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 'fe8dcd09c8'
${ noResults }
ML-For-Beginners/4-Classification/3-Classifiers-2/notebook.ipynb

585 lines
25 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.

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Build Classification Model"
]
},
{
"cell_type": "code",
"execution_count": 21,
"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": 22,
"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": 22,
"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": 23,
"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": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cuisines_label_df = cuisines_df['cuisine']\n",
"cuisines_label_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 24,
"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": 24,
"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": 25,
"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": 26,
"metadata": {},
"outputs": [],
"source": [
"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",
"}"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy (train) for Linear SVC: 77.8% \n",
" precision recall f1-score support\n",
"\n",
" chinese 0.68 0.75 0.71 260\n",
" indian 0.89 0.86 0.87 258\n",
" japanese 0.77 0.69 0.73 219\n",
" korean 0.85 0.77 0.81 221\n",
" thai 0.72 0.81 0.76 241\n",
"\n",
" accuracy 0.78 1199\n",
" macro avg 0.78 0.78 0.78 1199\n",
"weighted avg 0.78 0.78 0.78 1199\n",
"\n"
]
},
{
"ename": "AttributeError",
"evalue": "'Flags' object has no attribute 'c_contiguous'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32md:\\DEV WORK\\Data Science Library\\ML-For-Beginners\\4-Classification\\3-Classifiers-2\\notebook.ipynb Cell 8\u001b[0m line \u001b[0;36m6\n\u001b[0;32m <a href='vscode-notebook-cell:/d%3A/DEV%20WORK/Data%20Science%20Library/ML-For-Beginners/4-Classification/3-Classifiers-2/notebook.ipynb#X11sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m \u001b[39mfor\u001b[39;00m index, (name, classifier) \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(classifiers\u001b[39m.\u001b[39mitems()):\n\u001b[0;32m <a href='vscode-notebook-cell:/d%3A/DEV%20WORK/Data%20Science%20Library/ML-For-Beginners/4-Classification/3-Classifiers-2/notebook.ipynb#X11sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m classifier\u001b[39m.\u001b[39mfit(X_train, np\u001b[39m.\u001b[39mravel(y_train))\n\u001b[1;32m----> <a href='vscode-notebook-cell:/d%3A/DEV%20WORK/Data%20Science%20Library/ML-For-Beginners/4-Classification/3-Classifiers-2/notebook.ipynb#X11sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m y_pred \u001b[39m=\u001b[39m classifier\u001b[39m.\u001b[39;49mpredict(X_test)\n\u001b[0;32m <a href='vscode-notebook-cell:/d%3A/DEV%20WORK/Data%20Science%20Library/ML-For-Beginners/4-Classification/3-Classifiers-2/notebook.ipynb#X11sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m accuracy \u001b[39m=\u001b[39m accuracy_score(y_test, y_pred)\n\u001b[0;32m <a href='vscode-notebook-cell:/d%3A/DEV%20WORK/Data%20Science%20Library/ML-For-Beginners/4-Classification/3-Classifiers-2/notebook.ipynb#X11sZmlsZQ%3D%3D?line=7'>8</a>\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mAccuracy (train) for \u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m: \u001b[39m\u001b[39m%0.1f\u001b[39;00m\u001b[39m%%\u001b[39;00m\u001b[39m \u001b[39m\u001b[39m\"\u001b[39m \u001b[39m%\u001b[39m (name, accuracy \u001b[39m*\u001b[39m \u001b[39m100\u001b[39m))\n",
"File \u001b[1;32md:\\DEV WORK\\Data Science Library\\ML-For-Beginners\\.venv\\lib\\site-packages\\sklearn\\neighbors\\_classification.py:246\u001b[0m, in \u001b[0;36mKNeighborsClassifier.predict\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m 244\u001b[0m check_is_fitted(\u001b[39mself\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39m_fit_method\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m 245\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mweights \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39muniform\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[1;32m--> 246\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_fit_method \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mbrute\u001b[39m\u001b[39m\"\u001b[39m \u001b[39mand\u001b[39;00m ArgKminClassMode\u001b[39m.\u001b[39;49mis_usable_for(\n\u001b[0;32m 247\u001b[0m X, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_fit_X, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmetric\n\u001b[0;32m 248\u001b[0m ):\n\u001b[0;32m 249\u001b[0m probabilities \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpredict_proba(X)\n\u001b[0;32m 250\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39moutputs_2d_:\n",
