agobbi/pid
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
1e882df7584c5c4cb65ea56fbe1827bc8382e4fd
pid/notebooks/old_notebooks/test_binary.ipynb

1191 lines
79 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"cell_type": "code",
"execution_count": 4,
"id": "7c5d059b-ed8a-4e2e-9420-25890f648895",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_42878/2472232159.py:7: UserWarning: pandas only supports SQLAlchemy connectable (engine/connection) or database string URI or sqlite3 DBAPI2 connection. Other DBAPI2 objects are not tested. Please consider using SQLAlchemy.\n",
" df = pd.read_sql('select * from data_safeidx', con=engine)\n"
]
}
],
"source": [
"import pandas as pd\n",
"import psycopg2 as pg\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"from sklearn.model_selection import train_test_split\n",
"engine = pg.connect(\"dbname='safeidx' user='fbk_mpba' host='172.104.247.67' port='5432' password='fbk2024$'\")\n",
"df = pd.read_sql('select * from data_safeidx', con=engine)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "03aa2a04-93fa-469e-a678-685cacdebd6c",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>difficulty</th>\n",
" <th>cause</th>\n",
" <th>town</th>\n",
" <th>province</th>\n",
" <th>gender</th>\n",
" <th>equipment</th>\n",
" <th>helmet</th>\n",
" <th>destination</th>\n",
" <th>diagnosis</th>\n",
" <th>india</th>\n",
" <th>age</th>\n",
" <th>country</th>\n",
" <th>injury_side</th>\n",
" <th>injury_general_location</th>\n",
" <th>evacuation_vehicles</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>novice</td>\n",
" <td>fall_alone</td>\n",
" <td>SIKLOS</td>\n",
" <td></td>\n",
" <td>F</td>\n",
" <td>ski</td>\n",
" <td>None</td>\n",
" <td>hospital_emergency_room</td>\n",
" <td>distortion</td>\n",
" <td>None</td>\n",
" <td>32.0</td>\n",
" <td>Ungheria</td>\n",
" <td>L</td>\n",
" <td>lower_limbs</td>\n",
" <td>[akja]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>advanced</td>\n",
" <td>fall_alone</td>\n",
" <td>MALMO</td>\n",
" <td></td>\n",
" <td>M</td>\n",
" <td>ski</td>\n",
" <td>None</td>\n",
" <td>hospital_emergency_room</td>\n",
" <td>bruise</td>\n",
" <td>None</td>\n",
" <td>32.0</td>\n",
" <td>Svezia</td>\n",
" <td>R</td>\n",
" <td>skull_or_face</td>\n",
" <td>[akja]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>advanced</td>\n",
" <td>fall_alone</td>\n",
" <td>CALDARO</td>\n",
" <td>BZ</td>\n",
" <td>F</td>\n",
" <td>ski</td>\n",
" <td>None</td>\n",
" <td>domicile</td>\n",
" <td>other</td>\n",
" <td>None</td>\n",
" <td>12.0</td>\n",
" <td>Italia</td>\n",
" <td>R</td>\n",
" <td>None</td>\n",
" <td>[snowmobile]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>advanced</td>\n",
" <td>collision_person</td>\n",
" <td>LINZ</td>\n",
" <td></td>\n",
" <td>M</td>\n",
" <td>ski</td>\n",
" <td>None</td>\n",
" <td>hospital_emergency_room</td>\n",
" <td>bruise</td>\n",
" <td>None</td>\n",
" <td>58.0</td>\n",
" <td>Austria</td>\n",
" <td>R</td>\n",
" <td>lower_limbs</td>\n",
" <td>[snowmobile]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>advanced</td>\n",
" <td>collision_person</td>\n",
" <td>RUSAVA</td>\n",
" <td></td>\n",
" <td>M</td>\n",
" <td>ski</td>\n",
" <td>None</td>\n",
" <td>other</td>\n",
" <td>bruise</td>\n",
" <td>None</td>\n",
" <td>25.0</td>\n",
" <td>Repubblica Ceca</td>\n",
" <td>L</td>\n",
" <td>lower_limbs</td>\n",
" <td>[other]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" difficulty cause town province gender equipment helmet \\\n",
"0 novice fall_alone SIKLOS F ski None \n",
"1 advanced fall_alone MALMO M ski None \n",
"2 advanced fall_alone CALDARO BZ F ski None \n",
"3 advanced collision_person LINZ M ski None \n",
"4 advanced collision_person RUSAVA M ski None \n",
"\n",
" destination diagnosis india age country \\\n",
"0 hospital_emergency_room distortion None 32.0 Ungheria \n",
"1 hospital_emergency_room bruise None 32.0 Svezia \n",
"2 domicile other None 12.0 Italia \n",
"3 hospital_emergency_room bruise None 58.0 Austria \n",
"4 other bruise None 25.0 Repubblica Ceca \n",
"\n",
