notebook.community

Edit and run



In [115]:

    
def output( filename, text ):
    "Writes a file"
    f = open('./answers/'+str(filename), 'w')
    f.write(str(text))
    f.close()
    return

import pandas as pd
data = pd.read_csv('./data/titanic.csv', index_col='PassengerId')



In [116]:

    
data









    Out[116]:






  
    
      
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Ticket
      Fare
      Cabin
      Embarked
    
    
      PassengerId
      
      
      
      
      
      
      
      
      
      
      
    
  
  
    
      1
      0
      3
      Braund, Mr. Owen Harris
      male
      22
      1
      0
      A/5 21171
      7.2500
      NaN
      S
    
    
      2
      1
      1
      Cumings, Mrs. John Bradley (Florence Briggs Th...
      female
      38
      1
      0
      PC 17599
      71.2833
      C85
      C
    
    
      3
      1
      3
      Heikkinen, Miss. Laina
      female
      26
      0
      0
      STON/O2. 3101282
      7.9250
      NaN
      S
    
    
      4
      1
      1
      Futrelle, Mrs. Jacques Heath (Lily May Peel)
      female
      35
      1
      0
      113803
      53.1000
      C123
      S
    
    
      5
      0
      3
      Allen, Mr. William Henry
      male
      35
      0
      0
      373450
      8.0500
      NaN
      S
    
    
      6
      0
      3
      Moran, Mr. James
      male
      NaN
      0
      0
      330877
      8.4583
      NaN
      Q
    
    
      7
      0
      1
      McCarthy, Mr. Timothy J
      male
      54
      0
      0
      17463
      51.8625
      E46
      S
    
    
      8
      0
      3
      Palsson, Master. Gosta Leonard
      male
      2
      3
      1
      349909
      21.0750
      NaN
      S
    
    
      9
      1
      3
      Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)
      female
      27
      0
      2
      347742
      11.1333
      NaN
      S
    
    
      10
      1
      2
      Nasser, Mrs. Nicholas (Adele Achem)
      female
      14
      1
      0
      237736
      30.0708
      NaN
      C
    
    
      11
      1
      3
      Sandstrom, Miss. Marguerite Rut
      female
      4
      1
      1
      PP 9549
      16.7000
      G6
      S
    
    
      12
      1
      1
      Bonnell, Miss. Elizabeth
      female
      58
      0
      0
      113783
      26.5500
      C103
      S
    
    
      13
      0
      3
      Saundercock, Mr. William Henry
      male
      20
      0
      0
      A/5. 2151
      8.0500
      NaN
      S
    
    
      14
      0
      3
      Andersson, Mr. Anders Johan
      male
      39
      1
      5
      347082
      31.2750
      NaN
      S
    
    
      15
      0
      3
      Vestrom, Miss. Hulda Amanda Adolfina
      female
      14
      0
      0
      350406
      7.8542
      NaN
      S
    
    
      16
      1
      2
      Hewlett, Mrs. (Mary D Kingcome)
      female
      55
      0
      0
      248706
      16.0000
      NaN
      S
    
    
      17
      0
      3
      Rice, Master. Eugene
      male
      2
      4
      1
      382652
      29.1250
      NaN
      Q
    
    
      18
      1
      2
      Williams, Mr. Charles Eugene
      male
      NaN
      0
      0
      244373
      13.0000
      NaN
      S
    
    
      19
      0
      3
      Vander Planke, Mrs. Julius (Emelia Maria Vande...
      female
      31
      1
      0
      345763
      18.0000
      NaN
      S
    
    
      20
      1
      3
      Masselmani, Mrs. Fatima
      female
      NaN
      0
      0
      2649
      7.2250
      NaN
      C
    
    
      21
      0
      2
      Fynney, Mr. Joseph J
      male
      35
      0
      0
      239865
      26.0000
      NaN
      S
    
    
      22
      1
      2
      Beesley, Mr. Lawrence
      male
      34
      0
      0
      248698
      13.0000
      D56
      S
    
    
      23
      1
      3
      McGowan, Miss. Anna "Annie"
      female
      15
      0
      0
      330923
      8.0292
      NaN
      Q
    
    
      24
      1
      1
      Sloper, Mr. William Thompson
      male
      28
      0
      0
      113788
      35.5000
      A6
      S
    
    
      25
      0
      3
      Palsson, Miss. Torborg Danira
      female
      8
      3
      1
      349909
      21.0750
      NaN
      S
    