"File \u001b[1;32md:\\DEV WORK\\Data Science Library\\ML-For-Beginners\\.venv\\lib\\site-packages\\sklearn\\metrics\\_pairwise_distances_reduction\\_dispatcher.py:471\u001b[0m, in \u001b[0;36mArgKminClassMode.is_usable_for\u001b[1;34m(cls, X, Y, metric)\u001b[0m\n\u001b[0;32m 448\u001b[0m \u001b[39m@classmethod\u001b[39m\n\u001b[0;32m 449\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mis_usable_for\u001b[39m(\u001b[39mcls\u001b[39m, X, Y, metric) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m \u001b[39mbool\u001b[39m:\n\u001b[0;32m 450\u001b[0m \u001b[39m \u001b[39m\u001b[39m\"\"\"Return True if the dispatcher can be used for the given parameters.\u001b[39;00m\n\u001b[0;32m 451\u001b[0m \n\u001b[0;32m 452\u001b[0m \u001b[39m Parameters\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 468\u001b[0m \u001b[39m True if the PairwiseDistancesReduction can be used, else False.\u001b[39;00m\n\u001b[0;32m 469\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[0;32m 470\u001b[0m \u001b[39mreturn\u001b[39;00m (\n\u001b[1;32m--> 471\u001b[0m ArgKmin\u001b[39m.\u001b[39;49mis_usable_for(X, Y, metric)\n\u001b[0;32m 472\u001b[0m \u001b[39m# TODO: Support CSR matrices.\u001b[39;00m\n\u001b[0;32m 473\u001b[0m \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m issparse(X)\n\u001b[0;32m 474\u001b[0m \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m issparse(Y)\n\u001b[0;32m 475\u001b[0m \u001b[39m# TODO: implement Euclidean specialization with GEMM.\u001b[39;00m\n\u001b[0;32m 476\u001b[0m \u001b[39mand\u001b[39;00m metric \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m (\u001b[39m\"\u001b[39m\u001b[39meuclidean\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39msqeuclidean\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m 477\u001b[0m )\n",
"File \u001b[1;32md:\\DEV WORK\\Data Science Library\\ML-For-Beginners\\.venv\\lib\\site-packages\\sklearn\\metrics\\_pairwise_distances_reduction\\_dispatcher.py:115\u001b[0m, in \u001b[0;36mBaseDistancesReductionDispatcher.is_usable_for\u001b[1;34m(cls, X, Y, metric)\u001b[0m\n\u001b[0;32m 101\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mis_valid_sparse_matrix\u001b[39m(X):\n\u001b[0;32m 102\u001b[0m \u001b[39mreturn\u001b[39;00m (\n\u001b[0;32m 103\u001b[0m isspmatrix_csr(X)\n\u001b[0;32m 104\u001b[0m \u001b[39mand\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 110\u001b[0m X\u001b[39m.\u001b[39mindices\u001b[39m.\u001b[39mdtype \u001b[39m==\u001b[39m X\u001b[39m.\u001b[39mindptr\u001b[39m.\u001b[39mdtype \u001b[39m==\u001b[39m np\u001b[39m.\u001b[39mint32\n\u001b[0;32m 111\u001b[0m )\n\u001b[0;32m 113\u001b[0m is_usable \u001b[39m=\u001b[39m (\n\u001b[0;32m 114\u001b[0m get_config()\u001b[39m.\u001b[39mget(\u001b[39m\"\u001b[39m\u001b[39menable_cython_pairwise_dist\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39mTrue\u001b[39;00m)\n\u001b[1;32m--> 115\u001b[0m \u001b[39mand\u001b[39;00m (is_numpy_c_ordered(X) \u001b[39mor\u001b[39;00m is_valid_sparse_matrix(X))\n\u001b[0;32m 116\u001b[0m \u001b[39mand\u001b[39;00m (is_numpy_c_ordered(Y) \u001b[39mor\u001b[39;00m is_valid_sparse_matrix(Y))\n\u001b[0;32m 117\u001b[0m \u001b[39mand\u001b[39;00m X\u001b[39m.\u001b[39mdtype \u001b[39m==\u001b[39m Y\u001b[39m.\u001b[39mdtype\n\u001b[0;32m 118\u001b[0m \u001b[39mand\u001b[39;00m X\u001b[39m.\u001b[39mdtype \u001b[39min\u001b[39;00m (np\u001b[39m.\u001b[39mfloat32, np\u001b[39m.\u001b[39mfloat64)\n\u001b[0;32m 119\u001b[0m \u001b[39mand\u001b[39;00m metric \u001b[39min\u001b[39;00m \u001b[39mcls\u001b[39m\u001b[39m.\u001b[39mvalid_metrics()\n\u001b[0;32m 120\u001b[0m )\n\u001b[0;32m 122\u001b[0m \u001b[39mreturn\u001b[39;00m is_usable\n",
"File \u001b[1;32md:\\DEV WORK\\Data Science Library\\ML-For-Beginners\\.venv\\lib\\site-packages\\sklearn\\metrics\\_pairwise_distances_reduction\\_dispatcher.py:99\u001b[0m, in \u001b[0;36mBaseDistancesReductionDispatcher.is_usable_for.<locals>.is_numpy_c_ordered\u001b[1;34m(X)\u001b[0m\n\u001b[0;32m 98\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mis_numpy_c_ordered\u001b[39m(X):\n\u001b[1;32m---> 99\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mhasattr\u001b[39m(X, \u001b[39m\"\u001b[39m\u001b[39mflags\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mand\u001b[39;00m X\u001b[39m.\u001b[39;49mflags\u001b[39m.\u001b[39;49mc_contiguous\n",
"\u001b[1;31mAttributeError\u001b[0m: 'Flags' object has no attribute 'c_contiguous'"
]
}
],
"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))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"interpreter": {
"hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
},
"kernelspec": {
"display_name": "Python 3.7.0 64-bit ('3.7')",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
},
"metadata": {
"interpreter": {
"hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in new issue View Git Blame Copy Permalink