From 4bd81f0f18723d309bcb8dbbaf48c2ba73b3a461 Mon Sep 17 00:00:00 2001
From: Filip Johnsson <filjo653@student.liu.se>
Date: Mon, 25 Nov 2024 14:52:59 +0100
Subject: [PATCH] part 5
---
l3/TM-Lab3.ipynb | 111 ++++++++++++++++++++++++++---------------------
1 file changed, 61 insertions(+), 50 deletions(-)
diff --git a/l3/TM-Lab3.ipynb b/l3/TM-Lab3.ipynb
index fc9c593..b14e058 100644
--- a/l3/TM-Lab3.ipynb
+++ b/l3/TM-Lab3.ipynb
@@ -37,7 +37,7 @@
},
{
"cell_type": "code",
- "execution_count": 332,
+ "execution_count": 2,
"metadata": {
"deletable": false,
"editable": false,
@@ -82,7 +82,7 @@
},
{
"cell_type": "code",
- "execution_count": 333,
+ "execution_count": 3,
"metadata": {
"deletable": false,
"editable": false,
@@ -128,7 +128,7 @@
},
{
"cell_type": "code",
- "execution_count": 334,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
@@ -220,7 +220,7 @@
"4 Brussels "
]
},
- "execution_count": 334,
+ "execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -262,7 +262,7 @@
},
{
"cell_type": "code",
- "execution_count": 335,
+ "execution_count": 5,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -312,7 +312,7 @@
},
{
"cell_type": "code",
- "execution_count": 336,
+ "execution_count": 6,
"metadata": {
"deletable": false,
"editable": false,
@@ -350,7 +350,7 @@
},
{
"cell_type": "code",
- "execution_count": 337,
+ "execution_count": 7,
"metadata": {
"deletable": false,
"editable": false,
@@ -419,7 +419,7 @@
},
{
"cell_type": "code",
- "execution_count": 338,
+ "execution_count": 8,
"metadata": {
"deletable": false,
"editable": false,
@@ -464,7 +464,7 @@
},
{
"cell_type": "code",
- "execution_count": 339,
+ "execution_count": 9,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -498,7 +498,7 @@
},
{
"cell_type": "code",
- "execution_count": 340,
+ "execution_count": 10,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -552,7 +552,7 @@
},
{
"cell_type": "code",
- "execution_count": 341,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -575,7 +575,7 @@
},
{
"cell_type": "code",
- "execution_count": 342,
+ "execution_count": 12,
"metadata": {
"deletable": false,
"editable": false,
@@ -630,7 +630,7 @@
},
{
"cell_type": "code",
- "execution_count": 343,
+ "execution_count": 13,
"metadata": {
"deletable": false,
"editable": false,
@@ -692,7 +692,7 @@
},
{
"cell_type": "code",
- "execution_count": 344,
+ "execution_count": 14,
"metadata": {
"tags": [
"solution"
@@ -16062,7 +16062,7 @@
},
{
"cell_type": "code",
- "execution_count": 345,
+ "execution_count": 15,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16123,7 +16123,7 @@
},
{
"cell_type": "code",
- "execution_count": 346,
+ "execution_count": 16,
"metadata": {
"tags": [
"solution"
@@ -16147,7 +16147,7 @@
},
{
"cell_type": "code",
- "execution_count": 347,
+ "execution_count": 17,
"metadata": {
"deletable": false,
"editable": false,
@@ -16193,7 +16193,7 @@
},
{
"cell_type": "code",
- "execution_count": 348,
+ "execution_count": 18,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16245,7 +16245,7 @@
},
{
"cell_type": "code",
- "execution_count": 349,
+ "execution_count": 19,
"metadata": {
"deletable": false,
"editable": false,
@@ -16290,6 +16290,7 @@
" <th>sentence</th>\n",
" <th>beg</th>\n",
" <th>end</th>\n",
+ " <th>label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
@@ -16299,6 +16300,7 @@
" <td>LONDON 1996-08-30</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
+ " <td>--NME--</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
@@ -16306,6 +16308,7 @@
" <td>West Indian all-rounder Phil Simmons took four...</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
+ " <td>--NME--</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
@@ -16313,6 +16316,7 @@
" <td>West Indian all-rounder Phil Simmons took four...</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
+ " <td>--NME--</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
@@ -16320,6 +16324,7 @@
" <td>West Indian all-rounder Phil Simmons took four...</td>\n",
" <td>12</td>\n",
" <td>13</td>\n",
+ " <td>--NME--</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
@@ -16327,18 +16332,26 @@
" <td>West Indian all-rounder Phil Simmons took four...</td>\n",
" <td>14</td>\n",
" <td>15</td>\n",
+ " <td>--NME--</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
- " sentence_id sentence beg end\n",
- "0 0946-001 LONDON 1996-08-30 0 1\n",
- "1 0946-002 West Indian all-rounder Phil Simmons took four... 0 2\n",
- "2 0946-002 West Indian all-rounder Phil Simmons took four... 3 5\n",
- "3 0946-002 West Indian all-rounder Phil Simmons took four... 12 13\n",
- "4 0946-002 West Indian all-rounder Phil Simmons took four... 14 15"
+ " sentence_id sentence beg end \\\n",
+ "0 0946-001 LONDON 1996-08-30 0 1 \n",
+ "1 0946-002 West Indian all-rounder Phil Simmons took four... 0 2 \n",
+ "2 0946-002 West Indian all-rounder Phil Simmons took four... 3 5 \n",
+ "3 0946-002 West Indian all-rounder Phil Simmons took four... 12 13 \n",
+ "4 0946-002 West Indian all-rounder Phil Simmons took four... 14 15 \n",
+ "\n",
+ " label \n",
+ "0 --NME-- \n",
+ "1 --NME-- \n",
+ "2 --NME-- \n",
+ "3 --NME-- \n",
+ "4 --NME-- "
]
},
"metadata": {},
@@ -16375,7 +16388,7 @@
},
{
"cell_type": "code",
- "execution_count": 350,
+ "execution_count": 20,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16417,7 +16430,7 @@
},
{
"cell_type": "code",
- "execution_count": 351,
+ "execution_count": 21,
"metadata": {
"deletable": false,
"editable": false,
@@ -16482,7 +16495,7 @@
},
{
"cell_type": "code",
- "execution_count": 352,
+ "execution_count": 22,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16531,7 +16544,7 @@
},
{
"cell_type": "code",
- "execution_count": 353,
+ "execution_count": 23,
"metadata": {
"deletable": false,
"editable": false,
@@ -16600,7 +16613,7 @@
},
{
"cell_type": "code",
- "execution_count": 354,
+ "execution_count": 24,
"metadata": {
"deletable": false,
"editable": false,
@@ -16630,7 +16643,7 @@
},
{
"cell_type": "code",
- "execution_count": 355,
+ "execution_count": 25,
"metadata": {},
"outputs": [
{
@@ -16689,7 +16702,7 @@
"17438 Sweden Sweden_men's_national_ice_hockey_team 0.000059"
]
},
- "execution_count": 355,
+ "execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
@@ -16714,7 +16727,7 @@
},
{
"cell_type": "code",
- "execution_count": 356,
+ "execution_count": 58,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16745,8 +16758,19 @@
" quadruples consisting of the sentence id, start position, end\n",
" position and the predicted entity label of each span.\n",
" \"\"\"\n",
- " # YOUR CODE HERE\n",
- " raise NotImplementedError()"
+ " for row in df.itertuples():\n",
+ " sentence_id = row[1]\n",
+ " sentence = row[2]\n",
+ " start = row[3]\n",
+ " end = row[4]\n",
+ "\n",
+ " words = sentence.split()\n",
+ " spliced_sentence = ' '.join(words[int(start):int(end)])\n",
+ " entity = df_kb.loc[df_kb.mention == spliced_sentence].entity\n",
+ "\n",
+ " entity_val = entity.values[0] if len(entity.values) > 0 else \"--NME--\"\n",
+ "\n",
+ " yield sentence_id, start, end, entity_val\n"
]
},
{
@@ -16760,7 +16784,7 @@
},
{
"cell_type": "code",
- "execution_count": 357,
+ "execution_count": 61,
"metadata": {
"deletable": false,
"editable": false,
@@ -16779,20 +16803,7 @@
"solution"
]
},
- "outputs": [
- {
- "ename": "NotImplementedError",
- "evalue": "",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNotImplementedError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[357], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m scores \u001b[38;5;241m=\u001b[39m evaluation_scores(dev_gold_mentions, \u001b[38;5;28mset\u001b[39m(\u001b[43mmost_probable_method\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf_dev_pred\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdf_kb\u001b[49m\u001b[43m)\u001b[49m))\n\u001b[1;32m 2\u001b[0m print_evaluation_scores(scores)\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m scores[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m.64\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPrecision should be above 64\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
- "Cell \u001b[0;32mIn[356], line 14\u001b[0m, in \u001b[0;36mmost_probable_method\u001b[0;34m(df, df_kb)\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"An entity linker that resolves each mention to the most probably entity in a knowledge base.\u001b[39;00m\n\u001b[1;32m 3\u001b[0m \n\u001b[1;32m 4\u001b[0m \u001b[38;5;124;03mArguments:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 11\u001b[0m \u001b[38;5;124;03m position and the predicted entity label of each span.\u001b[39;00m\n\u001b[1;32m 12\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;66;03m# YOUR CODE HERE\u001b[39;00m\n\u001b[0;32m---> 14\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m()\n",
- "\u001b[0;31mNotImplementedError\u001b[0m: "
- ]
- }
- ],
+ "outputs": [],
"source": [
"scores = evaluation_scores(dev_gold_mentions, set(most_probable_method(df_dev_pred, df_kb)))\n",
"print_evaluation_scores(scores)\n",
--
GitLab