" injury_side injury_general_location evacuation_vehicles \n",
"0 L lower_limbs [akja] \n",
"1 R skull_or_face [akja] \n",
"2 R None [snowmobile] \n",
"3 R lower_limbs [snowmobile] \n",
"4 L lower_limbs [other] "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 99,
"id": "babc2e8b-1030-4e8a-aa41-6d2a788959a5",
"metadata": {},
"outputs": [
{
"ename": "AttributeError",
"evalue": "'Series' object has no attribute 'evacuation_vehicles'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/tmp/ipykernel_42878/3368331793.py\u001b[0m in \u001b[0;36m?\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mev\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mrow\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0miterrows\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mev\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mev\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munion\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevacuation_vehicles\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m~/miniconda3/envs/pid/lib/python3.11/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m?\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 6289\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_accessors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6290\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6291\u001b[0m ):\n\u001b[1;32m 6292\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 6293\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m: 'Series' object has no attribute 'evacuation_vehicles'"
]
}
],
"source": [
"ev = set({})\n",
"for i,row in df.iterrows():\n",
" ev = ev.union(set(row.evacuation_vehicles))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "c8d6cc1c-f4f5-44ec-8652-b135963452ab",
"metadata": {},
"outputs": [],
"source": [
"for c in ev:\n",
" df[c] = False\n",
"for i,row in df.iterrows():\n",
" for c in row.evacuation_vehicles:\n",
" df.loc[i,c] = True"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "758c3317-1b02-4aed-b94d-7b6998d23797",
"metadata": {},
"outputs": [],
"source": [
"df.drop(columns=['town','province','evacuation_vehicles'],inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "adadc0dc-9d6e-4277-8956-d1d4b2492e7e",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 100,
"id": "33617e77-7c2b-41a3-96c0-8930aa5ac869",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(array([1.3808e+04, 0.0000e+00, 8.8100e+02, 0.0000e+00, 0.0000e+00,\n",
" 3.3690e+03, 0.0000e+00, 1.5200e+02, 0.0000e+00, 1.1000e+01]),\n",
" array([0. , 0.4, 0.8, 1.2, 1.6, 2. , 2.4, 2.8, 3.2, 3.6, 4. ]),\n",
" <BarContainer object of 10 artists>)"
]
},
"execution_count": 100,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"labeled = df[~pd.isna(df.india)]\n",
"plt.hist(labeled.india)"
]
},
{
"cell_type": "code",
"execution_count": 101,
"id": "2bda819b-4d4b-4e71-960a-53dd74d80b71",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_42878/2289208715.py:1: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled['is_i1']=0\n"
]
},
{
"data": {
"text/plain": [
"(array([ 3532., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 14689.]),\n",
" array([0. , 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1. ]),\n",
" <BarContainer object of 10 artists>)"
]
},
"execution_count": 101,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"labeled['is_i1']=0\n",
"labeled.loc[labeled.india.isin(['i1','i0']),'is_i1']=1\n",
"plt.hist(labeled.is_i1)"
]
},
{
"cell_type": "code",
"execution_count": 103,
"id": "e8c139d9-bf61-45ec-9da1-7eaf4ff754b4",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_42878/1116779111.py:1: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].astype(np.float32).fillna(np.nan)\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n",
"/tmp/ipykernel_42878/1116779111.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n"
]
}
],
"source": [
"labeled[c] = labeled[c].astype(np.float32).fillna(np.nan)\n",
"for c in labeled.columns:\n",
" if c!='age':\n",
" labeled[c] = labeled[c].fillna('None').astype('category')\n"
]
},
{
