{"cells":[{"metadata":{},"id":"19f2643f-063c-4b69-818d-f9ecfd35dd86","cell_type":"markdown","source":"# How to Pivot and Plot Data With Pandas\n\nA big challenge of working with data is manipulating its format for the analysis at hand. To make things a bit more difficult, the \"proper format\" can depend on what you are trying to analyze, meaning we have to know how to melt, pivot, and transpose our data.\n\nIn this article, we will discuss how to create a pivot table of aggregated data in order to make a stacked bar visualization of 2019 airline market share for the top 10 destination cities. All the code for this analysis is available on GitHub [here](https://github.com/stefmolin/airline-market-share-analysis) and can also be run using [this](https://mybinder.org/v2/gh/stefmolin/airline-market-share-analysis/master) Binder environment.\n\nWe will be using 2019 flight statistics from the United States Department of Transportation’s Bureau of Transportation Statistics (available [here](https://www.transtats.bts.gov/DL_SelectFields.asp?gnoyr_VQ=FMF&QO_fu146_anzr=Nv4%20Pn44vr45)). It contains 321,409 rows and 41 columns:"},{"metadata":{"trusted":true},"id":"323e257b-4e6f-4943-a53c-bf10ce412570","cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_csv('865214564_T_T100_MARKET_ALL_CARRIER.zip')\ndf.shape","execution_count":1,"outputs":[{"output_type":"execute_result","execution_count":1,"data":{"text/plain":"(321409, 41)"},"metadata":{}}]},{"metadata":{},"id":"c57b16d2-c117-4319-877a-4bf5a7055a51","cell_type":"markdown","source":"Each row contains monthly-aggregated information on flights operated by a variety of airline carriers, including both passenger and cargo service. Note that the columns are all in uppercase at the moment:"},{"metadata":{"trusted":true},"id":"419e6629-8d24-4447-8e42-75bba22e9b73","cell_type":"code","source":"df.columns","execution_count":2,"outputs":[{"output_type":"execute_result","execution_count":2,"data":{"text/plain":"Index(['PASSENGERS', 'FREIGHT', 'MAIL', 'DISTANCE', 'UNIQUE_CARRIER',\n       'AIRLINE_ID', 'UNIQUE_CARRIER_NAME', 'UNIQUE_CARRIER_ENTITY', 'REGION',\n       'CARRIER', 'CARRIER_NAME', 'CARRIER_GROUP', 'CARRIER_GROUP_NEW',\n       'ORIGIN_AIRPORT_ID', 'ORIGIN_AIRPORT_SEQ_ID', 'ORIGIN_CITY_MARKET_ID',\n       'ORIGIN', 'ORIGIN_CITY_NAME', 'ORIGIN_STATE_ABR', 'ORIGIN_STATE_FIPS',\n       'ORIGIN_STATE_NM', 'ORIGIN_COUNTRY', 'ORIGIN_COUNTRY_NAME',\n       'ORIGIN_WAC', 'DEST_AIRPORT_ID', 'DEST_AIRPORT_SEQ_ID',\n       'DEST_CITY_MARKET_ID', 'DEST', 'DEST_CITY_NAME', 'DEST_STATE_ABR',\n       'DEST_STATE_FIPS', 'DEST_STATE_NM', 'DEST_COUNTRY', 'DEST_COUNTRY_NAME',\n       'DEST_WAC', 'YEAR', 'QUARTER', 'MONTH', 'DISTANCE_GROUP', 'CLASS',\n       'DATA_SOURCE'],\n      dtype='object')"},"metadata":{}}]},{"metadata":{},"id":"b512ac68-e156-4082-84cd-8c4158304172","cell_type":"markdown","source":"To make the data easier to work with, we will transform the column names into lowercase using the `rename()` method:"},{"metadata":{"trusted":true},"id":"107d74c9-ce33-4e41-8f96-d52b0ec91c6f","cell_type":"code","source":"df = df.rename(lambda x: x.lower(), axis=1)\ndf.head()","execution_count":3,"outputs":[{"output_type":"execute_result","execution_count":3,"data":{"text/plain":"   passengers    freight  mail  distance unique_carrier  airline_id  \\\n0         0.0    53185.0   0.0    8165.0             EK       20392   \n1         0.0     9002.0   0.0    6849.0             EK       20392   \n2         0.0  2220750.0   0.0    7247.0             EK       20392   \n3         0.0  1201490.0   0.0    8165.0             EK       20392   \n4         0.0   248642.0   0.0    6849.0             EK       20392   \n\n  unique_carrier_name unique_carrier_entity region carrier  ... dest_state_nm  \\\n0            Emirates                 9678A      I      EK  ...         Texas   \n1            Emirates                 9678A      I      EK  ...      New York   \n2            Emirates                 9678A      I      EK  ...      Illinois   \n3            Emirates                 9678A      I      EK  ...           NaN   \n4            Emirates                 9678A      I      EK  ...           