notebook.community

Edit and run



In [1]:

    
%matplotlib inline
import csv
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt



In [ ]:

    
# IF TIME, PLEASE CLEAN THESE LOCS



In [2]:

    
records = pd.read_csv('../data/fucking_final_dataset.csv')
records = records[records.pub_year > 1499]
records = records[records.pub_year < 1600]



In [5]:

    
len(records)









    Out[5]:





15127



In [6]:

    
records.head(1)









    Out[6]:






  
    
      
      Unnamed: 0
      Unnamed: 0.1
      Unnamed: 0.1
      Unnamed: 0.1.1
      control_number
      title
      uniform_title
      author
      publisher
      pub_location
      pub_year
      translation
      prev_language
      title_auth_slug
      canonical_title
      canonical_author
      slug
      canonical_city
      canonical_country
      full_text_slug
    
  
  
    
      571
      571
      670
      670
      670
      14321112
      libro de proprietatibus rerum en romancehystor...
      NaN
      bartholomaeus
      gaspar de avila, a costa de joan thomas fabio
      toledo
      1529
      NaN
      NaN
      libro de proprietatibus rerum en romancehystor...
      libro de proprietatibus rerum en romancehystor...
      bartholomaeus
      toledo,spain
      toledo
      spain
      libro de proprietatibus rerum en romancehystor...



In [7]:

    
plt.rcParams['figure.figsize'] = (12.0, 6.0)



In [8]:

    
records.groupby('canonical_country').count()['control_number'].sort_values(inplace=False, ascending=False).ix[:10].plot(kind="bar")









    Out[8]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fd0872fd9e8>



In [9]:

    
records.groupby('slug').count()['control_number'].sort_values(inplace=False, ascending=False).ix[:25].plot(kind="bar")









    Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fd0af2e3ba8>

Global Publication By Year



In [10]:

    
records.sort_values('pub_year').groupby('pub_year').count()['control_number'].plot()









    Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fd0d7119fd0>



In [29]:

    
# records[records.pub_year < 1900].sort_values('pub_year').groupby('pub_year').count()['control_number'].plot()



In [30]:

    
# records[records.pub_year > 1900].sort_values('pub_year').groupby('pub_year').count()['control_number'].plot()



In [11]:

    
top_slugs = records.groupby('slug').count()['control_number'].sort_values(inplace=False, ascending=False).ix[:10].index



In [12]:

    
top_producers = records[records.slug.isin(top_slugs)]
top_slugs









    Out[12]:





Index(['sevilla,spain', 'madrid,spain', 'salamanca,spain', 'barcelona,spain',
       'alcala de henares,spain', 'valladolid,spain', 'toledo,spain',
       'zaragoza,spain', 'valencia,spain', 's.l.'],
      dtype='object', name='slug')



In [13]:

    
group_top_producers = top_producers.sort_values('pub_year').groupby(['slug', 'pub_year']).count()['control_number']



In [22]:

    
top_producer_df = pd.DataFrame({
    'sevilla,spain': group_top_producers.ix['sevilla,spain'],
    'madrid,spain': group_top_producers.ix['madrid,spain'],
    'salamanca,spain': group_top_producers.ix['salamanca,spain'],
    'barcelona,spain': group_top_producers.ix['barcelona,spain'],
    'valladolid,spain': group_top_producers.ix['valladolid,spain'],
    'alcala de henares,spain': group_top_producers.ix['alcala de henares,spain'],
#     'toledo,spain': group_top_producers.ix['toledo,spain'],
#     'zaragoza,spain': group_top_producers.ix['zaragoza,spain'],
#     'valencia,spain': group_top_producers.ix['valencia,spain'],
#     'antwerp,netherlands': group_top_producers.ix['antwerp,netherlands'],
}).fillna(0)



In [23]:

    
top_producer_df.plot()









    Out[23]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fd1319964a8>



In [24]:

    
top_producer_df









    Out[24]:






  
    
      
      alcala de henares,spain
      barcelona,spain
      madrid,spain
      salamanca,spain
      sevilla,spain
      valladolid,spain
    
    
      pub_year
      
      
      
      
      
      
    
  
  
    
      1500
      0
      0
      0
      10
      13
      3
    
    
      1501
      0
      2
      0
      1
      4
      1
    
    
      1502
      2
      0
      0
      2
      13
      2
    
    
      1503
      3
      3
      0
      6
      8
      0
    
    
      1504
      0
      2
      1
      0
      2
      0
    
    
      1505
      0
      2
      0
      2
      0
      0
    
    
      1506
      0
      0
      0
      3
      3
      1
    
    
      1507
      0
      0
      0
      1
      1
      0
    
    
      1508
      0
      0
      0
      0
      4
      1
    
    
      1509
      0
      1
      0
      9
      0
      2
    
    
      1510
      0
      6
      0
      3
      3
      4
    
    
      1511
      2
      0
      0
      1
      7
      4
    
    
      1512
      2
      0
      0
      4
      11
      1
    
    
      1513
      2
      2
      1
      0
      3
      1
    
    
      1514
      0
      0
      1
      1
      4
      0
    
    
      1515
      0
      1
      0
      0
      5
      4
    
    
      1516
      1
      0
      0
      2
      4
      4
    
    
      1517
      2
      1
      0
      1
      4
      0
    
    
      1518
      0
      6
      0
      0
      16
      1
    
    
      1519
      3
      0
      0
      4
      12
      3
    
    
      1520
      1
      5
      0
      1
      16
      0
    
    
      1521
      0
      0
      0
      2
      5
      0
    
    
      1522
      0
      0
      0
      0
      6
      0
    
    
      1523
      1
      1
      0
      0
      10
      0
    
    
      1524
      3
      0
      0
      6
      9
      0
    
    
      1525
      1
      1
      0
      5
      10
      0
    
    
      1526
      1
      0
      0
      3
      18
      2
    
    
      1527
      2
      0
      0
      0
      23
      9
    
    
      1528
      2
      6
      0
      2
      16
      0
    
    
      1529
      8
      0
      0
      0
      6
      4
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      1570
      11
      0
      8
      36
      24
      17
    
    
      1571
      9
      10
      14
      22
      31
      0
    
    
      1572
      10
      14
      14
      19
      16
      21
    
    
      1573
      14
      8
      18
      23
      7
      0
    
    
      1574
      5
      6
      9
      27
      19
      0
    
    
      1575
      8
      7
      15
      20
      12
      1
    
    
      1576
      6
      9
      10
      33
      14
      1
    
    
      1577
      14
      3
      17
      11
      18
      0
    
    
      1578
      7
      6
      33
      20
      3
      3
    
    
      1579
      3
      0
      6
      20
      6
      0
    
    
      1580
      14
      10
      18
      17
      49
      2
    
    
      1581
      18
      10
      10
      22
      9
      1
    
    
      1582
      10
      9
      10
      25
      38
      0
    
    
      1583
      1
      7
      30
      18
      15
      9
    
    
      1584
      17
      6
      43
      12
      20
      4
    
    
      1585
      5
      11
      38
      17
      15
      5
    
    
      1586
      16
      27
      30
      18
      15
      7
    
    
      1587
      30
      20
      36
      38
      27
      9
    
    
      1588
      15
      35
      43
      34
      25
      12
    
    
      1589
      17
      22
      57
      37
      3
      24
    
    
      1590
      7
      7
      72
      11
      13
      6
    
    
      1591
      10
      31
      81
      10
      5
      2
    
    
      1592
      20
      41
      51
      13
      4
      12
    
    
      1593
      0
      11
      42
      1
      5
      6
    
    
      1594
      5
      38
      74
      11
      17
      9
    
    
      1595
      11
      9
      87
      52
      18
      8
    
    
      1596
      9
      20
      77
      26
      14
      5
    
    
      1597
      7
      42
      65
      21
      1
      5
    
    
      1598
      6
      49
      120
      10
      15
      9
    
    
      1599
      18
      36
      104
      15
      46
      7
    
  

100 rows × 6 columns



In [25]:

    
counted_by_year = records.sort_values('pub_year').groupby('pub_year').count()['control_number']



In [29]:

    
top_producer_df_percent = pd.DataFrame({
    'sevilla,spain': top_producer_df['sevilla,spain'].div(counted_by_year.values),
    'madrid,spain': top_producer_df['madrid,spain'].div(counted_by_year.values),
    'salamanca,spain': top_producer_df['salamanca,spain'].div(counted_by_year.values),
    'barcelona,spain': top_producer_df['barcelona,spain'].div(counted_by_year.values),
#     'valladolid,spain': top_producer_df['valladolid,spain'].div(counted_by_year.values),
    'alcala de henares,spain': top_producer_df['alcala de henares,spain'].div(counted_by_year.values),
#     'toledo,spain': top_producer_df['toledo,spain'].div(counted_by_year.values),
#     'zaragoza,spain': top_producer_df['zaragoza,spain'].div(counted_by_year.values),
#     'valencia,spain': top_producer_df['valencia,spain'].div(counted_by_year.values),
#     'antwerp,netherlands': top_producer_df['antwerp,netherlands'].div(counted_by_year.values),
})



In [30]:

    
top_producer_df_percent.plot.area(stacked=False)









    Out[30]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fd0830b3780>



In [ ]:

	alcala de henares,spain	barcelona,spain	madrid,spain	salamanca,spain	sevilla,spain	valladolid,spain
pub_year
1500	0	0	0	10	13	3
1501	0	2	0	1	4	1
1502	2	0	0	2	13	2
1503	3	3	0	6	8	0
1504	0	2	1	0	2	0
1505	0	2	0	2	0	0
1506	0	0	0	3	3	1
1507	0	0	0	1	1	0
1508	0	0	0	0	4	1
1509	0	1	0	9	0	2
1510	0	6	0	3	3	4
1511	2	0	0	1	7	4
1512	2	0	0	4	11	1
1513	2	2	1	0	3	1
1514	0	0	1	1	4	0
1515	0	1	0	0	5	4
1516	1	0	0	2	4	4
1517	2	1	0	1	4	0
1518	0	6	0	0	16	1
1519	3	0	0	4	12	3
1520	1	5	0	1	16	0
1521	0	0	0	2	5	0
1522	0	0	0	0	6	0
1523	1	1	0	0	10	0
1524	3	0	0	6	9	0
1525	1	1	0	5	10	0
1526	1	0	0	3	18	2
1527	2	0	0	0	23	9
1528	2	6	0	2	16	0
1529	8	0	0	0	6	4
...	...	...	...	...	...	...
1570	11	0	8	36	24	17
1571	9	10	14	22	31	0
1572	10	14	14	19	16	21
1573	14	8	18	23	7	0
1574	5	6	9	27	19	0
1575	8	7	15	20	12	1
1576	6	9	10	33	14	1
1577	14	3	17	11	18	0
1578	7	6	33	20	3	3
1579	3	0	6	20	6	0
1580	14	10	18	17	49	2
1581	18	10	10	22	9	1
1582	10	9	10	25	38	0
1583	1	7	30	18	15	9
1584	17	6	43	12	20	4
1585	5	11	38	17	15	5
1586	16	27	30	18	15	7
1587	30	20	36	38	27	9
1588	15	35	43	34	25	12
1589	17	22	57	37	3	24
1590	7	7	72	11	13	6
1591	10	31	81	10	5	2
1592	20	41	51	13	4	12
1593	0	11	42	1	5	6
1594	5	38	74	11	17	9
1595	11	9	87	52	18	8
1596	9	20	77	26	14	5
1597	7	42	65	21	1	5
1598	6	49	120	10	15	9
1599	18	36	104	15	46	7