"cell_type": "code",
"execution_count": 104,
"id": "fabf354e-f39e-4cde-af84-c65a277d309a",
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split( labeled.drop(columns=['india','is_i1']),\n",
" labeled.is_i1, test_size=0.33, random_state=0,stratify=labeled.is_i1)"
]
},
{
"cell_type": "code",
"execution_count": 105,
"id": "cf6cf5d8-d43e-499e-98a5-65ecd0b8ccda",
"metadata": {},
"outputs": [],
"source": [
"X_train, X_valid, y_train, y_valid = train_test_split(X_train,y_train, test_size=0.33, random_state=0,stratify=y_train)"
]
},
{
"cell_type": "code",
"execution_count": 147,
"id": "774ad570-a60b-475b-80cf-4f9b9949cc9d",
"metadata": {},
"outputs": [],
"source": [
"weight_train = (1-y_train.values.astype(int))*5+1 ## peso classi unbalanced"
]
},
{
"cell_type": "code",
"execution_count": 149,
"id": "1fcc5234-abad-459a-9420-810833657796",
"metadata": {},
"outputs": [],
"source": [
"from catboost import CatBoostClassifier, Pool\n",
"\n",
"train_data = Pool(data=X_train,\n",
" label=y_train,\n",
" weight=weight_train,cat_features=[c for c in X_train.columns if c!='age'])\n",
"valid_data = Pool(data=X_valid,\n",
" label=y_valid,cat_features=[c for c in X_train.columns if c!='age']\n",
" )\n",
"model = CatBoostClassifier(iterations=1000)\n",
"\n",
"model.fit(train_data,eval_set=valid_data,verbose=False,early_stopping_rounds=100)\n",
"preds_class = model.predict(valid_data,)"
]
},
{
"cell_type": "code",
"execution_count": 150,
"id": "8df84007-110b-4f31-bc7d-53e7d5c9a178",
"metadata": {},
"outputs": [],
"source": [
"preds_class_valid = model.predict(valid_data)\n",
"preds_class_train= model.predict(train_data)"
]
},
{
"cell_type": "code",
"execution_count": 151,
"id": "55627ec4-fd24-4815-98d4-d8462bbfdd9a",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics import confusion_matrix,matthews_corrcoef,accuracy_score"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "877e914d-44d4-4299-8d3c-24c4fc353317",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 152,
"id": "776395d9-a8e2-4fda-90e1-11d6dbe80de8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 622 159]\n",
" [ 778 2470]]\n",
"0.4623150659581546\n",
"0.7674360883593944\n",
"########################################\n",
"[[1436 149]\n",
" [1358 5236]]\n",
"0.5834604503367398\n",
"0.8157476464115417\n"
]
}
],
"source": [
"print(confusion_matrix(y_valid,preds_class_valid))\n",
"print(matthews_corrcoef(y_valid,preds_class_valid))\n",
"print(accuracy_score(y_valid,preds_class_valid))\n",
"print('########################################')\n",
"print(confusion_matrix(y_train,preds_class_train))\n",
"print(matthews_corrcoef(y_train,preds_class_train))\n",
"print(accuracy_score(y_train,preds_class_train))"
]
},
{
"cell_type": "code",
"execution_count": 157,
"id": "34c397bc-529a-4c52-b30e-957b28021200",
"metadata": {},
"outputs": [
{
"ename": "TypeError",
"evalue": "DMatrix.__init__() got an unexpected keyword argument 'scale_pos_weight'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[157], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mxgboost\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mxgb\u001b[39;00m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;66;03m# Create regression matrices\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m dtrain \u001b[38;5;241m=\u001b[39m \u001b[43mxgb\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mDMatrix\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mastype\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mint\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43menable_categorical\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43mscale_pos_weight\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m100\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;66;03m#,weight=weight_train)\u001b[39;00m\n\u001b[1;32m 6\u001b[0m dvalid \u001b[38;5;241m=\u001b[39m xgb\u001b[38;5;241m.\u001b[39mDMatrix(X_valid, y_valid\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mint\u001b[39m), enable_categorical\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
"File \u001b[0;32m~/miniconda3/envs/pid/lib/python3.11/site-packages/xgboost/core.py:730\u001b[0m, in \u001b[0;36mrequire_keyword_args.<locals>.throw_if.<locals>.inner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 728\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m k, arg \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mzip\u001b[39m(sig\u001b[38;5;241m.\u001b[39mparameters, args):\n\u001b[1;32m 729\u001b[0m kwargs[k] \u001b[38;5;241m=\u001b[39m arg\n\u001b[0;32m--> 730\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[0;31mTypeError\u001b[0m: DMatrix.__init__() got an unexpected keyword argument 'scale_pos_weight'"
]
}
],
"source": [
"##try with xgboost\n",
"import xgboost as xgb\n",
"\n",
"# Create regression matrices\n",
"dtrain = xgb.DMatrix(X_train, y_train.astype(int), enable_categorical=True)#,weight=weight_train)\n",
"dvalid = xgb.DMatrix(X_valid, y_valid.astype(int), enable_categorical=True)"
]
},
{
"cell_type": "code",
"execution_count": 161,
"id": "7bb54c1d-ed2c-496a-b149-d567246bfee0",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/agobbi/miniconda3/envs/pid/lib/python3.11/site-packages/xgboost/core.py:160: UserWarning: [11:26:44] WARNING: /workspace/src/learner.cc:742: \n",
"Parameters: { \"scale_pos_weight\" } are not used.\n",
"\n",
" warnings.warn(smsg, UserWarning)\n"
]
}
],
"source": [
"params = {\"objective\": \"multi:softprob\", \"num_class\": 2,'scale_pos_weight':100}\n",
"n = 1000\n",
"\n",
"results = xgb.train(\n",
" params, dtrain,\n",
"\n",
" num_boost_round=n,\n",
" evals = [(dtrain, \"train\"), (dvalid, \"valid\")],\n",
" verbose_eval=False,\n",
" early_stopping_rounds=100\n",
" # metrics=[\"mlogloss\", \"auc\", \"merror\"],\n",
")\n"
]
},
{
"cell_type": "code",
"execution_count": 182,
"id": "353b9430-61ff-4d15-869e-8a5a06a1fb51",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 492 289]\n",
" [ 471 2777]]\n",
"0.4495009568013873\n",
"0.811367585008687\n",
"########################################\n",
"[[1584 1]\n",
" [ 389 6205]]\n",
"0.8688028589259579\n",
"0.9523169091575987\n"
]
}
],
"source": [
"preds_class_valid = results.predict(dvalid)\n",
"preds_class_train= results.predict(dtrain)\n",
"print(confusion_matrix(y_valid,preds_class_valid.argmax(1)))\n",
"print(matthews_corrcoef(y_valid,preds_class_valid.argmax(1)))\n",
"print(accuracy_score(y_valid,preds_class_valid.argmax(1)))\n",
"print('########################################')\n",
"print(confusion_matrix(y_train,preds_class_train.argmax(1)))\n",
"print(matthews_corrcoef(y_train,preds_class_train.argmax(1)))\n",
"print(accuracy_score(y_train,preds_class_train.argmax(1)))"
]
},
{
"cell_type": "code",
"execution_count": 183,
"id": "5120687b-02ed-42ee-80ca-543fe6aa540d",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/agobbi/miniconda3/envs/pid/lib/python3.11/site-packages/xgboost/sklearn.py:889: UserWarning: `early_stopping_rounds` in `fit` method is deprecated for better compatibility with scikit-learn, use `early_stopping_rounds` in constructor or`set_params` instead.\n",
" warnings.warn(\n",
"/home/agobbi/miniconda3/envs/pid/lib/python3.11/site-packages/xgboost/core.py:160: UserWarning: [11:33:33] WARNING: /workspace/src/learner.cc:742: \n",
"Parameters: { \"scale_pos_weight\" } are not used.\n",
"\n",
" warnings.warn(smsg, UserWarning)\n"
]
},
{
"data": {
"text/html": [
"<style>#sk-container-id-4 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: black;\n",
" --sklearn-color-line: gray;\n",
" /* Definition of color scheme for unfitted estimators */\n",
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
" --sklearn-color-unfitted-level-3: chocolate;\n",
" /* Definition of color scheme for fitted estimators */\n",
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
" --sklearn-color-fitted-level-1: #d4ebff;\n",
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
"\n",
" /* Specific color for light theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-icon: #696969;\n",
"\n",
" @media (prefers-color-scheme: dark) {\n",
" /* Redefinition of color scheme for dark theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-icon: #878787;\n",
" }\n",
"}\n",
"\n",
"#sk-container-id-4 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"#sk-container-id-4 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
"#sk-container-id-4 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
" height: 1px;\n",
" margin: -1px;\n",
" overflow: hidden;\n",
" padding: 0;\n",
" position: absolute;\n",
" width: 1px;\n",
"}\n",
"\n",
"#sk-container-id-4 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",
" padding-bottom: 0.4em;\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"#sk-container-id-4 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",
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
" display: inline-block !important;\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
"div.sk-parallel-item,\n",
"div.sk-serial,\n",
"div.sk-item {\n",
" /* draw centered vertical line to link estimators */\n",
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
" background-size: 2px 100%;\n",
" background-repeat: no-repeat;\n",
" background-position: center center;\n",
"}\n",
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
"#sk-container-id-4 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-4 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
" background-color: var(--sklearn-color-background);\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
"#sk-container-id-4 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
" background-color: var(--sklearn-color-background);\n",
" padding-right: 1em;\n",
" padding-left: 1em;\n",
"}\n",
"\n",
"\n",
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
"clickable and can be expanded/collapsed.\n",
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
"*/\n",
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
"#sk-container-id-4 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-4 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: block;\n",
" width: 100%;\n",
" margin-bottom: 0;\n",
" padding: 0.5em;\n",
" box-sizing: border-box;\n",
" text-align: center;\n",
"}\n",
"\n",
"#sk-container-id-4 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
" margin-right: 0.25em;\n",
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
"#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
"#sk-container-id-4 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
" text-align: left;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-4 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-4 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-4 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-4 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-4 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-4 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-4 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-4 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-4 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-4 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-4 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-4 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
"#sk-container-id-4 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
" box-sizing: border-box;\n",
" margin-bottom: 0.5em;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
"#sk-container-id-4 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-4 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
"\n",
"/* Common style for \"i\" and \"?\" */\n",
"\n",
".sk-estimator-doc-link,\n",
"a:link.sk-estimator-doc-link,\n",
"a:visited.sk-estimator-doc-link {\n",
" float: right;\n",
" font-size: smaller;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1em;\n",
" height: 1em;\n",
" width: 1em;\n",
" text-decoration: none !important;\n",
" margin-left: 1ex;\n",
" /* unfitted */\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted,\n",
"a:link.sk-estimator-doc-link.fitted,\n",
"a:visited.sk-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",
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
".sk-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",
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"/* Span, style for the box shown on hovering the info icon */\n",
".sk-estimator-doc-link span {\n",
" display: none;\n",
" z-index: 9999;\n",
" position: relative;\n",
" font-weight: normal;\n",
" right: .2ex;\n",
" padding: .5ex;\n",
" margin: .5ex;\n",
" width: min-content;\n",
" min-width: 20ex;\n",
" max-width: 50ex;\n",
" color: var(--sklearn-color-text);\n",
" box-shadow: 2pt 2pt 4pt #999;\n",
" /* unfitted */\n",
" background: var(--sklearn-color-unfitted-level-0);\n",
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted span {\n",
" /* fitted */\n",
" background: var(--sklearn-color-fitted-level-0);\n",
" border: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link:hover span {\n",
" display: block;\n",
"}\n",
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
"#sk-container-id-4 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1rem;\n",
" height: 1rem;\n",
" width: 1rem;\n",
" text-decoration: none;\n",
" /* unfitted */\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
"#sk-container-id-4 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-4 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-4 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-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=True, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=1000, n_jobs=None, num_class=2,\n",
" num_parallel_tree=None, ...)</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-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBClassifier<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=True, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=1000, n_jobs=None, num_class=2,\n",
" num_parallel_tree=None, ...)</pre></div> </div></div></div></div>"
],
"text/plain": [
"XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
" colsample_bylevel=None, colsample_bynode=None,\n",
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
" enable_categorical=True, eval_metric=None, feature_types=None,\n",
" gamma=None, grow_policy=None, importance_type=None,\n",
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
" multi_strategy=None, n_estimators=1000, n_jobs=None, num_class=2,\n",
" num_parallel_tree=None, ...)"
]
},
"execution_count": 183,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = xgb.XGBClassifier(n_estimators=1000,scale_pos_weight=50,objective=\"multi:softprob\",num_class=2,enable_categorical=True)\n",
"model.fit(X_train, y_train.astype(int), early_stopping_rounds=100,eval_set = [(X_valid, y_valid.astype(int))],verbose=False)"
]
},
{
"cell_type": "code",
"execution_count": 184,
"id": "9cdb16a1-0761-4e3d-9214-6fef6ced875a",
"metadata": {},
"outputs": [],
"source": [
"preds_class_valid = model.predict(X_valid)\n",
"preds_class_train= model.predict(X_train)"
]
},
{
"cell_type": "code",
"execution_count": 185,
"id": "65228d59-e4c2-411d-8535-b36c15a55bfd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 308 473]\n",
" [ 151 3097]]\n",
"0.4328302503376973\n",
"0.8451228592702904\n",
"########################################\n",
"[[ 825 760]\n",
" [ 221 6373]]\n",
"0.5763770395263901\n",
"0.8800586868810368\n"
]
}
],
"source": [
"print(confusion_matrix(y_valid,preds_class_valid.argmax(1)))\n",
"print(matthews_corrcoef(y_valid,preds_class_valid.argmax(1)))\n",
"print(accuracy_score(y_valid,preds_class_valid.argmax(1)))\n",
"print('########################################')\n",
"print(confusion_matrix(y_train,preds_class_train.argmax(1)))\n",
"print(matthews_corrcoef(y_train,preds_class_train.argmax(1)))\n",
"print(accuracy_score(y_train,preds_class_train.argmax(1)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "95461970-fad9-4c50-84d3-e139bedfec3f",
"metadata": {},
"outputs": [],
"source": [
"0.4495009568013873\n",
"0.811367585008687\n",
"########################################\n",
"[[1584 1]\n",
" [ 389 6205]]\n",
"0.8688028589259579\n",
"0.9523169091575987"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink