{
"cells": [
{
"cell_type": "markdown",
"id": "ace1c12f",
"metadata": {},
"source": [
"## Détection des fraud dans l'assurance automobile"
]
},
{
"cell_type": "markdown",
"id": "7677a074",
"metadata": {},
"source": [
"### Importation des libreries"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "1a97c97c-1498-4995-abb8-4abf54037428",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"from pathlib import Path\n",
"\n",
"import torch\n",
"import torch.nn.functional as F\n",
"from torch.utils.data import Dataset, DataLoader, random_split\n",
"import torchvision\n",
"from torchvision import transforms\n",
"\n",
"import lightning as L\n",
"from lightning.pytorch.loggers import CSVLogger\n",
"from torchmetrics.classification import BinaryAccuracy\n",
"\n",
"import numpy as np\n",
"from PIL import Image\n",
"\n",
"import tensorflow as tf\n",
"from pt2keras import Pt2Keras\n",
"from pt2keras import converter"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "77d1f1a0-080a-4dd8-a3c9-09de7969415a",
"metadata": {},
"outputs": [],
"source": [
"TRAIN_PATH = Path('C:/Users/hp/Documents/MASTER/Master2/data_viz/fraud_auto/dataset/train/train')\n",
"TEST_PATH = Path('C:/Users/hp/Documents/MASTER/Master2/data_viz/fraud_auto/dataset/test/test')\n",
"\n",
"df_train = pd.read_csv(TRAIN_PATH/'train.csv')\n",
"df_test = pd.read_csv(TEST_PATH/'test.csv')\n",
"df_submission = pd.read_csv('/Users/hp/Documents/MASTER/Master2/data_viz/fraud_auto/dataset/sample_submission.csv')"
]
},
{
"cell_type": "markdown",
"id": "af9aa1dc",
"metadata": {},
"source": [
"## Exploration des données"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "c8ace465-dd68-40a3-9b38-2c1580611c98",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((8079, 3), (3462, 2))"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train.shape, df_test.shape"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "c7cceb85-d827-4aa3-b759-5016d84ad1c4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['image_id', 'filename', 'label'], dtype='object')"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train.columns"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "bf9475df-6dc6-4f34-b99f-249e238ba1b6",
"metadata": {},
"outputs": [],
"source": [
"df_train, df_val = train_test_split(df_train, test_size=0.2, random_state=123, stratify=df_train['label'])"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "ef803c7c-6a30-4986-a24f-60f71b631507",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((6463, 3), (1616, 3), (3462, 2))"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train.shape, df_val.shape, df_test.shape"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "c933e717-918e-47d0-8b05-1098fa8fe520",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" image_id | \n",
" filename | \n",
" label | \n",
"
\n",
" \n",
" \n",
" \n",
" | 723 | \n",
" 724 | \n",
" 724.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 3038 | \n",
" 3039 | \n",
" 3039.jpg | \n",
" 0 | \n",
"
\n",
" \n",
" | 5226 | \n",
" 5227 | \n",
" 5227.jpg | \n",
" 1 | \n",
"
\n",
" \n",
" | 3609 | \n",
" 3610 | \n",
" 3610.jpg | \n",
" 1 | \n",
"
\n",
" \n",
" | 4341 | \n",
" 4342 | \n",
" 4342.jpg | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" image_id | \n",
" filename | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 8080 | \n",
" 8080.jpg | \n",
"
\n",
" \n",
" | 1 | \n",
" 8081 | \n",
" 8081.jpg | \n",
"
\n",
" \n",
" | 2 | \n",
" 8082 | \n",
" 8082.jpg | \n",
"
\n",
" \n",
" | 3 | \n",
" 8083 | \n",
" 8083.jpg | \n",
"
\n",
" \n",
" | 4 | \n",
" 8084 | \n",
" 8084.jpg | \n",
"
\n",
" \n",
"
\n",
"