04_Merging_Flight_and_Weather_Data.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "increased-lighter",
   "metadata": {},
   "source": [
    "# Flight Delay Prediction\n",
    "## Merging Flight and Weather Data\n",
    "\n",
    "- Loading the aggregated flight and weather dataset csv files into Data Frames\n",
    "- Column <strong>time</strong> in the weather dataset has been rounded to the nearest hour\n",
    "- Processing the <strong>CRSDepTime</strong> column in the <strong>flight dataset</strong> to set up a <strong>Time_new</strong> column for merging by rounding to the nearest hour to match with the <strong>weather dataset</strong>\n",
    "- Merging both the datasets into a df\n",
    "- Ensuring by visualizing that the data has no missing values\n",
    "- Storing df as <strong>flight_and_weather.csv</strong> in the <strong>Data</strong> directory"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "brilliant-collectible",
   "metadata": {},
   "source": [
    "## Prerequisites"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "atmospheric-diameter",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/admin/.local/lib/python3.8/site-packages/numpy/lib/arraysetops.py:580: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n",
      "  mask |= (ar1 == a)\n"
     ]
    }
   ],
   "source": [
    "# Loading the required modules\n",
    "import pandas as pd\n",
    "import missingno as msno\n",
    "\n",
    "# Loading the aggregated flight dataset and weather dataset\n",
    "fd_df = pd.read_csv(\"Data/flight_data.csv\", index_col=0)\n",
    "wd_df = pd.read_csv(\"Data/weather_data.csv\", index_col=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "chronic-brown",
   "metadata": {},
   "source": [
    "## Merge Criteria Analysis\n",
    "The time column observations are rounded up to the nearest full hour in the weather dataset. Therefore, the CRSDepTime (scheduled flight departure time) of the flight dataset is also rounded up to the nearest full hour, so that the column can be equi-joined with the weather dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "tribal-increase",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0            0\n",
       "1          100\n",
       "2          200\n",
       "3          300\n",
       "4          400\n",
       "          ... \n",
       "263155    1900\n",
       "263156    2000\n",
       "263157    2100\n",
       "263158    2200\n",
       "263159    2300\n",
       "Name: time, Length: 263160, dtype: int64"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wd_df[\"time\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "material-fetish",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0          2010\n",
       "1          1450\n",
       "2          2025\n",
       "3            52\n",
       "4          1445\n",
       "           ... \n",
       "1851431    1500\n",
       "1851432    1820\n",
       "1851433     955\n",
       "1851434     630\n",
       "1851435    1235\n",
       "Name: CRSDepTime, Length: 1851436, dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fd_df[\"CRSDepTime\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cathedral-geography",
   "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>Time_new</th>\n",
       "      <th>CRSDepTime</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2000</td>\n",
       "      <td>2010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1500</td>\n",
       "      <td>1450</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2000</td>\n",
       "      <td>2025</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100</td>\n",
       "      <td>52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1500</td>\n",
       "      <td>1445</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1851431</th>\n",
       "      <td>1500</td>\n",
       "      <td>1500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1851432</th>\n",
       "      <td>1800</td>\n",
       "      <td>1820</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1851433</th>\n",
       "      <td>1000</td>\n",
       "      <td>955</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1851434</th>\n",
       "      <td>700</td>\n",
       "      <td>630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1851435</th>\n",
       "      <td>1300</td>\n",
       "      <td>1235</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1851436 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         Time_new  CRSDepTime\n",
       "0            2000        2010\n",
       "1            1500        1450\n",
       "2            2000        2025\n",
       "3             100          52\n",
       "4            1500        1445\n",
       "...           ...         ...\n",
       "1851431      1500        1500\n",
       "1851432      1800        1820\n",
       "1851433      1000         955\n",
       "1851434       700         630\n",
       "1851435      1300        1235\n",
       "\n",
       "[1851436 rows x 2 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating a list to store the rounded CRSDepTime of flight data \n",
    "new_time = []\n",
    "# Iterating through CRSDepTime\n",
    "for time in fd_df[\"CRSDepTime\"]:\n",
