{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3c142580",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-block alert-success\">\n",
    "    <h1 align=\"center\">Titanic Dataset</h1>\n",
    "    <h3 align=\"center\">Make final model and use it in Streamlit</h3>\n",
    "    <h4 align=\"center\"><a href=\"http://www.iran-machinelearning.ir\">Soheil Tehranipour</a></h5>\n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "405e33d5",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "pip install xgboost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "97f5a509",
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'xgboost'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[2], line 9\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcompose\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ColumnTransformer , make_column_transformer\n\u001b[0;32m      8\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mbase\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BaseEstimator, TransformerMixin\n\u001b[1;32m----> 9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mxgboost\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m XGBClassifier\n\u001b[0;32m     10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodel_selection\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m train_test_split\n\u001b[0;32m     11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmetrics\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m confusion_matrix, precision_score, recall_score\n",
      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'xgboost'"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import OneHotEncoder, StandardScaler\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.compose import ColumnTransformer , make_column_transformer\n",
    "from sklearn.base import BaseEstimator, TransformerMixin\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix, precision_score, recall_score\n",
    "import warnings\n",
    "warnings. filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c73e3ee5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('train.csv')\n",
    "X = df.drop('Survived', axis=1) \n",
    "y = df.Survived"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ea854483",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e82c900f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# The BaseEstimator just gives it the get_params and set_params methods that all Scikit-learn estimators require. \n",
    "#The TransformerMixin gives it the fit_transform method.\n",
    "\n",
    "class PrepProcesor(BaseEstimator, TransformerMixin): \n",
    "    def fit(self, X, y=None): \n",
    "        self.ageImputer = SimpleImputer()\n",
    "        self.ageImputer.fit(X[['Age']])        \n",
    "        return self \n",
    "        \n",
    "    def transform(self, X, y=None):\n",
    "        X['Age'] = self.ageImputer.transform(X[['Age']])\n",
    "        X['CabinClass'] = X['Cabin'].fillna('M').apply(lambda x: str(x).replace(\" \", \"\")).apply(lambda x: re.sub(r'[^a-zA-Z]', '', x))\n",
    "        X['CabinNumber'] = X['Cabin'].fillna('M').apply(lambda x: str(x).replace(\" \", \"\")).apply(lambda x: re.sub(r'[^0-9]', '', x)).replace('', 0) \n",
    "        X['Embarked'] = X['Embarked'].fillna('M')\n",
    "        X = X.drop(['PassengerId', 'Name', 'Ticket','Cabin'], axis=1)\n",
    "        return X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c89feab",
   "metadata": {},
   "outputs": [],
   "source": [
    "preproc = PrepProcesor()\n",
    "numeric_pipeline = Pipeline([('Scaler', StandardScaler())]) \n",
    "categorical_pipeline = Pipeline([('OneHot', OneHotEncoder(handle_unknown='ignore'))])\n",
    "transformer = ColumnTransformer([('num', numeric_pipeline, ['Pclass','Age','SibSp','Parch','Fare','CabinNumber']), ('cat', categorical_pipeline, ['Sex','Embarked','CabinClass'])])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "61d620be",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.10, random_state=1234) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6a10b0a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "db5de807",
   "metadata": {},
   "outputs": [],
   "source": [
    "mlpipe = Pipeline([('InitialPreproc', PrepProcesor()), ('Transformer',transformer), ('xgb', XGBClassifier())])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ec852a78",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "mlpipe.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3c048d1",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_hat = mlpipe.predict(X_test) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cc40818e",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_hat.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9dee0c0e",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a914cc2e",
   "metadata": {},
   "outputs": [],
   "source": [
    "precision_score(y_test, y_hat) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cf0270c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cd7011a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "joblib.dump(mlpipe, 'xgbpipe.joblib') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3ea7174",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "model = joblib.load('xgbpipe.joblib')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "60f0d045",
   "metadata": {},
   "outputs": [],
   "source": [
    "test = pd.read_csv('test.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b46ac674",
   "metadata": {},
   "outputs": [],
   "source": [
    "test.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c2ce6aec",
   "metadata": {
    "scrolled": true,
    "tags": []
   },
   "outputs": [],
   "source": [
    "yhat = model.predict(test)\n",
    "yhat"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "92ee0e6a",
   "metadata": {},
   "source": [
    "<img src=\"https://webna.ir/wp-content/uploads/2018/08/%D9%85%DA%A9%D8%AA%D8%A8-%D8%AE%D9%88%D9%86%D9%87.png\" width=50% />"
   ]
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}