arthur/ArtStudies
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/ArtStudies.git synced 2026-01-14 13:54:06 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add Jupyter notebook for supervised machine learning algorithms and update dependencies

Browse Source 
- Created a new Jupyter notebook: 2025_M2_ISF_TP_4.ipynb for supervised machine learning exercises, including data preparation, model building, and performance analysis.
- Added 'imblearn' as a dependency in pyproject.toml to support handling imbalanced datasets.
- Updated uv.lock to include the 'imbalanced-learn' package and its dependencies.
This commit is contained in:
Arthur Danjou
2025-10-20 17:43:11 +02:00
parent e1255f326d
commit cf7d23261b
6 changed files with 14956 additions and 448 deletions
Download Patch File Download Diff File Expand all files Collapse all files

544
M2/Machine Learning/TP_1/2025_TP_1_M2_ISF.ipynb
View File

File diff suppressed because it is too large Load Diff

172
M2/Machine Learning/TP_3/2025_TP_3_M2_ISF.ipynb
View File

@@ -46,7 +46,7 @@
},
{
"cell_type": "code",
"execution_count": 56,
"execution_count": 1,
"id": "97d58527",
"metadata": {},
"outputs": [],
@@ -100,7 +100,7 @@
},
{
"cell_type": "code",
"execution_count": 57,
"execution_count": 2,
"id": "c9597b48",
"metadata": {},
"outputs": [],
@@ -119,7 +119,7 @@
},
{
"cell_type": "code",
"execution_count": 58,
"execution_count": 3,
"id": "8051b5f4",
"metadata": {},
"outputs": [],
@@ -163,7 +163,7 @@
},
{
"cell_type": "code",
"execution_count": 59,
"execution_count": 4,
"id": "c427a4b8",
"metadata": {},
"outputs": [
@@ -173,7 +173,7 @@
"(824, 14)"
]
},
"execution_count": 59,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -200,7 +200,7 @@
},
{
"cell_type": "code",
"execution_count": 60,
"execution_count": 5,
"id": "c8fd3ee1",
"metadata": {},
"outputs": [
@@ -284,7 +284,7 @@
"type": "float"
}
],
"ref": "8fcd0abc-8334-4a0d-96b7-b6d7e17b3fb7",
"ref": "e29190e7-d62c-4ab7-ab0a-43dd875c8b98",
"rows": [
[
"count",
@@ -760,7 +760,7 @@
"max NaN 83421.850000 "
]
},
"execution_count": 60,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -795,7 +795,7 @@
},
{
"cell_type": "code",
"execution_count": 61,
"execution_count": 6,
"id": "1b156435",
"metadata": {},
"outputs": [
@@ -805,7 +805,7 @@
"(824, 13)"
]
},
"execution_count": 61,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
@@ -817,7 +817,7 @@
},
{
"cell_type": "code",
"execution_count": 62,
"execution_count": 7,
"id": "0ef0fcc0",
"metadata": {},
"outputs": [],
@@ -853,7 +853,7 @@
},
{
"cell_type": "code",
"execution_count": 63,
"execution_count": 8,
"id": "e130aae5",
"metadata": {},
"outputs": [],
@@ -863,7 +863,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"id": "c39e2ad0",
"metadata": {},
"outputs": [
@@ -1811,7 +1811,7 @@
},
{
"cell_type": "code",
"execution_count": 65,
"execution_count": 10,
"id": "a16215ab",
"metadata": {},
"outputs": [],
@@ -1821,7 +1821,7 @@
},
{
"cell_type": "code",
"execution_count": 66,
"execution_count": 11,
"id": "532ca6c4",
"metadata": {},
"outputs": [
@@ -2764,7 +2764,7 @@
},
{
"cell_type": "code",
"execution_count": 67,
"execution_count": 12,
"id": "b8530717",
"metadata": {},
"outputs": [],
@@ -2785,7 +2785,7 @@
},
{
"cell_type": "code",
"execution_count": 68,
"execution_count": 13,
"id": "4ff3847d",
"metadata": {},
"outputs": [],
@@ -2814,7 +2814,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 14,
"id": "6a1c7907",
"metadata": {},
"outputs": [],
@@ -2845,14 +2845,14 @@
},
{
"cell_type": "code",
"execution_count": 70,
"execution_count": 15,
"id": "053e013c",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>#sk-container-id-3 {\n",
"<style>#sk-container-id-1 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: #000;\n",
" --sklearn-color-text-muted: #666;\n",
@@ -2883,15 +2883,15 @@
" }\n",
"}\n",
"\n",
"#sk-container-id-3 {\n",
"#sk-container-id-1 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"#sk-container-id-3 pre {\n",
"#sk-container-id-1 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
"#sk-container-id-3 input.sk-hidden--visually {\n",
"#sk-container-id-1 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
@@ -2903,7 +2903,7 @@
" width: 1px;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-dashed-wrapped {\n",
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
" border: 1px dashed var(--sklearn-color-line);\n",
" margin: 0 0.4em 0.5em 0.4em;\n",
" box-sizing: border-box;\n",
@@ -2911,7 +2911,7 @@
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-container {\n",
"#sk-container-id-1 div.sk-container {\n",
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
" so we also need the `!important` here to be able to override the\n",
@@ -2921,7 +2921,7 @@
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-text-repr-fallback {\n",
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
@@ -2937,14 +2937,14 @@
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
"#sk-container-id-3 div.sk-parallel-item::after {\n",
"#sk-container-id-1 div.sk-parallel-item::after {\n",
" content: \"\";\n",
" width: 100%;\n",
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
" flex-grow: 1;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-parallel {\n",
"#sk-container-id-1 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
@@ -2952,28 +2952,28 @@
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-parallel-item {\n",
"#sk-container-id-1 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
"#sk-container-id-3 div.sk-serial {\n",
"#sk-container-id-1 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
@@ -2991,14 +2991,14 @@
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
"#sk-container-id-3 div.sk-toggleable {\n",
"#sk-container-id-1 div.sk-toggleable {\n",
" /* Default theme specific background. It is overwritten whether we have a\n",
" specific estimator or a Pipeline/ColumnTransformer */\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"/* Toggleable label */\n",
"#sk-container-id-3 label.sk-toggleable__label {\n",
"#sk-container-id-1 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: flex;\n",
" width: 100%;\n",
@@ -3011,13 +3011,13 @@
" gap: 0.5em;\n",
"}\n",
"\n",
"#sk-container-id-3 label.sk-toggleable__label .caption {\n",
"#sk-container-id-1 label.sk-toggleable__label .caption {\n",
" font-size: 0.6rem;\n",
" font-weight: lighter;\n",
" color: var(--sklearn-color-text-muted);\n",
"}\n",
"\n",
"#sk-container-id-3 label.sk-toggleable__label-arrow:before {\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
@@ -3025,13 +3025,13 @@
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
"#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
"#sk-container-id-3 div.sk-toggleable__content {\n",
"#sk-container-id-1 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
@@ -3040,12 +3040,12 @@
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-toggleable__content pre {\n",
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
@@ -3053,79 +3053,79 @@
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-toggleable__content.fitted pre {\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
" /* Expand drop-down */\n",
" max-height: 200px;\n",
" max-width: 100%;\n",
" overflow: auto;\n",
"}\n",
"\n",
"#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
" content: \"▾\";\n",
"}\n",
"\n",
"/* Pipeline/ColumnTransformer-specific style */\n",
"\n",
"#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator-specific style */\n",
"\n",
"/* Colorize estimator box */\n",
"#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-3 div.sk-label label {\n",
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-1 div.sk-label label {\n",
" /* The background is the default theme color */\n",
" color: var(--sklearn-color-text-on-default-background);\n",
"}\n",
"\n",
"/* On hover, darken the color of the background */\n",
"#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {\n",
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"/* Label box, darken color on hover, fitted */\n",
"#sk-container-id-3 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator label */\n",
"\n",
"#sk-container-id-3 div.sk-label label {\n",
"#sk-container-id-1 div.sk-label label {\n",
" font-family: monospace;\n",
" font-weight: bold;\n",
" display: inline-block;\n",
" line-height: 1.2em;\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-label-container {\n",
"#sk-container-id-1 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
"#sk-container-id-3 div.sk-estimator {\n",
"#sk-container-id-1 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
@@ -3135,18 +3135,18 @@
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-estimator.fitted {\n",
"#sk-container-id-1 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
"#sk-container-id-3 div.sk-estimator:hover {\n",
"#sk-container-id-1 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-3 div.sk-estimator.fitted:hover {\n",
