diff --git a/Project/naive_approach/naive_approach.ipynb b/Project/naive_approach/naive_approach.ipynb
index 0e4205e..c508e17 100644
--- a/Project/naive_approach/naive_approach.ipynb
+++ b/Project/naive_approach/naive_approach.ipynb
@@ -247,11 +247,12 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
- "def evaluate_sentence(sentence, description_key = 'description'):\n",
+ "def evaluate_sentence(sentence, description_key = 'description', lang = 'eng'):\n",
+ " \n",
" tokenized_sentence = word_tokenize(sentence)\n",
" n = len(tokenized_sentence)\n",
" l = table.shape[0]\n",
@@ -264,12 +265,12 @@
" mat = np.zeros(shape=(m,n))\n",
" for i in range(len(emoji_tokens)):\n",
" for j in range(len(tokenized_sentence)):\n",
- " syn1 = wordnet.synsets(emoji_tokens[i])\n",
+ " syn1 = wordnet.synsets(emoji_tokens[i],lang=lang)\n",
" if len(syn1) == 0:\n",
" continue\n",
" w1 = syn1[0]\n",
" #print(j, tokenized_sentence)\n",
- " syn2 = wordnet.synsets(tokenized_sentence[j])\n",
+ " syn2 = wordnet.synsets(tokenized_sentence[j], lang=lang)\n",
" if len(syn2) == 0:\n",
" continue\n",
" w2 = syn2[0]\n",
@@ -294,7 +295,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
@@ -316,13 +317,13 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
- "def predict(sentence, description_key='description', n=10, t=0.9):\n",
+ "def predict(sentence, description_key='description', lang = 'eng', n=10, t=0.9):\n",
"\n",
- " result = evaluate_sentence(sentence, description_key)\n",
+ " result = evaluate_sentence(sentence, description_key, lang)\n",
" \n",
" summed = np.argsort([-np.sum(x) for x in result])[0:n]\n",
" max_val = np.argsort([-np.max(x) for x in result])[0:n]\n",
@@ -343,7 +344,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 29,
"metadata": {},
"outputs": [
{
@@ -380,113 +381,113 @@
"
\n",
" \n",
" 0 | \n",
- " ๐คช | \n",
- " GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE | \n",
+ " ๐คญ | \n",
+ " SMILING FACE WITH SMILING EYES AND HAND COVERI... | \n",
" ๐ค | \n",
" I LOVE YOU HAND SIGN | \n",
- " ๐ข | \n",
- " ANGER SYMBOL | \n",
- " ๐ | \n",
- " LOVE LETTER | \n",
+ " ๐ | \n",
+ " BOUQUET | \n",
+ " ๐ | \n",
+ " TRAIN | \n",
"
\n",
" \n",
" 1 | \n",
- " ๐ฎ | \n",
- " PUT LITTER IN ITS PLACE SYMBOL | \n",
- " ๐ | \n",
- " LOVE LETTER | \n",
- " ๐ฆ | \n",
- " PACKAGE | \n",
