Skip to content

Fix "data-preparation-and-post-processing.ipynb" #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 1, 2019
Merged

Fix "data-preparation-and-post-processing.ipynb" #6

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
79 changes: 40 additions & 39 deletions word-tokenization/data-preparation-and-post-processing.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,13 @@
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2019-09-12T08:19:35.741983Z",
"start_time": "2019-09-12T08:19:35.323151Z"
}
},
"outputs": [],
"source": [
"import pandas as pd\n",
Expand All @@ -19,13 +24,18 @@
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2019-09-12T08:19:43.555275Z",
"start_time": "2019-09-12T08:19:43.440900Z"
}
},
"outputs": [],
"source": [
"data = []\n",
"with open (\"./kaggle-competition/train.txt\", \"r\") as ftxt, \\\n",
" open (\"./kaggle-competition/train_label.txt\", \"r\") as flabel :\n",
"with open (\"../kaggle-competition/train.txt\", \"r\") as ftxt, \\\n",
" open (\"../kaggle-competition/train_label.txt\", \"r\") as flabel :\n",
" for t, l in zip(ftxt, flabel):\n",
" t = t.strip()\n",
" l = l.strip()\n",
Expand All @@ -39,8 +49,13 @@
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"execution_count": 4,
"metadata": {
"ExecuteTime": {
"end_time": "2019-09-12T08:19:49.840676Z",
"start_time": "2019-09-12T08:19:49.826456Z"
}
},
"outputs": [],
"source": [
"def sampling_class(df, cls_name, n=20, seed=71):\n",
Expand All @@ -56,7 +71,12 @@
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"metadata": {
"ExecuteTime": {
"end_time": "2019-09-12T08:19:51.210467Z",
"start_time": "2019-09-12T08:19:51.158301Z"
}
},
"outputs": [],
"source": [
"seeds = dict(zip(['neg', 'neu', 'pos', 'q'], range(4)))\n",
Expand Down Expand Up @@ -91,7 +111,12 @@
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"metadata": {
"ExecuteTime": {
"end_time": "2019-09-12T08:19:52.294514Z",
"start_time": "2019-09-12T08:19:52.270380Z"
}
},
"outputs": [
{
"data": {
Expand All @@ -108,26 +133,6 @@
"set(df_train.label.values)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([0, 4, 3, 2, 1])"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"b"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -220,20 +225,13 @@
" ft.write(\"%s\\n\" % l.replace(\"|\", \"\"))\n",
" fl.write(\"%s\\n\" % l)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv-python3-global",
"display_name": "Python 3",
"language": "python",
"name": "venv-python3-global"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -248,10 +246,13 @@
"version": "3.7.3"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": "block",
Expand Down