How to iterate over rows in Pandas dataframe - Speed comparison.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "eb295de5",
   "metadata": {},
   "source": [
    "# Speed Comparison"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f3c38deb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(237519, 7)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df = pd.read_csv('Suicides in India 2001-2012.csv')\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3e8af1cf",
   "metadata": {},
   "outputs": [
    {
     "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>State</th>\n",
       "      <th>Year</th>\n",
       "      <th>Type_code</th>\n",
       "      <th>Type</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age_group</th>\n",
       "      <th>Total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A &amp; N Islands</td>\n",
       "      <td>2001</td>\n",
       "      <td>Causes</td>\n",
       "      <td>Illness (Aids/STD)</td>\n",
       "      <td>Female</td>\n",
       "      <td>0-14</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A &amp; N Islands</td>\n",
       "      <td>2001</td>\n",
       "      <td>Causes</td>\n",
       "      <td>Bankruptcy or Sudden change in Economic</td>\n",
       "      <td>Female</td>\n",
       "      <td>0-14</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           State  Year Type_code                                     Type  \\\n",
       "0  A & N Islands  2001    Causes                       Illness (Aids/STD)   \n",
       "1  A & N Islands  2001    Causes  Bankruptcy or Sudden change in Economic   \n",
       "\n",
       "   Gender Age_group  Total  \n",
       "0  Female      0-14      0  \n",
       "1  Female      0-14      0  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7f45cad2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "27.8 s ± 3.84 s per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for idx, row in df.iterrows():\n",
    "    row['State'], row['Year'], row['Type']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "41477099",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "496 ms ± 140 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for row in df.itertuples():\n",
    "    row.State, row.Year, row.Type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "afddd65e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "8.69 s ± 381 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for idx in range(len(df)):\n",
    "    df.loc[idx, \"State\"], df.loc[idx, \"Year\"], df.loc[idx, 'Type']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6a6cfdf4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "37.3 s ± 11.8 s per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for idx in range(len(df)):\n",
    "    df.iloc[idx, 0], df.iloc[idx, 1], df.iloc[idx, 3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "0e3269bf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "8.2 s ± 1.15 s per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for idx in df.index:\n",
    "     df['State'][idx], df['Year'][idx], df['Type'][idx]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6a6f9f8b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.99 s ± 272 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for item in df.to_dict(orient='records'):\n",
    "    item['State'], item['Year'], item['Type']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "fed012c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "211 ms ± 25 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for item in df.to_numpy():\n",
    "    item[0], item[1], item[3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "301be1c3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "50 s ± 8.64 s per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for key, value in df.T.iteritems():\n",
    "    value.State, value.Year, value.Type"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "ec498337",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "52.8 s ± 13 s per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for key, value in df.T.items():\n",
    "    value.State, value.Year, value.Type"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}