-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Grigory Zhigalov
committed
Feb 21, 2019
1 parent
dcf5aa3
commit 7608c2c
Showing
9 changed files
with
923 additions
and
373 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -9,7 +9,7 @@ data/ | |
| *.gexf | ||
| *.html | ||
| *.csv | ||
| tensorboard/ | ||
| cc_env/ | ||
| runs/ | ||
| models/ | ||
| tmp/ | ||
| tmp_*/ | ||
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,120 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import pandas as pd\n", | ||
| "from bert_serving.client import BertClient" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 1, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "bc = BertClient(ip='localhost', check_length=False)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 3, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "oc = pd.read_csv('tmp/opencorpora.csv.gz', compression='gzip')\n", | ||
| "criminal_code = pd.read_csv('tmp/vectors/criminal_code.csv.gz', compression='gzip')\n", | ||
| "criminal_court_orders = pd.read_csv('tmp/vectors/criminal_court_orders.csv.gz', compression='gzip')\n", | ||
| "civil_code = pd.read_csv('tmp/vectors/civil_code.csv.gz', compression='gzip')\n", | ||
| "civil_court_orders = pd.read_csv('tmp/vectors/civil_court_orders.csv.gz', compression='gzip')\n", | ||
| "\n", | ||
| "oc['source'] = 'opencorpora'\n", | ||
| "criminal_code['source'] = 'criminal_code'\n", | ||
| "criminal_court_orders['source'] = 'criminal_court_orders'\n", | ||
| "civil_code['source'] = 'civil_code'\n", | ||
| "civil_court_orders['source'] = 'civil_court_orders'\n", | ||
| "\n", | ||
| "criminal_code['name'] = criminal_code.apply(lambda x: \"Ст.{} {}\".format(x['article_number'], x['article_name']), axis=1)\n", | ||
| "civil_code['name'] = civil_code.apply(lambda x: \"Ст.{} {}\".format(x['article_number'], x['article_name']), axis=1)\n", | ||
| "\n", | ||
| "civil_court_orders['name'] = [\"Гражд. дело {}\".format(i) for i in range(civil_court_orders.shape[0])]" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 4, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "tmp = pd.concat([\n", | ||
| " oc.reset_index()[['index', 'title', 'text', 'source']].rename(columns={'title':'name'}), \n", | ||
| " criminal_code.reset_index()[['index', 'name', 'article', 'source']].rename(columns={\"article\": \"text\"}),\n", | ||
| " criminal_court_orders.reset_index()[['index', 'title', 'case', 'source']].rename(columns={'title':'name', \"case\":\"text\"}),\n", | ||
| " civil_code.reset_index()[['index', 'name', 'article', 'source']].rename(columns={\"article\": \"text\"}),\n", | ||
| " civil_court_orders.reset_index()[['index', 'name', 'text', 'source']],\n", | ||
| "]).reset_index(drop=True)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 13, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "CPU times: user 4.13 s, sys: 3.28 s, total: 7.41 s\n", | ||
| "Wall time: 21min 29s\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "%%time\n", | ||
| "bert_vec = bc.encode(tmp['text'].tolist())" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 22, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "tmp['vectors'] = bert_vec.tolist()" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 27, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "tmp.to_csv(\"tmp/vectors/bert_all.csv.gz\", compression='gzip', index=False)" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "display_name": "Python 3.6 (testing)", | ||
| "language": "python", | ||
| "name": "testing" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 3 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython3", | ||
| "version": "3.6.7" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |
Oops, something went wrong.