{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ef372322",
   "metadata": {},
   "source": [
    "# Reshaping Data\n",
    "\n",
    "Today, we'll begin reshaping data.  We'll  cover:\n",
    "- filtering\n",
    "- applying a function to all rows\n",
    "- what is tidy data\n",
    "- reshaping data into tidy data\n",
    "\n",
    "First some setup:\n",
    "\n",
    "````{margin}\n",
    "```{tip}\n",
    "I used `set_theme` to change both the fond size and the color palette.\n",
    "Seaborn has a [detailed guide](https://seaborn.pydata.org/tutorial/color_palettes.html#palette-tutorial)\n",
    "for choosing colors. The `colorblind` palette uses colors that are distinguishable under most common\n",
    "forms of color blindness.\n",
    "```\n",
    "````"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7bdb5d8d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "\n",
    "sns.set_theme(font_scale=2, palette='colorblind')\n",
    "arabica_data_url = 'https://raw.githubusercontent.com/jldbc/coffee-quality-database/master/data/arabica_data_cleaned.csv'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f4408035",
   "metadata": {},
   "source": [
    "## Cleaning Data\n",
    "This week, we'll be cleaning data.\n",
    "\n",
    "Cleaning data is labor intensive and requires making subjective choices.  \n",
    "We'll focus on, and assess you on, manipulating data correctly, making reasonable\n",
    "choices, and documenting the choices you make carefully.\n",
    "\n",
    "\n",
    "We'll focus on the programming tools that get used in cleaning data in class\n",
    "\n",
    "this week:\n",
    "- reshaping data\n",
    "- handling missing or incorrect values\n",
    "- changing the representation of information\n",
    "\n",
    "## Tidy Data\n",
    "\n",
    "Read in the three csv files described below and store them in a list of DataFrames."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7fd172ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "url_base = 'https://raw.githubusercontent.com/rhodyprog4ds/rhodyds/main/data/'\n",
    "\n",
    "datasets = ['study_a.csv','study_b.csv','study_c.csv']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "95ad2ad2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_list = [pd.read_csv(url_base + file,na_values= '') for file in datasets]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "66ffb48f",
   "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>name</th>\n",
       "      <th>treatmenta</th>\n",
       "      <th>treatmentb</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Smith</td>\n",
       "      <td>-</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jane Doe</td>\n",
       "      <td>16</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mary Johnson</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           name treatmenta  treatmentb\n",
       "0    John Smith          -           2\n",
       "1      Jane Doe         16          11\n",
       "2  Mary Johnson          3           1"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "df47bf2a",
   "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>intervention</th>\n",
       "      <th>John Smith</th>\n",
       "      <th>Jane Doe</th>\n",
       "      <th>Mary Johnson</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>treatmenta</td>\n",
       "      <td>-</td>\n",
       "      <td>16</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>treatmentb</td>\n",
       "      <td>2</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  intervention John Smith  Jane Doe  Mary Johnson\n",
       "0   treatmenta          -        16             3\n",
       "1   treatmentb          2        11             1"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9ee8e9a3",
   "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>person</th>\n",
       "      <th>treatment</th>\n",
       "      <th>result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Smith</td>\n",
       "      <td>a</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jane Doe</td>\n",
       "      <td>a</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mary Johnson</td>\n",
       "      <td>a</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>John Smith</td>\n",
       "      <td>b</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Jane Doe</td>\n",
       "      <td>b</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mary Johnson</td>\n",
       "      <td>b</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         person treatment result\n",
       "0    John Smith         a      -\n",
       "1      Jane Doe         a     16\n",
       "2  Mary Johnson         a      3\n",
       "3    John Smith         b      2\n",
       "4      Jane Doe         b     11\n",
       "5  Mary Johnson         b      1"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[2]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f5ba2fd0",
   "metadata": {},
   "source": [
    "These three all show the same data, but let's say we have two goals:\n",
    "- find the average  effect per person across treatments\n",
    "- find the average effect per treatment across people\n",
    "\n",
    "This works differently for these three versions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ac1d43cb",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/2274987639.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