    "    time = int(time)\n",
    "    # Obtaining the minutes\n",
    "    m = time % 100\n",
    "    # If it is less than 30 mins, just subtract to round down\n",
    "    if m < 30:\n",
    "        time = time - m\n",
    "    # If it is greater than or equal to 30 mins, round up\n",
    "    elif(m >= 30) :\n",
    "        time = time + (100 - m)\n",
    "    # If it is 2400, make it 0\n",
    "    if(time == 2400):\n",
    "        time = 0\n",
    "    new_time.append(time)\n",
    "fd_df[\"Time_new\"] = new_time\n",
    "fd_df[[\"Time_new\", \"CRSDepTime\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dressed-excuse",
   "metadata": {},
   "source": [
    "## Merging the Flight and Weather Data\n",
    "Merging the data based on the departure airport, scheduled departure time (CRSDepTime) and date."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "white-uzbekistan",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Merging the data based on the departure airport, scheduled departure time and date\n",
    "merged_df = pd.merge(fd_df, wd_df,\n",
    "              how = \"inner\",\n",
    "              left_on = [\"Origin\",\"Time_new\", \"FlightDate\"],\n",
    "              right_on = [\"airport\",\"time\", \"date\"])\n",
    "# Storing the merged dataset as a csv file\n",
    "merged_df.to_csv(\"Data/flight_and_weather.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "charming-mauritius",
   "metadata": {},
   "source": [
    "## Checking for Missing Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "emerging-pittsburgh",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AxesSubplot(0.125,0.125;0.698618x0.755)\n",
      "Year               0\n",
      "Quarter            0\n",
      "Month              0\n",
      "DayofMonth         0\n",
      "FlightDate         0\n",
      "OriginAirportID    0\n",
      "Origin             0\n",
      "DestAirportID      0\n",
      "Dest               0\n",
      "CRSDepTime         0\n",
      "DepTime            0\n",
      "DepDelayMinutes    0\n",
      "DepDel15           0\n",
      "CRSArrTime         0\n",
      "ArrTime            0\n",
      "ArrDelayMinutes    0\n",
      "ArrDel15           0\n",
      "Time_new           0\n",
      "windspeedKmph      0\n",
      "winddirDegree      0\n",
      "weatherCode        0\n",
      "precipMM           0\n",
      "visibility         0\n",
      "pressure           0\n",
      "cloudcover         0\n",
      "DewPointF          0\n",
      "WindGustKmph       0\n",
      "tempF              0\n",
      "WindChillF         0\n",
      "humidity           0\n",
      "date               0\n",
      "time               0\n",
      "airport            0\n",
      "dtype: int64\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1800x720 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "print(msno.matrix(merged_df))\n",
    "print(merged_df.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ceramic-trigger",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape: (1851436, 33)\n",
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 1851436 entries, 0 to 1851435\n",
      "Data columns (total 33 columns):\n",
      " #   Column           Dtype  \n",
      "---  ------           -----  \n",
      " 0   Year             int64  \n",
      " 1   Quarter          int64  \n",
      " 2   Month            int64  \n",
      " 3   DayofMonth       int64  \n",
      " 4   FlightDate       object \n",
      " 5   OriginAirportID  int64  \n",
      " 6   Origin           object \n",
      " 7   DestAirportID    int64  \n",
      " 8   Dest             object \n",
      " 9   CRSDepTime       int64  \n",
      " 10  DepTime          float64\n",
      " 11  DepDelayMinutes  float64\n",
      " 12  DepDel15         float64\n",
      " 13  CRSArrTime       int64  \n",
      " 14  ArrTime          float64\n",
      " 15  ArrDelayMinutes  float64\n",
      " 16  ArrDel15         float64\n",
      " 17  Time_new         int64  \n",
      " 18  windspeedKmph    int64  \n",
      " 19  winddirDegree    int64  \n",
      " 20  weatherCode      int64  \n",
      " 21  precipMM         float64\n",
      " 22  visibility       int64  \n",
      " 23  pressure         int64  \n",
      " 24  cloudcover       int64  \n",
      " 25  DewPointF        int64  \n",
      " 26  WindGustKmph     int64  \n",
      " 27  tempF            int64  \n",
      " 28  WindChillF       int64  \n",
      " 29  humidity         int64  \n",
      " 30  date             object \n",
      " 31  time             int64  \n",
      " 32  airport          object \n",
      "dtypes: float64(7), int64(21), object(5)\n",
      "memory usage: 480.3+ MB\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "print(f\"Shape: {merged_df.shape}\\n\\n\")\n",
    "print(merged_df.info())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "steady-shopper",
   "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>Year</th>\n",
       "      <th>Quarter</th>\n",
       "      <th>Month</th>\n",
       "      <th>DayofMonth</th>\n",
       "      <th>FlightDate</th>\n",
       "      <th>OriginAirportID</th>\n",
       "      <th>Origin</th>\n",
       "      <th>DestAirportID</th>\n",
       "      <th>Dest</th>\n",
