{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Before you turn this problem in, make sure everything runs as expected. First, **restart the kernel** (in the menubar, select Kernel$\\rightarrow$Restart) and then **run all cells** (in the menubar, select Cell$\\rightarrow$Run All).\n",
    "\n",
    "Make sure you fill in any place that says `YOUR CODE HERE` or \"YOUR ANSWER HERE\", as well as your name and collaborators below:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "NAME = \"\"\n",
    "COLLABORATORS = \"\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import os.path\n",
    "import pandas as pd\n",
    "\n",
    "datadir = \"publicdata\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example1: Column Values as a Mashup\n",
    "\n",
    "df1 = pd.read_csv(os.path.join(datadir, \"mashup1.csv\"))\n",
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. function to extract code\n",
    "# 2. function to extract country\n",
    "# 3. apply to get code vector\n",
    "# 4. apply to get country vector\n",
    "# 5. drop current country\n",
    "# 6. add new code and new country\n",
    "# 7. cleanup on index and column order\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example2: Year/Month Mashup/String\n",
    "\n",
    "df2 = pd.read_csv(os.path.join(datadir, \"metropolis.csv\"))\n",
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Steps?\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example3: Multiple rows per country\n",
    "\n",
    "df3 = pd.read_csv(os.path.join(datadir, \"mult_rows.csv\"))\n",
    "df3.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# What operation to solve this one?\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example4: Multiple rows per country/year combination\n",
    "\n",
    "df4 = pd.read_csv(os.path.join(datadir, \"mult_rows2.csv\"))\n",
    "df4.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# What operation(s) to solve this?\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example5: Single indicator variable with multiple years\n",
    "\n",
    "df5 = pd.read_csv(os.path.join(datadir, \"pop_columns.csv\"))\n",
    "df5.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Steps to resolve??\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example6: Multiple indicator variables with multiple years\n",
    "\n",
    "df6 = pd.read_csv(os.path.join(datadir, \"popgdp_columns.csv\"))\n",
    "df6.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Steps to resolve??\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example7: Two tables for a single mapping\n",
    "\n",
    "df7a = pd.read_csv(os.path.join(datadir, \"topfemale.csv\"))\n",
    "df7b = pd.read_csv(os.path.join(datadir, \"topmale.csv\"))\n",
    "df7a.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df7b.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# How to solve??\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Example8: One table with multiple mappings\n",
    "\n",
    "df8 = pd.read_csv(os.path.join(datadir, \"mixed_table.csv\"))\n",
    "df8.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# How to solve?\n",
    "\n",
    "\n"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}