369 lines
16 KiB
Text
369 lines
16 KiB
Text
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "530f620c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn.datasets import fetch_openml\n",
|
|
"from sklearn import model_selection\n",
|
|
"from sklearn import neighbors\n",
|
|
"import sklearn\n",
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"mnist = fetch_openml('mnist_784',as_frame=False)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "eb2c4496",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Dataset : [[0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" ...\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]]\n",
|
|
"Etiquettes : ['1' '3' '4' ... '5' '1' '2']\n",
|
|
"Prédiction : ['6' '7' '1' '4' '2' '7' '6' '6' '4' '9' '8' '4' '0' '0' '6' '8' '5' '0'\n",
|
|
" '9' '6' '5' '0' '7' '7' '0' '7' '6' '1' '0' '1' '6' '6' '5' '8' '5' '6'\n",
|
|
" '6' '5' '0' '7' '7' '5' '2' '7' '3' '2' '2' '6' '0' '0' '5' '8' '2' '4'\n",
|
|
" '1' '0' '9' '6' '3' '7' '6' '3' '9' '4' '0' '0' '8' '8' '0' '6' '7' '1'\n",
|
|
" '8' '3' '1' '6' '9' '1' '8' '0' '2' '0' '4' '5' '9' '3' '4' '3' '6' '3'\n",
|
|
" '2' '3' '8' '0' '8' '6' '1' '7' '3' '8' '4' '2' '0' '7' '9' '4' '0' '2'\n",
|
|
" '2' '0' '2' '2' '3' '0' '0' '0' '6' '8' '2' '4' '3' '7' '2' '6' '8' '4'\n",
|
|
" '3' '8' '8' '0' '4' '6' '1' '0' '4' '6' '6' '0' '0' '6' '1' '6' '5' '5'\n",
|
|
" '1' '5' '8' '2' '6' '4' '7' '5' '3' '2' '5' '8' '5' '2' '2' '3' '0' '3'\n",
|
|
" '6' '1' '4' '8' '1' '7' '7' '5' '9' '1' '3' '5' '0' '7' '8' '6' '5' '0'\n",
|
|
" '6' '6' '8' '5' '9' '5' '3' '9' '7' '4' '9' '0' '1' '5' '3' '3' '6' '1'\n",
|
|
" '1' '1' '8' '7' '7' '1' '7' '4' '1' '1' '3' '8' '4' '4' '3' '9' '8' '4'\n",
|
|
" '0' '4' '4' '9' '6' '0' '6' '0' '3' '8' '8' '0' '9' '1' '4' '4' '2' '1'\n",
|
|
" '5' '7' '5' '0' '7' '6' '0' '4' '5' '7' '5' '9' '4' '3' '4' '4' '0' '5'\n",
|
|
" '0' '0' '1' '9' '1' '7' '3' '4' '6' '0' '5' '9' '6' '1' '1' '5' '6' '5'\n",
|
|
" '2' '9' '4' '3' '4' '1' '0' '0' '4' '2' '1' '7' '1' '4' '1' '3' '9' '2'\n",
|
|
" '0' '8' '7' '7' '4' '4' '7' '1' '8' '7' '1' '4' '6' '9' '2' '7' '1' '4'\n",
|
|
" '5' '1' '1' '4' '2' '7' '3' '8' '5' '8' '3' '3' '4' '7' '2' '1' '4' '9'\n",
|
|
" '9' '4' '7' '9' '3' '4' '9' '7' '1' '0' '7' '7' '3' '8' '4' '6' '1' '3'\n",
|
|
" '5' '5' '4' '9' '6' '0' '1' '1' '0' '0' '0' '3' '2' '7' '9' '8' '0' '3'\n",
|
|
" '6' '1' '9' '4' '0' '1' '0' '0' '1' '6' '9' '6' '3' '8' '2' '5' '9' '5'\n",
|
|
" '1' '3' '7' '0' '9' '3' '2' '6' '8' '5' '1' '5' '4' '1' '4' '1' '1' '3'\n",
|
|
" '1' '5' '7' '2' '3' '2' '6' '1' '2' '6' '3' '8' '7' '3' '3' '9' '8' '0'\n",
|
|
" '4' '3' '7' '7' '9' '3' '9' '8' '7' '8' '0' '4' '8' '8' '0' '4' '1' '5'\n",
|
|
" '1' '2' '1' '3' '5' '4' '9' '8' '1' '3' '1' '5' '8' '4' '8' '2' '9' '8'\n",
|
|
" '2' '3' '6' '3' '5' '2' '4' '0' '1' '0' '1' '8' '9' '9' '6' '2' '4' '1'\n",
