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.
ML-For-Beginners/4-Classification/2-Classifiers-1/solution/notebook.ipynb

268 lines
15 KiB

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.

{
"cells": [
{
"source": [
"# Build Classification Models"
],
"cell_type": "markdown",
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 1,
"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": 1
}
],
"source": [
"import pandas as pd\n",
"cuisines_df = pd.read_csv(\"../../data/cleaned_cuisine.csv\")\n",
"cuisines_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"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": 3,
"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": 3
}
],
"source": [
"cuisines_label_df = cuisines_df['cuisine']\n",
"cuisines_label_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"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": 4
}
],
"source": [
"cuisines_feature_df = cuisines_df.drop(['Unnamed: 0', 'cuisine'], axis=1)\n",
"cuisines_feature_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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": 6,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Accuracy is 0.8181818181818182\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": 7,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"ingredients: Index(['artemisia', 'black_pepper', 'mushroom', 'shiitake', 'soy_sauce',\n 'vegetable_oil'],\n dtype='object')\ncuisine: korean\n"
]
}
],
"source": [
"# test an item\n",
"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": 8,
"metadata": {},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" 0\n",
"korean 0.392231\n",
"chinese 0.372872\n",
"japanese 0.218825\n",
"thai 0.013427\n",
"indian 0.002645"
],
"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>korean</th>\n <td>0.392231</td>\n </tr>\n <tr>\n <th>chinese</th>\n <td>0.372872</td>\n </tr>\n <tr>\n <th>japanese</th>\n <td>0.218825</td>\n </tr>\n <tr>\n <th>thai</th>\n <td>0.013427</td>\n </tr>\n <tr>\n <th>indian</th>\n <td>0.002645</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"metadata": {},
"execution_count": 8
}
],
"source": [
"#rehsape to 2d array and transpose\n",
"test= X_test.iloc[50].values.reshape(-1, 1).T\n",
"# predict with score\n",
"proba = model.predict_proba(test)\n",
"classes = model.classes_\n",
"# create df with classes and scores\n",
"resultdf = pd.DataFrame(data=proba, columns=classes)\n",
"\n",
"# create df to show results\n",
"topPrediction = resultdf.T.sort_values(by=[0], ascending = [False])\n",
"topPrediction.head()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" precision recall f1-score support\n\n chinese 0.75 0.73 0.74 223\n indian 0.93 0.88 0.90 255\n japanese 0.78 0.78 0.78 253\n korean 0.87 0.86 0.86 236\n thai 0.76 0.84 0.80 232\n\n accuracy 0.82 1199\n macro avg 0.82 0.82 0.82 1199\nweighted avg 0.82 0.82 0.82 1199\n\n"
]
}
],
"source": [
"y_pred = model.predict(X_test)\r\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
}