- " ๐ฉ | \n",
- " LOVE HOTEL | \n",
+ " ๐ | \n",
+ " ON WITH EXCLAMATION MARK WITH LEFT RIGHT ARROW... | \n",
+ " ๐ฎ | \n",
+ " REGIONAL INDICATOR SYMBOL LETTER I | \n",
+ " ๐ณ | \n",
+ " COOKING | \n",
+ " ๐ธ | \n",
+ " CHILDREN CROSSING | \n",
"
\n",
" \n",
" 2 | \n",
- " ๐ | \n",
- " RAISED HAND WITH PART BETWEEN MIDDLE AND RING ... | \n",
- " ๐ฎ | \n",
- " REGIONAL INDICATOR SYMBOL LETTER I | \n",
- " ๐ | \n",
- " LOVE LETTER | \n",
- " ๐ค | \n",
- " I LOVE YOU HAND SIGN | \n",
+ " ๐ฎ | \n",
+ " PUT LITTER IN ITS PLACE SYMBOL | \n",
+ " ๐ | \n",
+ " TRAIN | \n",
+ " ๐ | \n",
+ " TRAIN | \n",
+ " ๐ | \n",
+ " HIGH-SPEED TRAIN | \n",
"
\n",
" \n",
" 3 | \n",
- " ๐ฅฐ | \n",
- " SMILING FACE WITH SMILING EYES AND THREE HEARTS | \n",
- " ๐ฉ | \n",
- " LOVE HOTEL | \n",
- " ๐ | \n",
- " SQUARED CL | \n",
+ " ๐คช | \n",
+ " GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE | \n",
+ " ๐
| \n",
+ " HIGH-SPEED TRAIN WITH BULLET NOSE | \n",
+ " ๐ฅ | \n",
+ " MOVIE CAMERA | \n",
" ๐ฎ | \n",
" REGIONAL INDICATOR SYMBOL LETTER I | \n",
"
\n",
" \n",
" 4 | \n",
- " ๐คญ | \n",
- " SMILING FACE WITH SMILING EYES AND HAND COVERI... | \n",
- " ๐ฑ | \n",
- " FACE SCREAMING IN FEAR | \n",
- " ๐ | \n",
- " BRIDGE AT NIGHT | \n",
- " ๐จ | \n",
- " INCOMING ENVELOPE | \n",
+ " ๐ฅฐ | \n",
+ " SMILING FACE WITH SMILING EYES AND THREE HEARTS | \n",
+ " ๐ | \n",
+ " HIGH-SPEED TRAIN | \n",
+ " ๐ญ | \n",
+ " PERFORMING ARTS | \n",
+ " ๐ค | \n",
+ " I LOVE YOU HAND SIGN | \n",
"
\n",
" \n",
" 5 | \n",
- " ๐ | \n",
- " CLOCKWISE RIGHTWARDS AND LEFTWARDS OPEN CIRCLE... | \n",
- " ๐ญ | \n",
- " REGIONAL INDICATOR SYMBOL LETTER H | \n",
- " ๐ | \n",
- " BOUQUET | \n",
- " ๐ฉ | \n",
- " ENVELOPE WITH DOWNWARDS ARROW ABOVE | \n",
+ " ๐ | \n",
+ " PERSON RAISING BOTH HANDS IN CELEBRATION | \n",
+ " ๐ธ | \n",
+ " CHILDREN CROSSING | \n",
+ " ๐น | \n",
+ " MUSICAL KEYBOARD | \n",
+ " ๐
| \n",
+ " HIGH-SPEED TRAIN WITH BULLET NOSE | \n",
"
\n",
" \n",
" 6 | \n",
- " ๐ | \n",
- " ON WITH EXCLAMATION MARK WITH LEFT RIGHT ARROW... | \n",
- " ๐ณ | \n",
- " REGIONAL INDICATOR SYMBOL LETTER N | \n",
- " ๐ | \n",
- " SCROLL | \n",
- " ๐ช | \n",
- " CLOSED MAILBOX WITH LOWERED FLAG | \n",
+ " ๐ | \n",
+ " RAISED HAND WITH PART BETWEEN MIDDLE AND RING ... | \n",
+ " ๐ธ | \n",
+ " FLYING SAUCER | \n",
