{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0f5b3979-7704-4ea7-ac84-424f73e9a62d",
   "metadata": {},
   "source": [
    "# Predykcja na modelu zapisanym w pliku"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ef017730-4bbd-4fad-926a-2800fa636ccd",
   "metadata": {},
   "source": [
    "## Import bibliotek"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a330d65d-8876-49b8-9507-27ee9f50d1e6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import keras\n",
    "import pandas as pd\n",
    "from sklearn.preprocessing import MinMaxScaler, OneHotEncoder\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bd52369-8c81-45a1-b091-5edae9bc2673",
   "metadata": {},
   "source": [
    "## Pobranie modelu z pliku"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "aa7d4e1f-2924-4c84-a06b-f19b451e923b",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.models.load_model('./model.keras')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c94dca7-7670-4ed9-b6ca-5c59c734cc44",
   "metadata": {},
   "source": [
    "## Przygotowanie danych do testowania modelu"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3e72f7ea-91a6-45ac-9f38-872175ad2a8d",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = pd.read_csv('./lettuce-growth-days/lettuce_dataset_updated.csv', encoding='ISO-8859-1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9f52a6e7-ae62-4ea6-bde5-e2b221fa2d7a",
   "metadata": {},
   "outputs": [],
   "source": [
    "ph_level = dataset['pH Level'].values.tolist()\n",
    "temp_F = dataset['Temperature (F)'].values.tolist()\n",
    "humid = dataset['Humidity'].values.tolist()\n",
    "days = dataset['Growth Days'].values.tolist()\n",
    "plant_id = dataset['Plant_ID'].values.tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a720aa83-bb5a-4c6f-89a5-f6e1fb7cf0e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = []\n",
    "Y = []\n",
    "\n",
    "id = plant_id[0]\n",
    "temp_sum = 0\n",
    "humid_sum = 0\n",
    "ph_level_sum = 0\n",
    "day = 1\n",
    "\n",
    "for i in range(0, len(plant_id)):\n",
    "    if plant_id[i] == id:\n",
    "        temp_sum += temp_F[i]\n",
    "        humid_sum += humid[i]\n",
    "        ph_level_sum += ph_level[i]\n",
    "        day = days[i]\n",
    "    else:\n",
    "        temp = []\n",
    "        temp.append(temp_sum/day)\n",
    "        temp.append(humid_sum/day)\n",
    "        temp.append(ph_level_sum/day)\n",
    "        X.append(temp)\n",
    "        Y.append(day)\n",
    "        temp_sum = 0\n",
    "        humid_sum = 0\n",
    "        ph_level_sum = 0\n",
    "        day = 1\n",
    "        id = plant_id[i]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d8ef6898-38bb-4191-b7b9-bc47dd1ae5d8",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\obses\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:808: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "scaler = MinMaxScaler()\n",
    "X = scaler.fit_transform(X)\n",
    "X = np.array(X)\n",
    "Y = np.array(Y)\n",
    "\n",
    "encoder = OneHotEncoder(sparse=False)\n",
    "y_onehot = encoder.fit_transform(Y.reshape(-1,1))\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y_onehot, test_size=0.4, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "72650088-d370-4814-b381-6e5a5e01fe58",
   "metadata": {},
   "source": [
    "## Testowanie modelu"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ed8d7cb0-eefd-4e64-80e1-4ea4ff6bb369",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 216ms/step - accuracy: 0.8571 - loss: 0.7300\n",
      "Dokładność testowa: 85.71%\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_accuracy = model.evaluate(X_test, y_test)\n",
    "print(f\"Dokładność testowa: {test_accuracy:.2%}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5f0bceec-f95e-4192-aced-c9997eafee28",
   "metadata": {},
   "source": [
    "## Predykcja na zbiorze testowym"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6ce776f4-859b-42d9-a756-bd29b11d1b56",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step\n"
     ]
    }
   ],
   "source": [
    "predictions = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9908472c-08ae-4e46-afe3-27eefb43f671",
   "metadata": {},
   "source": [
    "## Zapisanie wyników predykcji do pliku tekstowego"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "738043a9-a312-4f96-af22-593362bc9624",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"predictions.txt\", \"w\") as txt_file:\n",
    "    for line in predictions:\n",
    "        txt_file.write(\" \".join(str(line)) + \"\\n\") "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "da604cf2-d13d-4dd3-a596-7b24ba5d92ef",
   "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": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}