    
      26
      1
      3
      Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...
      female
      38
      1
      5
      347077
      31.3875
      NaN
      S
    
    
      27
      0
      3
      Emir, Mr. Farred Chehab
      male
      NaN
      0
      0
      2631
      7.2250
      NaN
      C
    
    
      28
      0
      1
      Fortune, Mr. Charles Alexander
      male
      19
      3
      2
      19950
      263.0000
      C23 C25 C27
      S
    
    
      29
      1
      3
      O'Dwyer, Miss. Ellen "Nellie"
      female
      NaN
      0
      0
      330959
      7.8792
      NaN
      Q
    
    
      30
      0
      3
      Todoroff, Mr. Lalio
      male
      NaN
      0
      0
      349216
      7.8958
      NaN
      S
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      862
      0
      2
      Giles, Mr. Frederick Edward
      male
      21
      1
      0
      28134
      11.5000
      NaN
      S
    
    
      863
      1
      1
      Swift, Mrs. Frederick Joel (Margaret Welles Ba...
      female
      48
      0
      0
      17466
      25.9292
      D17
      S
    
    
      864
      0
      3
      Sage, Miss. Dorothy Edith "Dolly"
      female
      NaN
      8
      2
      CA. 2343
      69.5500
      NaN
      S
    
    
      865
      0
      2
      Gill, Mr. John William
      male
      24
      0
      0
      233866
      13.0000
      NaN
      S
    
    
      866
      1
      2
      Bystrom, Mrs. (Karolina)
      female
      42
      0
      0
      236852
      13.0000
      NaN
      S
    
    
      867
      1
      2
      Duran y More, Miss. Asuncion
      female
      27
      1
      0
      SC/PARIS 2149
      13.8583
      NaN
      C
    
    
      868
      0
      1
      Roebling, Mr. Washington Augustus II
      male
      31
      0
      0
      PC 17590
      50.4958
      A24
      S
    
    
      869
      0
      3
      van Melkebeke, Mr. Philemon
      male
      NaN
      0
      0
      345777
      9.5000
      NaN
      S
    
    
      870
      1
      3
      Johnson, Master. Harold Theodor
      male
      4
      1
      1
      347742
      11.1333
      NaN
      S
    
    
      871
      0
      3
      Balkic, Mr. Cerin
      male
      26
      0
      0
      349248
      7.8958
      NaN
      S
    
    
      872
      1
      1
      Beckwith, Mrs. Richard Leonard (Sallie Monypeny)
      female
      47
      1
      1
      11751
      52.5542
      D35
      S
    
    
      873
      0
      1
      Carlsson, Mr. Frans Olof
      male
      33
      0
      0
      695
      5.0000
      B51 B53 B55
      S
    
    
      874
      0
      3
      Vander Cruyssen, Mr. Victor
      male
      47
      0
      0
      345765
      9.0000
      NaN
      S
    
    
      875
      1
      2
      Abelson, Mrs. Samuel (Hannah Wizosky)
      female
      28
      1
      0
      P/PP 3381
      24.0000
      NaN
      C
    
    
      876
      1
      3
      Najib, Miss. Adele Kiamie "Jane"
      female
      15
      0
      0
      2667
      7.2250
      NaN
      C
    
    
      877
      0
      3
      Gustafsson, Mr. Alfred Ossian
      male
      20
      0
      0
      7534
      9.8458
      NaN
      S
    
    
      878
      0
      3
      Petroff, Mr. Nedelio
      male
      19
      0
      0
      349212
      7.8958
      NaN
      S
    
    
      879
      0
      3
      Laleff, Mr. Kristo
      male
      NaN
      0
      0
      349217
      7.8958
      NaN
      S
    
    
      880
      1
      1
      Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)
      female
      56
      0
      1
      11767
      83.1583
      C50
      C
    
    
      881
      1
      2
      Shelley, Mrs. William (Imanita Parrish Hall)
      female
      25
      0
      1
      230433
      26.0000
      NaN
      S
    
    
      882
      0
      3
      Markun, Mr. Johann
      male
      33
      0
      0
      349257
      7.8958
      NaN
      S
    
    
      883
      0
      3
      Dahlberg, Miss. Gerda Ulrika
      female
      22
      0
      0
      7552
      10.5167
      NaN
      S
    