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
@@ -3234,7 +3234,7 @@
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
"#sk-container-id-3 a.estimator_doc_link {\n",
"#sk-container-id-1 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
@@ -3249,31 +3249,31 @@
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
"#sk-container-id-3 a.estimator_doc_link.fitted {\n",
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"#sk-container-id-3 a.estimator_doc_link:hover {\n",
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"#sk-container-id-3 a.estimator_doc_link.fitted:hover {\n",
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeRegressor()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>DecisionTreeRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.tree.DecisionTreeRegressor.html\">?<span>Documentation for DecisionTreeRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeRegressor()</pre></div> </div></div></div></div>"
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeRegressor()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>DecisionTreeRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.tree.DecisionTreeRegressor.html\">?<span>Documentation for DecisionTreeRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeRegressor()</pre></div> </div></div></div></div>"
],
"text/plain": [
"DecisionTreeRegressor()"
]
},
"execution_count": 70,
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
@@ -3293,7 +3293,7 @@
},
{
"cell_type": "code",
"execution_count": 71,
"execution_count": 16,
"id": "c4ca2cf9",
"metadata": {},
"outputs": [
@@ -3322,7 +3322,7 @@
},
{
"cell_type": "code",
"execution_count": 72,
"execution_count": 17,
"id": "4b739d5b",
"metadata": {},
"outputs": [
@@ -3330,9 +3330,9 @@
"name": "stdout",
"output_type": "stream",
"text": [
"MAE: 5124.14\n",
"MSE: 84535204.52\n",
"RMSE: 9194.30\n"
"MAE: 5969.32\n",
"MSE: 161922043.77\n",
"RMSE: 12724.86\n"
]
}
],
@@ -3408,7 +3408,7 @@
},
{
"cell_type": "code",
"execution_count": 73,
"execution_count": 18,
"id": "ab1e1367",
"metadata": {},
"outputs": [],
@@ -3439,7 +3439,7 @@
},
{
"cell_type": "code",
"execution_count": 74,
"execution_count": 19,
"id": "b515460e",
"metadata": {},
"outputs": [],
@@ -3462,7 +3462,7 @@
},
{
"cell_type": "code",
"execution_count": 75,
"execution_count": 20,
"id": "eebb394f",
"metadata": {},
"outputs": [
@@ -3496,7 +3496,7 @@
},
{
"cell_type": "code",
"execution_count": 76,
"execution_count": 21,
"id": "b067126c",
"metadata": {},
"outputs": [
@@ -3522,7 +3522,7 @@
},
{
"cell_type": "code",
"execution_count": 77,
"execution_count": 22,
"id": "6597152c",
"metadata": {},
"outputs": [
@@ -3546,7 +3546,7 @@
},
{
"cell_type": "code",
"execution_count": 78,
"execution_count": 23,
"id": "63ff1c9d",
"metadata": {},
"outputs": [
@@ -3594,7 +3594,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 24,
"id": "d9342ad6",
"metadata": {},
"outputs": [],
@@ -3625,12 +3625,11 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 36,
"id": "6d58dbc2",
"metadata": {},
"outputs": [],
"source": [
"#Initialisation\n",
"# Nombre de sous-échantillons pour la cross-validation\n",
"num_splits = 5\n",
"\n",
@@ -3643,9 +3642,9 @@
"RMSE_scores = []\n",
"\n",
"# Hyperparamètres à tester\n",
"n_estimators_values = []\n",
"max_depth_values = []\n",
"min_samples_split_values = []\n",
"n_estimators_values = [50, 100, 200, 300]\n",
"max_depth_values = [2, 5, 10]\n",
"min_samples_split_values = [2, 5, 10]\n",
"\n",
"# Liste pour sauveagrder les meilleurs résultats\n",
"best_score = np.inf\n",
@@ -3658,12 +3657,11 @@
},
{
"cell_type": "code",
"execution_count": 87,
"execution_count": 37,
"id": "47da5172",
"metadata": {},
"outputs": [],
"source": [
"#Complétez ici avec votre code\n",
"for n_estimators in n_estimators_values:\n",
" for max_depth in max_depth_values:\n",
" for min_samples_split in min_samples_split_values:\n",
@@ -3710,7 +3708,7 @@
},
{
"cell_type": "code",
"execution_count": 88,
"execution_count": 33,
"id": "d4936c46",
"metadata": {},
"outputs": [
@@ -3731,7 +3729,7 @@
},
{
"cell_type": "code",
"execution_count": 82,
"execution_count": 34,
"id": "3215c463",
"metadata": {},
"outputs": [],
@@ -3745,7 +3743,7 @@
},
{
"cell_type": "code",
"execution_count": 83,
"execution_count": 29,
"id": "bb9a5c9b",
"metadata": {},
"outputs": [],
@@ -3757,7 +3755,7 @@
},
{
"cell_type": "code",
"execution_count": 84,
"execution_count": 30,
"id": "0f0768ad",
"metadata": {},
"outputs": [],

14237
M2/Machine Learning/TP_4/1_inputs/base_retraitee.csv Normal file
View File

File diff suppressed because it is too large Load Diff

420
M2/Machine Learning/TP_4/2025_M2_ISF_TP_4.ipynb Normal file
View File

@@ -0,0 +1,420 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "8750d15b",
"metadata": {},
"source": [
"# Cours 4 : Machine Learning - Algorithmes supervisés (2/2)"
]
},
{
"cell_type": "markdown",
"id": "f7c08ae5",
"metadata": {},
"source": [
"## Préambule"
]
},
{
"cell_type": "markdown",
"id": "ec7ecb4b",
"metadata": {},
"source": [
"Les objectifs de cette séance (3h) sont :\n",
"* Préparation des bases de modélisation (sampling)\n",
"* Construire un modèle de Machine Learning (cross-validation et hyperparamétrage) pour résoudre un problème de classification\n",
"* Analyser les performances du modèle"
]
},
{
"cell_type": "markdown",
"id": "4e99c600",
"metadata": {},
"source": [
"## Préparation du workspace"
]
},
{
"cell_type": "markdown",
"id": "c1b01045",
"metadata": {},
"source": [
"### Import de librairies "
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "97d58527",
"metadata": {},
"outputs": [],
"source": [
"# Données\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"# Graphiques \n",
"import seaborn as sns\n",
"sns.set()\n",
"import plotly.express as px\n",
"import plotly.graph_objects as gp\n",
"\n",
"# Machine Learning\n",
"import sklearn.preprocessing as preproc\n",
"from imblearn.over_sampling import RandomOverSampler\n",
"\n",
"# Statistiques\n",
"from scipy.stats import chi2_contingency\n",
"from sklearn import metrics\n",
"from sklearn.ensemble import GradientBoostingClassifier\n",
"from sklearn.model_selection import (\n",
" GridSearchCV,\n",
" KFold,\n",
" StratifiedKFold,\n",
" cross_val_score,\n",
" train_test_split,\n",
")\n"
]
},
{
"cell_type": "markdown",
"id": "06153286",
"metadata": {},
"source": [
"### Définition des fonctions "
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c67db932",
"metadata": {},
"outputs": [],
"source": [
"def cramers_V(var1,var2) :\n",
" crosstab =np.array(pd.crosstab(var1,var2, rownames=None, colnames=None)) # Cross table building\n",
" stat = chi2_contingency(crosstab)[0] # Keeping of the test statistic of the Chi2 test\n",
" obs = np.sum(crosstab) # Number of observations\n",
" mini = min(crosstab.shape)-1 # Take the minimum value between the columns and the rows of the cross table\n",
" return (stat/(obs*mini))"
]
},
{
"cell_type": "markdown",
"id": "985e4e97",
"metadata": {},
"source": [
"### Constantes"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "c9597b48",
"metadata": {},
"outputs": [],
"source": [
"input_path = \"./1_inputs\"\n",
"output_path = \"./2_outputs\""
]
},
{
"cell_type": "markdown",
"id": "b2b035d2",
"metadata": {},
"source": [
"### Import des données"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "8051b5f4",
"metadata": {},
"outputs": [
{
"ename": "FileNotFoundError",
"evalue": "[Errno 2] No such file or directory: './1_inputs/base_retraitee.csv'",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mFileNotFoundError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[9]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m 1\u001b[39m path =input_path + \u001b[33m'\u001b[39m\u001b[33m/base_retraitee.csv\u001b[39m\u001b[33m'\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m data_retraitee = \u001b[43mpd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43msep\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m,\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43mdecimal\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m.\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Workspace/studies/.venv/lib/python3.13/site-packages/pandas/io/parsers/readers.py:1026\u001b[39m, in \u001b[36mread_csv\u001b[39m\u001b[34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[39m\n\u001b[32m 1013\u001b[39m kwds_defaults = _refine_defaults_read(\n\u001b[32m 1014\u001b[39m dialect,\n\u001b[32m 1015\u001b[39m delimiter,\n\u001b[32m (...)\u001b[39m\u001b[32m 1022\u001b[39m dtype_backend=dtype_backend,\n\u001b[32m 1023\u001b[39m )\n\u001b[32m 1024\u001b[39m kwds.update(kwds_defaults)\n\u001b[32m-> \u001b[39m\u001b[32m1026\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Workspace/studies/.venv/lib/python3.13/site-packages/pandas/io/parsers/readers.py:620\u001b[39m, in \u001b[36m_read\u001b[39m\u001b[34m(filepath_or_buffer, kwds)\u001b[39m\n\u001b[32m 617\u001b[39m _validate_names(kwds.get(\u001b[33m\"\u001b[39m\u001b[33mnames\u001b[39m\u001b[33m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[32m 619\u001b[39m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m620\u001b[39m parser = \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 622\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[32m 623\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Workspace/studies/.venv/lib/python3.13/site-packages/pandas/io/parsers/readers.py:1620\u001b[39m, in \u001b[36mTextFileReader.