s444519/ireland-news-headlines-new
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

new

Browse Source
This commit is contained in:
s444519 2022-06-07 18:00:10 +02:00
parent 2aca23985e
commit abb01e949e
4 changed files with 24676 additions and 24707 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

137
Untitled.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 57, "execution_count": 1,
"id": "f902472d", "id": "f902472d",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -20,7 +20,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 58, "execution_count": 2,
"id": "2324a8dd", "id": "2324a8dd",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -35,7 +35,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 59, "execution_count": 3,
"id": "e4ba4b52", "id": "e4ba4b52",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -144,7 +144,7 @@
"9 2017.005479 20170103 Sinn Féin warns Stormont may collapse over 'ca..." "9 2017.005479 20170103 Sinn Féin warns Stormont may collapse over 'ca..."
] ]
}, },
"execution_count": 59, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -155,7 +155,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 60, "execution_count": 4,
"id": "d4a64cb8", "id": "d4a64cb8",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -264,7 +264,7 @@
"9 2012.791781 20121016 UK investigation into Icelandic bank fraud aba..." "9 2012.791781 20121016 UK investigation into Icelandic bank fraud aba..."
] ]
}, },
"execution_count": 60, "execution_count": 4,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -275,7 +275,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 61, "execution_count": 5,
"id": "1221baee", "id": "1221baee",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -384,7 +384,7 @@
"9 2005.569863 20050728 IRA must hand over criminal assets - McDowell" "9 2005.569863 20050728 IRA must hand over criminal assets - McDowell"
] ]
}, },
"execution_count": 61, "execution_count": 5,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -395,7 +395,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 62, "execution_count": 6,
"id": "58cb7b89", "id": "58cb7b89",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -482,7 +482,7 @@
"9 news" "9 news"
] ]
}, },
"execution_count": 62, "execution_count": 6,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -493,7 +493,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 63, "execution_count": 7,
"id": "cfb113b6", "id": "cfb113b6",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -506,7 +506,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 64, "execution_count": 8,
"id": "046f00be", "id": "046f00be",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -516,7 +516,7 @@
"'Sudan claims it is disarming militias'" "'Sudan claims it is disarming militias'"
] ]
}, },
"execution_count": 64, "execution_count": 8,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -527,7 +527,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 65, "execution_count": 9,
"id": "9d36394d", "id": "9d36394d",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -548,7 +548,7 @@
"Name: 2, Length: 1186898, dtype: object" "Name: 2, Length: 1186898, dtype: object"
] ]
}, },
"execution_count": 65, "execution_count": 9,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -559,7 +559,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 66, "execution_count": 10,
"id": "58d6e666", "id": "58d6e666",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -570,7 +570,7 @@
" 'removed'], dtype=object)" " 'removed'], dtype=object)"
] ]
}, },
"execution_count": 66, "execution_count": 10,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -581,7 +581,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 67, "execution_count": 11,
"id": "86d6f712", "id": "86d6f712",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -594,7 +594,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 68, "execution_count": 12,
"id": "4491cae8", "id": "4491cae8",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -651,7 +651,7 @@
"3 3" "3 3"
] ]
}, },
"execution_count": 68, "execution_count": 12,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -662,7 +662,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 84, "execution_count": 13,
"id": "6eccbc39", "id": "6eccbc39",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -672,7 +672,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 85, "execution_count": 14,
"id": "e09e6a3f", "id": "e09e6a3f",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -682,7 +682,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 86, "execution_count": 15,
"id": "f0e4b5fc", "id": "f0e4b5fc",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -692,7 +692,7 @@
"pandas.core.frame.DataFrame" "pandas.core.frame.DataFrame"
] ]
}, },
"execution_count": 86, "execution_count": 15,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -703,7 +703,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 87, "execution_count": 16,
"id": "7662ca93", "id": "7662ca93",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -713,7 +713,7 @@
"pandas.core.series.Series" "pandas.core.series.Series"
] ]
}, },
"execution_count": 87, "execution_count": 16,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -724,7 +724,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 88, "execution_count": 17,
"id": "a1838cd6", "id": "a1838cd6",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -1734,7 +1734,7 @@
" ...]" " ...]"
] ]
}, },
"execution_count": 88, "execution_count": 17,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1745,7 +1745,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 89, "execution_count": 18,
"id": "3eedae48", "id": "3eedae48",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -1756,7 +1756,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 90, "execution_count": 19,
"id": "adc7bcd0", "id": "adc7bcd0",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -1769,7 +1769,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 91, "execution_count": 20,
"id": "2b9ce936", "id": "2b9ce936",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -1781,26 +1781,26 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 92, "execution_count": 21,
"id": "cef5f0c2", "id": "cef5f0c2",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"['| headline: | headline: President Higgins and Xi Jinping enjoy productive talks',\n", "['| headline: President Higgins and Xi Jinping enjoy productive talks',\n",
" '| headline: | headline: German trade surplus at seven-year low',\n", " '| headline: German trade surplus at seven-year low',\n",
" \"| headline: | headline: Potatoes have 'huge image issue' among the youth\",\n", " \"| headline: Potatoes have 'huge image issue' among the youth\",\n",
" \"| headline: | headline: New home education guidelines favour school teachers; says parents' group\",\n", " \"| headline: New home education guidelines favour school teachers; says parents' group\",\n",
" '| headline: | headline: Mindhunter drags us back to the place where the serial killer craze began',\n", " '| headline: Mindhunter drags us back to the place where the serial killer craze began',\n",
" \"| headline: | headline: 'Asgard' to escape from Kilmainham Gaol and appear at RDS boat show next week\",\n", " \"| headline: 'Asgard' to escape from Kilmainham Gaol and appear at RDS boat show next week\",\n",
" '| headline: | headline: Five dead after British bus crashes in Austria',\n", " '| headline: Five dead after British bus crashes in Austria',\n",
" '| headline: | headline: Clane General Hospital expects to return to profit this year',\n", " '| headline: Clane General Hospital expects to return to profit this year',\n",
" \"| headline: | headline: NI death cert plan 'won't bring closure'\",\n", " \"| headline: NI death cert plan 'won't bring closure'\",\n",
" '| headline: | headline: UK investigation into Icelandic bank fraud abandoned']" " '| headline: UK investigation into Icelandic bank fraud abandoned']"
] ]
}, },
"execution_count": 92, "execution_count": 21,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1811,20 +1811,20 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 93, "execution_count": 22,
"id": "062f0bd1", "id": "062f0bd1",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"['| headline: | headline: Erratic Wales do it the hard way',\n", "['| headline: Erratic Wales do it the hard way',\n",
" \"| headline: | headline: Girls in my daughter's class are calling her fat\",\n", " \"| headline: Girls in my daughter's class are calling her fat\",\n",
" \"| headline: | headline: Russia 'not ready' for Y2K\",\n", " \"| headline: Russia 'not ready' for Y2K\",\n",
" \"| headline: | headline: Those who can't\"]" " \"| headline: Those who can't\"]"
] ]
}, },
"execution_count": 93, "execution_count": 22,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1835,7 +1835,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 102, "execution_count": 23,
"id": "f20d5d1d", "id": "f20d5d1d",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -1854,7 +1854,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 103, "execution_count": 24,
"id": "4c68c041", "id": "4c68c041",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -1864,7 +1864,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 104, "execution_count": 25,
"id": "9da03434", "id": "9da03434",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -1874,44 +1874,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 105, "execution_count": 26,
"id": "f8d5471d", "id": "f8d5471d",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"predictions(testb_x, 'test-B\\out.tsv')" "predictions(testb_x, 'test-B\\out.tsv')"
] ]
},
{
"cell_type": "code",
"execution_count": 97,
"id": "bf17408d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"NoneType"
]
},
"execution_count": 97,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(pred_dev)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bf9302cb",
"metadata": {},
"outputs": [],
"source": [
"pred_dev"
]
} }
], ],
"metadata": { "metadata": {

19464
dev-0/out.tsv
View File

File diff suppressed because it is too large Load Diff

19988
test-A/out.tsv
View File

File diff suppressed because it is too large Load Diff

9794
test-B/out.tsv
View File

File diff suppressed because it is too large Load Diff