kaggle实例学习-Titanic(2)

继续完善很久以前没有写完的东西。。。

import csv as csv import numpy as npcsv_file_object = csv.reader(open('train.csv', 'rb')) header = csv_file_object.next()data=[]for row in csv_file_object:    data.append(row)data = np.array(data)#将list转成arrayprint data

看看结果:

[['1' '0' '3' ..., '7.25' '' 'S'] ['2' '1' '1' ..., '71.2833' 'C85' 'C'] ['3' '1' '3' ..., '7.925' '' 'S'] ...,  ['889' '0' '3' ..., '23.45' '' 'S'] ['890' '1' '1' ..., '30' 'C148' 'C'] ['891' '0' '3' ..., '7.75' '' 'Q']]

现在的data为array类型，注意到data里的元素都属于同意类型，即字符串类型。
完整查看第一行和最后一行的数据：

In [7]:data[0]Out[7]:array(['1', '0', '3', 'Braund, Mr. Owen Harris', 'male', '22', '1', '0',       'A/5 21171', '7.25', '', 'S'],       dtype='|S82')In [8]:data[-1]Out[8]:array(['891', '0', '3', 'Dooley, Mr. Patrick', 'male', '32', '0', '0',       '370376', '7.75', '', 'Q'],       dtype='|S82')

再进行统计时需要将string转为float

number_passengers = np.size(data[0::,1].astype(np.float))

简单统计下survived的人数

In [11]:number_survived = np.sum(data[0::,1].astype(np.float))In [12]:number_survivedOut[12]:342.0

计算一下生存率:

In [13]:proportion_survivors = number_survived / number_passengersIn [14]:proportion_survivorsOut[14]:0.38383838383838381

把人群中male和female记录下来：

women_only_stats = data[0::,4] == "female"men_only_stats = data[0::,4] != "female"

将male和female分开分析一下：

women_onboard = data[women_only_stats,1].astype(np.float)     men_onboard = data[men_only_stats,1].astype(np.float)

计算下男女获救的比例：

In [23]:proportion_women_survived = \                       np.sum(women_onboard) / np.size(women_onboard)  In [24]:proportion_men_survived = \                       np.sum(men_onboard) / np.size(men_onboard)In [26]:proportion_women_survivedOut[26]:0.7420382165605095In [27]:proportion_men_survivedOut[27]:0.18890814558058924

我的天！男女获救比例相差极大，看来Lady First 这一点做得很好！这样我们就大概从数据中学到了以上结果，现在在test.csv中测试一下:

In [28]:test_file = open('test.csv', 'rb')test_file_object = csv.reader(test_file)header = test_file_object.next()In [29]:prediction_file = open("genderbasedmodel.csv", "wb")prediction_file_object = csv.writer(prediction_file)In [30]:prediction_file_object.writerow(["PassengerId", "Survived"])for row in test_file_object:       # For each row in test.csv    if row[3] == 'female':         # is it a female, if yes then                                               prediction_file_object.writerow([row[0],'1'])    # predict 1    else:                              # or else if male,               prediction_file_object.writerow([row[0],'0'])    # predict 0test_file.close()prediction_file.close()

看一下预测结果:

………
现在得到的这个结果文件已经是可以submission了！