NaN   \n\n   dest_country     dest_country_name  dest_wac  year  quarter month  \\\n0            US         United States        74  2019        1     3   \n1            US         United States        22  2019        1     3   \n2            US         United States        41  2019        1     3   \n3            AE  United Arab Emirates       678  2019        1     3   \n4            AE  United Arab Emirates       678  2019        1     3   \n\n  distance_group class  data_source  \n0             17     G           IF  \n1             14     G           IF  \n2             15     G           IF  \n3             17     G           IF  \n4             14     G           IF  \n\n[5 rows x 41 columns]","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>passengers</th>\n      <th>freight</th>\n      <th>mail</th>\n      <th>distance</th>\n      <th>unique_carrier</th>\n      <th>airline_id</th>\n      <th>unique_carrier_name</th>\n      <th>unique_carrier_entity</th>\n      <th>region</th>\n      <th>carrier</th>\n      <th>...</th>\n      <th>dest_state_nm</th>\n      <th>dest_country</th>\n      <th>dest_country_name</th>\n      <th>dest_wac</th>\n      <th>year</th>\n      <th>quarter</th>\n      <th>month</th>\n      <th>distance_group</th>\n      <th>class</th>\n      <th>data_source</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0.0</td>\n      <td>53185.0</td>\n      <td>0.0</td>\n      <td>8165.0</td>\n      <td>EK</td>\n      <td>20392</td>\n      <td>Emirates</td>\n      <td>9678A</td>\n      <td>I</td>\n      <td>EK</td>\n      <td>...</td>\n      <td>Texas</td>\n      <td>US</td>\n      <td>United States</td>\n      <td>74</td>\n      <td>2019</td>\n      <td>1</td>\n      <td>3</td>\n      <td>17</td>\n      <td>G</td>\n      <td>IF</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>0.0</td>\n      <td>9002.0</td>\n      <td>0.0</td>\n      <td>6849.0</td>\n      <td>EK</td>\n      <td>20392</td>\n      <td>Emirates</td>\n      <td>9678A</td>\n      <td>I</td>\n      <td>EK</td>\n      <td>...</td>\n      <td>New York</td>\n      <td>US</td>\n      <td>United States</td>\n      <td>22</td>\n      <td>2019</td>\n      <td>1</td>\n      <td>3</td>\n      <td>14</td>\n      <td>G</td>\n      <td>IF</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>0.0</td>\n      <td>2220750.0</td>\n      <td>0.0</td>\n      <td>7247.0</td>\n      <td>EK</td>\n      <td>20392</td>\n      <td>Emirates</td>\n      <td>9678A</td>\n      <td>I</td>\n      <td>EK</td>\n      <td>...</td>\n      <td>Illinois</td>\n      <td>US</td>\n      <td>United States</td>\n      <td>41</td>\n      <td>2019</td>\n      <td>1</td>\n      <td>3</td>\n      <td>15</td>\n      <td>G</td>\n      <td>IF</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>0.0</td>\n      <td>1201490.0</td>\n      <td>0.0</td>\n      <td>8165.0</td>\n      <td>EK</td>\n      <td>20392</td>\n      <td>Emirates</td>\n      <td>9678A</td>\n      <td>I</td>\n      <td>EK</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>AE</td>\n      <td>United Arab Emirates</td>\n      <td>678</td>\n      <td>2019</td>\n      <td>1</td>\n      <td>3</td>\n      <td>17</td>\n      <td>G</td>\n      <td>IF</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0.0</td>\n      <td>248642.0</td>\n      <td>0.0</td>\n      <td>6849.0</td>\n      <td>EK</td>\n      <td>20392</td>\n      <td>Emirates</td>\n      <td>9678A</td>\n      <td>I</td>\n      <td>EK</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>AE</td>\n      <td>United Arab Emirates</td>\n      <td>678</td>\n      <td>2019</td>\n      <td>1</td>\n      <td>3</td>\n      <td>14</td>\n      <td>G</td>\n      <td>IF</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 41 columns</p>\n</div>"},"metadata":{}}]},{"metadata":{},"id":"01f939b5-d7b5-48a4-aad0-2afb8ae99439","cell_type":"markdown","source":"For our analysis, we want to look at passenger airlines to find the 2019 market share of the top 5 carriers (based on total number of passengers in 2019). To do so, we first need to figure out which carriers were in the top 5. Remember, the data contains information on all types of flights, but we only want passenger flights, so we first query `df` for flights marked `F` in the `class` column (note that we need backticks to reference this column because `class` is a reserved keyword). Then, we group by the carrier name and sum each carrier's passenger counts. Finally, we call the `nlargest()` method to return only the top 5:"},{"metadata":{"trusted":true},"id":"6c52b07f-767a-4323-91d1-506c508edab2","cell_type":"code","source":"# download flight class meanings at\n# https://www.transtats.bts.gov/Download_Lookup.asp?Y11x72=Y_fReiVPR_PYNff\ntop_airlines = df.query('`class` == \"F\"')\\\n    .groupby('unique_carrier_name').passengers.sum()\\\n    .nlargest(5)\ntop_airlines","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":"unique_carrier_name\nSouthwest Airlines Co.    162681011.0\nDelta Air Lines Inc.      162260114.0\nAmerican Airlines Inc.    155782611.0\nUnited Air Lines Inc.     116212143.0\nJetBlue Airways            42830602.0\nName: passengers, dtype: float64"},"metadata":{}}]},{"metadata":{},"id":"16f2c170-59b3-4561-9782-50824825fa3e","cell_type":"markdown","source":"Note that the top 5 airlines also run flights of a different class, so we can't remove this filter for the rest of our analysis:"},{"metadata":{"trusted":true},"id":"001a9bab-731f-48c5-83da-712f796e940f","cell_type":"code","source":"df.loc[\n    df.unique_carrier_name.isin(top_airlines.index), 'class'\n].value_counts()","execution_count":5,"outputs":[{"output_type":"execute_result","execution_count":5,"data":{"text/plain":"F    97293\nL     3994\nName: class, dtype: int64"},"metadata":{}}]},{"metadata":{},"id":"2673fdbe-28b4-4e02-9e7d-e43a7d50bcd8","cell_type":"markdown","source":"Now, we can create the pivot table; however, we cannot filter down to the top 5 airlines just yet, because, in order to get market share, we need to know the numbers for the other airlines as well. Therefore, we will build a pivot table that calculates the total number of passengers each airline flew to each destination city. To do so, we specify that we want the following in our call to the `pivot_table()` method:\n\n- Unique values in the `dest_city_name` column should be used as our row labels (the `index` argument)\n- Unique values in the `unique_carrier_name` column should be used as our column labels (the `columns` argument)\n- The values used for the aggregation should come from the `passengers` column (the `values` argument), and they should be summed (the `aggfunc` argument)\n- Row/column subtotals should be calculated (the `margins` argument)\n\nFinally, since we want to look at the top 10 destinations, we will sort the data in descending order using the `All` column, which contains the total passengers flown to each city in 2019 for all carriers combined (this was created by passing in `margins=True` in the call to the `pivot_table()` method):"},{"metadata":{"trusted":true},"id":"80a948dc-e47b-48f6-bfb8-a981b91659e6","cell_type":"code","source":"pivot = df.query('`class` == \"F\"').pivot_table(\n    index='dest_city_name', \n    columns='unique_carrier_name', \n    values='passengers',\n    aggfunc='sum', \n    margins=True\n).sort_values('All', ascending=False)\npivot.head(10)","execution_count":6,"outputs":[{"output_type":"execute_result","execution_count":6,"data":{"text/plain":"unique_carrier_name    40-Mile Air  ABC Aerolineas SA de CV dba Interjet  \\\ndest_city_name                                                             \nAll                          502.0                             2249942.0   \nAtlanta, GA                    NaN                                   NaN   \nChicago, IL                    NaN                              134049.0   \nNew York, NY                   NaN                              150680.0   \nLos Angeles, CA                NaN                              226119.0   \nDallas/Fort Worth, TX          NaN                               75046.0   \nDenver, CO                     NaN                                   NaN   \nHouston, TX                    NaN                              107018.0   \nSan Francisco, CA              NaN                               59014.0   \nSeattle, WA                    NaN                                   NaN   \n\nunique_carrier_name    ADVANCED AIR, LLC  Aer Lingus Plc  \\\ndest_city_name                                             \nAll                              27049.0       2396297.0   \nAtlanta, GA                          NaN             NaN   \nChicago, IL                          NaN        175630.0   \nNew York, NY                         NaN        243337.0   \nLos