TensorFlow泰坦尼克号实战

• 本次实战数据来源于Kaggle，网址是Titanic: Machine Learning from Disaster，可以自行下载，
• 本次任务的目标是根据乘客信息预测他们在Titanic号撞击冰山沉没后能否生存。

准备数据

读取数据

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt
import tensorflow as tf 
from tensorflow.keras import models,layers

dftrain_raw = pd.read_csv('./data/titanic/train.csv')
dftest_raw = pd.read_csv('./data/titanic/test.csv')
print(dftrain_raw.head(10))

数据字段说明

数据预处理

def preprocessing(dfdata):

    dfresult= pd.DataFrame()

    #Pclass
    dfPclass = pd.get_dummies(dfdata['Pclass'])
    dfPclass.columns = ['Pclass_' +str(x) for x in dfPclass.columns ]
    dfresult = pd.concat([dfresult,dfPclass],axis = 1)

    #Sex
    dfSex = pd.get_dummies(dfdata['Sex'])
    dfresult = pd.concat([dfresult,dfSex],axis = 1)

    #Age
    dfresult['Age'] = dfdata['Age'].fillna(0)
    dfresult['Age_null'] = pd.isna(dfdata['Age']).astype('int32')

    #SibSp,Parch,Fare
    dfresult['SibSp'] = dfdata['SibSp']
    dfresult['Parch'] = dfdata['Parch']
    dfresult['Fare'] = dfdata['Fare']

    #Carbin
    dfresult['Cabin_null'] =  pd.isna(dfdata['Cabin']).astype('int32')

    #Embarked
    dfEmbarked = pd.get_dummies(dfdata['Embarked'],dummy_na=True)
    dfEmbarked.columns = ['Embarked_' + str(x) for x in dfEmbarked.columns]
    dfresult = pd.concat([dfresult,dfEmbarked],axis = 1)

    return(dfresult)

x_train = preprocessing(dftrain_raw)
y_train = dftrain_raw['Survived'].values

x_test = preprocessing(dftest_raw)
y_test = dftest_raw['Survived'].values

print("x_train.shape =", x_train.shape )
print("x_test.shape =", x_test.shape )