|
|
" '5' '6' '7' '7' '1' '5' '0' '2' '6' '5' '0' '3' '2' '8' '8' '9' '7' '9'\n",
|
|
" '4' '4' '1' '9' '7' '8' '2' '1' '9' '6' '2' '4' '8' '7' '8' '9' '9' '4'\n",
|
|
" '6' '9' '9' '5' '6' '9' '9' '8' '5' '5' '6' '4' '6' '8' '8' '7' '6' '0'\n",
|
|
" '0' '9' '2' '3' '7' '7' '1' '5' '9' '1' '9' '9' '1' '4' '1' '9' '6' '9'\n",
|
|
" '0' '9' '4' '6' '1' '0' '7' '0' '8' '9' '7' '3' '8' '2' '3' '0' '2' '8'\n",
|
|
" '3' '1' '7' '0' '2' '1' '0' '4' '2' '0' '8' '1' '5' '2' '4' '5' '0' '9'\n",
|
|
" '8' '1' '3' '9' '8' '7' '2' '4' '6' '2' '3' '9' '1' '8' '2' '1' '9' '0'\n",
|
|
" '2' '4' '0' '9' '1' '4' '1' '3' '2' '4' '9' '5' '0' '2' '2' '1' '1' '7'\n",
|
|
" '6' '8' '4' '9' '7' '7' '9' '4' '2' '3' '8' '1' '3' '5' '7' '9' '2' '0'\n",
|
|
" '4' '8' '1' '6' '1' '7' '9' '6' '3' '6' '0' '0' '4' '7' '1' '1' '1' '4'\n",
|
|
" '5' '6' '6' '1' '7' '6' '1' '7' '6' '1' '1' '2' '0' '8' '6' '1' '4' '3'\n",
|
|
" '3' '6' '8' '7' '1' '1' '1' '4' '3' '3' '2' '6' '3' '3' '8' '8' '3' '1'\n",
|
|
" '8' '6' '6' '8' '8' '9' '6' '7' '6' '7' '8' '9' '1' '8' '3' '9' '5' '0'\n",
|
|
" '6' '6' '9' '3' '1' '2' '5' '5' '0' '9' '5' '9' '0' '0' '6' '1' '8' '5'\n",
|
|
" '0' '2' '2' '8' '3' '9' '7' '2' '7' '6' '2' '8' '6' '8' '8' '0' '2' '0'\n",
|
|
" '6' '2' '7' '7' '3' '7' '2' '7' '1' '7' '9' '3' '4' '7' '7' '9' '9' '2'\n",
|
|
" '5' '8' '3' '7' '7' '2' '1' '7' '1' '1' '9' '9' '3' '0' '9' '4' '9' '0'\n",
|
|
" '7' '6' '7' '7' '7' '7' '9' '7' '8' '1' '1' '6' '2' '6' '3' '8' '2' '8'\n",
|
|
" '1' '5' '7' '0' '8' '3' '2' '7' '5' '1' '5' '3' '5' '2' '1' '7' '6' '0'\n",
|
|
" '2' '6' '3' '2' '6' '0' '6' '2' '3' '9' '8' '6' '4' '9' '1' '3' '0' '4'\n",
|
|
" '2' '3' '8' '1' '9' '0' '3' '5' '4' '5' '3' '2' '5' '0' '1' '1' '8' '3'\n",
|
|
" '5' '6' '2' '1' '9' '3' '0' '4' '5' '9' '7' '2' '2' '1' '2' '1' '1' '5'\n",
|
|
" '0' '9' '3' '7' '1' '9' '6' '5' '1' '6' '0' '1' '1' '6' '5' '8' '2' '2'\n",
|
|
" '1' '8' '9' '7' '6' '8' '4' '5' '2' '3' '0' '7' '6' '0' '6' '6' '6' '0'\n",
|
|
" '8' '8' '3' '4' '0' '9' '7' '5' '1' '1' '1' '4' '6' '7' '9' '6' '3' '9'\n",
|
|
" '3' '9' '1' '9' '6' '4' '5' '4' '7' '0' '1' '9' '4' '8' '4' '6' '1' '8'\n",
|
|
" '5' '6' '5' '1' '2' '7' '9' '5' '8' '0' '8' '8' '3' '2' '9' '4' '4' '8'\n",
|
|
" '3' '0' '6' '5' '9' '7' '0' '0' '9' '7' '0' '3' '2' '1' '0' '5' '6' '4'\n",
|
|
" '0' '4' '6' '9' '3' '0' '4' '1' '5' '6' '3' '6' '9' '1' '5' '6' '3' '0'\n",
|
|
" '1' '6' '1' '0' '6' '2' '1' '7' '1' '9']\n",
|
|
"Probabilités : [[0. 0. 0. ... 0. 0. 0. ]\n",
|
|
" [0. 0. 0. ... 1. 0. 0. ]\n",
|
|
" [0. 1. 0. ... 0. 0. 0. ]\n",
|
|
" ...\n",
|
|
" [0. 0. 0. ... 1. 0. 0. ]\n",
|
|
" [0. 0.4 0. ... 0.1 0. 0.3]\n",
|
|
" [0. 0. 0. ... 0.1 0. 0.9]]\n",
|
|
"Classe image 4 : 9\n",
|
|
"Classe prédite image 4 : 4\n",
|
|
"Score échantillon de test : 0.912\n",
|
|
