Files
solveig_master/sustainability_word_list.ipynb
T
2023-04-13 18:20:32 +00:00

919 lines
32 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "0c875ce0-80ad-42f3-af90-9bb1c1e53858",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['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']\n"
]
}
],
"source": [
"# load list of words related to sustainability\n",
"path = 'sustainability_words.txt'\n",
"word_list = list()\n",
"with open(path, 'r') as f:\n",
" for line in f.readlines():\n",
" word_list.append(line.replace('\\n', ''))\n",
"\n",
"word_list.sort()\n",
"print(word_list)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "99837ffc-0eb7-4e89-87e5-eedbe35219bc",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>word</th>\n",
" <th>counts</th>\n",
" <th>ratio</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>maersk</td>\n",
" <td>3207</td>\n",
" <td>0.04001</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>is</td>\n",
" <td>1025</td>\n",
" <td>0.01279</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>more</td>\n",
" <td>989</td>\n",
" <td>0.01234</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>here</td>\n",
" <td>825</td>\n",
" <td>0.01029</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>trade</td>\n",
" <td>642</td>\n",
" <td>0.00801</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10920</th>\n",
" <td>ritzau</td>\n",
" <td>1</td>\n",
" <td>0.00001</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10921</th>\n",
" <td>baan</td>\n",
" <td>1</td>\n",
" <td>0.00001</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10922</th>\n",
" <td>indiabased</td>\n",
" <td>1</td>\n",
" <td>0.00001</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10923</th>\n",
" <td>occurs</td>\n",
" <td>1</td>\n",
" <td>0.00001</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10924</th>\n",
" <td>multicarrier</td>\n",
" <td>1</td>\n",
" <td>0.00001</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10925 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" word counts ratio\n",
"0 maersk 3207 0.04001\n",
"1 is 1025 0.01279\n",
"2 more 989 0.01234\n",
"3 here 825 0.01029\n",
"4 trade 642 0.00801\n",
"... ... ... ...\n",
"10920 ritzau 1 0.00001\n",
"10921 baan 1 0.00001\n",
"10922 indiabased 1 0.00001\n",
"10923 occurs 1 0.00001\n",
"10924 multicarrier 1 0.00001\n",
"\n",
"[10925 rows x 3 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# load word counts from tweets\n",
"import pandas as pd\n",
"\n",
"word_df = pd.read_csv('word_count.csv', index_col=0)\n",
"\n",
"word_df"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "57e749a9-3401-4cb5-98b0-ad68098bf5b4",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['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']\n"
]
}
],
"source": [
"# load ignore list\n",
"ignore_list = list()\n",
"path = 'ignore_words.txt'\n",
"with open(path, 'r') as f:\n",
" for line in f.readlines():\n",
" ignore_list.append(line.replace('\\n', ''))\n",
" \n",
"ignore_list.sort()\n",
"print(ignore_list)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "f2f37c6b-cb1f-4c71-aa24-9601d5bfe7b8",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CO2\n",
"['co2', 'co2neutral', 'co2emission']\n",
"3390.0\n",
"2275.0\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
"match_word_list = list()\n",
"mean_idx_list = list()\n",
"sigma_idx_list = list()\n",
"for i, word in enumerate(word_list):\n",
" # find index of matching words\n",
" contains_word_mask = word_df['word'].str.contains(word.lower())==True\n",
" counts_above_limit_mask = word_df['counts'].gt(1)\n",
" match_mask = contains_word_mask & counts_above_limit_mask\n",
" match_idx_list = word_df[match_mask].index.tolist()\n",
" # remove indices of unwanted words\n",
" remove_idx_list = list()\n",
" for idx in match_idx_list:\n",
