泰坦尼克号数据分析 预测建模 准确率测算

本文思路：

https://blog.csdn.net/u013788252/article/details/105528116

（运行环境: jupyter notebook python3）
完善后的完整代码：
下面展示 完整代码。

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
get_ipython().run_line_magic('matplotlib', 'inline')
from sklearn.linear_model import LogisticRegressionCV
from sklearn.ensemble import RandomForestClassifier
from sklearn import tree
from sklearn.model_selection import train_test_split

path=r'C:\Users\Administrator\Desktop\titanic.csv'

data = pd.read_csv(path)
data['Survived'].value_counts().plot.pie(autopct='%0.2f%%')

data[['Sex','Survived']].groupby(['Sex']).mean().plot.bar()

data[['Pclass','Survived']].groupby(['Pclass']).mean().plot.bar()

bins = [0, 12, 18, 65, 100]
data['Age_group'] = pd.cut(data['Age'], bins)
by_age = data.groupby('Age_group')['Survived'].mean()
by_age.plot.bar()

fig, ax = plt.subplots(1, 2, figsize = (18, 8))
sns.violinplot("Pclass", "Age", hue="Survived", data=data, split=True, ax=ax[0])
ax[0].set_title('Pclass and Age vs Survived')

sns.violinplot("Sex", "Age", hue="Survived", data=data, split=True, ax=ax[1])
ax[1].set_title('Sex and Age vs Survived')

plt.show()

data.Embarked[data.Embarked.isnull()] = data.Embarked.dropna().mode().values

from sklearn.ensemble import RandomForestRegressor
age_df = data[['Age','Survived','Fare', 'Parch', 'SibSp', 'Pclass']]
age_df_notnull = age_df.loc[(data['Age'].notnull())]
age_df_isnull = age_df.loc[(data['Age'].isnull())]
X = age_df_notnull.values[:,1:]
Y = age_df_notnull.values[:,0]
RFR = RandomForestRegressor(n_estimators=1000, n_jobs=-1)
RFR.fit(X,Y)
predictAges = RFR.predict(age_df_isnull.values[:,1:])
data.loc[data['Age'].isnull(), ['Age']]= predictAges

df =pd.get_dummies(data)

x=df.drop('Survived',1)
y=df.Survived
x_train,x_test,y_train,y_test = train_test_split(x, y, test_size=0.2, random_state=0)

lr = LogisticRegressionCV(multi_class='ovr',fit_intercept=True, Cs=np.logspace(-2, 2, 20), cv=2, penalty='l2', solver='lbfgs', tol=0.01)

re=lr.fit(x_train, y_train)

print("准确率:",lr.score(x_test, y_test))

（截止上一步已完成了建模与准确率测算）
本部分结合参考：https://blog.csdn.net/weixin_43532000/article/details/108086363

分析中用到的相关库

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')
seed =2020

PassengerId => 乘客ID
Survived=>是否生存下来
Pclass => 乘客等级(1/2/3等舱位)
Name => 乘客姓名
Sex => 性别
Age => 年龄
SibSp => 堂兄弟/妹个数
Parch => 父母与小孩个数
Ticket => 船票信息
Fare => 票价
Cabin => 客舱
Embarked => 登船港口

如下代码也可查看数据情况： 代码片。

def _data_info(data,categorical_features):
    print('number of train examples = {}'.format(data.shape[0]))
    print('number of train Shape = {}'.format(data.shape))
    print('Features={}'.format(data.columns))
    print('\n--------输出类别特征的种类--------')
    for i in categorical_features:
        if i in list(data.columns):
            print("train："+i+":",list(data[i].unique()))
    print('\n--------缺失值--------')
    missing = data.isnull().sum()
    missing = missing[missing > 0]
    print(missing)
    missing.sort_values(inplace=True)
    missing.plot.bar()
    plt.show()
def data_info(data_train,data_test,categorical_features):
    print('--------训练集基本概况--------')
    _data_info(data_train,categorical_features)
    print('\n\n--------测试集基本概况--------')
    _data_info(data_test,categorical_features)

调用函数：

data_info(train_df,test_df,['Survived','Pclass','Sex','Cabin','Embarked','SibSp','Parch'])

数据清洗及分析在jupyter notebook中进行，便于观察及分析。

代码如下：

train_df['train'] = 1
test_df['train'] = 0
data_df = pd.concat([train_df,test_df],sort=True).reset_index(drop=True)

data_df.drop('PassengerId',inplace=True,axis=1)

from sklearn import preprocessing
ler_sex = preprocessing.LabelEncoder()
ler_sex.fit(data_df['Sex'])
data_df['Sex'] = ler_sex.transform(data_df['Sex'])

data_df['Embarked'].fillna(data_df['Embarked'].mode()[0],inplace=True)

ler_Embarked = preprocessing.LabelEncoder()
ler_Embarked.fit(data_df['Embarked'])
data_df['Embarked'] = ler_Embarked.transform(data_df['Embarked'])

data_df.drop('Cabin',inplace=True,axis=1)

在该阶段可以自由分析，维度自行选择。最终得到清洗好的集合即可。

train_data = data_df[data_df.train==1]
train_data['Survived'] = train_df['Survived']
train_data.drop('train',axis=1,inplace=True)

test_data = data_df[data_df.train==0]
test_data.drop(['Survived','train'],axis=1,inplace=True)

import pandas as pd

from sklearn.model_selection import train_test_split
if __name__ == "__main__":
    data = pd.read_csv(r'C:\Users\Administrator\Desktop\titanic.csv')

    x = data.iloc[:,:-1]
    y = data.iloc[:,-1]

    x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=0)

    print(len(x_train))
    print(len(x_test))
    res_train = pd.concat([x_train, y_train], axis=1, ignore_index=True)
    res_test = pd.concat([x_test, y_test], axis=1, ignore_index=True)
    print(len(res_train))
    print(len(res_test))
    res_train.columns = data.columns
    res_test.columns = data.columns    res_train.to_csv(r'C:\Users\Administrator\Desktop\titanic_train.csv', index=False, header=True)    res_test.to_csv(r'C:\Users\Administrator\Desktop\titanic_test.csv', index=False, header=True)

Original: https://blog.csdn.net/caoyatingde/article/details/122594773
Author: dai_ricky
Title: 泰坦尼克号数据分析 预测建模 准确率测算