|
a |
|
b/notebooks/split_data.ipynb |
|
|
1 |
{ |
|
|
2 |
"cells": [ |
|
|
3 |
{ |
|
|
4 |
"cell_type": "code", |
|
|
5 |
"execution_count": 2, |
|
|
6 |
"metadata": {}, |
|
|
7 |
"outputs": [], |
|
|
8 |
"source": [ |
|
|
9 |
"import pandas as pd\n", |
|
|
10 |
"import warnings\n", |
|
|
11 |
"warnings.filterwarnings('ignore')\n", |
|
|
12 |
"from sklearn.model_selection import train_test_split" |
|
|
13 |
] |
|
|
14 |
}, |
|
|
15 |
{ |
|
|
16 |
"cell_type": "code", |
|
|
17 |
"execution_count": 3, |
|
|
18 |
"metadata": {}, |
|
|
19 |
"outputs": [], |
|
|
20 |
"source": [ |
|
|
21 |
"df = pd.read_csv(\"D:/Studia/Semestr 4/WB/project/data/data.csv\")\n", |
|
|
22 |
"learning_data, validation_data = train_test_split(df, test_size=0.3, random_state=42)\n", |
|
|
23 |
"\n", |
|
|
24 |
"learning_data.to_csv(\"D:/Studia/Semestr 4/WB/project/data/learning_data.csv\", index=False)\n", |
|
|
25 |
"validation_data.to_csv(\"D:/Studia/Semestr 4/WB/project/validation_data/validation_data.csv\", index=False)" |
|
|
26 |
] |
|
|
27 |
} |
|
|
28 |
], |
|
|
29 |
"metadata": { |
|
|
30 |
"kernelspec": { |
|
|
31 |
"display_name": "DataFrames", |
|
|
32 |
"language": "python", |
|
|
33 |
"name": "python3" |
|
|
34 |
}, |
|
|
35 |
"language_info": { |
|
|
36 |
"codemirror_mode": { |
|
|
37 |
"name": "ipython", |
|
|
38 |
"version": 3 |
|
|
39 |
}, |
|
|
40 |
"file_extension": ".py", |
|
|
41 |
"mimetype": "text/x-python", |
|
|
42 |
"name": "python", |
|
|
43 |
"nbconvert_exporter": "python", |
|
|
44 |
"pygments_lexer": "ipython3", |
|
|
45 |
"version": "3.12.2" |
|
|
46 |
} |
|
|
47 |
}, |
|
|
48 |
"nbformat": 4, |
|
|
49 |
"nbformat_minor": 2 |
|
|
50 |
} |