],
"source": [
"X, y = make_blobs(n_samples=300, centers =3, cluster_std=3.5,random_state=42)\n",
"plt.figure(figsize=(8, 6))\n",
"ax=plt.subplot(111)\n",
"ax.scatter(X[:, 0], X[:, 1], c=y, s=40, cmap='viridis')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "URtzpJITZ04e"
},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4,\n",
"random_state=0)"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "MHhIZTnVba0U"
},
"source": [
"## 1."
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "MNNnB5IAbaUA"
},
"outputs": [],
"source": [
"k = 3\n",
"\n",
"epsilon = 0.00001\n",
"max_iter = 10000\n",
"\n",
"\n",
"def dist(row_a, row_b):\n",
" d = 0\n",
" for i in range(len(row_a)):\n",
"    d += (row_a[i] - row_b[i]) ** 2\n",
" d = math.sqrt(d)\n",
" return d\n",
"\n",
"df = pd.DataFrame(X_train)\n",
"df.reset_index()\n",
"\n",
"n_test = len(X_test)\n",
"\n",
"df[\"pseudo\"] = y_train\n",
"\n",
"centroids = df.groupby(\"pseudo\").agg(np.mean)\n",
"centroids.reset_index()\n",
"\n",
"\n",
"index = 0\n",
"df_test = None\n",
"while index < max_iter:\n",
" pseudo_labels = []\n",
" for i in range(0, n_test):\n",
"    dis = []\n",
"    for cluster in range(0, k):\n",
"          d = dist(centroids.iloc[cluster,], X_test[i])\n",
"          dis.append(d)\n",
"    pseudo_label = dis.index(min(dis))\n",
"    pseudo_labels.append(pseudo_label)\n",
"\n",
" df_test = pd.DataFrame(X_test)\n",
" df_test[\"pseudo\"] = pseudo_labels\n",
" df3 = df.append(df_test, ignore_index=True)\n",
" centroids_new = df3.groupby(\"pseudo\").agg(np.mean)\n",
" centroids_new.reset_index()\n",
" all_converged = 0\n",
" for i in range(0, len(centroids)):\n",
"    d = dist(centroids.iloc[i, ], centroids_new.iloc[i,])\n",
"    if d < epsilon:\n",
"          all_converged += 1\n",
" if all_converged == k:\n",
"    break\n",
" else:\n",
"    centroids = centroids_new\n",
"\n",
" index += 1\n",
"df_test[\"y\"] = y_test\n",
"df[\"y\"] = y_train\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "rFYcDlko-5Tq"
},
"source": [
"## 2."
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 190
},
"colab_type": "code",
"id": "NN6hYscT8ctk",
"outputId": "def713ac-5095-4e15-de09-9e12f2b663be"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
   "Mean of each cluster:\n"
]
},
{
"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>0</th>\n",
   "    <th>1</th>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>y</th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   " </tr>\n",
   " </thead>\n",
   " <tbody>\n",
   " <tr>\n",
   "    <th>0</th>\n",
   "    <td>-2.836760</td>\n",
   "    <td>9.192985</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>1</th>\n",
   "    <td>4.654930</td>\n",
   "    <td>2.271495</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>2</th>\n",
   "    <td>-6.839723</td>\n",
   "    <td>-7.237148</td>\n",
   " </tr>\n",
   " </tbody>\n",
   "</table>\n",
   "</div>"
   ],
   "text/plain": [
   "       0       1\n",
   "y                \n",
   "0 -2.836760 9.192985\n",
   "1 4.654930 2.271495\n",
   "2 -6.839723 -7.237148"
   ]
},
"execution_count": 42,
"metadata": {
   "tags": []
},
"output_type": "execute_result"
}
],
"source": [
"test_pseudo = df_test[\"pseudo\"]\n",
"del df_test[\"pseudo\"]\n",
"df_test.reset_index()\n",
"mean_mat = df_test.groupby(\"y\").agg(np.mean)\n",
"print(\"Mean of each cluster:\")\n",
"mean_mat"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 190
},
"colab_type": "code",
"id": "aQvDj9dT8p3r",
"outputId": "22cd8019-8c58-4cf2-ee74-f74ad790eb86"
},
"outputs": [
{
"name": "stdout

Project Consider the following synthetic data In [1]: from sklear...