wehub-resource-sync
269 lines
12 KiB
Plaintext
269 lines
12 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"source": [
|
||
"# Build More Classification Models"
|
||
],
|
||
"cell_type": "markdown",
|
||
"metadata": {}
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Dataset Overview\n",
|
||
"This dataset contains individual samples (for example, recipes) labeled by cuisine.\n",
|
||
"Each row corresponds to a single sample/record, and the columns represent ingredients or other attributes used for classification, including the `cuisine` label."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"# Load dataset containing cuisine features\n",
|
||
"cuisines_df = pd.read_csv(\"../../data/cleaned_cuisines.csv\")\n",
|
||
"cuisines_df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"output_type": "execute_result",
|
||
"data": {
|
||
"text/plain": [
|
||
"0 indian\n",
|
||
"1 indian\n",
|
||
"2 indian\n",
|
||
"3 indian\n",
|
||
"4 indian\n",
|
||
"Name: cuisine, dtype: object"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"execution_count": 2
|
||
}
|
||
],
|
||
"source": [
|
||
"cuisines_label_df = cuisines_df['cuisine']\n",
|
||
"cuisines_label_df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"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": 3
|
||
}
|
||
],
|
||
"source": [
|
||
"cuisines_features_df = cuisines_df.drop(['Unnamed: 0', 'cuisine'], axis=1)\n",
|
||
"cuisines_features_df.head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Try different classifiers"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.neighbors import KNeighborsClassifier\n",
|
||
"from sklearn.linear_model import LogisticRegression\n",
|
||
"from sklearn.svm import SVC\n",
|
||
"from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\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",
|
||
"import numpy as np"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"X_train, X_test, y_train, y_test = train_test_split(cuisines_features_df, cuisines_label_df, test_size=0.3)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"\n",
|
||
"C = 10\n",
|
||
"# Create different classifiers.\n",
|
||
"classifiers = {\n",
|
||
" 'Linear SVC': SVC(kernel='linear', C=C, probability=True,random_state=0),\n",
|
||
" 'KNN classifier': KNeighborsClassifier(C),\n",
|
||
" 'SVC': SVC(),\n",
|
||
" 'RFST': RandomForestClassifier(n_estimators=100),\n",
|
||
" 'ADA': AdaBoostClassifier(n_estimators=100)\n",
|
||
" \n",
|
||
"}\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"output_type": "stream",
|
||
"name": "stdout",
|
||
"text": [
|
||
"Accuracy (train) for Linear SVC: 76.4% \n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" chinese 0.64 0.66 0.65 242\n",
|
||
" indian 0.91 0.86 0.89 236\n",
|
||
" japanese 0.72 0.73 0.73 245\n",
|
||
" korean 0.83 0.75 0.79 234\n",
|
||
" thai 0.75 0.82 0.78 242\n",
|
||
"\n",
|
||
" accuracy 0.76 1199\n",
|
||
" macro avg 0.77 0.76 0.77 1199\n",
|
||
"weighted avg 0.77 0.76 0.77 1199\n",
|
||
"\n",
|
||
"Accuracy (train) for KNN classifier: 70.7% \n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" chinese 0.65 0.63 0.64 242\n",
|
||
" indian 0.84 0.81 0.82 236\n",
|
||
" japanese 0.60 0.81 0.69 245\n",
|
||
" korean 0.89 0.53 0.67 234\n",
|
||
" thai 0.69 0.75 0.72 242\n",
|
||
"\n",
|
||
" accuracy 0.71 1199\n",
|
||
" macro avg 0.73 0.71 0.71 1199\n",
|
||
"weighted avg 0.73 0.71 0.71 1199\n",
|
||
"\n",
|
||
"Accuracy (train) for SVC: 80.1% \n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" chinese 0.71 0.69 0.70 242\n",
|
||
" indian 0.92 0.92 0.92 236\n",
|
||
" japanese 0.77 0.78 0.77 245\n",
|
||
" korean 0.87 0.77 0.82 234\n",
|
||
" thai 0.75 0.86 0.80 242\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",
|
||
"Accuracy (train) for RFST: 82.8% \n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" chinese 0.80 0.75 0.77 242\n",
|
||
" indian 0.90 0.91 0.90 236\n",
|
||
" japanese 0.82 0.78 0.80 245\n",
|
||
" korean 0.85 0.82 0.83 234\n",
|
||
" thai 0.78 0.89 0.83 242\n",
|
||
"\n",
|
||
" accuracy 0.83 1199\n",
|
||
" macro avg 0.83 0.83 0.83 1199\n",
|
||
"weighted avg 0.83 0.83 0.83 1199\n",
|
||
"\n",
|
||
"Accuracy (train) for ADA: 71.1% \n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" chinese 0.60 0.57 0.58 242\n",
|
||
" indian 0.87 0.84 0.86 236\n",
|
||
" japanese 0.71 0.60 0.65 245\n",
|
||
" korean 0.68 0.78 0.72 234\n",
|
||
" thai 0.70 0.78 0.74 242\n",
|
||
"\n",
|
||
" accuracy 0.71 1199\n",
|
||
" macro avg 0.71 0.71 0.71 1199\n",
|
||
"weighted avg 0.71 0.71 0.71 1199\n",
|
||
"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"n_classifiers = len(classifiers)\n",
|
||
"\n",
|
||
"for index, (name, classifier) in enumerate(classifiers.items()):\n",
|
||
" classifier.fit(X_train, np.ravel(y_train))\n",
|
||
"\n",
|
||
" y_pred = classifier.predict(X_test)\n",
|
||
" accuracy = accuracy_score(y_test, y_pred)\n",
|
||
" print(\"Accuracy (train) for %s: %0.1f%% \" % (name, accuracy * 100))\n",
|
||
" print(classification_report(y_test,y_pred))"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"interpreter": {
|
||
"hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
|
||
},
|
||
"kernelspec": {
|
||
"name": "python3",
|
||
"display_name": "Python 3.7.0 64-bit ('3.7')"
|
||
},
|
||
"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"
|
||
},
|
||
"metadata": {
|
||
"interpreter": {
|
||
"hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
|
||
}
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 4
|
||
}
|