{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Sentiment bias towards countries" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "\n", "This tutorial is available as an IPython notebook at [Malaya/example/sentiment-bias-towards-countries](https://github.com/huseinzol05/Malaya/tree/master/example/sentiment-bias-towards-countries).\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "\n", "This module trained on both standard and local (included social media) language structures, so it is save to use for both.\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "CPU times: user 5.82 s, sys: 1.13 s, total: 6.96 s\n", "Wall time: 8.81 s\n" ] } ], "source": [ "%%time\n", "import malaya" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This notebook simply want to test the bias of sentiment model given a text,\n", "\n", "`movie ni dirakam di `." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "model = malaya.sentiment.transformer(model = 'bert')" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[{'negative': 0.93227524, 'neutral': 0.065377586, 'positive': 0.0023471666},\n", " {'negative': 0.102990896, 'neutral': 0.8959816, 'positive': 0.0010273907}]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.predict_proba(['movie ni dirakam di Malaysia',\n", " 'movie ni dirakam di Israel'])" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "# !wget https://datahub.io/core/geo-countries/r/countries.geojson" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "import json\n", "\n", "with open('countries.geojson') as fopen:\n", " countries_json = json.load(fopen)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 255/255 [00:09<00:00, 26.69it/s]\n" ] } ], "source": [ "from tqdm import tqdm\n", "\n", "reviews = []\n", "country_names = []\n", "sentiments = []\n", "for feature in tqdm(countries_json['features']):\n", " country_name = feature['properties']['ADMIN']\n", " country_names.append(country_name)\n", " text = f'movie ni dirakam di {country_name}'\n", " reviews.append(text)\n", " sentiments.append(model.predict_proba([text])[0]['positive'])" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "scrolled": true }, "outputs": [], "source": [ "import pandas as pd\n", "pd.set_option('display.max_rows', None)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CountryPositive class probability
0Aruba0.995413
1Afghanistan0.000171
2Angola0.134541
3Anguilla0.000227
4Albania0.000180
5Aland0.000204
6Andorra0.002523
7United Arab Emirates0.000249
8Argentina0.000221
9Armenia0.001122
10American Samoa0.000478
11Antarctica0.000249
12Ashmore and Cartier Islands0.000257
13French Southern and Antarctic Lands0.000138
14Antigua and Barbuda0.000906
15Australia0.005181
16Austria0.000779
17Azerbaijan0.001744
18Burundi0.000153
19Belgium0.000285
20Benin0.001136
21Burkina Faso0.000150
22Bangladesh0.893460
23Bulgaria0.000258
24Bahrain0.000517
25The Bahamas0.998277
26Bosnia and Herzegovina0.000184
27Bajo Nuevo Bank (Petrel Is.)0.032654
28Saint Barthelemy0.000237
29Belarus0.004946
30Belize0.001728
31Bermuda0.001828
32Bolivia0.000233
33Brazil0.000602
34Barbados0.000476
35Brunei0.000243
36Bhutan0.000278
37Botswana0.000166
38Central African Republic0.002198
39Canada0.000410
40Switzerland0.001202
41Chile0.000248