" match_word = word_df.loc[idx, 'word']\n",
" if match_word in ignore_list:\n",
" remove_idx_list.append(idx)\n",
" for idx in remove_idx_list:\n",
" match_idx_list.remove(idx)\n",
" # store matched words\n",
" match_word_list.append(list())\n",
" for idx in match_idx_list:\n",
" match_word = word_df.loc[idx, 'word']\n",
" match_word_list[i].append(match_word)\n",
" # calculate mean and std of word ranking from located indices\n",
" mu = np.array(match_idx_list).mean().round()\n",
" mean_idx_list.append(mu)\n",
" sigma = np.array(match_idx_list).std().round()\n",
" sigma_idx_list.append(sigma)\n",
"\n",
"# show example of results\n",
"idx = 0\n",
"print(word_list[idx])\n",
"print(match_word_list[idx])\n",
"print(mean_idx_list[idx])\n",
"print(sigma_idx_list[idx])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f825653d-6c43-46bc-bc11-f9b8f4de5414",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>root</th>\n",
" <th>mean_ranking</th>\n",
" <th>std_ranking</th>\n",
" <th>word_matches</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>CO2</td>\n",
" <td>3390.0</td>\n",
" <td>2275.0</td>\n",
" <td>[co2, co2neutral, co2emission]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>CSR</td>\n",
" <td>1371.0</td>\n",
" <td>0.0</td>\n",
" <td>[csr]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ESG</td>\n",
" <td>636.0</td>\n",
" <td>0.0</td>\n",
" <td>[esg]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>SDG</td>\n",
" <td>423.0</td>\n",
" <td>0.0</td>\n",
" <td>[sdgs]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>bio</td>\n",
" <td>3687.0</td>\n",
" <td>1274.0</td>\n",
" <td>[biofuel, biofuels, biohuts, biodiversity]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>carb</td>\n",
" <td>1952.0</td>\n",
" <td>1526.0</td>\n",
" <td>[decarbonisation, carbon, decarbonization, car...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>challeng</td>\n",
" <td>420.0</td>\n",
" <td>264.0</td>\n",
" <td>[challenges, challenge, challenging]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>chang</td>\n",
" <td>2148.0</td>\n",
" <td>1667.0</td>\n",
" <td>[change, changing, climatechange, changes, exc...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>clean</td>\n",
" <td>1695.0</td>\n",
" <td>837.0</td>\n",
" <td>[theoceancleanup, cleanup, clean, cleanseas, o...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>climate</td>\n",
" <td>3046.0</td>\n",
" <td>2095.0</td>\n",
" <td>[climateaction, climate, climatechange, climat...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>eco</td>\n",
" <td>3074.0</td>\n",
" <td>1269.0</td>\n",
" <td>[ecosystem, eco, maerskecodelivery, ecofriendl...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>emissions</td>\n",
" <td>2925.0</td>\n",
" <td>2046.0</td>\n",
" <td>[emissions, carbonemissions, zeroemissions]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>environment</td>\n",
" <td>2391.0</td>\n",
" <td>1574.0</td>\n",
" <td>[environment, environmental, unenvironment, en...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>future</td>\n",
" <td>1770.0</td>\n",
" <td>1684.0</td>\n",
" <td>[future, futureproofing]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>garbage</td>\n",
" <td>1808.0</td>\n",
" <td>612.0</td>\n",
" <td>[garbage, greatpacificgarbagepatch]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>green</td>\n",
" <td>2393.0</td>\n",
" <td>1158.0</td>\n",
" <td>[green, greenfuels, greener, greenfuel, greent...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>methanol</td>\n",
" <td>1700.0</td>\n",
" <td>1044.0</td>\n",
" <td>[methanol, emethanol]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>mission</td>\n",
" <td>3247.0</td>\n",
" <td>1950.0</td>\n",
" <td>[emissions, mission, eucommission, carbonemiss...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>neutral</td>\n",
