msb-public
/
ML-For-Beginners
mirror of https://github.com/microsoft/ML-For-Beginners.git
1
0
Code Issues Projects Releases Wiki Activity

ML Model Predict Cuisine Based on Ingridients

Browse Source
pull/719/head
raygaeta 2 years ago
parent d33fba0977
commit f6855e0c65
1 changed files with 809 additions and 12 deletions
Show Stats Download Patch File Download Diff File

819
4-Classification/2-Classifiers-1/notebook.ipynb
Unescape View File

@ -1,5 +1,811 @@
{ {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Build Classification Models"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"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>"
],
"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]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"cuisines_df = pd.read_csv(\"../data/cleaned_cuisines.csv\")\n",
"cuisines_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.model_selection import train_test_split, cross_val_score\n",
"from sklearn.metrics import accuracy_score,precision_score,confusion_matrix,classification_report, precision_recall_curve\n",
"from sklearn.svm import SVC\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 indian\n",
"1 indian\n",
"2 indian\n",
"3 indian\n",
"4 indian\n",
"Name: cuisine, dtype: object"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cuisines_label_df = cuisines_df['cuisine']\n",
"cuisines_label_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"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>"
],
"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]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cuisines_feature_df = cuisines_df.drop(['Unnamed: 0', 'cuisine'], axis=1)\n",
"cuisines_feature_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(cuisines_feature_df, cuisines_label_df, test_size=0.3)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy is 0.7881567973311092\n"
]
}
],
"source": [
"lr = LogisticRegression(multi_class='ovr',solver='liblinear')\n",
"model = lr.fit(X_train, np.ravel(y_train))\n",
"\n",
"accuracy = model.score(X_test, y_test)\n",
"print (\"Accuracy is {}\".format(accuracy))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ingredients: Index(['black_pepper', 'carrot', 'corn', 'onion', 'pineapple', 'pork',\n",
" 'shiitake', 'soy_sauce', 'starch', 'vinegar'],\n",
" dtype='object')\n",
"cuisine: chinese\n"
]
}
],
"source": [
"print(f'ingredients: {X_test.iloc[50][X_test.iloc[50]!=0].keys()}')\n",
"print(f'cuisine: {y_test.iloc[50]}')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/ray/Desktop/ML-For-Beginners/.venv/lib/python3.12/site-packages/sklearn/base.py:465: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
" warnings.warn(\n"
]
},
{
"data": {
"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>0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>chinese</th>\n",
" <td>0.954918</td>\n",
" </tr>\n",
" <tr>\n",
" <th>korean</th>\n",
" <td>0.023422</td>\n",
" </tr>\n",
" <tr>\n",
" <th>japanese</th>\n",
" <td>0.018495</td>\n",
" </tr>\n",
" <tr>\n",
" <th>thai</th>\n",
" <td>0.002817</td>\n",
" </tr>\n",
" <tr>\n",
" <th>indian</th>\n",
" <td>0.000348</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0\n",
"chinese 0.954918\n",
"korean 0.023422\n",
"japanese 0.018495\n",
"thai 0.002817\n",
"indian 0.000348"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test= X_test.iloc[50].values.reshape(-1, 1).T\n",
"proba = model.predict_proba(test)\n",
"classes = model.classes_\n",
"resultdf = pd.DataFrame(data=proba, columns=classes)\n",
"\n",
"topPrediction = resultdf.T.sort_values(by=[0], ascending = [False])\n",
"topPrediction.head()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" chinese 0.74 0.74 0.74 234\n",
" indian 0.92 0.91 0.92 254\n",
" japanese 0.63 0.75 0.68 222\n",
" korean 0.80 0.78 0.79 235\n",
" thai 0.86 0.75 0.80 254\n",
"\n",
" accuracy 0.79 1199\n",
" macro avg 0.79 0.79 0.79 1199\n",
"weighted avg 0.80 0.79 0.79 1199\n",
"\n"
]
}
],
"source": [
"y_pred = model.predict(X_test)\n",
"print(classification_report(y_test,y_pred))"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(cuisines_feature_df, cuisines_label_df, test_size=0.3)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy is 0.8006672226855713\n"
]
}
],
"source": [
"lr = LogisticRegression(multi_class='ovr',solver='liblinear')\n",
"model = lr.fit(X_train, np.ravel(y_train))\n",
"\n",
"accuracy = model.score(X_test, y_test)\n",
"print (\"Accuracy is {}\".format(accuracy))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ingredients: Index(['bell_pepper', 'carrot', 'egg', 'pork', 'shiitake', 'soy_sauce',\n",
" 'starch', 'vegetable', 'vegetable_oil'],\n",
" dtype='object')\n",
"cuisine: chinese\n"
]
}
],
"source": [
"print(f'ingredients: {X_test.iloc[50][X_test.iloc[50]!=0].keys()}')\n",
"print(f'cuisine: {y_test.iloc[50]}')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/ray/Desktop/ML-For-Beginners/.venv/lib/python3.12/site-packages/sklearn/base.py:465: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
" warnings.warn(\n"
]
},
{
"data": {
"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>0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>chinese</th>\n",
" <td>0.928517</td>\n",
" </tr>\n",
" <tr>\n",
" <th>japanese</th>\n",
" <td>0.042258</td>\n",
" </tr>\n",
" <tr>\n",
" <th>korean</th>\n",
" <td>0.026577</td>\n",
" </tr>\n",
" <tr>\n",
" <th>thai</th>\n",
" <td>0.002424</td>\n",
" </tr>\n",
" <tr>\n",
" <th>indian</th>\n",
" <td>0.000223</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0\n",
"chinese 0.928517\n",
"japanese 0.042258\n",
"korean 0.026577\n",
"thai 0.002424\n",
"indian 0.000223"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test= X_test.iloc[50].values.reshape(-1, 1).T\n",
"proba = model.predict_proba(test)\n",
"classes = model.classes_\n",
"resultdf = pd.DataFrame(data=proba, columns=classes)\n",
"\n",
"topPrediction = resultdf.T.sort_values(by=[0], ascending = [False])\n",
"topPrediction.head()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" chinese 0.74 0.69 0.71 243\n",
" indian 0.91 0.90 0.90 233\n",
" japanese 0.74 0.76 0.75 238\n",
" korean 0.82 0.81 0.81 238\n",
" thai 0.81 0.84 0.83 247\n",
"\n",
" accuracy 0.80 1199\n",
" macro avg 0.80 0.80 0.80 1199\n",
"weighted avg 0.80 0.80 0.80 1199\n",
"\n"
]
}
],
"source": [
"y_pred = model.predict(X_test)\n",
"print(classification_report(y_test,y_pred))"
]
}
],
"metadata": { "metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": { "language_info": {
"codemirror_mode": { "codemirror_mode": {
"name": "ipython", "name": "ipython",
@ -10,19 +816,10 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": 3 "version": "3.12.0"
}, },
"orig_nbformat": 2 "orig_nbformat": 2
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2, "nbformat_minor": 2
"cells": [
{
"source": [
"# Build Classification Models"
],
"cell_type": "markdown",
"metadata": {}
}
]
} }
Write Preview
Loading…
Cancel
Save