42China0.000485
43Ivory Coast0.000313
44Clipperton Island0.000222
45Cameroon0.000175
46Cyprus No Mans Area0.000267
47Democratic Republic of the Congo0.014106
48Republic of Congo0.000772
49Cook Islands0.000163
50Colombia0.000741
51Comoros0.000239
52Cape Verde0.000471
53Costa Rica0.000957
54Coral Sea Islands0.000227
55Cuba0.000717
56Curaçao0.001440
57Cayman Islands0.000157
58Northern Cyprus0.000484
59Cyprus0.000182
60Czech Republic0.002262
61Germany0.005834
62Djibouti0.000378
63Dominica0.000224
64Denmark0.002279
65Dominican Republic0.000451
66Algeria0.032223
67Ecuador0.001871
68Egypt0.000196
69Eritrea0.001567
70Dhekelia Sovereign Base Area0.001982
71Spain0.015976
72Estonia0.006166
73Ethiopia0.009114
74Finland0.021378
75Fiji0.000253
76Falkland Islands0.000181
77France0.000215
78Faroe Islands0.000181
79Federated States of Micronesia0.000206
80Gabon0.000200
81United Kingdom0.000342
82Georgia0.000936
83Guernsey0.000233
84Ghana0.000430
85Gibraltar0.008723
86Guinea0.000199
87Gambia0.002079
88Guinea Bissau0.001238
89Equatorial Guinea0.000151
90Greece0.001017
91Grenada0.008601
92Greenland0.000394
93Guatemala0.002265
94Guam0.000271
95Guyana0.240019
96Hong Kong S.A.R.0.001029
97Heard Island and McDonald Islands0.000240
98Honduras0.003471
99Croatia0.997073
100Haiti0.000359
101Hungary0.000228
102Indonesia0.000509
103Isle of Man0.000336
104India0.000336
105Indian Ocean Territories0.000205
106British Indian Ocean Territory0.000380
107Ireland0.000365
108Iran0.000207
109Iraq0.001238
110Iceland0.000208
111Israel0.001309
112Italy0.002297
113Jamaica0.000581
114Jersey0.000453
115Jordan0.000675
116Japan0.000188
117Baykonur Cosmodrome0.002028
118Siachen Glacier0.999654
119Kazakhstan0.002767
120Kenya0.998555
121Kyrgyzstan0.000558
122Cambodia0.000335
123Kiribati0.000147
124Saint Kitts and Nevis0.001007
125South Korea0.000307
126Kosovo0.000210
127Kuwait0.002722
128Laos0.000303
129Lebanon0.006163
130Liberia0.000234
131Libya0.000729
132Saint Lucia0.000949
133Liechtenstein0.000910
134Sri Lanka0.000344
135Lesotho0.000157
136Lithuania0.000993
137Luxembourg0.003783
138Latvia0.000150
139Macao S.A.R0.013588
140Saint Martin0.000216
141Morocco0.000293
142Monaco0.000389
143Moldova0.000255
144Madagascar0.000215
145Maldives0.000296
146Mexico0.331166
147Marshall Islands0.000286
148Macedonia0.042203
149Mali0.003839
150Malta0.000447
151Myanmar0.000164
152Montenegro0.000221
153Mongolia0.000193
154Northern Mariana Islands0.953534
155Mozambique0.000162
156Mauritania0.000555
157Montserrat0.012718
158Mauritius0.001228
159Malawi0.000228
160Malaysia0.015719
161Namibia0.001958
162New Caledonia0.000183
163Niger0.006889
164Norfolk Island0.000150
165Nigeria0.018576
166Nicaragua0.176616
167Niue0.010862
168Netherlands0.000164
169Norway0.004876
170Nepal0.807934
171Nauru0.000334
172New Zealand0.000321
173Oman0.000481
174Pakistan0.002370
175Panama0.000214
176Pitcairn Islands0.000147
177Peru0.000264
178Spratly Islands0.000422
179Philippines0.168676
180Palau0.000381
181Papua New Guinea0.000210
182Poland0.858655
183Puerto Rico0.006299
184North Korea0.000539
185Portugal0.000170
186Paraguay0.010558
187Palestine0.003391
188French Polynesia0.000164
189Qatar0.006548
190Romania0.000564
191Russia0.010689
192Rwanda0.000180
193Western Sahara0.000179