__init__\u001b[39m\u001b[34m(self, f, engine, **kwds)\u001b[39m\n\u001b[32m 1617\u001b[39m \u001b[38;5;28mself\u001b[39m.options[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m] = kwds[\u001b[33m\"\u001b[39m\u001b[33mhas_index_names\u001b[39m\u001b[33m\"\u001b[39m]\n\u001b[32m 1619\u001b[39m \u001b[38;5;28mself\u001b[39m.handles: IOHandles | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1620\u001b[39m \u001b[38;5;28mself\u001b[39m._engine = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Workspace/studies/.venv/lib/python3.13/site-packages/pandas/io/parsers/readers.py:1880\u001b[39m, in \u001b[36mTextFileReader._make_engine\u001b[39m\u001b[34m(self, f, engine)\u001b[39m\n\u001b[32m 1878\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[32m 1879\u001b[39m mode += \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m-> \u001b[39m\u001b[32m1880\u001b[39m \u001b[38;5;28mself\u001b[39m.handles = \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1881\u001b[39m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1882\u001b[39m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1883\u001b[39m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1884\u001b[39m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mcompression\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1885\u001b[39m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmemory_map\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1886\u001b[39m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m=\u001b[49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1887\u001b[39m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mencoding_errors\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstrict\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1888\u001b[39m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43moptions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstorage_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1889\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1890\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m.handles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 1891\u001b[39m f = \u001b[38;5;28mself\u001b[39m.handles.handle\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Workspace/studies/.venv/lib/python3.13/site-packages/pandas/io/common.py:873\u001b[39m, in \u001b[36mget_handle\u001b[39m\u001b[34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[39m\n\u001b[32m 868\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[32m 869\u001b[39m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[32m 870\u001b[39m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[32m 871\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m ioargs.encoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mb\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs.mode:\n\u001b[32m 872\u001b[39m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m873\u001b[39m handle = \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[32m 874\u001b[39m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 875\u001b[39m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 876\u001b[39m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m=\u001b[49m\u001b[43mioargs\u001b[49m\u001b[43m.\u001b[49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 877\u001b[39m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[43m=\u001b[49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 878\u001b[39m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 879\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 880\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 881\u001b[39m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[32m 882\u001b[39m handle = \u001b[38;5;28mopen\u001b[39m(handle, ioargs.mode)\n",
"\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: './1_inputs/base_retraitee.csv'"
]
}
],
"source": [
"path =input_path + '/base_retraitee.csv'\n",
"data_retraitee = pd.read_csv(path,sep=\",\",decimal=\".\")"
]
},
{
"cell_type": "markdown",
"id": "a2578ba1",
"metadata": {},
"source": [
"## Préparation de la base de données"
]
},
{
"cell_type": "markdown",
"id": "b3715c37",
"metadata": {},
"source": [
"Dans cette partie nous souhaitons expliquer la survenance d'un sinistre en fonction des variables explicatives i.e. une variable binaire qui : \n",
"* est égale à 1 si la personne a eu 1 ou plus de sinistres.\n",