Angeles, CA                      0.0         73206.0   \nDallas/Fort Worth, TX                NaN             NaN   \nDenver, CO                           NaN             NaN   \nHouston, TX                          NaN             NaN   \nSan Francisco, CA                    NaN         91075.0   \nSeattle, WA                          NaN         46682.0   \n\nunique_carrier_name    Aeroenlaces Nacionales, S.A. de C.V. d/b/a VivaAerobus  \\\ndest_city_name                                                                  \nAll                                                             503660.0        \nAtlanta, GA                                                          NaN        \nChicago, IL                                                       5189.0        \nNew York, NY                                                     46497.0        \nLos Angeles, CA                                                  66846.0        \nDallas/Fort Worth, TX                                                NaN        \nDenver, CO                                                           NaN        \nHouston, TX                                                      50053.0        \nSan Francisco, CA                                                    NaN        \nSeattle, WA                                                          NaN        \n\nunique_carrier_name    Aeroflot Russian Airlines  Aerolineas Argentinas  \\\ndest_city_name                                                            \nAll                                     893421.0               406959.0   \nAtlanta, GA                                  NaN                    NaN   \nChicago, IL                                  NaN                    NaN   \nNew York, NY                            277853.0                64696.0   \nLos Angeles, CA                          98407.0                    NaN   \nDallas/Fort Worth, TX                        NaN                    NaN   \nDenver, CO                                   NaN                    NaN   \nHouston, TX                                  NaN                    NaN   \nSan Francisco, CA                            NaN                    NaN   \nSeattle, WA                                  NaN                    NaN   \n\nunique_carrier_name    Aerolitoral  Aeromexico  Aerovias Nacl De Colombia  \\\ndest_city_name                                                              \nAll                       767266.0   2660861.0                  1796877.0   \nAtlanta, GA                42332.0         NaN                        NaN   \nChicago, IL                    NaN    183061.0                     5998.0   \nNew York, NY               28660.0    217652.0                   238556.0   \nLos Angeles, CA            42672.0    281284.0                    76943.0   \nDallas/Fort Worth, TX      44437.0         NaN                        NaN   \nDenver, CO                   660.0     18101.0                        NaN   \nHouston, TX                72805.0      2780.0                        NaN   \nSan Francisco, CA              NaN    171296.0                        NaN   \nSeattle, WA                    NaN     44214.0                        NaN   \n\nunique_carrier_name    ...  Virgin Atlantic Airways  \\\ndest_city_name         ...                            \nAll                    ...                4139847.0   \nAtlanta, GA            ...                 166993.0   \nChicago, IL            ...                    203.0   \nNew York, NY           ...                 589804.0   \nLos Angeles, CA        ...                 171369.0   \nDallas/Fort Worth, TX  ...                      NaN   \nDenver, CO             ...                      NaN   \nHouston, TX            ...                      NaN   \nSan Francisco, CA      ...                 144379.0   \nSeattle, WA            ...                  