index=False).mean()
image.png 
train = train.drop(["Parch","SibSp","FamilySize"],axis=1)
test = test.drop(["Parch","SibSp","FamilySize"],axis=1)
combine = [train,test]

train.head()
image.png 
# 生成新字段2
for dataset in combine:
    dataset["Age*Class"] = dataset.Age * dataset.Pclass
    
train.head()
image.png 
# Embarked字段的分类
train.isnull().sum()
image.png 
freq_port = train["Embarked"].dropna().mode()[0]
freq_port
image.png 
for dataset in combine:
    dataset["Embarked"] = dataset["Embarked"].fillna(freq_port)

train[["Embarked","Survived"]].groupby(["Embarked"],as_index=False).mean().sort_values(by="Survived",ascending=False)
image.png 
for dataset in combine:
    dataset["Embarked"] = dataset["Embarked"].map({"S":0,"C":1,"Q":2}).astype(int)
    
train.head()
image.png 
# Fare字段处理
train.isnull().sum()
image.png 
test.isnull().sum()
image.png 
test["Fare"].fillna(test["Fare"].dropna().median(),inplace=True)
test.head()
image.png 
train["FareBand"] = pd.qcut(train["Fare"],4)
train[["FareBand","Survived"]].groupby(["FareBand"],as_index=False).mean().sort_values(by="FareBand",ascending=True)
image.png 
for dataset in combine:
    dataset.loc[dataset["Fare"]<=7.91,"Fare"] = 0
    dataset.loc[(dataset["Fare"]>7.91) & (dataset["Fare"]<=14.454),"Fare"] = 1
    dataset.loc[(dataset["Fare"]>14.454) & (dataset["Fare"]<=31),"Fare"] = 2
    dataset.loc[dataset["Fare"]>31,"Fare"] = 3
    dataset["Fare"] = dataset["Fare"].astype(int)
    
train = train.drop(["FareBand"],axis=1)
combine = [train,test]

test.head()
image.png

建模

X_train = train.drop("Survived",axis=1)
Y_train = train["Survived"]

X_test = test.drop("PassengerId",axis=1).copy()

print(X_train.shape,Y_train.shape,X_test.shape)
image.png 
# 模型1：逻辑回归
logreg = LogisticRegression()
logreg.fit(X_train,Y_train)

Y_pred = logreg.predict(X_test)
acc_log = round(logreg.score(X_train,Y_train)*100,2)
acc_log
image.png 
coeff_df = pd.DataFrame(train.columns[1:])
coeff_df.columns = ["Features"]
coeff_df["Correlation"] = pd.Series(logreg.coef_[0])

coeff_df.sort_values(by="Correlation",ascending=False)
image.png 
# 模型2：支持向量机SVM
svc = SVC()
svc.fit(X_train,Y_train)

Y_pred = svc.predict(X_test)
acc_svc = round(svc.score(X_train,Y_train)*100,2)
acc_svc
image.png 
# 模型3：KNN
knn = KNeighborsClassifier(n_neighbors=3)
knn.fit(X_train,Y_train)

Y_pred = knn.predict(X_test)
acc_knn = round(knn.score(X_train,Y_train)*100,2)
acc_knn
image.png 
# 模型4：朴素贝叶斯
gaussian = GaussianNB()
gaussian.fit(X_train,Y_train)

Y_pred = gaussian.predict(X_test)
acc_gaussian = round(gaussian.score(X_train,Y_train)*100,2)
acc_gaussian
image.png 
# 模型5：感知机
perceptron = Perceptron()
perceptron.fit(X_train,Y_train)

Y_pred = perceptron.predict(X_test)
acc_perceptron = round(perceptron.score(X_train,Y_train)*100,2)
acc_perceptron
image.png 
# 模型6：线性支持向量分类
linear_svc = LinearSVC()
linear_svc.fit(X_train,Y_train)

Y_pred = linear_svc.predict(X_test)
acc_linear_svc = round(linear_svc.score(X_train,Y_train)*100,2)
acc_linear_svc
image.png 
# 模型7：随机梯度下降
sgd = SGDClassifier()
sgd.fit(X_train,Y_train)

Y_pred = sgd.predict(X_test)
acc_sgd = round(sgd.score(X_train,Y_train)*100,2)
acc_sgd
image.png 
# 模型8：决策树
decision_tree = DecisionTreeClassifier()
decision_tree.fit(X_train,Y_train)

Y_pred = decision_tree.predict(X_test)
acc_decision_tree = round(decision_tree.score(X_train,Y_train)*100,2)
acc_decision_tree
image.png 
# 模型9：随机森林
random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(X_train,Y_train)

Y_pred = random_forest.predict(X_test)
acc_random_forest = round(random_forest.score(X_train,Y_train)*100,2)
acc_random_forest
image.png

模型对比

models = pd.DataFrame({
    "Model":["Support Vector Machines","KNN","Logistic Regression",
            "Random Forest","Naive Bayes","Perceptron",
            "Stochastic Gradient Decent","Linear SVC","Decision Tree"],
    "Score":[acc_svc,acc_knn,acc_log,
            acc_random_forest,acc_gaussian,acc_perceptron,
            acc_sgd,acc_linear_svc,acc_decision_tree]
})

models.sort_values(by="Score",ascending=False)
image.png

相关文章

网友评论

      本文标题：04泰坦尼克数据分析

      本文链接：https://www.haomeiwen.com/subject/cftiqdtx.html

      延伸阅读

      深度阅读

      • 您也可以注册成为美文阅读网的作者，发表您的原创作品、分享您的心情！

      栏目导航

      热点阅读

      关于我们|服务条款|联系我们|04泰坦尼克数据分析|投稿指南|网站地图|RSS订阅|排版工具|手机版

      提供经典美文摘抄,优美散文欣赏,现代诗歌精选,短篇小说,心情随笔,表白情书范文,故事会在线阅读欣赏

      Copyright © 2014-2023 Haomeiwen.com All Rights Reserved. 好美文阅读网 版权所有

      备案信息：桂公网安备 45052102000051号 · 桂ICP备13007215号-3

      本站所收录作品、热点评论等信息部分来源互联网，目的只是为了系统归纳学习和传递资讯

      所有作品版权归原创作者所有，与本站立场无关，如不慎侵犯了你的权益，请联系我们告知，我们将做删除处理！