diff --git a/l3/TM-Lab3.ipynb b/l3/TM-Lab3.ipynb
index 10e046b53ec2cc3d981c35c8d84f40f17d7d74b5..fc9c5933865efdc68a5d9e8d5809dff46af7d50d 100644
--- a/l3/TM-Lab3.ipynb
+++ b/l3/TM-Lab3.ipynb
@@ -37,7 +37,7 @@
},
{
"cell_type": "code",
- "execution_count": 303,
+ "execution_count": 332,
"metadata": {
"deletable": false,
"editable": false,
@@ -82,7 +82,7 @@
},
{
"cell_type": "code",
- "execution_count": 304,
+ "execution_count": 333,
"metadata": {
"deletable": false,
"editable": false,
@@ -128,7 +128,7 @@
},
{
"cell_type": "code",
- "execution_count": 305,
+ "execution_count": 334,
"metadata": {},
"outputs": [
{
@@ -220,7 +220,7 @@
"4 Brussels "
]
},
- "execution_count": 305,
+ "execution_count": 334,
"metadata": {},
"output_type": "execute_result"
}
@@ -262,7 +262,7 @@
},
{
"cell_type": "code",
- "execution_count": 306,
+ "execution_count": 335,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -312,7 +312,7 @@
},
{
"cell_type": "code",
- "execution_count": 307,
+ "execution_count": 336,
"metadata": {
"deletable": false,
"editable": false,
@@ -350,7 +350,7 @@
},
{
"cell_type": "code",
- "execution_count": 308,
+ "execution_count": 337,
"metadata": {
"deletable": false,
"editable": false,
@@ -419,7 +419,7 @@
},
{
"cell_type": "code",
- "execution_count": 309,
+ "execution_count": 338,
"metadata": {
"deletable": false,
"editable": false,
@@ -464,7 +464,7 @@
},
{
"cell_type": "code",
- "execution_count": 310,
+ "execution_count": 339,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -498,7 +498,7 @@
},
{
"cell_type": "code",
- "execution_count": 311,
+ "execution_count": 340,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -552,7 +552,7 @@
},
{
"cell_type": "code",
- "execution_count": 312,
+ "execution_count": 341,
"metadata": {},
"outputs": [
{
@@ -575,7 +575,7 @@
},
{
"cell_type": "code",
- "execution_count": 313,
+ "execution_count": 342,
"metadata": {
"deletable": false,
"editable": false,
@@ -630,7 +630,7 @@
},
{
"cell_type": "code",
- "execution_count": 314,
+ "execution_count": 343,
"metadata": {
"deletable": false,
"editable": false,
@@ -692,7 +692,7 @@
},
{
"cell_type": "code",
- "execution_count": 315,
+ "execution_count": 344,
"metadata": {
"tags": [
"solution"
@@ -16062,7 +16062,7 @@
},
{
"cell_type": "code",
- "execution_count": 323,
+ "execution_count": 345,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16123,7 +16123,7 @@
},
{
"cell_type": "code",
- "execution_count": 324,
+ "execution_count": 346,
"metadata": {
"tags": [
"solution"
@@ -16147,7 +16147,7 @@
},
{
"cell_type": "code",
- "execution_count": 325,
+ "execution_count": 347,
"metadata": {
"deletable": false,
"editable": false,
@@ -16193,7 +16193,7 @@
},
{
"cell_type": "code",
- "execution_count": 326,
+ "execution_count": 348,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16226,9 +16226,9 @@
"\n",
" for index, (sentence_id, beg, end) in enumerate(pred_spans_improved(df)):\n",
" sentence = sentence_dict.get(sentence_id)\n",
- " rows.append({'sentence_id': sentence_id, 'sentence': sentence, 'beg': beg, 'end': end})\n",
+ " rows.append({'sentence_id': sentence_id, 'sentence': sentence, 'beg': beg, 'end': end, 'label': '--NME--'})\n",
"\n",
- " new_data_frame = pd.DataFrame(rows, columns=['sentence_id', 'sentence', 'beg', 'end'])\n",
+ " new_data_frame = pd.DataFrame(rows, columns=['sentence_id', 'sentence', 'beg', 'end', 'label'])\n",
"\n",
" return new_data_frame\n",
"\n"
@@ -16245,7 +16245,7 @@
},
{
"cell_type": "code",
- "execution_count": 327,
+ "execution_count": 349,
"metadata": {
"deletable": false,
"editable": false,
@@ -16343,98 +16343,6 @@
},
"metadata": {},
"output_type": "display_data"
- },
- {
- "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>sentence_id</th>\n",
- " <th>sentence</th>\n",
- " <th>beg</th>\n",
- " <th>end</th>\n",
- " <th>label</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>0946-000</td>\n",
