From 8da28111e84f67b36327930a57e6375cf5e34b35 Mon Sep 17 00:00:00 2001
From: Alice BRENON <alice.brenon@ens-lyon.fr>
Date: Tue, 29 Mar 2022 12:18:49 +0200
Subject: [PATCH] Adapt notebook computing confusion matrices
---
notebooks/Confusion Matrices.ipynb | 34 ++++--------------------------
1 file changed, 4 insertions(+), 30 deletions(-)
diff --git a/notebooks/Confusion Matrices.ipynb b/notebooks/Confusion Matrices.ipynb
index d7a11c5..38cb20a 100644
--- a/notebooks/Confusion Matrices.ipynb
+++ b/notebooks/Confusion Matrices.ipynb
@@ -18,6 +18,7 @@
"outputs": [],
"source": [
"from EDdA import data\n",
+ "from EDdA.store import preparePath\n",
"from EDdA.classification import confusionMatrix, metrics, toPNG, topNGrams\n",
"import os"
]
@@ -32,7 +33,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"id": "5ad65685",
"metadata": {},
"outputs": [],
@@ -40,39 +41,12 @@
"source = data.load('training_set')"
]
},
- {
- "cell_type": "markdown",
- "id": "4e958e04",
- "metadata": {},
- "source": [
- "This function rationalises the name of the files containing the confusion matrices to produce."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "id": "545bdb4f",
- "metadata": {},
- "outputs": [],
- "source": [
- "def preparePath(root, source, n, ranks, metricName):\n",
- " path = \"{root}/confusionMatrix/{inputHash}/{n}grams_top{ranks}_{name}.png\".format(\n",
- " root=root,\n",
- " inputHash=source.hash,\n",
- " n=n,\n",
- " ranks=ranks,\n",
- " name=metricName\n",
- " )\n",
- " os.makedirs(os.path.dirname(path), exist_ok=True)\n",
- " return path"
- ]
- },
{
"cell_type": "markdown",
"id": "4079559f",
"metadata": {},
"source": [
- "Then we only have to loop on the n-gram size (`n`), the number of `ranks` to keep when computing the most frequent ones and the comparison method (the metrics' `name`)."
+ "We loop on the n-gram size (`n`), the number of `ranks` to keep when computing the most frequent ones and the comparison method (the metrics' `name`)."
]
},
{
@@ -86,7 +60,7 @@
" for ranks in [10, 50, 100]:\n",
" vectorizer = topNGrams(source, n, ranks)\n",
" for name in ['colinearity', 'keysIntersection']:\n",
- " imagePath = preparePath('.', source, n, ranks, name)\n",
+ " imagePath = preparePath(f\"confusionMatrix/{source.hash}/{n}grams_top{ranks}_{name}.png\")\n",
" toPNG(confusionMatrix(vectorizer, metrics[name]), imagePath)"
]
}
--
GitLab