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 '788047ae1d'
${ noResults }
ML-For-Beginners/4-Classification/3-Classifiers-2/solution/notebook.ipynb

299 lines
17 KiB
Raw Normal View History Unescape

notebooks for classification
3 years ago
{
"cells": [
{
"source": [
classifier 3!
3 years ago
"# Build More Classification Models"
],
"cell_type": "markdown",
"metadata": {}
notebooks for classification
3 years ago
},
{
"cell_type": "code",
classifier 3!
3 years ago
"execution_count": 57,
notebooks for classification
3 years ago
"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": {},
classifier 3!
3 years ago
"execution_count": 57
notebooks for classification
3 years ago
}
],
"source": [
"import pandas as pd\n",
"recipes_df = pd.read_csv(\"../../data/cleaned_cuisine.csv\")\n",
"recipes_df.head()"
]
},
{
"cell_type": "code",
classifier 3!
3 years ago
"execution_count": 58,
notebooks for classification
3 years ago
"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": {},
classifier 3!
3 years ago
"execution_count": 58
notebooks for classification
3 years ago
}
],
"source": [
"recipes_label_df = recipes_df['cuisine']\n",
"recipes_label_df.head()"
]
},
{
"cell_type": "code",
classifier 3!
3 years ago
"execution_count": 59,
notebooks for classification
3 years ago
"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": {},
classifier 3!
3 years ago
"execution_count": 59
notebooks for classification
3 years ago
}
],
"source": [
"recipes_feature_df = recipes_df.drop(['Unnamed: 0', 'cuisine'], axis=1)\n",
"recipes_feature_df.head()"
]
},
classifier 3!
3 years ago
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Try different classifiers"
]
},
notebooks for classification
3 years ago
{
"cell_type": "code",
classifier 3!
3 years ago
"execution_count": 60,
base state for notebooks - classification 3
3 years ago
"metadata": {},
"outputs": [],
"source": [
classifier 3!
3 years ago
"from sklearn.neighbors import KNeighborsClassifier\n",
base state for notebooks - classification 3
3 years ago
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.svm import SVC\n",
classifier 3!
3 years ago
"from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\n",
base state for notebooks - classification 3
3 years ago
"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",
classifier 3!
3 years ago
"execution_count": 61,
notebooks for classification
3 years ago
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(recipes_feature_df, recipes_label_df, test_size=0.3)"
]
},
{
"cell_type": "code",
classifier 3!
3 years ago
"execution_count": 62,
notebooks for classification
3 years ago
"metadata": {},
"outputs": [],
"source": [
classifier 3!
3 years ago
"\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"
notebooks for classification
3 years ago
]
},
{
"cell_type": "code",
classifier 3!
3 years ago
"execution_count": 63,
notebooks for classification
3 years ago
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
classifier 3!
3 years ago
"Accuracy (train) for Linear SVC: 79.7% \n",
" precision recall f1-score support\n",
"\n",
" chinese 0.71 0.73 0.72 232\n",
" indian 0.91 0.88 0.89 251\n",
" japanese 0.76 0.78 0.77 239\n",
" korean 0.86 0.75 0.80 244\n",
" thai 0.76 0.84 0.80 233\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 KNN classifier: 72.9% \n",
" precision recall f1-score support\n",
"\n",
" chinese 0.62 0.68 0.65 232\n",
" indian 0.87 0.82 0.85 251\n",
" japanese 0.62 0.83 0.71 239\n",
" korean 0.92 0.55 0.68 244\n",
" thai 0.73 0.76 0.75 233\n",
"\n",
" accuracy 0.73 1199\n",
" macro avg 0.75 0.73 0.73 1199\n",
"weighted avg 0.76 0.73 0.73 1199\n",
"\n",
"Accuracy (train) for SVC: 81.8% \n",
" precision recall f1-score support\n",
"\n",
" chinese 0.78 0.71 0.74 232\n",
" indian 0.92 0.90 0.91 251\n",
" japanese 0.79 0.80 0.80 239\n",
" korean 0.85 0.78 0.82 244\n",
" thai 0.75 0.89 0.81 233\n",
"\n",
" accuracy 0.82 1199\n",
" macro avg 0.82 0.82 0.82 1199\n",
"weighted avg 0.82 0.82 0.82 1199\n",
"\n",
"Accuracy (train) for RFST: 83.3% \n",
" precision recall f1-score support\n",
"\n",
" chinese 0.80 0.75 0.77 232\n",
" indian 0.91 0.92 0.91 251\n",
" japanese 0.81 0.82 0.82 239\n",
" korean 0.85 0.81 0.83 244\n",
" thai 0.79 0.86 0.82 233\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: 70.8% \n",
" precision recall f1-score support\n",
"\n",
" chinese 0.60 0.45 0.51 232\n",
" indian 0.90 0.81 0.85 251\n",
" japanese 0.65 0.72 0.68 239\n",
" korean 0.72 0.76 0.74 244\n",
" thai 0.67 0.79 0.72 233\n",
"\n",
" accuracy 0.71 1199\n",
" macro avg 0.71 0.71 0.70 1199\n",
"weighted avg 0.71 0.71 0.70 1199\n",
"\n"
notebooks for classification
3 years ago
]
}
],
"source": [
classifier 3!
3 years ago
"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))"
notebooks for classification
3 years ago
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"interpreter": {
base state for notebooks - classification 3
3 years ago
"hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
notebooks for classification
3 years ago
},
"kernelspec": {
classifier 3!
3 years ago
"name": "python37364bit8d3b438fb5fc4430a93ac2cb74d693a7",
"display_name": "Python 3.7.3 64-bit",
"language": "python"
notebooks for classification
3 years ago
},
"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
}