msb-public
/
ML-For-Beginners
mirror of https://github.com/microsoft/ML-For-Beginners.git
1
0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '2b522d2370'
${ noResults }
ML-For-Beginners/4-Classification/4-Applied/solution/notebook.ipynb

279 lines
17 KiB
Raw Blame History Escape

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

{
"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"
}
},
"nbformat": 4,
"nbformat_minor": 2,
"cells": [
{
"source": [
"# Build a cuisine recommender"
],
"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": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>Unnamed: 0</th>\n <th>cuisine</th>\n <th>almond</th>\n <th>angelica</th>\n <th>anise</th>\n <th>anise_seed</th>\n <th>apple</th>\n <th>apple_brandy</th>\n <th>apricot</th>\n <th>armagnac</th>\n <th>...</th>\n <th>whiskey</th>\n <th>white_bread</th>\n <th>white_wine</th>\n <th>whole_grain_wheat_flour</th>\n <th>wine</th>\n <th>wood</th>\n <th>yam</th>\n <th>yeast</th>\n <th>yogurt</th>\n <th>zucchini</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>0</td>\n <td>indian</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>1</th>\n <td>1</td>\n <td>indian</td>\n <td>1</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>2</th>\n <td>2</td>\n <td>indian</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>3</th>\n <td>3</td>\n <td>indian</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>4</th>\n <td>4</td>\n <td>indian</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>1</td>\n <td>0</td>\n </tr>\n </tbody>\n</table>\n<p>5 rows × 382 columns</p>\n</div>"
},
"metadata": {},
"execution_count": 60
}
],
"source": [
"data = pd.read_csv('../../data/cleaned_cuisine.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": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>almond</th>\n <th>angelica</th>\n <th>anise</th>\n <th>anise_seed</th>\n <th>apple</th>\n <th>apple_brandy</th>\n <th>apricot</th>\n <th>armagnac</th>\n <th>artemisia</th>\n <th>artichoke</th>\n <th>...</th>\n <th>whiskey</th>\n <th>white_bread</th>\n <th>white_wine</th>\n <th>whole_grain_wheat_flour</th>\n <th>wine</th>\n <th>wood</th>\n <th>yam</th>\n <th>yeast</th>\n <th>yogurt</th>\n <th>zucchini</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>1</th>\n <td>1</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>2</th>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>3</th>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n </tr>\n <tr>\n <th>4</th>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>...</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>0</td>\n <td>1</td>\n <td>0</td>\n </tr>\n </tbody>\n</table>\n<p>5 rows × 380 columns</p>\n</div>"
},
"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": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>cuisine</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>indian</td>\n </tr>\n <tr>\n <th>1</th>\n <td>indian</td>\n </tr>\n <tr>\n <th>2</th>\n <td>indian</td>\n </tr>\n <tr>\n <th>3</th>\n <td>indian</td>\n </tr>\n <tr>\n <th>4</th>\n <td>indian</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"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"
]
}
]
}
Reference in new issue View Git Blame Copy Permalink