      "  df_list[0].mean()\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "treatmenta   -54.333333\n",
       "treatmentb     4.666667\n",
       "dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[0].mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49e2cde7",
   "metadata": {},
   "source": [
    "we get the average per treatment, but to get the average per person, we have to go across rows, which we can do here, but doesn't work as well with plotting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "29c8293a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/1371725361.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
      "  df_list[0].mean(axis=1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0     2.0\n",
       "1    11.0\n",
       "2     1.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[0].mean(axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8d9bfdc4",
   "metadata": {},
   "source": [
    "and this is not well labeled.\n",
    "\n",
    "Let's try the next one."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "01bf2266",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/1105758803.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
      "  df_list[1].mean()\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "John Smith      -1.0\n",
       "Jane Doe        13.5\n",
       "Mary Johnson     2.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[1].mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db0c0ceb",
   "metadata": {},
   "source": [
    "Now we get the average per person, but what about per treatment? again we have to go across rows instead."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8b567f5c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/1112167831.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.\n",
      "  df_list[1].mean(axis=1)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0    9.5\n",
       "1    6.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[1].mean(axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d13d6cd1",
   "metadata": {},
   "source": [
    "For the third one, however, we can use groupby"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1d0c5b8a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/906930014.py:1: FutureWarning: Dropping invalid columns in DataFrameGroupBy.mean is deprecated. In a future version, a TypeError will be raised. Before calling .mean, select only columns which should be valid for the function.\n",
      "  df_list[2].groupby('person').mean()\n"
     ]
    },
    {
     "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>result</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>person</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Jane Doe</th>\n",
       "      <td>805.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>John Smith</th>\n",
       "      <td>-1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mary Johnson</th>\n",
       "      <td>15.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              result\n",
       "person              \n",
       "Jane Doe       805.5\n",
       "John Smith      -1.0\n",
       "Mary Johnson    15.5"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[2].groupby('person').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ce7f665b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/2480310521.py:1: FutureWarning: Dropping invalid columns in DataFrameGroupBy.mean is deprecated. In a future version, a TypeError will be raised. Before calling .mean, select only columns which should be valid for the function.\n",
      "  df_list[2].groupby('treatment').mean()\n"
     ]
    },
    {
     "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>result</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>treatment</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>-54.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>703.666667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               result\n",
       "treatment            \n",
       "a          -54.333333\n",
       "b          703.666667"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_list[2].groupby('treatment').mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d198e085",
   "metadata": {},
   "source": [
    "The original [Tidy Data](https://www.jstatsoft.org/article/view/v059i10) paper is worth reading to build a deeper understanding of these ideas.  \n",
    "\n",
    "## Tidying Data\n",
    "\n",
    "\n",
    "Let's reshape the first one to match the tidy one. First, we\n",
    "will save it to a DataFrame, this makes things easier to read\n",
    "and enables us to use the built in help in jupyter, because it can't check types too many levels into a data structure."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a0f5eeca",
   "metadata": {},
   "outputs": [],
   "source": [
    "treat_df = df_list[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "29389e85",
   "metadata": {},
   "source": [
    "Let's look at it again, so we can see"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "192fc8f8",
   "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>name</th>\n",
       "      <th>treatmenta</th>\n",
       "      <th>treatmentb</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Smith</td>\n",
       "      <td>-</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jane Doe</td>\n",
       "      <td>16</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mary Johnson</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           name treatmenta  treatmentb\n",
       "0    John Smith          -           2\n",
       "1      Jane Doe         16          11\n",
       "2  Mary Johnson          3           1"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "treat_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aa09d12e",
   "metadata": {},
   "source": [
    "```{admonition} Correction\n",
    "I fixed the three data files so the spaces can be removed. You will need to\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "5e3e3d59",
   "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>name</th>\n",
       "      <th>treatment</th>\n",
       "      <th>result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Smith</td>\n",
       "      <td>treatmenta</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jane Doe</td>\n",
       "      <td>treatmenta</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mary Johnson</td>\n",
       "      <td>treatmenta</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>John Smith</td>\n",
       "      <td>treatmentb</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Jane Doe</td>\n",
       "      <td>treatmentb</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mary Johnson</td>\n",
       "      <td>treatmentb</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           name   treatment result\n",
       "0    John Smith  treatmenta      -\n",
       "1      Jane Doe  treatmenta     16\n",
       "2  Mary Johnson  treatmenta      3\n",
       "3    John Smith  treatmentb      2\n",
       "4      Jane Doe  treatmentb     11\n",
       "5  Mary Johnson  treatmentb      1"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "treat_df.melt(value_vars = ['treatmenta','treatmentb'],\n",
    "             id_vars = ['name'],\n",
    "             value_name = 'result', var_name = 'treatment' )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "64f88bdc",
   "metadata": {},
   "outputs": [],
   "source": [
    "tidy_treat_df = treat_df.melt(value_vars = ['treatmenta','treatmentb'],\n",
    "             id_vars = ['name'],\n",
    "             value_name = 'result', var_name = 'treatment' )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "20f15474",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_2499/3450628511.py:1: FutureWarning: Dropping invalid columns in DataFrameGroupBy.mean is deprecated. In a future version, a TypeError will be raised. Before calling .mean, select only columns which should be valid for the function.\n",
      "  tidy_treat_df.groupby('name').mean()\n"
     ]
    },
    {
     "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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Jane Doe</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>John Smith</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mary Johnson</th>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: []\n",
       "Index: [Jane Doe, John Smith, Mary Johnson]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tidy_treat_df.groupby('name').mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73f29815",
   "metadata": {},
   "source": [
    "## Filtering Data by a column\n",
    "\n",
    "Let's go back to the coffee dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "35f0cadf",
   "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>Species</th>\n",
       "      <th>Owner</th>\n",
       "      <th>Country.of.Origin</th>\n",
       "      <th>Farm.Name</th>\n",
       "      <th>Lot.Number</th>\n",
       "      <th>Mill</th>\n",
       "      <th>ICO.Number</th>\n",
       "      <th>Company</th>\n",
       "      <th>Altitude</th>\n",
       "      <th>Region</th>\n",
       "      <th>...</th>\n",
       "      <th>Color</th>\n",
       "      <th>Category.Two.Defects</th>\n",
       "      <th>Expiration</th>\n",
       "      <th>Certification.Body</th>\n",
       "      <th>Certification.Address</th>\n",
       "      <th>Certification.Contact</th>\n",
       "      <th>unit_of_measurement</th>\n",
       "      <th>altitude_low_meters</th>\n",
       "      <th>altitude_high_meters</th>\n",
       "      <th>altitude_mean_meters</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>NaN</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>2014/2015</td>\n",
       "      <td>metad agricultural developmet plc</td>\n",
       "      <td>1950-2200</td>\n",
       "      <td>guji-hambela</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>0</td>\n",
       "      <td>April 3rd, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1950.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2075.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>NaN</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>2014/2015</td>\n",
       "      <td>metad agricultural developmet plc</td>\n",
       "      <td>1950-2200</td>\n",
       "      <td>guji-hambela</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>1</td>\n",
       "      <td>April 3rd, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1950.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2075.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>grounds for health admin</td>\n",
       "      <td>Guatemala</td>\n",
       "      <td>san marcos barrancas \"san cristobal cuch</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1600 - 1800 m</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>May 31st, 2011</td>\n",
       "      <td>Specialty Coffee Association</td>\n",
       "      <td>36d0d00a3724338ba7937c52a378d085f2172daa</td>\n",
       "      <td>0878a7d4b9d35ddbf0fe2ce69a2062cceb45a660</td>\n",
       "      <td>m</td>\n",
       "      <td>1600.0</td>\n",
       "      <td>1800.0</td>\n",
       "      <td>1700.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>yidnekachew dabessa</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>yidnekachew dabessa coffee plantation</td>\n",
       "      <td>NaN</td>\n",
       "      <td>wolensu</td>\n",
       "      <td>NaN</td>\n",
       "      <td>yidnekachew debessa coffee plantation</td>\n",
       "      <td>1800-2200</td>\n",
       "      <td>oromia</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>2</td>\n",
       "      <td>March 25th, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1800.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>NaN</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>2014/2015</td>\n",
       "      <td>metad agricultural developmet plc</td>\n",
       "      <td>1950-2200</td>\n",
       "      <td>guji-hambela</td>\n",
       "      <td>...</td>\n",
       "      <td>Green</td>\n",
       "      <td>2</td>\n",
       "      <td>April 3rd, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1950.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2075.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 43 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Species                     Owner Country.of.Origin  \\\n",
       "1  Arabica                 metad plc          Ethiopia   \n",
       "2  Arabica                 metad plc          Ethiopia   \n",
       "3  Arabica  grounds for health admin         Guatemala   \n",
       "4  Arabica       yidnekachew dabessa          Ethiopia   \n",
       "5  Arabica                 metad plc          Ethiopia   \n",
       "\n",
       "                                  Farm.Name Lot.Number       Mill ICO.Number  \\\n",
       "1                                 metad plc        NaN  metad plc  2014/2015   \n",
       "2                                 metad plc        NaN  metad plc  2014/2015   \n",
       "3  san marcos barrancas \"san cristobal cuch        NaN        NaN        NaN   \n",
       "4     yidnekachew dabessa coffee plantation        NaN    wolensu        NaN   \n",
       "5                                 metad plc        NaN  metad plc  2014/2015   \n",
       "\n",
       "                                 Company       Altitude        Region  ...  \\\n",
       "1      metad agricultural developmet plc      1950-2200  guji-hambela  ...   \n",
       "2      metad agricultural developmet plc      1950-2200  guji-hambela  ...   \n",
       "3                                    NaN  1600 - 1800 m           NaN  ...   \n",
       "4  yidnekachew debessa coffee plantation      1800-2200        oromia  ...   \n",
       "5      metad agricultural developmet plc      1950-2200  guji-hambela  ...   \n",
       "\n",
       "   Color  Category.Two.Defects        Expiration  \\\n",
       "1  Green                     0   April 3rd, 2016   \n",
       "2  Green                     1   April 3rd, 2016   \n",
       "3    NaN                     0    May 31st, 2011   \n",
       "4  Green                     2  March 25th, 2016   \n",
       "5  Green                     2   April 3rd, 2016   \n",
       "\n",
       "                   Certification.Body  \\\n",
       "1  METAD Agricultural Development plc   \n",
       "2  METAD Agricultural Development plc   \n",
       "3        Specialty Coffee Association   \n",
       "4  METAD Agricultural Development plc   \n",
       "5  METAD Agricultural Development plc   \n",
       "\n",
       "                      Certification.Address  \\\n",
       "1  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "2  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "3  36d0d00a3724338ba7937c52a378d085f2172daa   \n",
       "4  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "5  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "\n",
       "                      Certification.Contact unit_of_measurement  \\\n",
       "1  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "2  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "3  0878a7d4b9d35ddbf0fe2ce69a2062cceb45a660                   m   \n",
       "4  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "5  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "\n",
       "  altitude_low_meters altitude_high_meters  altitude_mean_meters  \n",
       "1              1950.0               2200.0                2075.0  \n",
       "2              1950.0               2200.0                2075.0  \n",
       "3              1600.0               1800.0                1700.0  \n",
       "4              1800.0               2200.0                2000.0  \n",
       "5              1950.0               2200.0                2075.0  \n",
       "\n",
       "[5 rows x 43 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "coffee_df = pd.read_csv(arabica_data_url, index_col = 0)\n",
