Files
ArtStudies/M2/Advanced Machine Learning/TP3/TP3.ipynb

482 lines
110 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 97,
"id": "e2813538",
"metadata": {},
"outputs": [],
"source": [
"import time\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"from scipy.linalg import svd\n",
"\n",
"from sklearn.datasets import load_svmlight_file\n",
"from sklearn.metrics.pairwise import rbf_kernel\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"rng = np.random.default_rng(42)"
]
},
{
"cell_type": "code",
"execution_count": 98,
"id": "641aeaac",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(49990, 22) (49990,)\n"
]
}
],
"source": [
"X, y = load_svmlight_file(\"./data/ijcnn1.bz2\")\n",
"print(X.shape, y.shape)"
]
},
{
"cell_type": "code",
"execution_count": 99,
"id": "0e003e1e",
"metadata": {},
"outputs": [],
"source": [
"scaler = StandardScaler(with_mean=False)\n",
"X_scaled = scaler.fit_transform(X)"
]
},
{
"cell_type": "code",
"execution_count": 100,
"id": "a3a85d20",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((20000, 22), (29990, 22))"
]
},
"execution_count": 100,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(\n",
" X_scaled,\n",
" y,\n",
" test_size=29990 / 49990,\n",
" random_state=42,\n",
")\n",
"\n",
"X_train.shape, X_test.shape"
]
},
{
"cell_type": "code",
"execution_count": 101,
"id": "b78a08ae",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics import accuracy_score\n",
"from sklearn.svm import LinearSVC\n",
"\n",
"clf = LinearSVC(dual=False, random_state=42)\n",
"\n",
"start_time = time.time()\n",
"clf.fit(X_train, y_train)\n",
"training_time_svc = time.time() - start_time\n",
"y_pred_svc = clf.predict(X_test)\n",
"accuracy_svc = accuracy_score(y_test, y_pred_svc)"
]
},
{
"cell_type": "code",
"execution_count": 102,
"id": "8cb70eb0",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.svm import SVC\n",
"\n",
"clf_rbf = SVC(kernel=\"rbf\", random_state=42)\n",
"\n",
"start_time = time.time()\n",
"clf_rbf.fit(X_train, y_train)\n",
"training_time_rbf = time.time() - start_time\n",
"y_pred_rbf = clf_rbf.predict(X_test)\n",
"accuracy_rbf = accuracy_score(y_test, y_pred_rbf)"
]
},
{
"cell_type": "code",
"execution_count": 103,
"id": "cf96d113",
"metadata": {},
"outputs": [],
"source": [
"def compute_rkf(\n",
" X_train: np.ndarray,\n",
" X_test: np.ndarray,\n",
" c: int = 300,\n",
" gamma: float | None = None,\n",
") -> tuple[np.ndarray, np.ndarray]:\n",
" \"\"\"Compute Random Kitchen Features for RBF kernel approximation.\n",
"\n",
" Args:\n",
" X_train (np.ndarray): Training data of shape (n1, p).\n",
" X_test (np.ndarray): Test data of shape (n2, p).\n",
" c (int): Number of random features to generate.\n",
" gamma (float | None): Kernel coefficient for RBF kernel. If None, defaults to 1/p.\n",
"\n",
" Returns:\n",
" tuple[np.ndarray, np.ndarray]: Transformed training and test data of shapes (n1, c) and (n2, c).\n",
"\n",
" \"\"\"\n",
" p = X_train.shape[1]\n",
"\n",
" if gamma is None:\n",
" gamma = 1 / p\n",
"\n",
" W = rng.normal(0, np.sqrt(2 * gamma), size=(p, c))\n",
" b = rng.uniform(0, 2 * np.pi, size=(1, c))\n",
"\n",
" def transform(X: np.ndarray) -> np.ndarray:\n",
" \"\"\"Transform the input data using Random Kitchen Features.\"\"\"\n",