+ " ๐งพ | \n",
+ " RECEIPT | \n",
+ " ๐น | \n",
+ " SMALL BLUE DIAMOND | \n",
"
\n",
" \n",
" 7 | \n",
- " ๐ | \n",
- " INPUT SYMBOL FOR LATIN CAPITAL LETTERS | \n",
- " ๐ด | \n",
- " REGIONAL INDICATOR SYMBOL LETTER O | \n",
- " ๐ | \n",
- " WRAPPED PRESENT | \n",
- " ๐ซ | \n",
- " CLOSED MAILBOX WITH RAISED FLAG | \n",
+ " ๐ | \n",
+ " CLOCKWISE RIGHTWARDS AND LEFTWARDS OPEN CIRCLE... | \n",
+ " ๐ฅพ | \n",
+ " HIKING BOOT | \n",
+ " ๐ | \n",
+ " KISS | \n",
+ " ๐ | \n",
+ " FAX MACHINE | \n",
"
\n",
" \n",
" 8 | \n",
- " ๐ค | \n",
- " I LOVE YOU HAND SIGN | \n",
- " ๐ฒ | \n",
- " MOBILE PHONE WITH RIGHTWARDS ARROW AT LEFT | \n",
- " ๐จ | \n",
- " DASH SYMBOL | \n",
- " ๐ฐ | \n",
- " NEWSPAPER | \n",
+ " ๐ | \n",
+ " SMILING FACE WITH OPEN MOUTH AND SMILING EYES | \n",
+ " ๐ฅ | \n",
+ " FLYING DISC | \n",
+ " ๐ฅ | \n",
+ " FIRE | \n",
+ " ๐ก | \n",
+ " SATELLITE ANTENNA | \n",
"
\n",
" \n",
" 9 | \n",
- " ๐ฎ | \n",
- " REGIONAL INDICATOR SYMBOL LETTER I | \n",
- " ๐ | \n",
- " CITYSCAPE AT DUSK | \n",
- " ๐ค | \n",
- " SLEEPING SYMBOL | \n",
- " ๐ฌ | \n",
- " OPEN MAILBOX WITH RAISED FLAG | \n",
+ " ๐ | \n",
+ " WHITE RIGHT POINTING BACKHAND INDEX | \n",
+ " ๐ | \n",
+ " BUS STOP | \n",
+ " ๐ผ | \n",
+ " MUSICAL SCORE | \n",
+ " ๐ข | \n",
+ " PUBLIC ADDRESS LOUDSPEAKER | \n",
"
\n",
" \n",
"\n",
@@ -494,40 +495,40 @@
],
"text/plain": [
" summed summed_description max_val \\\n",
- "0 ๐คช GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE ๐ค \n",
- "1 ๐ฎ PUT LITTER IN ITS PLACE SYMBOL ๐ \n",
- "2 ๐ RAISED HAND WITH PART BETWEEN MIDDLE AND RING ... ๐ฎ \n",
- "3 ๐ฅฐ SMILING FACE WITH SMILING EYES AND THREE HEARTS ๐ฉ \n",
- "4 ๐คญ SMILING FACE WITH SMILING EYES AND HAND COVERI... ๐ฑ \n",
- "5 ๐ CLOCKWISE RIGHTWARDS AND LEFTWARDS OPEN CIRCLE... ๐ญ \n",
- "6 ๐ ON WITH EXCLAMATION MARK WITH LEFT RIGHT ARROW... ๐ณ \n",
- "7 ๐ INPUT SYMBOL FOR LATIN CAPITAL LETTERS ๐ด \n",
- "8 ๐ค I LOVE YOU HAND SIGN ๐ฒ \n",
- "9 ๐ฎ REGIONAL INDICATOR SYMBOL LETTER I ๐ \n",
+ "0 ๐คญ SMILING FACE WITH SMILING EYES AND HAND COVERI... ๐ค \n",
+ "1 ๐ ON WITH EXCLAMATION MARK WITH LEFT RIGHT ARROW... ๐ฎ \n",
+ "2 ๐ฎ PUT LITTER IN ITS PLACE SYMBOL ๐ \n",
+ "3 ๐คช GRINNING FACE WITH ONE LARGE AND ONE SMALL EYE ๐
\n",
+ "4 ๐ฅฐ SMILING FACE WITH SMILING EYES AND THREE HEARTS ๐ \n",