- " <td>CRICKET - LEICESTERSHIRE TAKE OVER AT TOP AFTE...</td>\n",
- " <td>2</td>\n",
- " <td>3</td>\n",
- " <td>Leicestershire_County_Cricket_Club</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>0946-001</td>\n",
- " <td>LONDON 1996-08-30</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>London</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>0946-002</td>\n",
- " <td>West Indian all-rounder Phil Simmons took four...</td>\n",
- " <td>0</td>\n",
- " <td>2</td>\n",
- " <td>West_Indies_cricket_team</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>0946-002</td>\n",
- " <td>West Indian all-rounder Phil Simmons took four...</td>\n",
- " <td>3</td>\n",
- " <td>5</td>\n",
- " <td>Phil_Simmons</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>0946-002</td>\n",
- " <td>West Indian all-rounder Phil Simmons took four...</td>\n",
- " <td>12</td>\n",
- " <td>13</td>\n",
- " <td>Leicestershire_County_Cricket_Club</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " sentence_id sentence beg end \\\n",
- "0 0946-000 CRICKET - LEICESTERSHIRE TAKE OVER AT TOP AFTE... 2 3 \n",
- "1 0946-001 LONDON 1996-08-30 0 1 \n",
- "2 0946-002 West Indian all-rounder Phil Simmons took four... 0 2 \n",
- "3 0946-002 West Indian all-rounder Phil Simmons took four... 3 5 \n",
- "4 0946-002 West Indian all-rounder Phil Simmons took four... 12 13 \n",
- "\n",
- " label \n",
- "0 Leicestershire_County_Cricket_Club \n",
- "1 London \n",
- "2 West_Indies_cricket_team \n",
- "3 Phil_Simmons \n",
- "4 Leicestershire_County_Cricket_Club "
- ]
- },
- "metadata": {},
- "output_type": "display_data"
}
],
"source": [
@@ -16467,7 +16375,7 @@
},
{
"cell_type": "code",
- "execution_count": 328,
+ "execution_count": 350,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16509,7 +16417,7 @@
},
{
"cell_type": "code",
- "execution_count": 329,
+ "execution_count": 351,
"metadata": {
"deletable": false,
"editable": false,
@@ -16574,7 +16482,7 @@
},
{
"cell_type": "code",
- "execution_count": 330,
+ "execution_count": 352,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16623,7 +16531,7 @@
},
{
"cell_type": "code",
- "execution_count": 331,
+ "execution_count": 353,
"metadata": {
"deletable": false,
"editable": false,
@@ -16692,7 +16600,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 354,
"metadata": {
"deletable": false,
"editable": false,
@@ -16722,9 +16630,70 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 355,
"metadata": {},
- "outputs": [],
+ "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>mention</th>\n",
+ " <th>entity</th>\n",
+ " <th>prob</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>17436</th>\n",
+ " <td>Sweden</td>\n",
+ " <td>Sweden</td>\n",
+ " <td>0.985768</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17437</th>\n",
+ " <td>Sweden</td>\n",
+ " <td>Sweden_national_football_team</td>\n",
+ " <td>0.014173</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17438</th>\n",
+ " <td>Sweden</td>\n",
+ " <td>Sweden_men's_national_ice_hockey_team</td>\n",
+ " <td>0.000059</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " mention entity prob\n",
+ "17436 Sweden Sweden 0.985768\n",
+ "17437 Sweden Sweden_national_football_team 0.014173\n",
+ "17438 Sweden Sweden_men's_national_ice_hockey_team 0.000059"
+ ]
+ },
+ "execution_count": 355,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"df_kb.loc[df_kb.mention == 'Sweden']"
]
@@ -16745,7 +16714,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 356,
"metadata": {
"deletable": false,
"nbgrader": {
@@ -16791,7 +16760,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 357,
"metadata": {
"deletable": false,
"editable": false,
@@ -16810,7 +16779,20 @@
"solution"
]
},
- "outputs": [],
+ "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: "
+ ]
+ }
+ ],
"source": [
"scores = evaluation_scores(dev_gold_mentions, set(most_probable_method(df_dev_pred, df_kb)))\n",
"print_evaluation_scores(scores)\n",