    "coffee_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8530862c",
   "metadata": {},
   "source": [
    "Recall on Friday we computed the total number of bags per country."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "bd1785a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# compute total bags per country\n",
    "bag_total_df = coffee_df.groupby('Country.of.Origin')['Number.of.Bags'].sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7eb2b682",
   "metadata": {},
   "source": [
    "We can subset this to get only the countries with over 15000 using a boolean mask:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "2aa36737",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Country.of.Origin\n",
       "Brazil       30534\n",
       "Colombia     41204\n",
       "Guatemala    36868\n",
       "Mexico       24140\n",
       "Name: Number.of.Bags, dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bag_total_df[bag_total_df>15000]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0bc47eae",
   "metadata": {},
   "source": [
    "what we put in the `[]` has to be the same length and each element has to be boolean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "f976585c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "36"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(bag_total_df>15000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "9ffc940a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "numpy.bool_"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mask = bag_total_df>15000\n",
    "type(mask[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09d2eddf",
   "metadata": {},
   "source": [
    "## Augmenting a dataset\n",
    "\n",
    "We want the names of the countries as a list, so we extract the index of that series and then cast it to a list."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "b96b401e",
   "metadata": {},
   "outputs": [],
   "source": [
    "high_prod_countries =  list(bag_total_df[bag_total_df>15000].index)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dcc1fba8",
   "metadata": {},
   "source": [
    "Next we want to be able to check if a country is in this list, so we'll make a lambda that can do that"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "ae270d5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "high_prod = lambda c: c in high_prod_countries"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "28bc5129",
   "metadata": {},
   "source": [
    "Recall, the `lambda` keyword makes a function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "9d668000",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "function"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(high_prod)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1bbe428c",
   "metadata": {},
   "source": [
    "We can test it"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "e2da9e02",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(True, False)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "high_prod('Mexico'), high_prod('Ethiopa')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a4846873",
   "metadata": {},
   "source": [
    "Now, we can apply that lambda function to each country in our whole coffee data frame. and save that to a new DataFrame."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "c043f12f",
   "metadata": {},
   "outputs": [],
   "source": [
    "coffee_df['high_production'] = coffee_df['Country.of.Origin'].apply(high_prod)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "6ea6368e",
   "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>Species</th>\n",
       "      <th>Owner</th>\n",
       "      <th>Country.of.Origin</th>\n",
       "      <th>Farm.Name</th>\n",
       "      <th>Lot.Number</th>\n",
       "      <th>Mill</th>\n",
       "      <th>ICO.Number</th>\n",
       "      <th>Company</th>\n",
       "      <th>Altitude</th>\n",
       "      <th>Region</th>\n",
       "      <th>...</th>\n",
       "      <th>Category.Two.Defects</th>\n",
       "      <th>Expiration</th>\n",
       "      <th>Certification.Body</th>\n",
       "      <th>Certification.Address</th>\n",
       "      <th>Certification.Contact</th>\n",
       "      <th>unit_of_measurement</th>\n",
       "      <th>altitude_low_meters</th>\n",
       "      <th>altitude_high_meters</th>\n",
       "      <th>altitude_mean_meters</th>\n",
       "      <th>high_production</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>NaN</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>2014/2015</td>\n",
       "      <td>metad agricultural developmet plc</td>\n",
       "      <td>1950-2200</td>\n",
       "      <td>guji-hambela</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>April 3rd, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1950.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2075.0</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>NaN</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>2014/2015</td>\n",
       "      <td>metad agricultural developmet plc</td>\n",
       "      <td>1950-2200</td>\n",
       "      <td>guji-hambela</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>April 3rd, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1950.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2075.0</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>grounds for health admin</td>\n",