+ "5 ๐ PERSON RAISING BOTH HANDS IN CELEBRATION ๐ธ \n",
+ "6 ๐ RAISED HAND WITH PART BETWEEN MIDDLE AND RING ... ๐ธ \n",
+ "7 ๐ CLOCKWISE RIGHTWARDS AND LEFTWARDS OPEN CIRCLE... ๐ฅพ \n",
+ "8 ๐ SMILING FACE WITH OPEN MOUTH AND SMILING EYES ๐ฅ \n",
+ "9 ๐ WHITE RIGHT POINTING BACKHAND INDEX ๐ \n",
"\n",
- " max_val_description avg avg_description threshold \\\n",
- "0 I LOVE YOU HAND SIGN ๐ข ANGER SYMBOL ๐ \n",
- "1 LOVE LETTER ๐ฆ PACKAGE ๐ฉ \n",
- "2 REGIONAL INDICATOR SYMBOL LETTER I ๐ LOVE LETTER ๐ค \n",
- "3 LOVE HOTEL ๐ SQUARED CL ๐ฎ \n",
- "4 FACE SCREAMING IN FEAR ๐ BRIDGE AT NIGHT ๐จ \n",
- "5 REGIONAL INDICATOR SYMBOL LETTER H ๐ BOUQUET ๐ฉ \n",
- "6 REGIONAL INDICATOR SYMBOL LETTER N ๐ SCROLL ๐ช \n",
- "7 REGIONAL INDICATOR SYMBOL LETTER O ๐ WRAPPED PRESENT ๐ซ \n",
- "8 MOBILE PHONE WITH RIGHTWARDS ARROW AT LEFT ๐จ DASH SYMBOL ๐ฐ \n",
- "9 CITYSCAPE AT DUSK ๐ค SLEEPING SYMBOL ๐ฌ \n",
+ " max_val_description avg avg_description threshold \\\n",
+ "0 I LOVE YOU HAND SIGN ๐ BOUQUET ๐ \n",
+ "1 REGIONAL INDICATOR SYMBOL LETTER I ๐ณ COOKING ๐ธ \n",
+ "2 TRAIN ๐ TRAIN ๐ \n",
+ "3 HIGH-SPEED TRAIN WITH BULLET NOSE ๐ฅ MOVIE CAMERA ๐ฎ \n",
+ "4 HIGH-SPEED TRAIN ๐ญ PERFORMING ARTS ๐ค \n",
+ "5 CHILDREN CROSSING ๐น MUSICAL KEYBOARD ๐
\n",
+ "6 FLYING SAUCER ๐งพ RECEIPT ๐น \n",
+ "7 HIKING BOOT ๐ KISS ๐ \n",
+ "8 FLYING DISC ๐ฅ FIRE ๐ก \n",
+ "9 BUS STOP ๐ผ MUSICAL SCORE ๐ข \n",
"\n",
- " threshold_description \n",
- "0 LOVE LETTER \n",
- "1 LOVE HOTEL \n",
- "2 I LOVE YOU HAND SIGN \n",
- "3 REGIONAL INDICATOR SYMBOL LETTER I \n",
- "4 INCOMING ENVELOPE \n",
- "5 ENVELOPE WITH DOWNWARDS ARROW ABOVE \n",
- "6 CLOSED MAILBOX WITH LOWERED FLAG \n",
- "7 CLOSED MAILBOX WITH RAISED FLAG \n",
- "8 NEWSPAPER \n",
- "9 OPEN MAILBOX WITH RAISED FLAG "
+ " threshold_description \n",
+ "0 TRAIN \n",
+ "1 CHILDREN CROSSING \n",
+ "2 HIGH-SPEED TRAIN \n",
+ "3 REGIONAL INDICATOR SYMBOL LETTER I \n",
+ "4 I LOVE YOU HAND SIGN \n",
+ "5 HIGH-SPEED TRAIN WITH BULLET NOSE \n",
+ "6 SMALL BLUE DIAMOND \n",
+ "7 FAX MACHINE \n",
+ "8 SATELLITE ANTENNA \n",
+ "9 PUBLIC ADDRESS LOUDSPEAKER "
]
},
"metadata": {},
@@ -535,7 +536,7 @@
}
],
"source": [
- "predict(\"I love sunny days!\", description_key='description' )"
+ "predict(\"I like to travel by train\", description_key='description' , lang='eng')"
]
},
{