" <td>2382.0</td>\n",
" <td>1798.0</td>\n",
" <td>[neutral, carbonneutral, neutrality, co2neutral]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>ocean</td>\n",
" <td>2169.0</td>\n",
" <td>1629.0</td>\n",
" <td>[ocean, theoceancleanup, oceans, oceanplastic,...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>planet</td>\n",
" <td>1295.0</td>\n",
" <td>0.0</td>\n",
" <td>[planet]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>plastic</td>\n",
" <td>2320.0</td>\n",
" <td>1490.0</td>\n",
" <td>[plastic, oceanplastic, plasticwaste, plasticp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>recycling</td>\n",
" <td>860.0</td>\n",
" <td>154.0</td>\n",
" <td>[recycling, shiprecycling]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>reduc</td>\n",
" <td>1242.0</td>\n",
" <td>965.0</td>\n",
" <td>[reduce, reducing, reduced, reduction, reducti...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>responsib</td>\n",
" <td>1889.0</td>\n",
" <td>1135.0</td>\n",
" <td>[responsible, responsibility, responsibly, res...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>sulphur</td>\n",
" <td>2828.0</td>\n",
" <td>1772.0</td>\n",
" <td>[sulphur, lowsulphur]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>sustainab</td>\n",
" <td>1527.0</td>\n",
" <td>1873.0</td>\n",
" <td>[sustainability, sustainable, sustainableshipp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>zero</td>\n",
" <td>2977.0</td>\n",
" <td>1646.0</td>\n",
" <td>[zero, netzero, zerocarbon, zerocarbonship, ze...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" root mean_ranking std_ranking \n",
"0 CO2 3390.0 2275.0 \\\n",
"1 CSR 1371.0 0.0 \n",
"2 ESG 636.0 0.0 \n",
"3 SDG 423.0 0.0 \n",
"4 bio 3687.0 1274.0 \n",
"5 carb 1952.0 1526.0 \n",
"6 challeng 420.0 264.0 \n",
"7 chang 2148.0 1667.0 \n",
"8 clean 1695.0 837.0 \n",
"9 climate 3046.0 2095.0 \n",
"10 eco 3074.0 1269.0 \n",
"11 emissions 2925.0 2046.0 \n",
"12 environment 2391.0 1574.0 \n",
"13 future 1770.0 1684.0 \n",
"14 garbage 1808.0 612.0 \n",
"15 green 2393.0 1158.0 \n",
"16 methanol 1700.0 1044.0 \n",
"17 mission 3247.0 1950.0 \n",
"18 neutral 2382.0 1798.0 \n",
"19 ocean 2169.0 1629.0 \n",
"20 planet 1295.0 0.0 \n",
"21 plastic 2320.0 1490.0 \n",
"22 recycling 860.0 154.0 \n",
"23 reduc 1242.0 965.0 \n",
"24 responsib 1889.0 1135.0 \n",
"25 sulphur 2828.0 1772.0 \n",
"26 sustainab 1527.0 1873.0 \n",
"27 zero 2977.0 1646.0 \n",
"\n",
" word_matches \n",
"0 [co2, co2neutral, co2emission] \n",
"1 [csr] \n",
"2 [esg] \n",
"3 [sdgs] \n",
"4 [biofuel, biofuels, biohuts, biodiversity] \n",
"5 [decarbonisation, carbon, decarbonization, car... \n",
"6 [challenges, challenge, challenging] \n",
"7 [change, changing, climatechange, changes, exc... \n",
"8 [theoceancleanup, cleanup, clean, cleanseas, o... \n",
"9 [climateaction, climate, climatechange, climat... \n",
"10 [ecosystem, eco, maerskecodelivery, ecofriendl... \n",
"11 [emissions, carbonemissions, zeroemissions] \n",
"12 [environment, environmental, unenvironment, en... \n",
"13 [future, futureproofing] \n",
"14 [garbage, greatpacificgarbagepatch] \n",
"15 [green, greenfuels, greener, greenfuel, greent... \n",
"16 [methanol, emethanol] \n",
"17 [emissions, mission, eucommission, carbonemiss... \n",
"18 [neutral, carbonneutral, neutrality, co2neutral] \n",
"19 [ocean, theoceancleanup, oceans, oceanplastic,... \n",
"20 [planet] \n",
"21 [plastic, oceanplastic, plasticwaste, plasticp... \n",
"22 [recycling, shiprecycling] \n",
"23 [reduce, reducing, reduced, reduction, reducti... \n",
"24 [responsible, responsibility, responsibly, res... \n",
"25 [sulphur, lowsulphur] \n",
"26 [sustainability, sustainable, sustainableshipp... \n",
