关于泰坦尼克号之灾

泰坦尼克号之灾

使人觉得遥远的不是时间长，而是两三件不可挽回的事。 from 博尔赫斯

1. import pandas as pd #数据分析

2. import numpy as np #科学计算

3. from pandas import Series,DataFrame

4. data_train = pd.read_csv("/Titanic_data/Train.csv")

5. import matplotlib.pyplot as plt

6. 
   

7. fig = plt.figure()

8. fig.set(alpha=0.2)  # 设定图表颜色alpha参数

9. plt.subplot2grid((2,3),(0,0))             # 在一张大图里分列几个小图

10. data_train.Survived.value_counts().plot(kind='bar')# 柱状图

11. plt.title(u"获救情况 (1为获救)") # 标题

12. plt.ylabel(u"人数")

13. 
    

14. plt.subplot2grid((2,3),(0,1))

15. data_train.Pclass.value_counts().plot(kind="bar")

16. plt.ylabel(u"人数")

17. plt.title(u"乘客等级分布")

18. 
    

19. plt.subplot2grid((2,3),(0,2))

20. plt.scatter(data_train.Survived, data_train.Age)

21. plt.ylabel(u"年龄")                         # 设定纵坐标名称

22. plt.grid(b=True, which='major', axis='y')

23. plt.title(u"按年龄看获救分布 (1为获救)")

24. 
    

25. plt.subplot2grid((2,3),(1,0), colspan=2)

26. data_train.Age[data_train.Pclass == 1].plot(kind='kde')

27. data_train.Age[data_train.Pclass == 2].plot(kind='kde')

28. data_train.Age[data_train.Pclass == 3].plot(kind='kde')

29. plt.xlabel(u"年龄")# plots an axis lable

30. plt.ylabel(u"密度")

31. plt.title(u"各等级的乘客年龄分布")

32. plt.legend((u'头等舱', u'2等舱',u'3等舱'),loc='best') # sets our legend for our graph.

33. 
    

34. plt.subplot2grid((2,3),(1,2))

35. data_train.Embarked.value_counts().plot(kind='bar')

36. plt.title(u"各登船口岸上船人数")

37. plt.ylabel(u"人数")

38. plt.show()

1. #然后我们再来看看各种舱级别情况下各性别的获救情况

   fig=plt.figure()

2. fig.set(alpha=0.65) # 设置图像透明度，无所谓

3. plt.title(u"根据舱等级和性别的获救情况")

4. 
   

5. ax1=fig.add_subplot(141)

6. data_train.Survived[data_train.Sex == 'female'][data_train.Pclass != 3].value_counts().plot(kind='bar', label="female highclass", color='#FA2479')

7. ax1.set_xticklabels([u"获救", u"未获救"], rotation=0)

8. ax1.legend([u"女性/高级舱"], loc='best')

9. 
   

10. ax2=fig.add_subplot(142, sharey=ax1)

11. data_train.Survived[data_train.Sex == 'female'][data_train.Pclass == 3].value_counts().plot(kind='bar', label='female, low class', color='pink')

12. ax2.set_xticklabels([u"未获救", u"获救"], rotation=0)

13. plt.legend([u"女性/低级舱"], loc='best')

14. 
    

15. ax3=fig.add_subplot(143, sharey=ax1)

16. data_train.Survived[data_train.Sex == 'male'][data_train.Pclass != 3].value_counts().plot(kind='bar', label='male, high class',color='lightblue')

17. ax3.set_xticklabels([u"未获救", u"获救"], rotation=0)

18. plt.legend([u"男性/高级舱"], loc='best')

19. 
    

20. ax4=fig.add_subplot(144, sharey=ax1)

21. data_train.Survived[data_train.Sex == 'male'][data_train.Pclass == 3].value_counts().plot(kind='bar', label='male low class', color='steelblue')

22. ax4.set_xticklabels([u"未获救", u"获救"], rotation=0)

23. plt.legend([u"男性/低级舱"], loc='best')

1. #看看各乘客等级的获救情况

2. fig = plt.figure()

3. fig.set(alpha=0.2)  # 设定图表颜色alpha参数

4. Survived_0 = data_train.Pclass[data_train.Survived == 0].value_counts()

5. Survived_1 = data_train.Pclass[data_train.Survived == 1].value_counts()

6. df=pd.DataFrame({u'获救':Survived_1, u'未获救':Survived_0})

7. df.plot(kind='bar', stacked=True)

8. plt.title(u"各乘客等级的获救情况")

9. plt.xlabel(u"乘客等级")

10. plt.ylabel(u"人数")

11. plt.show()

1. #看看各性别的获救情况

2. fig = plt.figure()

3. fig.set(alpha=0.2)  # 设定图表颜色alpha参数

4. 
   

5. Survived_m = data_train.Survived[data_train.Sex == 'male'].value_counts()

6. Survived_f = data_train.Survived[data_train.Sex == 'female'].value_counts()

7. df=pd.DataFrame({u'男性':Survived_m, u'女性':Survived_f})

8. df.plot(kind='bar', stacked=True)

9. plt.title(u"按性别看获救情况")

10. plt.xlabel(u"性别")

11. plt.ylabel(u"人数")

12. plt.show()

多年了，你一直在我的伤口中幽居，我放下过天地，却从未放下过你，我生命中的千山万水，任你一一告别。 --仓央嘉措