引入必要庫
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
讀取源文件并打印
在這部分嗽交，我們接觸了基本的csv操作，并顯示結(jié)果。
我們讀入kaggle上下載的train.csv文件弊添，并展示內(nèi)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)
讀取源文件并提取數(shù)據(jù)，建立神經(jīng)網(wǎng)絡(luò)
在這部分捌木，我們讀取源文件中的性別油坝，階級，船費(fèi)以及SibSp，用于擬合最終的生存概率
然后我們建立一個(gè)總共5層澈圈，中間3層的神經(jīng)網(wǎng)絡(luò)彬檀，神經(jīng)元的個(gè)數(shù)分別是4-10-20-10-2。
然后運(yùn)行讀取函數(shù)瞬女。
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)
創(chuàng)建輸入數(shù)據(jù)
我們將訓(xùn)練數(shù)據(jù)和標(biāo)簽包裝成一個(gè)二元組窍帝，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()
訓(xùn)練數(shù)據(jù)
我們開始訓(xùn)練神經(jīng)網(wǎng)絡(luò)
def train():
classifier.fit(input_fn=get_train_inputs, steps=2000)
train()
檢查準(zhǔn)確度
我們使用整個(gè)數(shù)據(jù)集來查看準(zhǔn)確度。注意诽偷，我們應(yīng)該使用驗(yàn)證集來完成這件事坤学。但是由于我們只是用來演示，所以就算了
accuracy_score = classifier.evaluate(input_fn=get_train_inputs,
steps=1)["accuracy"]
print("accuracy:",accuracy_score)
讀入測試集渤刃，并輸出結(jié)果
在這一部分拥峦，我們將讀入kaggle中的數(shù)據(jù)，并輸出到文件中卖子，最終提交官網(wǎng)
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
最終在只使用了4個(gè)特征值的情況下略号，準(zhǔn)確率有75%。接下來的目標(biāo)是將其他數(shù)據(jù)進(jìn)行利用洋闽。