"27 [zero, netzero, zerocarbon, zerocarbonship, ze... "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({\n",
" 'root': word_list,\n",
" 'mean_ranking': mean_idx_list,\n",
" 'std_ranking': sigma_idx_list,\n",
" 'word_matches': match_word_list\n",
"})\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "c4ea948f-66f6-405d-8b35-b390b1b3e4a7",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>root</th>\n",
" <th>mean_ranking</th>\n",
" <th>std_ranking</th>\n",
" <th>word_matches</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>challeng</td>\n",
" <td>420.0</td>\n",
" <td>264.0</td>\n",
" <td>[challenges, challenge, challenging]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>SDG</td>\n",
" <td>423.0</td>\n",
" <td>0.0</td>\n",
" <td>[sdgs]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>ESG</td>\n",
" <td>636.0</td>\n",
" <td>0.0</td>\n",
" <td>[esg]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>recycling</td>\n",
" <td>860.0</td>\n",
" <td>154.0</td>\n",
" <td>[recycling, shiprecycling]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>reduc</td>\n",
" <td>1242.0</td>\n",
" <td>965.0</td>\n",
" <td>[reduce, reducing, reduced, reduction, reducti...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>planet</td>\n",
" <td>1295.0</td>\n",
" <td>0.0</td>\n",
" <td>[planet]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>CSR</td>\n",
" <td>1371.0</td>\n",
" <td>0.0</td>\n",
" <td>[csr]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>sustainab</td>\n",
" <td>1527.0</td>\n",
" <td>1873.0</td>\n",
" <td>[sustainability, sustainable, sustainableshipp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>clean</td>\n",
" <td>1695.0</td>\n",
" <td>837.0</td>\n",
" <td>[theoceancleanup, cleanup, clean, cleanseas, o...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>methanol</td>\n",
" <td>1700.0</td>\n",
" <td>1044.0</td>\n",
" <td>[methanol, emethanol]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>future</td>\n",
" <td>1770.0</td>\n",
" <td>1684.0</td>\n",
" <td>[future, futureproofing]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>garbage</td>\n",
" <td>1808.0</td>\n",
" <td>612.0</td>\n",
" <td>[garbage, greatpacificgarbagepatch]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>responsib</td>\n",
" <td>1889.0</td>\n",
" <td>1135.0</td>\n",
" <td>[responsible, responsibility, responsibly, res...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>carb</td>\n",
" <td>1952.0</td>\n",
" <td>1526.0</td>\n",
" <td>[decarbonisation, carbon, decarbonization, car...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>chang</td>\n",
" <td>2148.0</td>\n",
" <td>1667.0</td>\n",
" <td>[change, changing, climatechange, changes, exc...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>ocean</td>\n",
" <td>2169.0</td>\n",
" <td>1629.0</td>\n",
" <td>[ocean, theoceancleanup, oceans, oceanplastic,...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>plastic</td>\n",
" <td>2320.0</td>\n",
" <td>1490.0</td>\n",
" <td>[plastic, oceanplastic, plasticwaste, plasticp...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>neutral</td>\n",
" <td>2382.0</td>\n",
" <td>1798.0</td>\n",
" <td>[neutral, carbonneutral, neutrality, co2neutral]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>environment</td>\n",
" <td>2391.0</td>\n",
" <td>1574.0</td>\n",
" <td>[environment, environmental, unenvironment, en...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>green</td>\n",
" <td>2393.0</td>\n",
" <td>1158.0</td>\n",
" <td>[green, greenfuels, greener, greenfuel, greent...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>sulphur</td>\n",
" <td>2828.0</td>\n",
" <td>1772.0</td>\n",
" <td>[sulphur, lowsulphur]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>emissions</td>\n",
" <td>2925.0</td>\n",
" <td>2046.0</td>\n",
