{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "\"\"\"\n",
    "how many profiles overlap between files 1 and 2, 1 and 3, 2 and 3\n",
    "\"\"\"\n",
    "\n",
    "file_1 = \"cluster_d_fb.csv\"\n",
    "file_2 = \"rfm_fb.csv\"\n",
    "file_3 = \"superfan_fb.csv\"\n",
    "\n",
    "df1 = pd.read_csv(file_1, sep=\",\")\n",
    "df2 = pd.read_csv(file_2, sep=\",\")\n",
    "df3 = pd.read_csv(file_3, sep=\",\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                    email\n",
      "0  amanda.g89@hotmail.com\n",
      "                             email\n",
      "0  thomas.fairlie@uqconnect.edu.au\n",
      "                             email\n",
      "0  thomas.fairlie@uqconnect.edu.au\n"
     ]
    }
   ],
   "source": [
    "print(df1[['email']].head(1))\n",
    "print(df2[['email']].head(1))\n",
    "print(df3[['email']].head(1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "545\n"
     ]
    }
   ],
   "source": [
    "df = pd.merge(df1, df2, how='inner', on=['email'])\n",
    "print(df['email'].nunique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63\n"
     ]
    }
   ],
   "source": [
    "df = pd.merge(df1, df3, how='inner', on=['email'])\n",
    "print(df['email'].nunique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "937\n"
     ]
    }
   ],
   "source": [
    "df = pd.merge(df2, df3, how='inner', on=['email'])\n",
    "print(df['email'].nunique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "1-2: 545\n",
    "1-3: 63\n",
    "2-3: 937"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}