"* est égale à 0 le cas échéant."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b9b98d36",
"metadata": {},
"outputs": [],
"source": [
"#Calculez la variable \"sinistré\" qui est vraie si la personne a eu un ou plusieurs sinistres ou faux le cas échéant \n"
]
},
{
"cell_type": "markdown",
"id": "657ebd89",
"metadata": {},
"source": [
"**Exercice :** construisez les statistiques descriptives de la base utilisée. Notamment la distribution de la variable réponse."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "47cf4b69",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "92d6156a",
"metadata": {},
"source": [
"#### Etude des corrélations parmi les variables explicatives"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a0bc6278",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "e82fcade",
"metadata": {},
"source": [
"##### Corrélation des variables catégorielles :"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "30df8bd5",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "8f615121",
"metadata": {},
"source": [
"##### Corrélation des variables numériques :"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d1fa12fc",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "5777d20f",
"metadata": {},
"source": [
"**Question :** quels sont vos commentaires ?"
]
},
{
"cell_type": "markdown",
"id": "212209ec",
"metadata": {},
"source": [
"#### Preprocessing"
]
},
{
"cell_type": "markdown",
"id": "65aca700",
"metadata": {},
"source": [
"Deux étapes sont nécessaires avant de lancer l'apprentissage d'un modèle, c'est ce qu'on connait comme le *Preprocessing* :\n",
"\n",
"* Les modèles proposés par la librairie \"sklearn\" ne gèrent que des variables numériques. Il est donc nécessaire de transformer les variables catégorielles en variables numériques : ce processus s'appelle le *One Hot Encoding*.\n",
"* Normaliser les données numériques"
]
},
{
"cell_type": "markdown",
"id": "6c23d236",
"metadata": {},
"source": [
"**Exercice :** proposez un bout de code permettant de réaliser le One Hot Encoding des variables catégorielles. Vous pourrez utiliser la fonction \"preproc.OneHotEncoder\" de la librairie sklearn"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b8530717",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "2be6a3e4",
"metadata": {},
"source": [
"**Exercice :** proposez un bout de code permettant noramliser les variables numériques présentes dans la base. Vous pourrez utiliser la fonction \"preproc.StandardScaler\" de la librairie sklearn"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4ff3847d",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "7ecba832",
"metadata": {},
"source": [
"## Algorithme supervisé : Gradient Boosting"
]
},
{
"cell_type": "markdown",
"id": "efcb8987",
"metadata": {},
"source": [
"A ce stade, nous avons vu les différentes étapes pour lancer un algorithme de Machine Learning. Néanmoins, ces étapes ne sont pas suffisantes pour construire un modèle performant. \n",
"En effet, afin de construire un modèle performant le Data Scientist doit agir sur l'apprentissage du modèle. Dans ce qui suit nous :\n",
"* Changerons d'algorithme pour utiliser un algorithme plus performant (Gradient Boosting)\n",
"* Raliserons un *grid search* sur les paramètres du modèle\n",
"* Appliquerons l'apprentissage par validation croisée\n"
]
},
{
"cell_type": "markdown",
"id": "3feaff44",
"metadata": {},
"source": [
"**Exercice :** Implémentez l'algorithme du Gradient Boosting en appliquant les techniques vues lors des derniers cours (sampling, Grid search et Cross Validation) \n",
"**Remarques :**\n",
"* Vous pouvez utiliser les modèles \"GradientBoostingClassifier\" et \"GridSearchCV\" de la libraire Sklearn. \n",
"* Pensez à utiliser les métriques relatives aux problèmes de classification."
]
},
{
"cell_type": "markdown",
"id": "5a6adbfe",
"metadata": {},
"source": [
"#### Sampling"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d9342ad6",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "76ece01f",
"metadata": {},
"source": [
"#### Fitting avec Cross-Validation et *Grid Search*"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cb60fe19",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "3a723cbc",
"metadata": {},
"source": [
"#### Validation du modèle - métriques"
]
},
{
"cell_type": "markdown",
"id": "60c0312d",
"metadata": {},
"source": [
"**Exercice :** \n",
"* Construisez la matrice de confusion (metrics.confusion_matrix).\n",
"* Calculez les métriques : accuracy, recall & precision."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5d9ef448",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "studies",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