" return np.sqrt(2 / c) * np.cos(np.dot(X, W) + b)\n",
"\n",
" return transform(X_train), transform(X_test)\n"
]
},
{
"cell_type": "code",
"execution_count": 104,
"id": "d0487ec1",
"metadata": {},
"outputs": [],
"source": [
"Z_train, Z_test = compute_rkf(X_train.toarray(), X_test.toarray(), c=300)\n",
"\n",
"clf_rkf = LinearSVC(dual=False, random_state=42)\n",
"\n",
"start_time = time.time()\n",
"clf_rkf.fit(Z_train, y_train)\n",
"training_time_rkf = time.time() - start_time\n",
"\n",
"y_pred_rkf = clf_rkf.predict(Z_test)\n",
"accuracy_rkf = accuracy_score(y_test, y_pred_rkf)"
]
},
{
"cell_type": "code",
"execution_count": 105,
"id": "bf07c16e",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.microsoft.datawrangler.viewer.v0+json": {
"columns": [
{
"name": "index",
"rawType": "int64",
"type": "integer"
},
{
"name": "Méthode",
"rawType": "object",
"type": "string"
},
{
"name": "Accuracy",
"rawType": "float64",
"type": "float"
},
{
"name": "Temps (s)",
"rawType": "float64",
"type": "float"
}
],
"ref": "5e2536cf-d951-4c4a-9a11-c620b11f6cce",
"rows": [
[
"0",
"Linear SVM (Raw)",
"0.9221407135711904",
"0.08201122283935547"
],
[
"1",
"Full RBF SVM",
"0.9737912637545849",
"1.1328659057617188"
],
[
"2",
"RKF (c=300)",
"0.9551517172390797",
"0.713508129119873"
]
],
"shape": {
"columns": 3,
"rows": 3
}
},
"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>Méthode</th>\n",
" <th>Accuracy</th>\n",
" <th>Temps (s)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Linear SVM (Raw)</td>\n",
" <td>0.922141</td>\n",
" <td>0.082011</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Full RBF SVM</td>\n",
" <td>0.973791</td>\n",
" <td>1.132866</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>RKF (c=300)</td>\n",
" <td>0.955152</td>\n",
" <td>0.713508</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Méthode Accuracy Temps (s)\n",
"0 Linear SVM (Raw) 0.922141 0.082011\n",
"1 Full RBF SVM 0.973791 1.132866\n",
"2 RKF (c=300) 0.955152 0.713508"
]
},
"execution_count": 105,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results = pd.DataFrame(\n",
" {\n",
" \"Méthode\": [\"Linear SVM (Raw)\", \"Full RBF SVM\", \"RKF (c=300)\"],\n",
" \"Accuracy\": [accuracy_svc, accuracy_rbf, accuracy_rkf],\n",
" \"Temps (s)\": [\n",
" training_time_svc,\n",
" training_time_rbf,\n",
" training_time_rkf,\n",
" ],\n",
" },\n",
")\n",
"\n",
"results\n"
]
},
{
"cell_type": "code",
"execution_count": 106,
"id": "56a3bce6",
"metadata": {},
"outputs": [],
"source": [
"def compute_nystrom(\n",
" X_train: np.ndarray,\n",
" X_test: np.ndarray,\n",
" c: int = 500,\n",
" k: int = 300,\n",
" gamma: float | None = None,\n",
") -> tuple[np.ndarray, np.ndarray]:\n",
" \"\"\"Compute Nystrom features for RBF kernel approximation.\n",
"\n",
" Args:\n",
" X_train (np.ndarray): Training data of shape (n1, p).\n",
" X_test (np.ndarray): Test data of shape (n2, p).\n",
" c (int): Number of landmark points to use.\n",
" k (int): Number of singular vectors to retain.\n",
" gamma (float | None): Kernel coefficient for RBF kernel. If None, defaults to 1/p.\n",
"\n",
" Returns:\n",
" tuple[np.ndarray, np.ndarray]: Transformed training and test data of shapes (n1, k) and (n2, k).\n",
"\n",
" \"\"\"\n",
" n1, p = X_train.shape\n",