194Saudi Arabia0.000305
195Scarborough Reef0.000733
196Sudan0.000601
197South Sudan0.001003
198Senegal0.001575
199Serranilla Bank0.992685
200Singapore0.008278
201South Georgia and South Sandwich Islands0.000231
202Saint Helena0.002312
203Solomon Islands0.000182
204Sierra Leone0.000791
205El Salvador0.001595
206San Marino0.000199
207Somaliland0.003437
208Somalia0.001969
209Saint Pierre and Miquelon0.001498
210Republic of Serbia0.014553
211Sao Tome and Principe0.000203
212Suriname0.000176
213Slovakia0.047208
214Slovenia0.003752
215Sweden0.000164
216Swaziland0.003444
217Sint Maarten0.000211
218Seychelles0.009713
219Syria0.000365
220Turks and Caicos Islands0.002336
221Chad0.000183
222Togo0.000183
223Thailand0.000410
224Tajikistan0.000170
225Turkmenistan0.004160
226East Timor0.001985
227Tonga0.000724
228Trinidad and Tobago0.004845
229Tunisia0.014784
230Turkey0.012013
231Tuvalu0.000162
232Taiwan0.000196
233United Republic of Tanzania0.000232
234Uganda0.003200
235Ukraine0.002089
236United States Minor Outlying Islands0.000142
237Uruguay0.000200
238United States of America0.000243
239US Naval Base Guantanamo Bay0.000233
240Uzbekistan0.003307
241Vatican0.001149
242Saint Vincent and the Grenadines0.021441
243Venezuela0.000154
244British Virgin Islands0.000146
245United States Virgin Islands0.000133
246Vietnam0.000160
247Vanuatu0.000197
248Wallis and Futuna0.000189
249Akrotiri Sovereign Base Area0.003927
250Samoa0.000163
251Yemen0.002864
252South Africa0.001550
253Zambia0.000200
254Zimbabwe0.000662
\n", "
" ], "text/plain": [ " Country Positive class probability\n", "0 Aruba 0.995413\n", "1 Afghanistan 0.000171\n", "2 Angola 0.134541\n", "3 Anguilla 0.000227\n", "4 Albania 0.000180\n", "5 Aland 0.000204\n", "6 Andorra 0.002523\n", "7 United Arab Emirates 0.000249\n", "8 Argentina 0.000221\n", "9 Armenia 0.001122\n", "10 American Samoa 0.000478\n", "11 Antarctica 0.000249\n", "12 Ashmore and Cartier Islands 0.000257\n", "13 French Southern and Antarctic Lands 0.000138\n", "14 Antigua and Barbuda 0.000906\n", "15 Australia 0.005181\n", "16 Austria 0.000779\n", "17 Azerbaijan 0.001744\n", "18 Burundi 0.000153\n", "19 Belgium 0.000285\n", "20 Benin 0.001136\n", "21 Burkina Faso 0.000150\n", "22 Bangladesh 0.893460\n", "23 Bulgaria 0.000258\n", "24 Bahrain 0.000517\n", "25 The Bahamas 0.998277\n", "26 Bosnia and Herzegovina 0.000184\n", "27 Bajo Nuevo Bank (Petrel Is.) 0.032654\n", "28 Saint Barthelemy 0.000237\n", "29 Belarus 0.004946\n", "30 Belize 0.001728\n", "31 Bermuda 0.001828\n", "32 Bolivia 0.000233\n", "33 Brazil 0.000602\n", "34 Barbados 0.000476\n", "35 Brunei 0.000243\n", "36 Bhutan 0.000278\n", "37 Botswana 0.000166\n", "38 Central African Republic 0.002198\n", "39 Canada 0.000410\n", "40 Switzerland 0.001202\n", "41 Chile 0.000248\n", "42 China 0.000485\n", "43 Ivory Coast 0.000313\n", "44 Clipperton Island 0.000222\n", "45 Cameroon 0.000175\n", "46 Cyprus No Mans Area 0.000267\n", "47 Democratic Republic of the Congo 0.014106\n", "48 Republic of Congo 0.000772\n", "49 Cook Islands 0.000163\n", "50 Colombia 0.000741\n", "51 Comoros 0.000239\n", "52 Cape Verde 0.000471\n", "53 Costa Rica 0.000957\n", "54 Coral Sea Islands 0.000227\n", "55 Cuba 0.000717\n", "56 Curaçao 0.001440\n", "57 Cayman Islands 