使用Tensorflow完成Kaggle任务——泰坦尼克号Titanic: Machine Learning from Disaster

引入必要库

import csv
import tensorflow as tf
import numpy as np
import random
import sys
import pandas as pd
from pandas import DataFrame

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

读取源文件并打印

在这部分，我们接触了基本的csv操作，并显示结果。
我们读入kaggle上下载的train.csv文件，并展示内容

trainFilePath = './train.csv'

trainSize = 0

def testCSV(filePath):
    with open(filePath, 'rb') as trainFile:
        global trainSize
        csvReader = csv.reader(trainFile)
        dataList = [data for data in csvReader]
        df = DataFrame(dataList[1:], columns=dataList[0])
        trainSize = len(df)
        print(df)
        print("trainSize", trainSize)

testCSV(trainFilePath)

读取源文件并提取数据，建立神经网络

在这部分，我们读取源文件中的性别，阶级，船费以及SibSp，用于拟合最终的生存概率
然后我们建立一个总共5层，中间3层的神经网络，神经元的个数分别是4-10-20-10-2。
然后运行读取函数。

def readTrainDataCSV(filePath):
    global trainData, targetData, classifier
    with open(filePath, 'rb') as trainFile:
        csvReader = csv.reader(trainFile)
        dataList = [data for data in csvReader]
        dataSize = len(dataList) - 1
        trainData = np.ndarray((dataSize, 4), dtype=np.float32)
        targetData = np.ndarray((dataSize, 1), dtype=np.int32)
        trainDataFrame = DataFrame(dataList[1:], columns=dataList[0])
        trainDataFrame_fliter = trainDataFrame.loc[:,['Pclass','Sex','SibSp','Fare','Survived']]
        for i in range(dataSize):
            thisData = np.array(trainDataFrame_fliter.iloc[i])
            Pclass,Sex,SibSp,Fare,Survived = thisData
            Pclass = float(Pclass)
            Sex = 0 if Sex == 'female' else 1
            SibSp = float(SibSp)
            Fare = float(Fare)
            Survived = int(Survived)
            print(Pclass,Sex,SibSp,Fare,Survived)
            trainData[i,:] = [Pclass,Sex,SibSp,Fare]
            targetData[i,:] = [Survived]
            print(thisData)
        print(trainData)
        print(targetData)
        feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
        classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,
                                              hidden_units=[10, 20, 10],
                                              n_classes=2)
#                                               model_dir="/tmp/titanic_model")

readTrainDataCSV(trainFilePath)

创建输入数据

我们将训练数据和标签包装成一个二元组，并返回

def get_train_inputs():
    x = tf.constant(trainData)
    y = tf.constant(targetData)
    print(x)
    print(y)
    return x, y

get_train_inputs()

训练数据

我们开始训练神经网络

def train():
    classifier.fit(input_fn=get_train_inputs, steps=2000)

train()

检查准确度

我们使用整个数据集来查看准确度。注意，我们应该使用验证集来完成这件事。但是由于我们只是用来演示，所以就算了

accuracy_score = classifier.evaluate(input_fn=get_train_inputs,
                                       steps=1)["accuracy"]
print("accuracy:",accuracy_score)

读入测试集，并输出结果

在这一部分，我们将读入kaggle中的数据，并输出到文件中，最终提交官网

testFilePath = './test.csv'

def readTestDataCSV(filePath):
    global testData, PassengerIdStart
    with open(filePath, 'rb') as testFile:
        csvReader = csv.reader(testFile)
        dataList = [data for data in csvReader]
        dataSize = len(dataList)-1
        trainDataFrame = DataFrame(dataList[1:], columns=dataList[0])
        trainDataFrame_fliter = trainDataFrame.loc[:,['Pclass','Sex','SibSp','Fare']]
        testData = np.ndarray((dataSize, 4), dtype=np.float32)
        PassengerIdStart = trainDataFrame['PassengerId'][0]
        PassengerIdStart = int(PassengerIdStart)
        print('PassengerId',PassengerIdStart)
        for i in range(dataSize):
            thisData = np.array(trainDataFrame_fliter.iloc[i])
            Pclass,Sex,SibSp,Fare = thisData
            Pclass = float(Pclass)
            Sex = 0 if Sex == 'female' else 1
            SibSp = float(SibSp)
            Fare = 0 if Fare=='' else float(Fare)
            print(Pclass,Sex,SibSp,Fare)
            testData[i,:] = [Pclass,Sex,SibSp,Fare]
            print(thisData)
        print(testData)
        
def testData_samples():
    return testData

readTestDataCSV(testFilePath)
predictions = list(classifier.predict(input_fn=testData_samples))
print(predictions)


with open('predictions.csv', 'wb') as csvfile:
    writer = csv.writer(csvfile, dialect='excel')
    writer.writerow(['PassengerId','Survived'])
    PassengerId = PassengerIdStart 
    for i in predictions:
        writer.writerow([PassengerId, i])
        PassengerId += 1

最终在只使用了4个特征值的情况下，准确率有75%。接下来的目标是将其他数据进行利用。