{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e1bdbd46-1f35-4373-80ec-727f0e26f009",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.datasets import load_iris\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "327dafe0-68d4-4200-a889-b03bc97a1057",
   "metadata": {},
   "outputs": [],
   "source": [
    "iris = load_iris()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5ced7579-bb9f-4a20-abe2-c0c258ef4073",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = iris.data[:, :1]\n",
    "y = iris.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c8e84e37-e034-4dcb-af3d-03d9cae87a92",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = np.array([tuple(i.tolist()) for i in X], dtype=[(\"col1\", float)])\n",
    "y = np.array([i for i in y], dtype=[(\"col3\", y.dtype)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "fab25223-225c-430b-a58d-368466d7fe02",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = X.reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "50359601-4b0d-4a94-a1c8-44a833b8f4e5",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "17fc4619-c5c0-4beb-81df-81617b1c7a56",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([[(6.3,)],\n",
       "        [(6.5,)],\n",
       "        [(5.6,)],\n",
       "        [(5.7,)],\n",
       "        [(6.4,)]], dtype=[('col1', '<f8')]),\n",
       " array([(1,), (2,), (1,), (1,), (2,)], dtype=[('col3', '<i8')]))"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train[:5], y_train[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "510d7a07-7746-4305-96d6-a74bc5a7f144",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LinearRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "733f81f4-fc25-41a2-8c7d-e6e4abd70143",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression()"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "267ed05e-7285-4873-ae8c-2396f986bf31",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "0dd6f9d6-89d4-461f-9110-601d44126512",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1.22816565, 0.91925051, 2.46382623, 1.15093687, 1.76876716,\n",
       "       0.68756415, 0.84202172, 1.84599594, 1.30539444, 0.99647929,\n",
       "       1.5370808 , 0.22419143, 0.76479293, 0.30142022, 0.45587779])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "6a65cd71-b625-4f31-894d-a4d0403fd1b1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1., 1., 2., 1., 2., 1., 1., 2., 1., 1., 2., 0., 1., 0., 0.])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = np.round(y_pred)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ef5d8327-7ee8-43a6-b4f9-0785e8467d23",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([(1,), (0,), (2,), (1,), (1,), (0,), (1,), (2,), (1,), (1,), (2,),\n",
       "       (0,), (0,), (0,), (0,)], dtype=[('col3', '<i8')])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d01167c5-d4d1-4a67-86df-cc4f88abe421",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_test = np.array([i[0] for i in y_test])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b28aa4ac-87ab-45a4-b5c8-e7b125895c25",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7333333333333333"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test, np.round(y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d5cf8629-f623-4a3e-9400-8d7f6215383e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from joblib import dump, load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "caa6d389-b358-4160-a342-215013c5b2d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['structured_arr_model_1_dim.joblib']"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dump(model, \"structured_arr_model_1_dim.joblib\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f0804a91-46d4-4cec-bd60-bb5f022443bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = load(\"structured_arr_model_1_dim.joblib\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "07584f03-f1da-4014-a539-ca0e033a6356",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1.22816565])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.predict(x_test[:1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "06cf5cbb-0a96-4501-8fa6-bfc680d8aa20",
   "metadata": {},
   "outputs": [],
   "source": [
    "import skops.hub_utils as hub_utils"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "f4349089-88c9-49d2-8b65-351cabb74fd8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[(6.1,)],\n",
       "       [(5.7,)],\n",
       "       [(7.7,)],\n",
       "       [(6. ,)],\n",
       "       [(6.8,)],\n",
       "       [(5.4,)],\n",
       "       [(5.6,)],\n",
       "       [(6.9,)],\n",
       "       [(6.2,)],\n",
       "       [(5.8,)],\n",
       "       [(6.5,)],\n",
       "       [(4.8,)],\n",
       "       [(5.5,)],\n",
       "       [(4.9,)],\n",
       "       [(5.1,)]], dtype=[('col1', '<f8')])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "a4294f1f-5eeb-460f-a872-ba487a229093",
   "metadata": {},
   "outputs": [],
   "source": [
    "!rm -rf /Users/macbookpro/MyProjects/dev/dst\n",
    "!mkdir /Users/macbookpro/MyProjects/dev/dst"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "41a49678-1a01-439d-8f92-29f1884e5f79",
   "metadata": {},
   "outputs": [],
   "source": [
    "hub_utils.init(\n",
    "    model=\"/Users/macbookpro/MyProjects/dev/structured_arr_model_1_dim.joblib\",\n",
    "    requirements=[\"scikit-learn\", \"numpy\"],\n",
    "    dst=\"/Users/macbookpro/MyProjects/dev/dst\",\n",
    "    task=\"tabular-classification\",\n",
    "    data=x_train[:3]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "fe1a1620-66e3-4543-a506-1195ac39831e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from skops.card import metadata_from_config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "9e0a6d81-e1c4-4a75-b510-772eb44e924d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "library_name: sklearn\n",
       "tags:\n",
       "- sklearn\n",
       "- skops\n",
       "- tabular-classification\n",
       "widget:\n",
       "  structuredData:\n",
       "    x0:\n",
       "    - - 6.3\n",
       "    - - 6.5\n",
       "    - - 5.6"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metadata_from_config(\"/Users/macbookpro/MyProjects/dev/dst/config.json\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "412fc8e8-ab28-44bf-88be-6cac61c168f1",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}