74802.0   \n\nunique_carrier_name    Virgin Blue International Airlines t/a V Australia  \\\ndest_city_name                                                              \nAll                                                             507699.0    \nAtlanta, GA                                                          NaN    \nChicago, IL                                                          NaN    \nNew York, NY                                                         NaN    \nLos Angeles, CA                                                 250857.0    \nDallas/Fort Worth, TX                                                NaN    \nDenver, CO                                                           NaN    \nHouston, TX                                                          NaN    \nSan Francisco, CA                                                    NaN    \nSeattle, WA                                                          NaN    \n\nunique_carrier_name    Vuela Aviacion, S.A.  WOW Air ehf  Warbelow    Westjet  \\\ndest_city_name                                                                  \nAll                                170673.0      46485.0    4414.0  5273827.0   \nAtlanta, GA                             NaN          NaN       NaN    45398.0   \nChicago, IL                             NaN       2801.0       NaN        NaN   \nNew York, NY                        18722.0          NaN       NaN   309748.0   \nLos Angeles, CA                     45140.0       1999.0       NaN   371214.0   \nDallas/Fort Worth, TX                   NaN          NaN       NaN        NaN   \nDenver, CO                              NaN          NaN       NaN    18151.0   \nHouston, TX                             NaN          NaN       NaN    61949.0   \nSan Francisco, CA                       NaN          NaN       NaN    75104.0   \nSeattle, WA                             NaN          NaN       NaN        NaN   \n\nunique_carrier_name    Wright Air Service  XL Airways France  \\\ndest_city_name                                                 \nAll                               58652.0           196530.0   \nAtlanta, GA                           NaN                NaN   \nChicago, IL                           NaN                NaN   \nNew York, NY                          NaN            17582.0   \nLos Angeles, CA                       NaN            17016.0   \nDallas/Fort Worth, TX                 NaN                NaN   \nDenver, CO                            NaN                NaN   \nHouston, TX                           NaN                NaN   \nSan Francisco, CA                     NaN            11059.0   \nSeattle, WA                           NaN                NaN   \n\nunique_carrier_name    Xiamen Airlines Co., Ltd.           All  \ndest_city_name                                                  \nAll                                     265158.0  1.052983e+09  \nAtlanta, GA                                  NaN  5.354563e+07  \nChicago, IL                                  NaN  5.109597e+07  \nNew York, NY                             39095.0  4.667482e+07  \nLos Angeles, CA                          67388.0  4.285396e+07  \nDallas/Fort Worth, TX                        NaN  3.583777e+07  \nDenver, CO                                   NaN  3.359168e+07  \nHouston, TX                                  NaN  2.897363e+07  \nSan Francisco, CA                            NaN  2.788376e+07  \nSeattle, WA                              24954.0  2.508430e+07  \n\n[10 rows x 208 columns]","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>unique_carrier_name</th>\n      <th>40-Mile Air</th>\n      <th>ABC Aerolineas SA de CV dba Interjet</th>\n      <th>ADVANCED AIR, LLC</th>\n      <th>Aer Lingus Plc</th>\n      <th>Aeroenlaces Nacionales, S.A. de C.V. d/b/a VivaAerobus</th>\n      <th>Aeroflot Russian Airlines</th>\n      <th>Aerolineas Argentinas</th>\n      <th>Aerolitoral</th>\n      <th>Aeromexico</th>\n      <th>Aerovias Nacl De Colombia</th>\n      <th>...</th>\n      <th>Virgin Atlantic Airways</th>\n      <th>Virgin Blue International Airlines t/a V Australia</th>\n      <th>Vuela Aviacion, S.A.</th>\n      <th>WOW Air ehf</th>\n      <th>Warbelow</th>\n      <th>Westjet</th>\n      <th>Wright Air Service</th>\n      <th>XL Airways France</th>\n      <th>Xiamen Airlines Co., Ltd.</th>\n      <th>All</th>\n    </tr>\n    <tr>\n      <th>dest_city_name</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>All</th>\n      <td>502.0</td>\n      <td>2249942.0</td>\n      <td>27049.0</td>\n      <td>2396297.0</td>\n      <td>503660.0</td>\n      <td>893421.0</td>\n      <td>406959.0</td>\n      <td>767266.0</td>\n      <td>2660861.0</td>\n      <td>1796877.0</td>\n      <td>...