HW4-2-Bird_Flight_Patterns.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Using Python for Research Homework: Week 4, Case Study 2\n",
    "\n",
    "In this case study, we will continue taking a look at patterns of flight for each of the three birds in our dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "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>altitude</th>\n",
       "      <th>date_time</th>\n",
       "      <th>device_info_serial</th>\n",
       "      <th>direction</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>speed_2d</th>\n",
       "      <th>bird_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>71</td>\n",
       "      <td>2013-08-15 00:18:08+00</td>\n",
       "      <td>851</td>\n",
       "      <td>-150.469753</td>\n",
       "      <td>49.419860</td>\n",
       "      <td>2.120733</td>\n",
       "      <td>0.150000</td>\n",
       "      <td>Eric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>68</td>\n",
       "      <td>2013-08-15 00:48:07+00</td>\n",
       "      <td>851</td>\n",
       "      <td>-136.151141</td>\n",
       "      <td>49.419880</td>\n",
       "      <td>2.120746</td>\n",
       "      <td>2.438360</td>\n",
       "      <td>Eric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>68</td>\n",
       "      <td>2013-08-15 01:17:58+00</td>\n",
       "      <td>851</td>\n",
       "      <td>160.797477</td>\n",
       "      <td>49.420310</td>\n",
       "      <td>2.120885</td>\n",
       "      <td>0.596657</td>\n",
       "      <td>Eric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>73</td>\n",
       "      <td>2013-08-15 01:47:51+00</td>\n",
       "      <td>851</td>\n",
       "      <td>32.769360</td>\n",
       "      <td>49.420359</td>\n",
       "      <td>2.120859</td>\n",
       "      <td>0.310161</td>\n",
       "      <td>Eric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>69</td>\n",
       "      <td>2013-08-15 02:17:42+00</td>\n",
       "      <td>851</td>\n",
       "      <td>45.191230</td>\n",
       "      <td>49.420331</td>\n",
       "      <td>2.120887</td>\n",
       "      <td>0.193132</td>\n",
       "      <td>Eric</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   altitude               date_time  device_info_serial   direction  \\\n",
       "0        71  2013-08-15 00:18:08+00                 851 -150.469753   \n",
       "1        68  2013-08-15 00:48:07+00                 851 -136.151141   \n",
       "2        68  2013-08-15 01:17:58+00                 851  160.797477   \n",
       "3        73  2013-08-15 01:47:51+00                 851   32.769360   \n",
       "4        69  2013-08-15 02:17:42+00                 851   45.191230   \n",
       "\n",
       "    latitude  longitude  speed_2d bird_name  \n",
       "0  49.419860   2.120733  0.150000      Eric  \n",
       "1  49.419880   2.120746  2.438360      Eric  \n",
       "2  49.420310   2.120885  0.596657      Eric  \n",
       "3  49.420359   2.120859  0.310161      Eric  \n",
       "4  49.420331   2.120887  0.193132      Eric  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# DO NOT EDIT THIS CODE\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "birddata = pd.read_csv(\"https://courses.edx.org/asset-v1:HarvardX+PH526x+2T2019+type@asset+block@bird_tracking.csv\", index_col=0)\n",
    "birddata.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 1\n",
    "\n",
    "In this case study, we will continue taking a look at patterns of flight for each of the three birds in our dataset. We will group the flight patterns by bird and date, and plot the mean altitude for these groupings.\n",
    "\n",
    "`pandas` makes it easy to perform basic operations on groups within a dataframe without needing to loop through each value in the dataframe. In this exercise, we will group the dataframe by `birdname` and then find the average `speed_2d` for each bird.\n",
    "\n",
    "#### Instructions \n",
    "- Fill in the code to find the mean altitudes of each bird using the pre-loaded `birddata` dataframe. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# First, use `groupby()` to group the data by \"bird_name\".\n",
    "grouped_birds = birddata.groupby('bird_name')\n",
    "\n",
    "# Now calculate the mean of `speed_2d` using the `mean()` function.\n",
    "mean_speeds = grouped_birds['speed_2d'].mean()\n",
    "# Find the mean `altitude` for each bird.\n",
    "mean_altitudes = grouped_birds['altitude'].mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 2\n",
    "\n",
    "In this exercise, we will group the flight times by date and calculate the mean altitude within that day.\n",