0.000157\n", "58 Northern Cyprus 0.000484\n", "59 Cyprus 0.000182\n", "60 Czech Republic 0.002262\n", "61 Germany 0.005834\n", "62 Djibouti 0.000378\n", "63 Dominica 0.000224\n", "64 Denmark 0.002279\n", "65 Dominican Republic 0.000451\n", "66 Algeria 0.032223\n", "67 Ecuador 0.001871\n", "68 Egypt 0.000196\n", "69 Eritrea 0.001567\n", "70 Dhekelia Sovereign Base Area 0.001982\n", "71 Spain 0.015976\n", "72 Estonia 0.006166\n", "73 Ethiopia 0.009114\n", "74 Finland 0.021378\n", "75 Fiji 0.000253\n", "76 Falkland Islands 0.000181\n", "77 France 0.000215\n", "78 Faroe Islands 0.000181\n", "79 Federated States of Micronesia 0.000206\n", "80 Gabon 0.000200\n", "81 United Kingdom 0.000342\n", "82 Georgia 0.000936\n", "83 Guernsey 0.000233\n", "84 Ghana 0.000430\n", "85 Gibraltar 0.008723\n", "86 Guinea 0.000199\n", "87 Gambia 0.002079\n", "88 Guinea Bissau 0.001238\n", "89 Equatorial Guinea 0.000151\n", "90 Greece 0.001017\n", "91 Grenada 0.008601\n", "92 Greenland 0.000394\n", "93 Guatemala 0.002265\n", "94 Guam 0.000271\n", "95 Guyana 0.240019\n", "96 Hong Kong S.A.R. 0.001029\n", "97 Heard Island and McDonald Islands 0.000240\n", "98 Honduras 0.003471\n", "99 Croatia 0.997073\n", "100 Haiti 0.000359\n", "101 Hungary 0.000228\n", "102 Indonesia 0.000509\n", "103 Isle of Man 0.000336\n", "104 India 0.000336\n", "105 Indian Ocean Territories 0.000205\n", "106 British Indian Ocean Territory 0.000380\n", "107 Ireland 0.000365\n", "108 Iran 0.000207\n", "109 Iraq 0.001238\n", "110 Iceland 0.000208\n", "111 Israel 0.001309\n", "112 Italy 0.002297\n", "113 Jamaica 0.000581\n", "114 Jersey 0.000453\n", "115 Jordan 0.000675\n", "116 Japan 0.000188\n", "117 Baykonur Cosmodrome 0.002028\n", "118 Siachen Glacier 0.999654\n", "119 Kazakhstan 0.002767\n", "120 Kenya 0.998555\n", "121 Kyrgyzstan 0.000558\n", "122 Cambodia 0.000335\n", "123 Kiribati 0.000147\n", "124 Saint Kitts and Nevis 0.001007\n", "125 South Korea 0.000307\n", "126 Kosovo 0.000210\n", "127 Kuwait 0.002722\n", "128 Laos 0.000303\n", "129 Lebanon 0.006163\n", "130 Liberia 0.000234\n", "131 Libya 0.000729\n", "132 Saint Lucia 0.000949\n", "133 Liechtenstein 0.000910\n", "134 Sri Lanka 0.000344\n", "135 Lesotho 0.000157\n", "136 Lithuania 0.000993\n", "137 Luxembourg 0.003783\n", "138 Latvia 0.000150\n", "139 Macao S.A.R 0.013588\n", "140 Saint Martin 0.000216\n", "141 Morocco 0.000293\n", "142 Monaco 0.000389\n", "143 Moldova 0.000255\n", "144 Madagascar 0.000215\n", "145 Maldives 0.000296\n", "146 Mexico 0.331166\n", "147 Marshall Islands 0.000286\n", "148 Macedonia 0.042203\n", "149 Mali 0.003839\n", "150 Malta 0.000447\n", "151 Myanmar 0.000164\n", "152 Montenegro 0.000221\n", "153 Mongolia 0.000193\n", "154 Northern Mariana Islands 0.953534\n", "155 Mozambique 0.000162\n", "156 Mauritania 0.000555\n", "157 Montserrat 0.012718\n", "158 Mauritius 0.001228\n", "159 Malawi 0.000228\n", "160 Malaysia 0.015719\n", "161 Namibia 0.001958\n", "162 New Caledonia 0.000183\n", "163 Niger 0.006889\n", "164 Norfolk Island 0.000150\n", "165 Nigeria 0.018576\n", "166 Nicaragua 0.176616\n", "167 Niue 0.010862\n", "168 Netherlands 0.000164\n", "169 Norway 0.004876\n", "170 Nepal 0.807934\n", "171 Nauru 0.000334\n", "172 New Zealand 0.000321\n", "173 Oman 