1
pyproject.toml
View File

@@ -5,6 +5,7 @@ description = "A curated collection of mathematics and data science projects dev
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
"imblearn>=0.0",
"ipykernel>=6.29.5",
"keras>=3.11.3",
"matplotlib>=3.10.1",

30
uv.lock generated
View File

@@ -416,6 +416,34 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442, upload-time = "2024-09-15T18:07:37.964Z" },
]
[[package]]
name = "imbalanced-learn"
version = "0.14.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "joblib" },
{ name = "numpy" },
{ name = "scikit-learn" },
{ name = "scipy" },
{ name = "threadpoolctl" },
]
sdist = { url = "https://files.pythonhosted.org/packages/7b/5a/ad42e366914abfea7434b9ab7a821778be52dae4a8cbeac165918e66e7b0/imbalanced_learn-0.14.0.tar.gz", hash = "sha256:22b9ba6dbd681a9ec613cd6e08c21d39639fb5ccbf2a3c991f9c36415b70522c", size = 534790, upload-time = "2025-08-14T14:15:31.923Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/65/60/103dc71019ec2fa987f42f9dbe88641a74edc57f8499fac8896955b66065/imbalanced_learn-0.14.0-py3-none-any.whl", hash = "sha256:8a8700c02ca185e113064815513f990fbf84eb4e7701f1d4e944ce67fb259a60", size = 239958, upload-time = "2025-08-14T14:15:30.174Z" },
]
[[package]]
name = "imblearn"
version = "0.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "imbalanced-learn" },
]
sdist = { url = "https://files.pythonhosted.org/packages/32/0a/f83099534a77757abf27427d339590c83cc68c3386690d4741d6454e185f/imblearn-0.0.tar.gz", hash = "sha256:d8fbb662919c1b16f438ad91a8256220e53bcf6815c9ad5502c518b798de34f2", size = 945, upload-time = "2017-01-19T11:52:35.89Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/81/a7/4179e6ebfd654bd0eac0b9c06125b8b4c96a9d0a8ff9e9507eb2a26d2d7e/imblearn-0.0-py2.py3-none-any.whl", hash = "sha256:d42c2d709d22c00d2b9a91e638d57240a8b79b4014122d92181fcd2549a2f79a", size = 1874, upload-time = "2017-01-19T11:52:37.416Z" },
]
[[package]]
name = "ipykernel"
version = "6.29.5"
@@ -1518,6 +1546,7 @@ name = "studies"
version = "0.1.0"
source = { virtual = "." }
dependencies = [
{ name = "imblearn" },
{ name = "ipykernel" },
{ name = "keras" },
{ name = "matplotlib" },
@@ -1542,6 +1571,7 @@ dev = [
[package.metadata]
requires-dist = [
{ name = "imblearn", specifier = ">=0.0" },
{ name = "ipykernel", specifier = ">=6.29.5" },
{ name = "keras", specifier = ">=3.11.3" },
{ name = "matplotlib", specifier = ">=3.10.1" },