       "      <th>CRSDepTime</th>\n",
       "      <th>...</th>\n",
       "      <th>pressure</th>\n",
       "      <th>cloudcover</th>\n",
       "      <th>DewPointF</th>\n",
       "      <th>WindGustKmph</th>\n",
       "      <th>tempF</th>\n",
       "      <th>WindChillF</th>\n",
       "      <th>humidity</th>\n",
       "      <th>date</th>\n",
       "      <th>time</th>\n",
       "      <th>airport</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2017</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>11618</td>\n",
       "      <td>EWR</td>\n",
       "      <td>13930</td>\n",
       "      <td>ORD</td>\n",
       "      <td>2010</td>\n",
       "      <td>...</td>\n",
       "      <td>1018</td>\n",
       "      <td>13</td>\n",
       "      <td>68</td>\n",
       "      <td>8</td>\n",
       "      <td>78</td>\n",
       "      <td>78</td>\n",
       "      <td>73</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>2000</td>\n",
       "      <td>EWR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2017</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>11618</td>\n",
       "      <td>EWR</td>\n",
       "      <td>12266</td>\n",
       "      <td>IAH</td>\n",
       "      <td>2025</td>\n",
       "      <td>...</td>\n",
       "      <td>1018</td>\n",
       "      <td>13</td>\n",
       "      <td>68</td>\n",
       "      <td>8</td>\n",
       "      <td>78</td>\n",
       "      <td>78</td>\n",
       "      <td>73</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>2000</td>\n",
       "      <td>EWR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>11618</td>\n",
       "      <td>EWR</td>\n",
       "      <td>13204</td>\n",
       "      <td>MCO</td>\n",
       "      <td>1935</td>\n",
       "      <td>...</td>\n",
       "      <td>1018</td>\n",
       "      <td>13</td>\n",
       "      <td>68</td>\n",
       "      <td>8</td>\n",
       "      <td>78</td>\n",
       "      <td>78</td>\n",
       "      <td>73</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>2000</td>\n",
       "      <td>EWR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2017</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>11618</td>\n",
       "      <td>EWR</td>\n",
       "      <td>14107</td>\n",
       "      <td>PHX</td>\n",
       "      <td>1930</td>\n",
       "      <td>...</td>\n",
       "      <td>1018</td>\n",
       "      <td>13</td>\n",
       "      <td>68</td>\n",
       "      <td>8</td>\n",
       "      <td>78</td>\n",
       "      <td>78</td>\n",
       "      <td>73</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>2000</td>\n",
       "      <td>EWR</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2017</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>11618</td>\n",
       "      <td>EWR</td>\n",
       "      <td>14747</td>\n",
       "      <td>SEA</td>\n",
       "      <td>1940</td>\n",
       "      <td>...</td>\n",
       "      <td>1018</td>\n",
       "      <td>13</td>\n",
       "      <td>68</td>\n",
       "      <td>8</td>\n",
       "      <td>78</td>\n",
       "      <td>78</td>\n",
       "      <td>73</td>\n",
       "      <td>2017-10-06</td>\n",
       "      <td>2000</td>\n",
       "      <td>EWR</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Year  Quarter  Month  DayofMonth  FlightDate  OriginAirportID Origin  \\\n",
       "0  2017        4     10           6  2017-10-06            11618    EWR   \n",
       "1  2017        4     10           6  2017-10-06            11618    EWR   \n",
       "2  2017        4     10           6  2017-10-06            11618    EWR   \n",
       "3  2017        4     10           6  2017-10-06            11618    EWR   \n",
       "4  2017        4     10           6  2017-10-06            11618    EWR   \n",
       "\n",
       "   DestAirportID Dest  CRSDepTime  ...  pressure  cloudcover  DewPointF  \\\n",
       "0          13930  ORD        2010  ...      1018          13         68   \n",
       "1          12266  IAH        2025  ...      1018          13         68   \n",
       "2          13204  MCO        1935  ...      1018          13         68   \n",
       "3          14107  PHX        1930  ...      1018          13         68   \n",
       "4          14747  SEA        1940  ...      1018          13         68   \n",
       "\n",
       "   WindGustKmph  tempF  WindChillF  humidity        date  time  airport  \n",
       "0             8     78          78        73  2017-10-06  2000      EWR  \n",
       "1             8     78          78        73  2017-10-06  2000      EWR  \n",
       "2             8     78          78        73  2017-10-06  2000      EWR  \n",
       "3             8     78          78        73  2017-10-06  2000      EWR  \n",
       "4             8     78          78        73  2017-10-06  2000      EWR  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "provincial-color",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1851436, 33)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "merged_df.drop_duplicates()\n",
    "print(merged_df.shape, end=\"\\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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}