</td>\n      <td>4139847.0</td>\n      <td>507699.0</td>\n      <td>170673.0</td>\n      <td>46485.0</td>\n      <td>4414.0</td>\n      <td>5273827.0</td>\n      <td>58652.0</td>\n      <td>196530.0</td>\n      <td>265158.0</td>\n      <td>1.052983e+09</td>\n    </tr>\n    <tr>\n      <th>Atlanta, GA</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>42332.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>166993.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>45398.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>5.354563e+07</td>\n    </tr>\n    <tr>\n      <th>Chicago, IL</th>\n      <td>NaN</td>\n      <td>134049.0</td>\n      <td>NaN</td>\n      <td>175630.0</td>\n      <td>5189.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>183061.0</td>\n      <td>5998.0</td>\n      <td>...</td>\n      <td>203.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2801.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>5.109597e+07</td>\n    </tr>\n    <tr>\n      <th>New York, NY</th>\n      <td>NaN</td>\n      <td>150680.0</td>\n      <td>NaN</td>\n      <td>243337.0</td>\n      <td>46497.0</td>\n      <td>277853.0</td>\n      <td>64696.0</td>\n      <td>28660.0</td>\n      <td>217652.0</td>\n      <td>238556.0</td>\n      <td>...</td>\n      <td>589804.0</td>\n      <td>NaN</td>\n      <td>18722.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>309748.0</td>\n      <td>NaN</td>\n      <td>17582.0</td>\n      <td>39095.0</td>\n      <td>4.667482e+07</td>\n    </tr>\n    <tr>\n      <th>Los Angeles, CA</th>\n      <td>NaN</td>\n      <td>226119.0</td>\n      <td>0.0</td>\n      <td>73206.0</td>\n      <td>66846.0</td>\n      <td>98407.0</td>\n      <td>NaN</td>\n      <td>42672.0</td>\n      <td>281284.0</td>\n      <td>76943.0</td>\n      <td>...</td>\n      <td>171369.0</td>\n      <td>250857.0</td>\n      <td>45140.0</td>\n      <td>1999.0</td>\n      <td>NaN</td>\n      <td>371214.0</td>\n      <td>NaN</td>\n      <td>17016.0</td>\n      <td>67388.0</td>\n      <td>4.285396e+07</td>\n    </tr>\n    <tr>\n      <th>Dallas/Fort Worth, TX</th>\n      <td>NaN</td>\n      <td>75046.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>44437.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>3.583777e+07</td>\n    </tr>\n    <tr>\n      <th>Denver, CO</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>660.0</td>\n      <td>18101.0</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>18151.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>3.359168e+07</td>\n    </tr>\n    <tr>\n      <th>Houston, TX</th>\n      <td>NaN</td>\n      <td>107018.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>50053.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>72805.0</td>\n      <td>2780.0</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>61949.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2.897363e+07</td>\n    </tr>\n    <tr>\n      <th>San Francisco, CA</th>\n      <td>NaN</td>\n      <td>59014.0</td>\n      <td>NaN</td>\n      <td>91075.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>171296.0</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>144379.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>75104.0</td>\n      <td>NaN</td>\n      <td>11059.0</td>\n      <td>NaN</td>\n      <td>2.788376e+07</td>\n    </tr>\n    <tr>\n      <th>Seattle, WA</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>46682.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>44214.0</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>74802.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>24954.0</td>\n      <td>2.508430e+07</td>\n    </tr>\n  </tbody>\n</table>\n<p>10 rows × 208 columns</p>\n</div>"},"metadata":{}}]},{"metadata":{},"id":"4cb597b4-0160-45b9-b1b8-5e2577778873","cell_type":"markdown","source":"Notice that the first row in the previous result is not a city, but rather, the subtotal by airline, so we will drop that row before selecting the first 10 rows of the sorted data:"},{"metadata":{"trusted":true},"id":"f11700d1-fcb4-4f74-941f-4b344a07117f","cell_type":"code","source":"pivot = pivot.drop('All').head(10)","execution_count":7,"outputs":[]},{"metadata":{},"id":"97746539-890b-41f3-babf-2df9bc79cfcc","cell_type":"markdown","source":"Selecting the columns for the top 5 airlines now gives us the number of passengers that each airline flew to the top 10 cities. Note that we use `sort_index()` so that the resulting columns are displayed in alphabetical order:"},{"metadata":{"trusted":true},"id":"542b2dbb-acec-4968-a5bb-f50533d311f5","cell_type":"code","source":"pivot[top_airlines.sort_index().index]","execution_count":8,"outputs":[{"output_type":"execute_result","execution_count":8,"data":{"text/plain":"unique_carrier_name    American Airlines Inc.  