Refined Answers!

This commit is contained in:
bobbert committed 2026-04-26 16:01:45 +01:00
1 parent 1fcce03e9f
commit a91440f746
1 file changed
+6 -5
+6 -5
View File
@@ -24,6 +24,7 @@
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from fontTools.diff import color\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.linear_model import LogisticRegression\n",
@@ -4520,8 +4521,8 @@
"id": "78b84ffa610839ec",
"metadata": {
"ExecuteTime": {
"end_time": "2026-04-26T14:56:48.788059200Z",
"start_time": "2026-04-26T14:56:48.666808400Z"
"end_time": "2026-04-26T15:01:38.773145900Z",
"start_time": "2026-04-26T15:01:38.669533800Z"
}
},
"source": [
@@ -4533,7 +4534,7 @@
"display(comparison_c)\n",
"fig, ax = plt.subplots(figsize=(7, 4))\n",
"ax.bar(comparison_c[\"Model\"], comparison_c[\"Weighted F1\"], label=\"Weighted F1\")\n",
"ax.plot(comparison_c[\"Model\"], comparison_c[\"Accuracy\"], marker='o', linewidth=2, label=\"Accuracy\")\n",
"ax.plot(comparison_c[\"Model\"], comparison_c[\"Accuracy\"], marker='o', linewidth=2, label=\"Accuracy\", color='orange')\n",
"ax.set_title(\"Part C: Model comparison on Test set\")\n",
"ax.set_ylim(0, 1)\n",
"ax.grid(True, axis='y', alpha=0.3)\n",
@@ -4602,7 +4603,7 @@
"text/plain": [
"<Figure size 700x400 with 1 Axes>"
],
"image/png": "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 truncated
"image/png": "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 truncated
},
"metadata": {},
"output_type": "display_data",
@@ -4611,7 +4612,7 @@
}
}
],
"execution_count": 108
"execution_count": 116
},
{
"cell_type": "code",