s415366/challenging-america-word-gap-prediction
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

asdas

Browse Source
This commit is contained in:
Ramon Dyzman 2022-04-11 11:29:29 +02:00
parent a23511bd83
commit 943d78fe31
1 changed files with 21 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
main.ipynb
View File

@ -24,7 +24,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 88, "execution_count": 1,
"metadata": { "metadata": {
"tags": [] "tags": []
}, },
@ -36,9 +36,10 @@
"# dev_data = pd.read_csv('dev-0/in.tsv', sep='\\t', names=columns, engine='python', quotechar='\"', error_bad_lines=False)\n", "# dev_data = pd.read_csv('dev-0/in.tsv', sep='\\t', names=columns, engine='python', quotechar='\"', error_bad_lines=False)\n",
"# dev_expected = pd.read_csv('dev-0/expected.tsv', sep='\\t', engine='python', quotechar='\"', error_bad_lines=False)\n", "# dev_expected = pd.read_csv('dev-0/expected.tsv', sep='\\t', engine='python', quotechar='\"', error_bad_lines=False)\n",
"dev_data = list()\n", "dev_data = list()\n",
"data_path = 'dev-0/in.tsv'\n", "directory = 'dev-0'\n",
"expected_path = 'dev-0/expected.tsv'\n", "data_path = directory+'/in.tsv'\n",
"out_path = 'dev-0/out.tsv'\n", "expected_path = directory+'/expected.tsv'\n",
"out_path = directory+'/out.tsv'\n",
"\n", "\n",
"with open(data_path, \"r\") as f:\n", "with open(data_path, \"r\") as f:\n",
" for line in f.readlines():\n", " for line in f.readlines():\n",
@ -52,7 +53,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 89, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -93,7 +94,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 90, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -102,7 +103,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 91, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -111,7 +112,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 112, "execution_count": 51,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -123,16 +124,18 @@
" word = word.lower()\n", " word = word.lower()\n",
" word = re.sub('\\W+','', word)\n", " word = re.sub('\\W+','', word)\n",
" word_probs = dict(filter(lambda elem: elem[0][0] == word, probs.items()))\n", " word_probs = dict(filter(lambda elem: elem[0][0] == word, probs.items()))\n",
" word_probs = dict(sorted(word_probs.items(), key=lambda item: item[1], reverse=True))\n",
" rest = 1.0 - sum(word_probs.values())\n", " rest = 1.0 - sum(word_probs.values())\n",
" word_probs = list(map(lambda elem: elem[0][0] + \":\" + str(elem[1]), list(word_probs.items())))\n", " word_probs = list(map(lambda elem: elem[0][1] + \":\" + '{:.7f}'.format(elem[1]), list(word_probs.items())))\n",
" word_probs.append(':'+str(rest))\n", " word_probs.append(':'+ '{:.7f}'.format(rest))\n",
" word_probs.append('\\n')\n",
" word_probs = ' '.join(word_probs)\n", " word_probs = ' '.join(word_probs)\n",
" f.write(word_probs)" " f.write(word_probs)"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 113, "execution_count": 52,
"metadata": { "metadata": {
"tags": [] "tags": []
}, },
@ -140,6 +143,13 @@
"source": [ "source": [
"save_results(probs, dev_data)" "save_results(probs, dev_data)"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
} }
] ]
} }