gistfile1.txt

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sqlalchemy import *\n",
    "\n",
    "DATABASE_ENDPOINT = \"aqueduct30v04.cgpnumwmfcqc.eu-central-1.rds.amazonaws.com\"\n",
    "DATABASE_NAME = \"database01\"\n",
    "TABLE_NAME = \"test01\"\n",
    "\n",
    "F = open(\"/.password\",\"r\")\n",
    "password = F.read().splitlines()[0]\n",
    "F.close()\n",
    "\n",
    "engine = create_engine(\"postgresql://rutgerhofste:{}@{}:5432/{}\".format(password,DATABASE_ENDPOINT,DATABASE_NAME))\n",
    "connection = engine.connect()\n",
    "\n",
    "d1 = {'id' : [1, 2, 3],\n",
    "     'foo' : [20, 40, 10]}\n",
    "\n",
    "d2 = {'id' : [1, 2, 4],\n",
    "     'bar' : [21, 42, 13]}\n",
    "\n",
    "\n",
    "df1 = pd.DataFrame(d1)\n",
    "df2 = pd.DataFrame(d2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_merged = df1.merge(df2,on=\"id\",how=\"outer\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>foo</th>\n",
       "      <th>id</th>\n",
       "      <th>bar</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20.0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>40.0</td>\n",
       "      <td>2</td>\n",
       "      <td>42.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10.0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    foo  id   bar\n",
       "0  20.0   1  21.0\n",
       "1  40.0   2  42.0\n",
       "2  10.0   3   NaN\n",
       "3   NaN   4  13.0"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "foo    int64\n",
       "id     int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "foo    float64\n",
       "id       int64\n",
       "bar    float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#column types converted to float due to Nans"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# cannot store as integer\n",
    "# df_merged[\"bar\"] = df_merged[\"bar\"].astype(np.int64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df_merged.to_sql(\"test01\",engine,if_exists='replace', index=False,chunksize=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Suggested by coldspeed\n",
    "df_merged.astype(object).to_sql(\"test02\",engine,if_exists='replace', index=False,chunksize=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Suggested by Ami Tavory, \n",
    "df_merged2 = df_merged.copy()\n",
    "df_merged2[\"foo\"].fillna(-9999, inplace=True)\n",
    "df_merged2[\"bar\"].fillna(-9999, inplace=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>foo</th>\n",
       "      <th>id</th>\n",
       "      <th>bar</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20.0</td>\n",
       "      <td>1</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>40.0</td>\n",
       "      <td>2</td>\n",
       "      <td>42.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10.0</td>\n",
       "      <td>3</td>\n",
       "      <td>-9999.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-9999.0</td>\n",
       "      <td>4</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      foo  id     bar\n",
       "0    20.0   1    21.0\n",
       "1    40.0   2    42.0\n",
       "2    10.0   3 -9999.0\n",
       "3 -9999.0   4    13.0"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_merged2[\"foo\"] = df_merged2[\"foo\"].astype(np.int64)\n",
    "df_merged2[\"bar\"] = df_merged2[\"foo\"].astype(np.int64)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "foo    int64\n",
       "id     int64\n",
       "bar    int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df_merged2.to_sql(\"test03\",engine,if_exists='replace', index=False,chunksize=100)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 35",
   "language": "python",
   "name": "python35"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}