    
      884
      0
      2
      Banfield, Mr. Frederick James
      male
      28
      0
      0
      C.A./SOTON 34068
      10.5000
      NaN
      S
    
    
      885
      0
      3
      Sutehall, Mr. Henry Jr
      male
      25
      0
      0
      SOTON/OQ 392076
      7.0500
      NaN
      S
    
    
      886
      0
      3
      Rice, Mrs. William (Margaret Norton)
      female
      39
      0
      5
      382652
      29.1250
      NaN
      Q
    
    
      887
      0
      2
      Montvila, Rev. Juozas
      male
      27
      0
      0
      211536
      13.0000
      NaN
      S
    
    
      888
      1
      1
      Graham, Miss. Margaret Edith
      female
      19
      0
      0
      112053
      30.0000
      B42
      S
    
    
      889
      0
      3
      Johnston, Miss. Catherine Helen "Carrie"
      female
      NaN
      1
      2
      W./C. 6607
      23.4500
      NaN
      S
    
    
      890
      1
      1
      Behr, Mr. Karl Howell
      male
      26
      0
      0
      111369
      30.0000
      C148
      C
    
    
      891
      0
      3
      Dooley, Mr. Patrick
      male
      32
      0
      0
      370376
      7.7500
      NaN
      Q
    
  

891 rows × 11 columns



In [117]:

    
malesCount = data[(data.Sex=="male")].Sex.count()
femalesCount = data[(data.Sex=="female")].Sex.count()
print malesCount
print femalesCount



In [118]:

    
total = len(data)
check01 = femalesCount + malesCount == total
print "Q1 Check =", check01
print "Q1 = [",malesCount,femalesCount,"]"
output('q1_1.txt',str(malesCount)+" "+str(femalesCount))









    



Q1 Check = True
Q1 = [ 577 314 ]



In [119]:

    
survivedCount = data[(data.Survived==1)].Survived.count()
deadCount = data[(data.Survived==0)].Survived.count()
print survivedCount
print deadCount



In [120]:

    
check02 = survivedCount + deadCount == total
percent = float(survivedCount)/float(total)*100.0
print "Q2 Check =", check02, survivedCount, total
print "Q2 = [",(float(percent)),"]"
output('q1_2.txt',str(percent))









    



Q2 Check = True 342 891
Q2 = [ 38.3838383838 ]



In [121]:

    
firstClassCount = data[(data.Pclass==1)].Pclass.count()
print firstClassCount



In [122]:

    
percent = float(firstClassCount)/float(total)*100.0
print "Q3 = [",(float(percent)),"]"
output('q1_3.txt',str(percent))









    



Q3 = [ 24.2424242424 ]



In [123]:

    
meanAge = data.Age.mean()
medianAge = data.Age.median()
print "Q4_mean = [",meanAge,"]"
print "Q4_median = [",medianAge,"]"
output('q1_4.txt',str(meanAge)+" "+str(medianAge))









    



Q4_mean = [ 29.6991176471 ]
Q4_median = [ 28.0 ]



In [124]:

    
import numpy as np
a = np.corrcoef(data.SibSp, data.Parch)[0, 1]
a
print "Q5 = [",a,"]"
output('q1_5.txt',str(a))









    



Q5 = [ 0.41483769862 ]



In [ ]:



In [125]:

    
import scipy.stats as sc
b = sc.pearsonr(data.SibSp, data.Parch)
b
print "Q5 = [",b,"]"









    



Q5 = [ (0.41483769862015613, 2.2418236681398336e-38) ]



In [126]:

    
import re
del data['Pclass']
del data['SibSp']
del data['Parch']
del data['Ticket']
females = data[(data.Sex=="female")]



In [132]:

    
females['Surname'] = females.Name.str.split(',', expand=True)[0]
females['Names'] = females.Name.str.split(',', expand=True)[1]
females['Origin'] = females.Names.str.split('.', expand=True)[0]
females['Names'] = females.Names.str.split('.', expand=True)[1]
females['NamesD'] = females.Names.str.contains('(')===true and females.Names.str.split('(', expand=True)[1] or females.Names.str.split('(', expand=True)[0]
females









    