" <td>[emissions, carbonemissions, zeroemissions]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>zero</td>\n",
" <td>2977.0</td>\n",
" <td>1646.0</td>\n",
" <td>[zero, netzero, zerocarbon, zerocarbonship, ze...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>climate</td>\n",
" <td>3046.0</td>\n",
" <td>2095.0</td>\n",
" <td>[climateaction, climate, climatechange, climat...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>eco</td>\n",
" <td>3074.0</td>\n",
" <td>1269.0</td>\n",
" <td>[ecosystem, eco, maerskecodelivery, ecofriendl...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>mission</td>\n",
" <td>3247.0</td>\n",
" <td>1950.0</td>\n",
" <td>[emissions, mission, eucommission, carbonemiss...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>CO2</td>\n",
" <td>3390.0</td>\n",
" <td>2275.0</td>\n",
" <td>[co2, co2neutral, co2emission]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>bio</td>\n",
" <td>3687.0</td>\n",
" <td>1274.0</td>\n",
" <td>[biofuel, biofuels, biohuts, biodiversity]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" root mean_ranking std_ranking \n",
"0 challeng 420.0 264.0 \\\n",
"1 SDG 423.0 0.0 \n",
"2 ESG 636.0 0.0 \n",
"3 recycling 860.0 154.0 \n",
"4 reduc 1242.0 965.0 \n",
"5 planet 1295.0 0.0 \n",
"6 CSR 1371.0 0.0 \n",
"7 sustainab 1527.0 1873.0 \n",
"8 clean 1695.0 837.0 \n",
"9 methanol 1700.0 1044.0 \n",
"10 future 1770.0 1684.0 \n",
"11 garbage 1808.0 612.0 \n",
"12 responsib 1889.0 1135.0 \n",
"13 carb 1952.0 1526.0 \n",
"14 chang 2148.0 1667.0 \n",
"15 ocean 2169.0 1629.0 \n",
"16 plastic 2320.0 1490.0 \n",
"17 neutral 2382.0 1798.0 \n",
"18 environment 2391.0 1574.0 \n",
"19 green 2393.0 1158.0 \n",
"20 sulphur 2828.0 1772.0 \n",
"21 emissions 2925.0 2046.0 \n",
"22 zero 2977.0 1646.0 \n",
"23 climate 3046.0 2095.0 \n",
"24 eco 3074.0 1269.0 \n",
"25 mission 3247.0 1950.0 \n",
"26 CO2 3390.0 2275.0 \n",
"27 bio 3687.0 1274.0 \n",
"\n",
" word_matches \n",
"0 [challenges, challenge, challenging] \n",
"1 [sdgs] \n",
"2 [esg] \n",
"3 [recycling, shiprecycling] \n",
"4 [reduce, reducing, reduced, reduction, reducti... \n",
"5 [planet] \n",
"6 [csr] \n",
"7 [sustainability, sustainable, sustainableshipp... \n",
"8 [theoceancleanup, cleanup, clean, cleanseas, o... \n",
"9 [methanol, emethanol] \n",
"10 [future, futureproofing] \n",
"11 [garbage, greatpacificgarbagepatch] \n",
"12 [responsible, responsibility, responsibly, res... \n",
"13 [decarbonisation, carbon, decarbonization, car... \n",
"14 [change, changing, climatechange, changes, exc... \n",
"15 [ocean, theoceancleanup, oceans, oceanplastic,... \n",
"16 [plastic, oceanplastic, plasticwaste, plasticp... \n",
"17 [neutral, carbonneutral, neutrality, co2neutral] \n",
"18 [environment, environmental, unenvironment, en... \n",
"19 [green, greenfuels, greener, greenfuel, greent... \n",
"20 [sulphur, lowsulphur] \n",
"21 [emissions, carbonemissions, zeroemissions] \n",
"22 [zero, netzero, zerocarbon, zerocarbonship, ze... \n",
"23 [climateaction, climate, climatechange, climat... \n",
"24 [ecosystem, eco, maerskecodelivery, ecofriendl... \n",
"25 [emissions, mission, eucommission, carbonemiss... \n",
"26 [co2, co2neutral, co2emission] \n",
"27 [biofuel, biofuels, biohuts, biodiversity] "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# sort values by ranking\n",
"df = df.sort_values(by='mean_ranking').reset_index(drop=True)\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "7b3dbcf3-2d95-4a5e-b795-cea63da2a34a",
"metadata": {},
"outputs": [],
"source": [
"# save results\n",
"df['mean_ranking'] = df['mean_ranking'].astype(int)\n",
"df['std_ranking'] = df['std_ranking'].astype(int)\n",
"df.to_csv('word_root_ranking.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef515886-a918-49a0-b9df-7f20bfe4cea4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}