       "      <td>Guatemala</td>\n",
       "      <td>san marcos barrancas \"san cristobal cuch</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1600 - 1800 m</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>May 31st, 2011</td>\n",
       "      <td>Specialty Coffee Association</td>\n",
       "      <td>36d0d00a3724338ba7937c52a378d085f2172daa</td>\n",
       "      <td>0878a7d4b9d35ddbf0fe2ce69a2062cceb45a660</td>\n",
       "      <td>m</td>\n",
       "      <td>1600.0</td>\n",
       "      <td>1800.0</td>\n",
       "      <td>1700.0</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>yidnekachew dabessa</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>yidnekachew dabessa coffee plantation</td>\n",
       "      <td>NaN</td>\n",
       "      <td>wolensu</td>\n",
       "      <td>NaN</td>\n",
       "      <td>yidnekachew debessa coffee plantation</td>\n",
       "      <td>1800-2200</td>\n",
       "      <td>oromia</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>March 25th, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1800.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Arabica</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>Ethiopia</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>NaN</td>\n",
       "      <td>metad plc</td>\n",
       "      <td>2014/2015</td>\n",
       "      <td>metad agricultural developmet plc</td>\n",
       "      <td>1950-2200</td>\n",
       "      <td>guji-hambela</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>April 3rd, 2016</td>\n",
       "      <td>METAD Agricultural Development plc</td>\n",
       "      <td>309fcf77415a3661ae83e027f7e5f05dad786e44</td>\n",
       "      <td>19fef5a731de2db57d16da10287413f5f99bc2dd</td>\n",
       "      <td>m</td>\n",
       "      <td>1950.0</td>\n",
       "      <td>2200.0</td>\n",
       "      <td>2075.0</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 44 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Species                     Owner Country.of.Origin  \\\n",
       "1  Arabica                 metad plc          Ethiopia   \n",
       "2  Arabica                 metad plc          Ethiopia   \n",
       "3  Arabica  grounds for health admin         Guatemala   \n",
       "4  Arabica       yidnekachew dabessa          Ethiopia   \n",
       "5  Arabica                 metad plc          Ethiopia   \n",
       "\n",
       "                                  Farm.Name Lot.Number       Mill ICO.Number  \\\n",
       "1                                 metad plc        NaN  metad plc  2014/2015   \n",
       "2                                 metad plc        NaN  metad plc  2014/2015   \n",
       "3  san marcos barrancas \"san cristobal cuch        NaN        NaN        NaN   \n",
       "4     yidnekachew dabessa coffee plantation        NaN    wolensu        NaN   \n",
       "5                                 metad plc        NaN  metad plc  2014/2015   \n",
       "\n",
       "                                 Company       Altitude        Region  ...  \\\n",
       "1      metad agricultural developmet plc      1950-2200  guji-hambela  ...   \n",
       "2      metad agricultural developmet plc      1950-2200  guji-hambela  ...   \n",
       "3                                    NaN  1600 - 1800 m           NaN  ...   \n",
       "4  yidnekachew debessa coffee plantation      1800-2200        oromia  ...   \n",
       "5      metad agricultural developmet plc      1950-2200  guji-hambela  ...   \n",
       "\n",
       "  Category.Two.Defects        Expiration                  Certification.Body  \\\n",
       "1                    0   April 3rd, 2016  METAD Agricultural Development plc   \n",
       "2                    1   April 3rd, 2016  METAD Agricultural Development plc   \n",
       "3                    0    May 31st, 2011        Specialty Coffee Association   \n",
       "4                    2  March 25th, 2016  METAD Agricultural Development plc   \n",
       "5                    2   April 3rd, 2016  METAD Agricultural Development plc   \n",
       "\n",
       "                      Certification.Address  \\\n",
       "1  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "2  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "3  36d0d00a3724338ba7937c52a378d085f2172daa   \n",
       "4  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "5  309fcf77415a3661ae83e027f7e5f05dad786e44   \n",
       "\n",
       "                      Certification.Contact unit_of_measurement  \\\n",
       "1  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "2  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "3  0878a7d4b9d35ddbf0fe2ce69a2062cceb45a660                   m   \n",
       "4  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "5  19fef5a731de2db57d16da10287413f5f99bc2dd                   m   \n",
       "\n",
       "  altitude_low_meters altitude_high_meters altitude_mean_meters  \\\n",
       "1              1950.0               2200.0               2075.0   \n",
       "2              1950.0               2200.0               2075.0   \n",
       "3              1600.0               1800.0               1700.0   \n",
       "4              1800.0               2200.0               2000.0   \n",
