>>> to_drop = ['Edition Statement',
...            'Corporate Author',
...            'Corporate Contributors',
...            'Former owner',
...            'Engraver',
...            'Contributors',
...            'Issuance type',
...            'Shelfmarks']

>>> df.drop(to_drop, inplace=True, axis=1)

>>> df.head()
   Identifier      Place of Publication Date of Publication  \
0         206                    London         1879 [1878]
1         216  London; Virtue & Yorston                1868
2         218                    London                1869
3         472                    London                1851
4         480                    London                1857

               Publisher                                              Title  \
0       S. Tinsley & Co.                  Walter Forbes. [A novel.] By A. A
1           Virtue & Co.  All for Greed. [A novel. The dedication signed...
2  Bradbury, Evans & Co.  Love the Avenger. By the author of “All for Gr...
3          James Darling  Welsh Sketches, chiefly ecclesiastical, to the...
4   Wertheim & Macintosh  [The World in which I live, and my place in it...

      Author                                         Flickr URL
0      A. A.  http://www.flickr.com/photos/britishlibrary/ta...
1  A., A. A.  http://www.flickr.com/photos/britishlibrary/ta...
2  A., A. A.  http://www.flickr.com/photos/britishlibrary/ta...
3  A., E. S.  http://www.flickr.com/photos/britishlibrary/ta...
4  A., E. S.  http://www.flickr.com/photos/britishlibrary/ta...

>>> df.drop(columns=to_drop, inplace=True)

>>> df['Identifier'].is_unique
True

>>> df = df.set_index('Identifier')
>>> df.head()
                Place of Publication Date of Publication  \
206                           London         1879 [1878]
216         London; Virtue & Yorston                1868
218                           London                1869
472                           London                1851
480                           London                1857

                        Publisher  \
206              S. Tinsley & Co.
216                  Virtue & Co.
218         Bradbury, Evans & Co.
472                 James Darling
480          Wertheim & Macintosh

                                                        Title     Author  \
206                         Walter Forbes. [A novel.] By A. A      A. A.
216         All for Greed. [A novel. The dedication signed...  A., A. A.
218         Love the Avenger. By the author of “All for Gr...  A., A. A.
472         Welsh Sketches, chiefly ecclesiastical, to the...  A., E. S.
480         [The World in which I live, and my place in it...  A., E. S.

                                                   Flickr URL
206         http://www.flickr.com/photos/britishlibrary/ta...
216         http://www.flickr.com/photos/britishlibrary/ta...
218         http://www.flickr.com/photos/britishlibrary/ta...
472         http://www.flickr.com/photos/britishlibrary/ta...
480         http://www.flickr.com/photos/britishlibrary/ta...

>>> df.loc[206]
Place of Publication                                               London
Date of Publication                                           1879 [1878]
Publisher                                                S. Tinsley & Co.
Title                                   Walter Forbes. [A novel.] By A. A
Author                                                              A. A.
Flickr URL              http://www.flickr.com/photos/britishlibrary/ta...
Name: 206, dtype: object

>>> df.get_dtype_counts()
object    6

>>> df.loc[1905:, 'Date of Publication'].head(10)
Identifier
1905           1888
1929    1839, 38-54
2836        [1897?]
2854           1865
2956        1860-63
2957           1873
3017           1866
3131           1899
4598           1814
4884           1820
Name: Date of Publication, dtype: object

regex = r'^(\d{4})'

>>> extr = df['Date of Publication'].str.extract(r'^(\d{4})', expand=False)
>>> extr.head()
Identifier
206    1879
216    1868
218    1869
472    1851
480    1857
Name: Date of Publication, dtype: object

>>> df['Date of Publication'] = pd.to_numeric(extr)
>>> df['Date of Publication'].dtype
dtype('float64')

>>> df['Date of Publication'].isnull().sum() / len(df)
0.11717147339205986

>>> np.where(condition, then, else)

>>> np.where(condition1, x1, 
        np.where(condition2, x2, 
            np.where(condition3, x3, ...)))

>>> df['Place of Publication'].head(10)
Identifier
206                                  London
216                London; Virtue & Yorston
218                                  London
472                                  London
480                                  London
481                                  London
519                                  London
667     pp. 40. G. Bryan & Co: Oxford, 1898
874                                 London]
1143                                 London
Name: Place of Publication, dtype: object

>>> df.loc[4157862]
Place of Publication                                  Newcastle-upon-Tyne
Date of Publication                                                  1867
Publisher                                                      T. Fordyce
Title                   Local Records; or, Historical Register of rema...
Author                                                        T.  Fordyce
Flickr URL              http://www.flickr.com/photos/britishlibrary/ta...
Name: 4157862, dtype: object

>>> df.loc[4159587]
Place of Publication                                  Newcastle upon Tyne
Date of Publication                                                  1834
Publisher                                                Mackenzie & Dent
Title                   An historical, topographical and descriptive v...
Author                                               E. (Eneas) Mackenzie
Flickr URL              http://www.flickr.com/photos/britishlibrary/ta...
Name: 4159587, dtype: object

>>> pub = df['Place of Publication']
>>> london = pub.str.contains('London')
>>> london[:5]
Identifier
206    True
216    True
218    True
472    True
480    True
Name: Place of Publication, dtype: bool

>>> oxford = pub.str.contains('Oxford')

df['Place of Publication'] = np.where(london, 'London',
                                      np.where(oxford, 'Oxford',
                                               pub.str.replace('-', ' ')))

>>> df['Place of Publication'].head()
Identifier
206    London
216    London
218    London
472    London
480    London
Name: Place of Publication, dtype: object

>>> df.head()
           Place of Publication Date of Publication              Publisher  \
206                      London                1879        S. Tinsley & Co.
216                      London                1868           Virtue & Co.
218                      London                1869  Bradbury, Evans & Co.
472                      London                1851          James Darling
480                      London                1857   Wertheim & Macintosh

                                                        Title    Author  \
206                         Walter Forbes. [A novel.] By A. A        AA
216         All for Greed. [A novel. The dedication signed...   A. A A.
218         Love the Avenger. By the author of “All for Gr...   A. A A.
472         Welsh Sketches, chiefly ecclesiastical, to the...   E. S A.
480         [The World in which I live, and my place in it...   E. S A.

                                                   Flickr URL
206         http://www.flickr.com/photos/britishlibrary/ta...
216         http://www.flickr.com/photos/britishlibrary/ta...
218         http://www.flickr.com/photos/britishlibrary/ta...
472         http://www.flickr.com/photos/britishlibrary/ta...
480         http://www.flickr.com/photos/britishlibrary/ta...

$ head Datasets/univerisity_towns.txt
Alabama[edit]
Auburn (Auburn University)[1]
Florence (University of North Alabama)
Jacksonville (Jacksonville State University)[2]
Livingston (University of West Alabama)[2]
Montevallo (University of Montevallo)[2]
Troy (Troy University)[2]
Tuscaloosa (University of Alabama, Stillman College, Shelton State)[3][4]
Tuskegee (Tuskegee University)[5]
Alaska[edit]

>>> university_towns = []
>>> with open('Datasets/university_towns.txt') as file:
...     for line in file:
...         if '[edit]' in line:
...             # Remember this `state` until the next is found
...             state = line
...         else:
...             # Otherwise, we have a city; keep `state` as last-seen
...             university_towns.append((state, line))

>>> university_towns[:5]
[('Alabama[edit]\n', 'Auburn (Auburn University)[1]\n'),
 ('Alabama[edit]\n', 'Florence (University of North Alabama)\n'),
 ('Alabama[edit]\n', 'Jacksonville (Jacksonville State University)[2]\n'),
 ('Alabama[edit]\n', 'Livingston (University of West Alabama)[2]\n'),
 ('Alabama[edit]\n', 'Montevallo (University of Montevallo)[2]\n')]

>>> towns_df = pd.DataFrame(university_towns,
...                         columns=['State', 'RegionName'])

>>> towns_df.head()
 State                                         RegionName
0  Alabama[edit]\n                    Auburn (Auburn University)[1]\n
1  Alabama[edit]\n           Florence (University of North Alabama)\n
2  Alabama[edit]\n  Jacksonville (Jacksonville State University)[2]\n
3  Alabama[edit]\n       Livingston (University of West Alabama)[2]\n
4  Alabama[edit]\n         Montevallo (University of Montevallo)[2]\n

        0           1
0    Mock     Dataset
1  Python     Pandas
2    Real     Python
3   NumPy     Clean

>>> def get_citystate(item):
...     if ' (' in item:
...         return item[:item.find(' (')]
...     elif '[' in item:
...         return item[:item.find('[')]
...     else:
...         return item

>>> towns_df =  towns_df.applymap(get_citystate)

>>> towns_df.head()
     State    RegionName
0  Alabama        Auburn
1  Alabama      Florence
2  Alabama  Jacksonville
3  Alabama    Livingston
4  Alabama    Montevallo

$ head -n 5 Datasets/olympics.csv
0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
,? Summer,01 !,02 !,03 !,Total,? Winter,01 !,02 !,03 !,Total,? Games,01 !,02 !,03 !,Combined total
Afghanistan (AFG),13,0,0,2,2,0,0,0,0,0,13,0,0,2,2
Algeria (ALG),12,5,2,8,15,3,0,0,0,0,15,5,2,8,15
Argentina (ARG),23,18,24,28,70,18,0,0,0,0,41,18,24,28,70

>>> olympics_df = pd.read_csv('Datasets/olympics.csv')
>>> olympics_df.head()
                   0         1     2     3     4      5         6     7     8  \
0                NaN  ? Summer  01 !  02 !  03 !  Total  ? Winter  01 !  02 !
1  Afghanistan (AFG)        13     0     0     2      2         0     0     0
2      Algeria (ALG)        12     5     2     8     15         3     0     0
3    Argentina (ARG)        23    18    24    28     70        18     0     0
4      Armenia (ARM)         5     1     2     9     12         6     0     0

      9     10       11    12    13    14              15
0  03 !  Total  ? Games  01 !  02 !  03 !  Combined total
1     0      0       13     0     0     2               2
2     0      0       15     5     2     8              15
3     0      0       41    18    24    28              70
4     0      0       11     1     2     9              12

>>> olympics_df = pd.read_csv('Datasets/olympics.csv', header=1)
>>> olympics_df.head()
          Unnamed: 0  ? Summer  01 !  02 !  03 !  Total  ? Winter  \
0        Afghanistan (AFG)        13     0     0     2      2         0
1            Algeria (ALG)        12     5     2     8     15         3
2          Argentina (ARG)        23    18    24    28     70        18
3            Armenia (ARM)         5     1     2     9     12         6
4  Australasia (ANZ) [ANZ]         2     3     4     5     12         0

   01 !.1  02 !.1  03 !.1  Total.1  ? Games  01 !.2  02 !.2  03 !.2  \
0       0       0       0        0       13       0       0       2
1       0       0       0        0       15       5       2       8
2       0       0       0        0       41      18      24      28
3       0       0       0        0       11       1       2       9
4       0       0       0        0        2       3       4       5

   Combined total
0               2
1              15
2              70
3              12
4              12

>>> new_names =  {'Unnamed: 0': 'Country',
...               '? Summer': 'Summer Olympics',
...               '01 !': 'Gold',
...               '02 !': 'Silver',
...               '03 !': 'Bronze',
...               '? Winter': 'Winter Olympics',
...               '01 !.1': 'Gold.1',
...               '02 !.1': 'Silver.1',
...               '03 !.1': 'Bronze.1',
...               '? Games': '# Games',
...               '01 !.2': 'Gold.2',
...               '02 !.2': 'Silver.2',
...               '03 !.2': 'Bronze.2'}

>>> olympics_df.rename(columns=new_names, inplace=True)

>>> olympics_df.head()
                   Country  Summer Olympics  Gold  Silver  Bronze  Total  \
0        Afghanistan (AFG)               13     0       0       2      2
1            Algeria (ALG)               12     5       2       8     15
2          Argentina (ARG)               23    18      24      28     70
3            Armenia (ARM)                5     1       2       9     12
4  Australasia (ANZ) [ANZ]                2     3       4       5     12

   Winter Olympics  Gold.1  Silver.1  Bronze.1  Total.1  # Games  Gold.2  \
0                0       0         0         0        0       13       0
1                3       0         0         0        0       15       5
2               18       0         0         0        0       41      18
3                6       0         0         0        0       11       1
4                0       0         0         0        0        2       3

   Silver.2  Bronze.2  Combined total
0         0         2               2
1         2         8              15
2        24        28              70
3         2         9              12
4         4         5              12