    "\n",
    "#### Instructions \n",
    "- Convert `birddata.date_time` to the `pd.datetime` format, and store as `birddata[\"date\"]`.\n",
    "- Fill in the code to find the mean altitudes for each day."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert birddata.date_time to the `pd.datetime` format.\n",
    "date_times = []\n",
    "for i in range(len(birddata.date_time)):\n",
    "    date_times.append(pd.to_datetime(birddata.date_time.iloc[i][0:-12], format='%Y-%m-%d %H:%M:%S'))\n",
    "    \n",
    "# Create a new column of day of observation\n",
    "birddata[\"date\"] = date_times\n",
    "\n",
    "# Use `groupby()` to group the data by date.\n",
    "grouped_bydates = birddata.groupby('date')\n",
    "\n",
    "# Find the mean `altitude` for each date.\n",
    "mean_altitudes_perday = grouped_bydates['altitude'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bird_name  date      \n",
       "Eric       2013-08-15     74.988095\n",
       "           2013-08-16    127.773810\n",
       "           2013-08-17    125.890244\n",
       "           2013-08-18    121.353659\n",
       "           2013-08-19    134.928571\n",
       "Name: altitude, dtype: float64"
      ]
     },
     "execution_count": 163,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_altitudes_perday[0:5]\n",
    "# birddata.groupby('date').mean()[25:30]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 3\n",
    "\n",
    "In this exercise, we will group the flight times by both bird and date, and calculate the mean altitude for each.\n",
    "\n",
    "#### Instructions \n",
    "- `birddata` already contains the `date` column. To find the average speed for each bird and day, create a new grouped dataframe called `grouped_birdday` that groups the data by both `bird_name` and date."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use `groupby()` to group the data by bird and date.\n",
    "grouped_birdday = birddata.groupby(['bird_name', 'date'])\n",
    "\n",
    "# Find the mean `altitude` for each bird and date.\n",
    "mean_altitudes_perday = grouped_birdday['altitude'].mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 4\n",
    "\n",
    "Great! Now find the average speed for each bird and day.\n",
    "\n",
    "#### Instructions \n",
    "\n",
    "- Store these are three `pandas` `Series` objects, one for each bird.\n",
    "- Use the plotting code provided to plot the average speeds for each bird."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "eric_daily_speed  = grouped_birdday['speed_2d'].mean()[:252]\n",
    "sanne_daily_speed = grouped_birdday['speed_2d'].mean()[511:]\n",
    "nico_daily_speed  = grouped_birdday['speed_2d'].mean()[252:511]\n",
    "\n",
    "eric_daily_speed.plot(label=\"Eric\")\n",
    "sanne_daily_speed.plot(label=\"Sanne\")\n",
    "nico_daily_speed.plot(label=\"Nico\")\n",
    "plt.legend(loc=\"upper left\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "bird_name  date      \n",
       "Nico       2014-03-31     2.824631\n",
       "           2014-04-01     3.163723\n",
       "           2014-04-02     2.861222\n",
       "           2014-04-03     3.212099\n",
       "           2014-04-04     2.832465\n",
       "           2014-04-05     3.283842\n",
       "           2014-04-06     2.824700\n",
       "           2014-04-07     3.455989\n",
       "           2014-04-08     2.995421\n",
       "           2014-04-09     3.780186\n",
       "           2014-04-10     3.703409\n",
       "           2014-04-11     2.829536\n",
       "           2014-04-12     3.341111\n",
       "           2014-04-13     3.878121\n",
       "           2014-04-14     3.882314\n",
       "           2014-04-15     4.437659\n",
       "           2014-04-16     3.366451\n",
       "           2014-04-17     3.713230\n",
       "           2014-04-18     3.798646\n",
       "           2014-04-19     5.061530\n",
       "           2014-04-20    10.196981\n",
       "           2014-04-21     7.861385\n",
       "           2014-04-22     9.445087\n",
       "           2014-04-23     6.384096\n",
       "           2014-04-24     2.674536\n",
       "           2014-04-25     2.705160\n",
       "           2014-04-26     2.192028\n",
       "           2014-04-27     2.582072\n",
       "           2014-04-28     3.055051\n",
       "           2014-04-29     2.793232\n",
       "           2014-04-30     3.297032\n",
       "Name: speed_2d, dtype: float64"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped_birdday['speed_2d'].mean()[480:511]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": 2
}