" if gamma is None:\n",
" gamma = 1 / p\n",
"\n",
" indices = rng.choice(n1, size=c, replace=True)\n",
" X_subset = X_train[indices]\n",
"\n",
" W = rbf_kernel(X_subset, X_subset, gamma=gamma)\n",
" V, Sigma, _ = svd(W)\n",
"\n",
" Vk = V[:, :k]\n",
" Sigmak = Sigma[:k]\n",
"\n",
" Mk = Vk @ np.diag(1.0 / np.sqrt(Sigmak))\n",
"\n",
" C_train = rbf_kernel(X_train, X_subset, gamma=gamma)\n",
" C_test = rbf_kernel(X_test, X_subset, gamma=gamma)\n",
"\n",
" Z_train = C_train @ Mk\n",
" Z_test = C_test @ Mk\n",
"\n",
" return Z_train, Z_test\n"
]
},
{
"cell_type": "code",
"execution_count": 107,
"id": "2f922cbb",
"metadata": {},
"outputs": [],
"source": [
"c_values = np.arange(20, 650, 50)\n",
"results_list = []\n",
"\n",
"gamma_fixed = 1 / X_train.shape[1]\n",
"\n",
"for c in c_values:\n",
" start = time.time()\n",
" Z_tr_rkf, Z_te_rkf = compute_rkf(X_train.toarray(), X_test.toarray(), c=c, gamma=gamma_fixed)\n",
" clf = LinearSVC(dual=False, random_state=42).fit(Z_tr_rkf, y_train)\n",
" results_list.append(\n",
" {\n",
" \"c\": c,\n",
" \"Méthode\": \"RKF\",\n",
" \"Accuracy\": clf.score(Z_te_rkf, y_test),\n",
" \"Temps (s)\": time.time() - start,\n",
" },\n",
" )\n",
"\n",
" if c > 10: # noqa: PLR2004\n",
" start = time.time()\n",
" Z_tr_nys, Z_te_nys = compute_nystrom(\n",
" X_train, X_test, c=c, k=c - 10, gamma=gamma_fixed,\n",
" )\n",
" clf = LinearSVC(dual=False, random_state=42).fit(Z_tr_nys, y_train)\n",
" results_list.append(\n",
" {\n",
" \"c\": c,\n",
" \"Méthode\": \"Nyström\",\n",
" \"Accuracy\": clf.score(Z_te_nys, y_test),\n",
" \"Temps (s)\": time.time() - start,\n",
" },\n",
" )\n",
"\n",
"df_res = pd.DataFrame(results_list)\n"
]
},
{
"cell_type": "code",
"execution_count": 114,
"id": "199895c4",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1500x500 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig, ax = plt.subplots(1, 2, figsize=(15, 5))\n",
"\n",
"# Accuracy curves\n",
"sns.lineplot(data=df_res, x=\"c\", y=\"Accuracy\", hue=\"Méthode\", marker=\"o\", ax=ax[0])\n",
"ax[0].set_title(\"Évolution de la Précision\")\n",
"ax[0].axhline(y=accuracy_svc, color=\"k\", linestyle=\"-.\", label=\"Linear SVM\")\n",
"ax[0].axhline(y=accuracy_rkf, color=\"g\", linestyle=\"-.\", label=\"RKF\")\n",
"ax[0].axhline(y=accuracy_rbf, color=\"r\", linestyle=\"-.\", label=\"Full RBF SVM\")\n",
"\n",
"handles, labels = ax[0].get_legend_handles_labels()\n",
"ax[0].legend(handles=handles, labels=labels)\n",
"\n",
"# Time curves\n",
"sns.lineplot(data=df_res, x=\"c\", y=\"Temps (s)\", hue=\"Méthode\", marker=\"o\", ax=ax[1])\n",
"ax[1].set_title(\"Évolution du Temps de Calcul\")\n",
"\n",
"ax[1].axhline(y=training_time_svc, color=\"k\", linestyle=\"-.\", label=\"Linear SVM\")\n",
"ax[1].axhline(y=training_time_rkf, color=\"g\", linestyle=\"-.\", label=\"RKF\")\n",
"ax[1].axhline(y=training_time_rbf, color=\"r\", linestyle=\"-.\", label=\"Full RBF SVM\")\n",
"\n",
"handles, labels = ax[1].get_legend_handles_labels()\n",
"ax[1].legend(handles=handles, labels=labels)\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fda0a41c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "studies",
"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": "3.13.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}