solveig_master/sustainability_word_list.ipynb

In [1]:

# load list of words related to sustainability
path = 'sustainability_words.txt'
word_list = list()
with open(path, 'r') as f:
    for line in f.readlines():
        word_list.append(line.replace('\n', ''))

word_list.sort()
print(word_list)

['CO2', 'CSR', 'ESG', 'SDG', 'bio', 'carb', 'challeng', 'chang', 'clean', 'climate', 'eco', 'emissions', 'environment', 'future', 'garbage', 'green', 'methanol', 'mission', 'neutral', 'ocean', 'planet', 'plastic', 'recycling', 'reduc', 'responsib', 'sulphur', 'sustainab', 'zero']

In [2]:

# load word counts from tweets
import pandas as pd

word_df = pd.read_csv('word_count.csv', index_col=0)

word_df

Out [2]:

	word	counts	ratio
0	maersk	3207	0.04001
1	is	1025	0.01279
2	more	989	0.01234
3	here	825	0.01029
4	trade	642	0.00801
...	...	...	...
10920	ritzau	1	0.00001
10921	baan	1	0.00001
10922	indiabased	1	0.00001
10923	occurs	1	0.00001
10924	multicarrier	1	0.00001

10925 rows × 3 columns

In [3]:

# load ignore list
ignore_list = list()
path = 'ignore_words.txt'
with open(path, 'r') as f:
    for line in f.readlines():
        ignore_list.append(line.replace('\n', ''))
        
ignore_list.sort()
print(ignore_list)

['become', 'becomes', 'becoming', 'blueeconomy', 'changed', 'chinaeconomy', 'deconsolidation', 'decorated', 'decoupling', 'ecommerce', 'ecommercelogistics', 'economia', 'economic', 'economically', 'economicgrowth', 'economictimes', 'economies', 'economist', 'economistimpact', 'economy', 'environments', 'fairfuture4seafarers', 'mclean', 'portrecord', 'recognise', 'recognised', 'recognising', 'recognition', 'recognized', 'record', 'recorded', 'records', 'recovery', 'second', 'secondbusiest', 'secondgeneration', 'secondlargest', 'seconds', 'shetradesglobal', 'socioeconomic', 'telecoms', 'theeconomist', 'transoceanic', 'unchanged', 'worldrecord']

In [4]:

import numpy as np

match_word_list = list()
mean_idx_list = list()
sigma_idx_list = list()
for i, word in enumerate(word_list):
    # find index of matching words
    contains_word_mask = word_df['word'].str.contains(word.lower())==True
    counts_above_limit_mask = word_df['counts'].gt(1)
    match_mask = contains_word_mask & counts_above_limit_mask
    match_idx_list = word_df[match_mask].index.tolist()
    # remove indices of unwanted words
    remove_idx_list = list()
    for idx in match_idx_list:
        match_word = word_df.loc[idx, 'word']
        if match_word in ignore_list:
            remove_idx_list.append(idx)
    for idx in remove_idx_list:
        match_idx_list.remove(idx)
    # store matched words
    match_word_list.append(list())
    for idx in match_idx_list:
        match_word = word_df.loc[idx, 'word']
        match_word_list[i].append(match_word)
    # calculate mean and std of word ranking from located indices
    mu = np.array(match_idx_list).mean().round()
    mean_idx_list.append(mu)
    sigma = np.array(match_idx_list).std().round()
    sigma_idx_list.append(sigma)

# show example of results
idx = 0
print(word_list[idx])
print(match_word_list[idx])
print(mean_idx_list[idx])
print(sigma_idx_list[idx])

CO2
['co2', 'co2neutral', 'co2emission']
3390.0
2275.0

In [5]:

df = pd.DataFrame({
    'root': word_list,
    'mean_ranking': mean_idx_list,
    'std_ranking': sigma_idx_list,
    'word_matches': match_word_list
})

df

Out [5]:

	root	mean_ranking	std_ranking	word_matches
0	CO2	3390.0	2275.0	[co2, co2neutral, co2emission]
1	CSR	1371.0	0.0	[csr]
2	ESG	636.0	0.0	[esg]
3	SDG	423.0	0.0	[sdgs]
4	bio	3687.0	1274.0	[biofuel, biofuels, biohuts, biodiversity]
5	carb	1952.0	1526.0	[decarbonisation, carbon, decarbonization, car...
6	challeng	420.0	264.0	[challenges, challenge, challenging]
7	chang	2148.0	1667.0	[change, changing, climatechange, changes, exc...
8	clean	1695.0	837.0	[theoceancleanup, cleanup, clean, cleanseas, o...
9	climate	3046.0	2095.0	[climateaction, climate, climatechange, climat...
10	eco	3074.0	1269.0	[ecosystem, eco, maerskecodelivery, ecofriendl...
11	emissions	2925.0	2046.0	[emissions, carbonemissions, zeroemissions]
12	environment	2391.0	1574.0	[environment, environmental, unenvironment, en...
13	future	1770.0	1684.0	[future, futureproofing]
14	garbage	1808.0	612.0	[garbage, greatpacificgarbagepatch]
15	green	2393.0	1158.0	[green, greenfuels, greener, greenfuel, greent...
16	methanol	1700.0	1044.0	[methanol, emethanol]
17	mission	3247.0	1950.0	[emissions, mission, eucommission, carbonemiss...
18	neutral	2382.0	1798.0	[neutral, carbonneutral, neutrality, co2neutral]
19	ocean	2169.0	1629.0	[ocean, theoceancleanup, oceans, oceanplastic,...
20	planet	1295.0	0.0	[planet]
21	plastic	2320.0	1490.0	[plastic, oceanplastic, plasticwaste, plasticp...
22	recycling	860.0	154.0	[recycling, shiprecycling]
23	reduc	1242.0	965.0	[reduce, reducing, reduced, reduction, reducti...
24	responsib	1889.0	1135.0	[responsible, responsibility, responsibly, res...
25	sulphur	2828.0	1772.0	[sulphur, lowsulphur]
26	sustainab	1527.0	1873.0	[sustainability, sustainable, sustainableshipp...
27	zero	2977.0	1646.0	[zero, netzero, zerocarbon, zerocarbonship, ze...

In [6]:

# sort values by ranking
df = df.sort_values(by='mean_ranking').reset_index(drop=True)
df

Out [6]:

	root	mean_ranking	std_ranking	word_matches
0	challeng	420.0	264.0	[challenges, challenge, challenging]
1	SDG	423.0	0.0	[sdgs]
2	ESG	636.0	0.0	[esg]
3	recycling	860.0	154.0	[recycling, shiprecycling]
4	reduc	1242.0	965.0	[reduce, reducing, reduced, reduction, reducti...
5	planet	1295.0	0.0	[planet]
6	CSR	1371.0	0.0	[csr]
7	sustainab	1527.0	1873.0	[sustainability, sustainable, sustainableshipp...
8	clean	1695.0	837.0	[theoceancleanup, cleanup, clean, cleanseas, o...
9	methanol	1700.0	1044.0	[methanol, emethanol]
10	future	1770.0	1684.0	[future, futureproofing]
11	garbage	1808.0	612.0	[garbage, greatpacificgarbagepatch]
12	responsib	1889.0	1135.0	[responsible, responsibility, responsibly, res...
13	carb	1952.0	1526.0	[decarbonisation, carbon, decarbonization, car...
14	chang	2148.0	1667.0	[change, changing, climatechange, changes, exc...
15	ocean	2169.0	1629.0	[ocean, theoceancleanup, oceans, oceanplastic,...
16	plastic	2320.0	1490.0	[plastic, oceanplastic, plasticwaste, plasticp...
17	neutral	2382.0	1798.0	[neutral, carbonneutral, neutrality, co2neutral]
18	environment	2391.0	1574.0	[environment, environmental, unenvironment, en...
19	green	2393.0	1158.0	[green, greenfuels, greener, greenfuel, greent...
20	sulphur	2828.0	1772.0	[sulphur, lowsulphur]
21	emissions	2925.0	2046.0	[emissions, carbonemissions, zeroemissions]
22	zero	2977.0	1646.0	[zero, netzero, zerocarbon, zerocarbonship, ze...
23	climate	3046.0	2095.0	[climateaction, climate, climatechange, climat...
24	eco	3074.0	1269.0	[ecosystem, eco, maerskecodelivery, ecofriendl...
25	mission	3247.0	1950.0	[emissions, mission, eucommission, carbonemiss...
26	CO2	3390.0	2275.0	[co2, co2neutral, co2emission]
27	bio	3687.0	1274.0	[biofuel, biofuels, biohuts, biodiversity]

In [7]:

# save results
df['mean_ranking'] = df['mean_ranking'].astype(int)
df['std_ranking'] = df['std_ranking'].astype(int)
df.to_csv('word_root_ranking.csv')

In [ ]: