1826514
/
DSA_SS24
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added f1 score

main
Felix Jan Michael Mucha 2024-06-12 17:19:27 +02:00
parent 06b862b1a1
commit 2f89518bbf
2 changed files with 85 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

74
notebooks/ml_grad_boost_tree.ipynb
View File

File diff suppressed because one or more lines are too long

63
notebooks/ml_xgboost.ipynb
View File

@ -9,7 +9,7 @@
},
{
"cell_type": "code",
"execution_count": 36,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@ -20,10 +20,9 @@
"import matplotlib.pyplot as plt\n",
"import xgboost as xgb\n",
"from sklearn.model_selection import GridSearchCV\n",
"from sklearn.metrics import confusion_matrix\n",
"from sklearn.impute import SimpleImputer\n",
"from sklearn.preprocessing import MinMaxScaler\n",
"import seaborn as sns"
"from sklearn.metrics import confusion_matrix, f1_score\n",
"import seaborn as sns\n",
"import numpy as np"
]
},
{
@ -35,7 +34,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
@ -59,7 +58,7 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 8,
"metadata": {},
"outputs": [
{
@ -337,7 +336,7 @@
},
{
"cell_type": "code",
"execution_count": 43,
"execution_count": 3,
"metadata": {},
"outputs": [
{
@ -362,14 +361,14 @@
},
{
"cell_type": "code",
"execution_count": 44,
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[20:16:51] WARNING: C:/Users/administrator/workspace/xgboost-win64_release_1.6.0/src/learner.cc:627: \n",
"[16:58:49] WARNING: C:/Users/administrator/workspace/xgboost-win64_release_1.6.0/src/learner.cc:627: \n",
"Parameters: { \"best_iteration\", \"best_ntree_limit\", \"scikit_learn\" } might not be used.\n",
"\n",
" This could be a false alarm, with some parameters getting used by language bindings but\n",
@ -377,13 +376,7 @@
" but getting flagged wrongly here. Please open an issue if you find any such cases.\n",
"\n",
"\n",
"[0]\ttrain-merror:0.16762\teval-merror:0.22603\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0]\ttrain-merror:0.16762\teval-merror:0.22603\n",
"[1]\ttrain-merror:0.15220\teval-merror:0.22374\n",
"[2]\ttrain-merror:0.13849\teval-merror:0.21461\n",
"[3]\ttrain-merror:0.13535\teval-merror:0.20776\n",
@ -483,8 +476,8 @@
"[97]\ttrain-merror:0.00029\teval-merror:0.18265\n",
"[98]\ttrain-merror:0.00029\teval-merror:0.18265\n",
"[99]\ttrain-merror:0.00029\teval-merror:0.18265\n",
"CPU times: total: 17.6 s\n",
"Wall time: 1.36 s\n"
"CPU times: total: 14.3 s\n",
"Wall time: 1.22 s\n"
]
}
],
@ -506,7 +499,7 @@
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 10,
"metadata": {},
"outputs": [
{
@ -546,7 +539,7 @@
},
{
"cell_type": "code",
"execution_count": 46,
"execution_count": 11,
"metadata": {},
"outputs": [
{
@ -577,7 +570,7 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 12,
"metadata": {},
"outputs": [
{
@ -609,7 +602,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 13,
"metadata": {},
"outputs": [
{
@ -618,7 +611,7 @@
"<AxesSubplot:title={'center':'Feature importance'}, xlabel='F score', ylabel='Features'>"
]
},
"execution_count": 19,
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
},
@ -640,7 +633,7 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 14,
"metadata": {},
"outputs": [
{
@ -679,6 +672,26 @@
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"F1 Score: 0.8157211953487169\n"
]
}
],
"source": [
"# Calculate F1 Score for multiclass classification\n",
"f1 = f1_score(test_y, preds, average='macro')\n",
"\n",
"print('F1 Score:', f1)"
]
}
],
"metadata": {