       "5              1950.0               2200.0               2075.0   \n",
       "\n",
       "   high_production  \n",
       "1            False  \n",
       "2            False  \n",
       "3             True  \n",
       "4            False  \n",
       "5            False  \n",
       "\n",
       "[5 rows x 44 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "coffee_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cae363f5",
   "metadata": {},
   "source": [
    "Finally, we can filter the whole data frame using that new column."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "9fbdb78d",
   "metadata": {},
   "outputs": [],
   "source": [
    "high_prod_coffee_df = coffee_df[coffee_df['high_production']]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "19b8657c",
   "metadata": {},
   "source": [
    "```{admonition} Question from class\n",
    "How can we get the ones not on that list?\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "c4f888d6",
   "metadata": {},
   "outputs": [],
   "source": [
    "low_prod_coffee_df = coffee_df[coffee_df['high_production']==False]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af80c189",
   "metadata": {},
   "source": [
    "````{admonition} Try it Yourself\n",
    "\n",
    "Replace the FIXMEs in the excerpt below to reshape the data to have a value column with the value of the score\n",
    "and a Score column that indicates which score is in that . Keep the color and country as values\n",
    "\n",
    "```\n",
    "scores_of_interest = ['Balance','Aroma','Body','Aftertaste']\n",
    "attrs_of_interest = ['Country.of.Origin','Color']\n",
    "high_prod_coffee_df_melted = high_prod_coffee_df.melt(\n",
    "        id_vars = FIXME,\n",
    "        value_vars = FIXME,\n",
    "        value_name = 'Value',\n",
    "        var_name = 'Score')\n",
    "```\n",
    "\n",
    "so that it looks like the following\n",
    "````"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "199a3c64",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "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>Country.of.Origin</th>\n",
       "      <th>Color</th>\n",
       "      <th>Score</th>\n",
       "      <th>Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Guatemala</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Balance</td>\n",
       "      <td>8.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Brazil</td>\n",
       "      <td>Bluish-Green</td>\n",
       "      <td>Balance</td>\n",
       "      <td>8.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Mexico</td>\n",
       "      <td>Green</td>\n",
       "      <td>Balance</td>\n",
       "      <td>8.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Brazil</td>\n",
       "      <td>Green</td>\n",
       "      <td>Balance</td>\n",
       "      <td>8.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Brazil</td>\n",
       "      <td>Green</td>\n",
       "      <td>Balance</td>\n",
       "      <td>8.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Country.of.Origin         Color    Score  Value\n",
       "0         Guatemala           NaN  Balance   8.42\n",
       "1            Brazil  Bluish-Green  Balance   8.33\n",
       "2            Mexico         Green  Balance   8.17\n",
       "3            Brazil         Green  Balance   8.00\n",
       "4            Brazil         Green  Balance   8.00"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "high_prod_coffee_df_melted = high_prod_coffee_df.melt(\n",
    "        id_vars = ['Country.of.Origin','Color'],\n",
    "        value_vars = ['Balance','Aroma','Body','Aftertaste'],\n",
    "        value_name = 'Value',\n",
    "        var_name = 'Score')\n",
    "\n",
    "high_prod_coffee_df_melted.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2d61e03c",
   "metadata": {},
   "source": [
    "```{admonition} Try it Yourself\n",
    "Plot the distribution of each score on a separate subplot and use a different color for each country. Use a kde for the distributions.\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "3022f0e0",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7f3ed8c7bd30>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1298.97x720 with 4 Axes>"
      ]
     },
     "metadata": {
      "filenames": {
       "image/png": "/home/runner/work/BrownFall21/BrownFall21/_build/jupyter_execute/notes/2021-09-27_54_1.png"
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(data = high_prod_coffee_df_melted, x ='Value', hue = 'Country.of.Origin',\n",
    "            col = 'Score',col_wrap =2, aspect=1.5, kind = 'kde')"
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "text_representation": {
    "extension": ".md",
    "format_name": "myst",
    "format_version": 0.13,
    "jupytext_version": "1.10.3"
   }
  },
  "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": "3.8.13"
  },
  "source_map": [
   12,
   33,
   39,
   60,
   66,
   70,
   74,
   78,
   80,
   88,
   90,
   92,
   94,
   98,
   100,
   103,
   105,
   108,
   113,
   115,
   125,
   127,
   130,
   132,
   138,
   144,
   151,
   153,
   158,
   161,
   164,
   167,
   171,
   173,
   177,
   181,
   184,
   189,
   191,
   194,
   196,
   200,
   202,
   205,
   207,
   210,
   214,
   216,
   220,
   222,
   229,
   231,
   252,
   262,
   268
  ]
 },
 "nbformat": 4,
 "nbformat_minor": 5
}