"Score données apprentissage : 0.94325\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"rand_indexes = np.random.randint(70000, size=5000)\n",
|
|
"\n",
|
|
"data = mnist.data[rand_indexes]\n",
|
|
"print(\"Dataset : \", data)\n",
|
|
"target = mnist.target[rand_indexes]\n",
|
|
"print(\"Etiquettes : \", target)\n",
|
|
"\n",
|
|
"# xtrain data set d'entraînement et ytrain étiquettes de xtrain\n",
|
|
"# xtest dataset de prédiction et ytest étiquettes de xtest\n",
|
|
"xtrain, xtest, ytrain, ytest = model_selection.train_test_split(data, target,train_size=0.8)\n",
|
|
"\n",
|
|
"n_neighbors = 10\n",
|
|
"clf = neighbors.KNeighborsClassifier(n_neighbors)\n",
|
|
"# On entraîne l'algorithme sur xtrain et ytrain\n",
|
|
"clf.fit(xtrain, ytrain)\n",
|
|
"# On prédit sur xtest\n",
|
|
"pred = clf.predict(xtest)\n",
|
|
"print(\"Prédiction : \", pred)\n",
|
|
"# Probabilités des prédictions sur xtest\n",
|
|
"pred_proba = clf.predict_proba(xtest)\n",
|
|
"print(\"Probabilités : \", pred_proba)\n",
|
|
"# On calcule le score obtenu sur xtest avec les étiquettes ytest\n",
|
|
"score = clf.score(xtest, ytest)\n",
|
|
"print(\"Classe image 4 : \", target[3])\n",
|
|
"print(\"Classe prédite image 4 : \", pred[3])\n",
|
|
"print(\"Score échantillon de test : \", score)\n",
|
|
"\n",
|
|
"scoreApp = clf.score(xtrain, ytrain)\n",
|
|
"print(\"Score données apprentissage : \", scoreApp)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "90db6e29",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Dataset : [[0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" ...\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]]\n",
|
|
"Etiquettes : ['9' '9' '8' ... '9' '4' '6']\n",
|
|
"[0.92, 0.922, 0.93, 0.966, 0.924, 0.922, 0.922, 0.896, 0.92, 0.91, 0.916, 0.94, 0.938, 0.938, 0.926, 0.936, 0.932, 0.932, 0.934, 0.938, 0.922, 0.934, 0.96, 0.926, 0.942, 0.934, 0.908, 0.926, 0.92, 0.936, 0.932, 0.924, 0.922, 0.938, 0.938, 0.916, 0.932, 0.96, 0.942, 0.922, 0.926, 0.938, 0.936, 0.924, 0.938, 0.946, 0.922, 0.928, 0.912, 0.908, 0.916, 0.932, 0.932, 0.93, 0.92, 0.928, 0.908, 0.932, 0.918, 0.938, 0.92, 0.93, 0.938, 0.924, 0.924, 0.932, 0.916, 0.916, 0.934, 0.928, 0.924, 0.94, 0.942, 0.926, 0.924, 0.912, 0.93, 0.906, 0.894, 0.922, 0.924, 0.912, 0.906, 0.942, 0.95, 0.924, 0.926, 0.92, 0.92, 0.9, 0.918, 0.908, 0.93, 0.942, 0.916, 0.934, 0.916, 0.92, 0.91, 0.918, 0.93, 0.918, 0.916, 0.894, 0.934, 0.926, 0.934, 0.91, 0.9, 0.914, 0.928, 0.918, 0.924, 0.916, 0.908, 0.904, 0.922, 0.912, 0.92, 0.914, 0.926, 0.906, 0.902, 0.914, 0.9, 0.936, 0.906, 0.942, 0.922, 0.906]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.model_selection import KFold\n",
|
|
"\n",
|
|
"rand_indexes = np.random.randint(70000, size=5000)\n",
|
|
"\n",
|
|
"data = mnist.data[rand_indexes]\n",
|
|
"print(\"Dataset : \", data)\n",
|
|
"target = mnist.target[rand_indexes]\n",
|
|
"print(\"Etiquettes : \", target)\n",
|
|
"\n",
|
|
"# xtrain data set d'entraînement et ytrain étiquettes de xtrain\n",
|
|
"# xtest dataset de prédiction et ytest étiquettes de xtest\n",
|
|
"# xtrain, xtest, ytrain, ytest = model_selection.train_test_split(data, target,train_size=0.8)\n",
|
|
"\n",
|
|
"kf = KFold(n_splits=10, random_state=None, shuffle=True)\n",
|
|
"scores = []\n",
|
|
"\n",
|
|
"for k in range(2,15):\n",
|
|
" \n",
|
|
" for train_index, test_index in kf.split(data):\n",
|
|
"# print(\"TRAIN:\", train_index, \"TEST:\", test_index)\n",
|
|
" X_train, X_test = data[train_index], data[test_index]\n",
|
|
" y_train, y_test = target[train_index], target[test_index]\n",
|
|
" \n",
|
|
" clf = neighbors.KNeighborsClassifier(k)\n",
|
|
" # On entraîne l'algorithme sur xtrain et ytrain\n",
|
|
" clf.fit(X_train, y_train)\n",
|
|
" # On prédit sur xtest\n",
|
|
" pred = clf.predict(X_test)\n",
|
|
"# print(\"Prédiction : \", pred)\n",
|
|
" # Probabilités des prédictions sur xtest\n",
|
|
" pred_proba = clf.predict_proba(X_test)\n",
|
|
"# print(\"Probabilités : \", pred_proba)\n",
|
|
" # On calcule le score obtenu sur xtest avec les étiquettes ytest\n",
|
|
" score = clf.score(X_test, y_test)\n",
|
|
" scores += [score]\n",
|
|
"# print(\"Classe image 4 : \", target[3])\n",
|
|
"# print(\"Classe prédite image 4 : \", pred[3])\n",
|
|
"# print(\"Score échantillon de test : \", score)\n",
|
|
" scoreApp = clf.score(X_train, y_train)\n",
|
|
"# print(\"Score données apprentissage : \", scoreApp)\n",
|
|
"print(scores)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "bf91b914",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"2 : 0.9232000000000001\n",
|
|
"3 : 0.933\n",
|
|
"4 : 0.9308\n",
|
|
"5 : 0.9326000000000001\n",
|
|
"6 : 0.9300000000000002\n",
|
|
"7 : 0.922888888888889\n",
|
|
"8 : 0.9266666666666666\n",
|
|
"9 : 0.9273333333333333\n",
|
|
"10 : 0.9206666666666666\n",
|
|
"11 : 0.9208888888888889\n",
|
|
"12 : 0.9197777777777778\n",
|
|
"13 : 0.9175555555555555\n",
|
|
"14 : 0.9162222222222223\n",
|
|
"15 : 0.9148888888888889\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"nice_scores = np.array_split(scores, 14)\n",
|
|
"for i in range (0,14):\n",
|
|
" print (i+2, \" : \", nice_scores[i].mean())\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "cc24e898",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Dataset : [[0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" ...\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]\n",
|
|
" [0. 0. 0. ... 0. 0. 0.]]\n",
|
|
"Etiquettes : ['0' '0' '5' ... '9' '8' '6']\n",
|
|
"Temps d'entraînement : 0.002\n",
|
|
"Temps de prédiction : 0.338\n",
|
|
"Temps total : 0.34\n",
|
|
"Temps d'entraînement : 0.003\n",
|
|
"Temps de prédiction : 0.31\n",
|
|
"Temps total : 0.313\n",
|
|
"Temps d'entraînement : 0.002\n",
|
|
