Signed-off-by: András Schmelczer <andras@schmelczer.dev>
This commit is contained in:
Andras Schmelczer 2022-04-02 21:59:09 +02:00
parent acbdd96883
commit 1c501db81a
8 changed files with 16 additions and 11 deletions

View file

@ -119,7 +119,9 @@
" content = json.load(f)\n",
"\n",
" result = {\n",
" preprocess(clean(f'{c[\"title\"]} {c[\"abstract\"]}'), convert_to_ascii=True): c[\"domain\"]\n",
" preprocess(\n",
" clean(f'{c[\"title\"]} {c[\"abstract\"]}'), convert_to_ascii=True\n",
" ): c[\"domain\"]\n",
" for c in content\n",
" if (\n",
" c[\"domain\"]\n",
@ -242,7 +244,7 @@
"source": [
"classifier = Pipeline(\n",
" steps=[\n",
" (\"vectorizer\", TfidfVectorizer(min_df=10, max_df=0.1, token_pattern=r'[^ ]+')),\n",
" (\"vectorizer\", TfidfVectorizer(min_df=10, max_df=0.1, token_pattern=r\"[^ ]+\")),\n",
" (\"classifier\", ComplementNB(alpha=0.5, fit_prior=False)),\n",
" ],\n",
" verbose=1,\n",
@ -405,6 +407,7 @@
"source": [
"import logging\n",
"import sys\n",
"\n",
"logging.basicConfig(stream=sys.stdout, level=logging.INFO)\n",
"\n",
"save_model(classifier, key=model_key, keep_last_n=1)"