Gender Prediction From Name.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "9b51bae0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pickle\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "39697db5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"Indian-Name.csv\", encoding=\"latin-1\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c01e521",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "55846e1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[[\"Name\", \"Target\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "29f6ce1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "cd1ea8a6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Name      0\n",
       "Target    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "173573ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Target\"] = df[\"Target\"].map({\n",
    "    0: \"female\", 1: \"male\"\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "66441b66",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.countplot(x=\"Target\", data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "a12b7360",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df[\"Name\"].astype(\"str\")\n",
    "y = df[\"Target\"].astype(\"str\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "e15ff914",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=4242)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "a4cbc3ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(ngram_range=(1, 1))\n",
    "X_train_cv = cv.fit_transform(X_train)\n",
    "X_test_cv = cv.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "202a618f",
   "metadata": {},
   "outputs": [],
   "source": [
    "tfidf = TfidfTransformer(norm=\"l2\")\n",
    "X_train_tf = tfidf.fit_transform(X_train_cv)\n",
    "X_test_tf = tfidf.transform(X_test_cv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "95afb371",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: /~https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultinomialNB(alpha=0.1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB(alpha=0.1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MultinomialNB(alpha=0.1)"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mnb = MultinomialNB(alpha=0.1)\n",
    "mnb.fit(X_train_tf, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "b7769b24",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = mnb.predict(X_test_tf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "32dc7dcd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5846153846153846"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "e74e3b4d",
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(mnb, open(\"mnb.pkl\", \"wb\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8ba70ede",
   "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": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}