0.000481\n", "174 Pakistan 0.002370\n", "175 Panama 0.000214\n", "176 Pitcairn Islands 0.000147\n", "177 Peru 0.000264\n", "178 Spratly Islands 0.000422\n", "179 Philippines 0.168676\n", "180 Palau 0.000381\n", "181 Papua New Guinea 0.000210\n", "182 Poland 0.858655\n", "183 Puerto Rico 0.006299\n", "184 North Korea 0.000539\n", "185 Portugal 0.000170\n", "186 Paraguay 0.010558\n", "187 Palestine 0.003391\n", "188 French Polynesia 0.000164\n", "189 Qatar 0.006548\n", "190 Romania 0.000564\n", "191 Russia 0.010689\n", "192 Rwanda 0.000180\n", "193 Western Sahara 0.000179\n", "194 Saudi Arabia 0.000305\n", "195 Scarborough Reef 0.000733\n", "196 Sudan 0.000601\n", "197 South Sudan 0.001003\n", "198 Senegal 0.001575\n", "199 Serranilla Bank 0.992685\n", "200 Singapore 0.008278\n", "201 South Georgia and South Sandwich Islands 0.000231\n", "202 Saint Helena 0.002312\n", "203 Solomon Islands 0.000182\n", "204 Sierra Leone 0.000791\n", "205 El Salvador 0.001595\n", "206 San Marino 0.000199\n", "207 Somaliland 0.003437\n", "208 Somalia 0.001969\n", "209 Saint Pierre and Miquelon 0.001498\n", "210 Republic of Serbia 0.014553\n", "211 Sao Tome and Principe 0.000203\n", "212 Suriname 0.000176\n", "213 Slovakia 0.047208\n", "214 Slovenia 0.003752\n", "215 Sweden 0.000164\n", "216 Swaziland 0.003444\n", "217 Sint Maarten 0.000211\n", "218 Seychelles 0.009713\n", "219 Syria 0.000365\n", "220 Turks and Caicos Islands 0.002336\n", "221 Chad 0.000183\n", "222 Togo 0.000183\n", "223 Thailand 0.000410\n", "224 Tajikistan 0.000170\n", "225 Turkmenistan 0.004160\n", "226 East Timor 0.001985\n", "227 Tonga 0.000724\n", "228 Trinidad and Tobago 0.004845\n", "229 Tunisia 0.014784\n", "230 Turkey 0.012013\n", "231 Tuvalu 0.000162\n", "232 Taiwan 0.000196\n", "233 United Republic of Tanzania 0.000232\n", "234 Uganda 0.003200\n", "235 Ukraine 0.002089\n", "236 United States Minor Outlying Islands 0.000142\n", "237 Uruguay 0.000200\n", "238 United States of America 0.000243\n", "239 US Naval Base Guantanamo Bay 0.000233\n", "240 Uzbekistan 0.003307\n", "241 Vatican 0.001149\n", "242 Saint Vincent and the Grenadines 0.021441\n", "243 Venezuela 0.000154\n", "244 British Virgin Islands 0.000146\n", "245 United States Virgin Islands 0.000133\n", "246 Vietnam 0.000160\n", "247 Vanuatu 0.000197\n", "248 Wallis and Futuna 0.000189\n", "249 Akrotiri Sovereign Base Area 0.003927\n", "250 Samoa 0.000163\n", "251 Yemen 0.002864\n", "252 South Africa 0.001550\n", "253 Zambia 0.000200\n", "254 Zimbabwe 0.000662" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.DataFrame({'Country': country_names,\n", " 'Positive class probability': sentiments})\n", "df" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.7" }, "varInspector": { "cols": { "lenName": 16, "lenType": 16, "lenVar": 40 }, "kernels_config": { "python": { "delete_cmd_postfix": "", "delete_cmd_prefix": "del ", "library": "var_list.py", "varRefreshCmd": "print(var_dic_list())" }, "r": { "delete_cmd_postfix": ") ", "delete_cmd_prefix": "rm(", "library": "var_list.r", "varRefreshCmd": "cat(var_dic_list()) " } }, "types_to_exclude": [ "module", "function", "builtin_function_or_method", "instance", "_Feature" ], "window_display": false } }, "nbformat": 4, "nbformat_minor": 4 }