C:\Users\Kirill.Minenko\Anaconda2\lib\site-packages\ipykernel\__main__.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  if __name__ == '__main__':
C:\Users\Kirill.Minenko\Anaconda2\lib\site-packages\ipykernel\__main__.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  from ipykernel import kernelapp as app
C:\Users\Kirill.Minenko\Anaconda2\lib\site-packages\ipykernel\__main__.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  app.launch_new_instance()
C:\Users\Kirill.Minenko\Anaconda2\lib\site-packages\ipykernel\__main__.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy






    



---------------------------------------------------------------------------
error                                     Traceback (most recent call last)
<ipython-input-132-40d9b16aec5f> in <module>()
      3 females['Origin'] = females.Names.str.split('.', expand=True)[0]
      4 females['Names'] = females.Names.str.split('.', expand=True)[1]
----> 5 females['NamesD'] = females.Names.str.contains('(') and females.Names.str.split('(', expand=True)[1] or females.Names.str.split('(', expand=True)[0]
      6 females

C:\Users\Kirill.Minenko\Anaconda2\lib\site-packages\pandas\core\strings.py in contains(self, pat, case, flags, na, regex)
   1246     def contains(self, pat, case=True, flags=0, na=np.nan, regex=True):
   1247         result = str_contains(self._data, pat, case=case, flags=flags,
-> 1248                               na=na, regex=regex)
   1249         return self._wrap_result(result)
   1250 

C:\Users\Kirill.Minenko\Anaconda2\lib\site-packages\pandas\core\strings.py in str_contains(arr, pat, case, flags, na, regex)
    203             flags |= re.IGNORECASE
    204 
--> 205         regex = re.compile(pat, flags=flags)
    206 
    207         if regex.groups > 0:

C:\Users\Kirill.Minenko\Anaconda2\lib\re.pyc in compile(pattern, flags)
    192 def compile(pattern, flags=0):
    193     "Compile a regular expression pattern, returning a pattern object."
--> 194     return _compile(pattern, flags)
    195 
    196 def purge():

C:\Users\Kirill.Minenko\Anaconda2\lib\re.pyc in _compile(*key)
    249         p = sre_compile.compile(pattern, flags)
    250     except error, v:
--> 251         raise error, v # invalid expression
    252     if not bypass_cache:
    253         if len(_cache) >= _MAXCACHE:

error: unbalanced parenthesis



In [ ]:

	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
PassengerId
1	0	3	Braund, Mr. Owen Harris	male	22	1	0	A/5 21171	7.2500	NaN	S
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38	1	0	PC 17599	71.2833	C85	C
3	1	3	Heikkinen, Miss. Laina	female	26	0	0	STON/O2. 3101282	7.9250	NaN	S
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35	1	0	113803	53.1000	C123	S
5	0	3	Allen, Mr. William Henry	male	35	0	0	373450	8.0500	NaN	S
6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q
7	0	1	McCarthy, Mr. Timothy J	male	54	0	0	17463	51.8625	E46	S
8	0	3	Palsson, Master. Gosta Leonard	male	2	3	1	349909	21.0750	NaN	S
9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27	0	2	347742	11.1333	NaN	S
10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14	1	0	237736	30.0708	NaN	C
11	1	3	Sandstrom, Miss. Marguerite Rut	female	4	1	1	PP 9549	16.7000	G6	S
12	1	1	Bonnell, Miss. Elizabeth	female	58	0	0	113783	26.5500	C103	S
13	0	3	Saundercock, Mr. William Henry	male	20	0	0	A/5. 2151	8.0500	NaN	S
14	0	3	Andersson, Mr. Anders Johan	male	39	1	5	347082	31.2750	NaN	S
15	0	3	Vestrom, Miss. Hulda Amanda Adolfina	female	14	0	0	350406	7.8542	NaN	S
16	1	2	Hewlett, Mrs. (Mary D Kingcome)	female	55	0	0	248706	16.0000	NaN	S
17	0	3	Rice, Master. Eugene	male	2	4	1	382652	29.1250	NaN	Q
18	1	2	Williams, Mr. Charles Eugene	male	NaN	0	0	244373	13.0000	NaN	S
19	0	3	Vander Planke, Mrs. Julius (Emelia Maria Vande...	female	31	1	0	345763	18.0000	NaN	S
20	1	3	Masselmani, Mrs. Fatima	female	NaN	0	0	2649	7.2250	NaN	C
21	0	2	Fynney, Mr. Joseph J	male	35	0	0	239865	26.0000	NaN	S
22	1	2	Beesley, Mr. Lawrence	male	34	0	0	248698	13.0000	D56	S
23	1	3	McGowan, Miss. Anna "Annie"	female	15	0	0	330923	8.0292	NaN	Q
24	1	1	Sloper, Mr. William Thompson	male	28	0	0	113788	35.5000	A6	S
25	0	3	Palsson, Miss. Torborg Danira	female	8	3	1	349909	21.0750	NaN	S
26	1	3	Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...	female	38	1	5	347077	31.3875	NaN	S
27	0	3	Emir, Mr. Farred Chehab	male	NaN	0	0	2631	7.2250	NaN	C
28	0	1	Fortune, Mr. Charles Alexander	male	19	3	2	19950	263.0000	C23 C25 C27	S
29	1	3	O'Dwyer, Miss. Ellen "Nellie"	female	NaN	0	0	330959	7.8792	NaN	Q
30	0	3	Todoroff, Mr. Lalio	male	NaN	0	0	349216	7.8958	NaN	S
...	...	...	...	...	...	...	...	...	...	...	...
862	0	2	Giles, Mr. Frederick Edward	male	21	1	0	28134	11.5000	NaN	S
863	1	1	Swift, Mrs. Frederick Joel (Margaret Welles Ba...	female	48	0	0	17466	25.9292	D17	S
864	0	3	Sage, Miss. Dorothy Edith "Dolly"	female	NaN	8	2	CA. 2343	69.5500	NaN	S
865	0	2	Gill, Mr. John William	male	24	0	0	233866	13.0000	NaN	S
866	1	2	Bystrom, Mrs. (Karolina)	female	42	0	0	236852	13.0000	NaN	S
867	1	2	Duran y More, Miss. Asuncion	female	27	1	0	SC/PARIS 2149	13.8583	NaN	C
868	0	1	Roebling, Mr. Washington Augustus II	male	31	0	0	PC 17590	50.4958	A24	S
869	0	3	van Melkebeke, Mr. Philemon	male	NaN	0	0	345777	9.5000	NaN	S
870	1	3	Johnson, Master. Harold Theodor	male	4	1	1	347742	11.1333	NaN	S
871	0	3	Balkic, Mr. Cerin	male	26	0	0	349248	7.8958	NaN	S
872	1	1	Beckwith, Mrs. Richard Leonard (Sallie Monypeny)	female	47	1	1	11751	52.5542	D35	S
873	0	1	Carlsson, Mr. Frans Olof	male	33	0	0	695	5.0000	B51 B53 B55	S
874	0	3	Vander Cruyssen, Mr. Victor	male	47	0	0	345765	9.0000	NaN	S
875	1	2	Abelson, Mrs. Samuel (Hannah Wizosky)	female	28	1	0	P/PP 3381	24.0000	NaN	C
876	1	3	Najib, Miss. Adele Kiamie "Jane"	female	15	0	0	2667	7.2250	NaN	C
877	0	3	Gustafsson, Mr. Alfred Ossian	male	20	0	0	7534	9.8458	NaN	S
878	0	3	Petroff, Mr. Nedelio	male	19	0	0	349212	7.8958	NaN	S
879	0	3	Laleff, Mr. Kristo	male	NaN	0	0	349217	7.8958	NaN	S
880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56	0	1	11767	83.1583	C50	C
881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25	0	1	230433	26.0000	NaN	S
882	0	3	Markun, Mr. Johann	male	33	0	0	349257	7.8958	NaN	S
883	0	3	Dahlberg, Miss. Gerda Ulrika	female	22	0	0	7552	10.5167	NaN	S
884	0	2	Banfield, Mr. Frederick James	male	28	0	0	C.A./SOTON 34068	10.5000	NaN	S
885	0	3	Sutehall, Mr. Henry Jr	male	25	0	0	SOTON/OQ 392076	7.0500	NaN	S
886	0	3	Rice, Mrs. William (Margaret Norton)	female	39	0	5	382652	29.1250	NaN	Q
887	0	2	Montvila, Rev. Juozas	male	27	0	0	211536	13.0000	NaN	S
888	1	1	Graham, Miss. Margaret Edith	female	19	0	0	112053	30.0000	B42	S
889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	NaN	1	2	W./C. 6607	23.4500	NaN	S
890	1	1	Behr, Mr. Karl Howell	male	26	0	0	111369	30.0000	C148	C
891	0	3	Dooley, Mr. Patrick	male	32	0	0	370376	7.7500	NaN	Q