"Temps de prédiction : 0.328\n",
|
|
"Temps total : 0.33\n",
|
|
"Temps d'entraînement : 0.003\n",
|
|
"Temps de prédiction : 0.305\n",
|
|
"Temps total : 0.308\n",
|
|
"Temps d'entraînement : 0.003\n",
|
|
"Temps de prédiction : 0.254\n",
|
|
"Temps total : 0.257\n",
|
|
"Temps d'entraînement : 0.003\n",
|
|
"Temps de prédiction : 0.244\n",
|
|
"Temps total : 0.247\n",
|
|
"Temps d'entraînement : 0.004\n",
|
|
"Temps de prédiction : 0.203\n",
|
|
"Temps total : 0.207\n",
|
|
"3 : 0.9045714285714286\n",
|
|
"4 : 0.91\n",
|
|
"5 : 0.9168\n",
|
|
"6 : 0.925\n",
|
|
"7 : 0.934\n",
|
|
"8 : 0.922\n",
|
|
"9 : 0.952\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.model_selection import KFold\n",
|
|
"import time\n",
|
|
"\n",
|
|
"rand_indexes = np.random.randint(70000, size=5000)\n",
|
|
"\n",
|
|
"data = mnist.data[rand_indexes]\n",
|
|
"print(\"Dataset : \", data)\n",
|
|
"target = mnist.target[rand_indexes]\n",
|
|
"print(\"Etiquettes : \", target)\n",
|
|
"\n",
|
|
"# xtrain data set d'entraînement et ytrain étiquettes de xtrain\n",
|
|
"# xtest dataset de prédiction et ytest étiquettes de xtest\n",
|
|
"\n",
|
|
"scores = []\n",
|
|
"\n",
|
|
"for j in range (3, 10):\n",
|
|
" xtrain, xtest, ytrain, ytest = model_selection.train_test_split(data, target,train_size=(j/10))\n",
|
|
" \n",
|
|
" t1 = round(time.time(),3)\n",
|
|
" clf = neighbors.KNeighborsClassifier(n_neighbors=3,p = 2, n_jobs=-1)\n",
|
|
" # On entraîne l'algorithme sur xtrain et ytrain\n",
|
|
" clf.fit(xtrain, ytrain)\n",
|
|
" t2 = round(time.time(),3)\n",
|
|
" # On prédit sur xtest\n",
|
|
" pred = clf.predict(xtest)\n",
|
|
" t3 = round(time.time(),3)\n",
|
|
" \n",
|
|
" print(\"Temps d'entraînement : \", round(t2-t1,3))\n",
|
|
" print(\"Temps de prédiction : \", round(t3-t2,3))\n",
|
|
" print(\"Temps total : \", round(t3-t1,3))\n",
|
|
"# print(\"Prédiction : \", pred)\n",
|
|
" # Probabilités des prédictions sur xtest\n",
|
|
" pred_proba = clf.predict_proba(xtest)\n",
|
|
"# print(\"Probabilités : \", pred_proba)\n",
|
|
" # On calcule le score obtenu sur xtest avec les étiquettes ytest\n",
|
|
" score = clf.score(xtest, ytest)\n",
|
|
" scores += [score]\n",
|
|
"# print(\"Classe image 4 : \", target[3])\n",
|
|
"# print(\"Classe prédite image 4 : \", pred[3])\n",
|
|
"# print(\"Score échantillon de test : \", score)\n",
|
|
" scoreApp = clf.score(xtrain, ytrain)\n",
|
|
"# print(\"Score données apprentissage : \", scoreApp)\n",
|
|
"\n",
|
|
"# nice_scores = np.array_split(scores, 7)\n",
|
|
"# print(scores)\n",
|
|
"n = 3\n",
|
|
"for i in scores:\n",
|
|
" print (n, \" : \", i)\n",
|
|
" n += 1"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "cbb5eda6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"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": "3.8.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|