{ "metadata": { "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.0" }, "orig_nbformat": 2, "kernelspec": { "name": "python3", "display_name": "Python 3.7.0 64-bit ('3.7')" }, "metadata": { "interpreter": { "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d" } }, "interpreter": { "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d" }, "coopTranslator": { "original_hash": "49325d6dd12a3628fc64fa7ccb1a80ff", "translation_date": "2025-09-04T02:31:43+00:00", "source_file": "4-Classification/4-Applied/solution/notebook.ipynb", "language_code": "ko" } }, "nbformat": 4, "nbformat_minor": 2, "cells": [ { "source": [], "cell_type": "markdown", "metadata": {} }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Requirement already satisfied: skl2onnx in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (1.8.0)\n", "Requirement already satisfied: protobuf in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (3.8.0)\n", "Requirement already satisfied: numpy>=1.15 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.19.2)\n", "Requirement already satisfied: onnx>=1.2.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.9.0)\n", "Requirement already satisfied: six in /Users/jenlooper/Library/Python/3.7/lib/python/site-packages (from skl2onnx) (1.12.0)\n", "Requirement already satisfied: onnxconverter-common<1.9,>=1.6.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.8.1)\n", "Requirement already satisfied: scikit-learn>=0.19 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (0.24.2)\n", "Requirement already satisfied: scipy>=1.0 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from skl2onnx) (1.4.1)\n", "Requirement already satisfied: setuptools in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from protobuf->skl2onnx) (45.1.0)\n", "Requirement already satisfied: typing-extensions>=3.6.2.1 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from onnx>=1.2.1->skl2onnx) (3.10.0.0)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from scikit-learn>=0.19->skl2onnx) (2.1.0)\n", "Requirement already satisfied: joblib>=0.11 in /Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages (from scikit-learn>=0.19->skl2onnx) (0.16.0)\n", "\u001b[33mWARNING: You are using pip version 20.2.3; however, version 21.1.2 is available.\n", "You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.7/bin/python3.7 -m pip install --upgrade pip' command.\u001b[0m\n", "Note: you may need to restart the kernel to use updated packages.\n" ] } ], "source": [ "!pip install skl2onnx" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "import pandas as pd \n" ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Unnamed: 0 cuisine almond angelica anise anise_seed apple \\\n", "0 0 indian 0 0 0 0 0 \n", "1 1 indian 1 0 0 0 0 \n", "2 2 indian 0 0 0 0 0 \n", "3 3 indian 0 0 0 0 0 \n", "4 4 indian 0 0 0 0 0 \n", "\n", " apple_brandy apricot armagnac ... whiskey white_bread white_wine \\\n", "0 0 0 0 ... 0 0 0 \n", "1 0 0 0 ... 0 0 0 \n", "2 0 0 0 ... 0 0 0 \n", "3 0 0 0 ... 0 0 0 \n", "4 0 0 0 ... 0 0 0 \n", "\n", " whole_grain_wheat_flour wine wood yam yeast yogurt zucchini \n", "0 0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 0 \n", "4 0 0 0 0 0 1 0 \n", "\n", "[5 rows x 382 columns]" ], "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0cuisinealmondangelicaaniseanise_seedappleapple_brandyapricotarmagnac...whiskeywhite_breadwhite_winewhole_grain_wheat_flourwinewoodyamyeastyogurtzucchini
00indian00000000...0000000000
11indian10000000...0000000000
22indian00000000...0000000000
33indian00000000...0000000000
44indian00000000...0000000010
\n

5 rows × 382 columns

\n
" }, "metadata": {}, "execution_count": 60 } ], "source": [ "data = pd.read_csv('../../data/cleaned_cuisines.csv')\n", "data.head()" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " almond angelica anise anise_seed apple apple_brandy apricot \\\n", "0 0 0 0 0 0 0 0 \n", "1 1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 0 \n", "\n", " armagnac artemisia artichoke ... whiskey white_bread white_wine \\\n", "0 0 0 0 ... 0 0 0 \n", "1 0 0 0 ... 0 0 0 \n", "2 0 0 0 ... 0 0 0 \n", "3 0 0 0 ... 0 0 0 \n", "4 0 0 0 ... 0 0 0 \n", "\n", " whole_grain_wheat_flour wine wood yam yeast yogurt zucchini \n", "0 0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 0 \n", "4 0 0 0 0 0 1 0 \n", "\n", "[5 rows x 380 columns]" ], "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
almondangelicaaniseanise_seedappleapple_brandyapricotarmagnacartemisiaartichoke...whiskeywhite_breadwhite_winewhole_grain_wheat_flourwinewoodyamyeastyogurtzucchini
00000000000...0000000000
11000000000...0000000000
20000000000...0000000000
30000000000...0000000000
40000000000...0000000010
\n

5 rows × 380 columns

\n
" }, "metadata": {}, "execution_count": 61 } ], "source": [ "X = data.iloc[:,2:]\n", "X.head()" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " cuisine\n", "0 indian\n", "1 indian\n", "2 indian\n", "3 indian\n", "4 indian" ], "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
cuisine
0indian
1indian
2indian
3indian
4indian
\n
" }, "metadata": {}, "execution_count": 62 } ], "source": [ "y = data[['cuisine']]\n", "y.head()" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "from sklearn.svm import SVC\n", "from sklearn.model_selection import cross_val_score\n", "from sklearn.metrics import accuracy_score,precision_score,confusion_matrix,classification_report" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [], "source": [ "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3)" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "SVC(C=10, kernel='linear', probability=True, random_state=0)" ] }, "metadata": {}, "execution_count": 65 } ], "source": [ "model = SVC(kernel='linear', C=10, probability=True,random_state=0)\n", "model.fit(X_train,y_train.values.ravel())\n" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [], "source": [ "y_pred = model.predict(X_test)" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ " precision recall f1-score support\n\n chinese 0.72 0.70 0.71 236\n indian 0.91 0.88 0.89 243\n japanese 0.80 0.75 0.77 240\n korean 0.80 0.81 0.81 230\n thai 0.76 0.85 0.80 250\n\n accuracy 0.80 1199\n macro avg 0.80 0.80 0.80 1199\nweighted avg 0.80 0.80 0.80 1199\n\n" ] } ], "source": [ "print(classification_report(y_test,y_pred))" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [], "source": [ "from skl2onnx import convert_sklearn\n", "from skl2onnx.common.data_types import FloatTensorType\n", "\n", "initial_type = [('float_input', FloatTensorType([None, 380]))]\n", "options = {id(model): {'nocl': True, 'zipmap': False}}\n", "onx = convert_sklearn(model, initial_types=initial_type, options=options)\n", "with open(\"./model.onnx\", \"wb\") as f:\n", " f.write(onx.SerializeToString())\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n---\n\n**면책 조항**: \n이 문서는 AI 번역 서비스 [Co-op Translator](https://github.com/Azure/co-op-translator)를 사용하여 번역되었습니다. 정확성을 위해 최선을 다하고 있지만, 자동 번역에는 오류나 부정확성이 포함될 수 있습니다. 원본 문서의 원어 버전을 권위 있는 자료로 간주해야 합니다. 중요한 정보에 대해서는 전문적인 인간 번역을 권장합니다. 이 번역 사용으로 인해 발생하는 오해나 잘못된 해석에 대해 당사는 책임을 지지 않습니다. \n" ] } ] }