notebook.community

Edit and run



In [1]:

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



In [2]:

    
df = pd.read_json('Topwords_abstract_bypage_v4.json')



In [3]:

    
df.head()



In [4]:

    
page1 = df[df['pagegroup']==1]



In [27]:

    
page1.groupby('word')['year'].count().reset_index().sort(columns='year',ascending=False)[25:75]



In [16]:

    
plt.plot(df[df['word']=='British']['year'],df[df['word']=='British']['value'], sns.xkcd_rgb["denim blue"],
        label = 'British')
plt.plot(df[df['word']=='Chinese']['year'],df[df['word']=='Chinese']['value'], sns.xkcd_rgb["pale red"],
        label = 'Chinese')
plt.xlabel('Year')
plt.ylabel('Count')
plt.title('The Fall of "British" and the Rise of "Chinese"')
plt.legend(loc='upper right')
sns.set_style('white')
sns.despine()
plt.savefig('BritishChinese.pdf')



In [32]:

    
plt.plot(df[df['word']=='steamer']['year'],df[df['word']=='steamer']['value'])
plt.plot(df[df['word']=='Wharf']['year'],df[df['word']=='Wharf']['value'], color='red')
plt.plot(df[df['word']=='tons']['year'],df[df['word']=='tons']['value'], color='green')
plt.plot(df[df['word']=='bark']['year'],df[df['word']=='bark']['value'], color='purple')
plt.plot(df[df['word']=='ship']['year'],df[df['word']=='ship']['value'], color='pink')









    Out[32]:





[<matplotlib.lines.Line2D at 0x10ddddd10>]



In [26]:

    
plt.plot(df[df['word']=='minister']['year'],df[df['word']=='minister']['value'])









    Out[26]:





[<matplotlib.lines.Line2D at 0x106617550>]



In [ ]:

    
plt.plot(df[df['word']=='Rubber']['year'],df[df['word']=='Rubber']['value'], sns.xkcd_rgb["greyish"],
        label = 'Rubber')
plt.plot(df[df['word']=='Pepper']['year'],df[df['word']=='Pepper']['value'], sns.xkcd_rgb["faded green"],
        label = 'Pepper')
plt.xlabel('Year')
plt.ylabel('Count')
plt.title("Singapore's Transition from Agriculture")
plt.legend(loc='upper right')
sns.set_style('white')
sns.despine()
plt.savefig('BritishChinese.pdf')

	page	pagegroup	value	word	year
0	2	1	20.000000	bark	1845
1	2	1	15.833333	received	1845
2	2	1	15.000000	Steamer	1845
3	2	1	14.166667	Dutch	1845
4	2	1	14.166667	China	1845

	word	year
336	instant	13
405	received	13
244	Tin	13
280	arrival	13
240	Tengku	12
207	Sarawak	12
11	Bali	12
325	general	12
34	Captain	12
235	Tan	11
267	York	11
350	lie	11
363	military	11
0	Abdul	11
335	ill	11
19	Black	11
205	Sago	11
407	recently	11
158	Malaysia	10
6	American	10
54	Company	10
53	Communist	10
31	Calcutta	10
89	Goh	10
357	mail	10
48	Coffee	10
111	India	10
449	visit	9
328	help	9
274	announce	9
275	annual	9
87	German	9
397	present	9
124	Japanese	9
412	set	9
402	quality	8
181	Pearl	8
361	men	8
79	Flour	8
81	Foreign	8
448	via	8
25	Britain	8
347	left	8
345	lbs	8
114	Indonesian	7
330	home	7
386	passengers	7
113	Indonesia	7
252	Urn	7
221	South	7