Delta Air Lines Inc.  \\\ndest_city_name                                                        \nAtlanta, GA                         1408293.0            39316060.0   \nChicago, IL                         9765334.0             1630202.0   \nNew York, NY                        5679066.0            11018205.0   \nLos Angeles, CA                     7066848.0             6490402.0   \nDallas/Fort Worth, TX              24398889.0             1166353.0   \nDenver, CO                          1515364.0             1707589.0   \nHouston, TX                         1022137.0              747316.0   \nSan Francisco, CA                   1979323.0             2160946.0   \nSeattle, WA                         1187459.0             4906617.0   \nOrlando, FL                         2751766.0             3259437.0   \n\nunique_carrier_name    JetBlue Airways  Southwest Airlines Co.  \\\ndest_city_name                                                   \nAtlanta, GA                   379978.0               4532294.0   \nChicago, IL                   243332.0               9467759.0   \nNew York, NY                 7856711.0               1455566.0   \nLos Angeles, CA               975568.0               4840787.0   \nDallas/Fort Worth, TX          83249.0                     NaN   \nDenver, CO                    182436.0               9279814.0   \nHouston, TX                    89390.0               6627678.0   \nSan Francisco, CA             715299.0               1608102.0   \nSeattle, WA                   276241.0               1446404.0   \nOrlando, FL                  2926725.0               5300777.0   \n\nunique_carrier_name    United Air Lines Inc.  \ndest_city_name                                \nAtlanta, GA                         464029.0  \nChicago, IL                       12487875.0  \nNew York, NY                       1057162.0  \nLos Angeles, CA                    5032208.0  \nDallas/Fort Worth, TX               702076.0  \nDenver, CO                        10625467.0  \nHouston, TX                       11500414.0  \nSan Francisco, CA                 10803363.0  \nSeattle, WA                        1383381.0  \nOrlando, FL                        2000013.0  ","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>unique_carrier_name</th>\n      <th>American Airlines Inc.</th>\n      <th>Delta Air Lines Inc.</th>\n      <th>JetBlue Airways</th>\n      <th>Southwest Airlines Co.</th>\n      <th>United Air Lines Inc.</th>\n    </tr>\n    <tr>\n      <th>dest_city_name</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Atlanta, GA</th>\n      <td>1408293.0</td>\n      <td>39316060.0</td>\n      <td>379978.0</td>\n      <td>4532294.0</td>\n      <td>464029.0</td>\n    </tr>\n    <tr>\n      <th>Chicago, IL</th>\n      <td>9765334.0</td>\n      <td>1630202.0</td>\n      <td>243332.0</td>\n      <td>9467759.0</td>\n      <td>12487875.0</td>\n    </tr>\n    <tr>\n      <th>New York, NY</th>\n      <td>5679066.0</td>\n      <td>11018205.0</td>\n      <td>7856711.0</td>\n      <td>1455566.0</td>\n      <td>1057162.0</td>\n    </tr>\n    <tr>\n      <th>Los Angeles, CA</th>\n      <td>7066848.0</td>\n      <td>6490402.0</td>\n      <td>975568.0</td>\n      <td>4840787.0</td>\n      <td>5032208.0</td>\n    </tr>\n    <tr>\n      <th>Dallas/Fort Worth, TX</th>\n      <td>24398889.0</td>\n      <td>1166353.0</td>\n      <td>83249.0</td>\n      <td>NaN</td>\n      <td>702076.0</td>\n    </tr>\n    <tr>\n      <th>Denver, CO</th>\n      <td>1515364.0</td>\n      <td>1707589.0</td>\n      <td>182436.0</td>\n      <td>9279814.0</td>\n      <td>10625467.0</td>\n    </tr>\n    <tr>\n      <th>Houston, TX</th>\n      <td>1022137.0</td>\n      <td>747316.0</td>\n      <td>89390.0</td>\n      <td>6627678.0</td>\n      <td>11500414.0</td>\n    </tr>\n    <tr>\n      <th>San Francisco, CA</th>\n      <td>1979323.0</td>\n      <td>2160946.0</td>\n      <td>715299.0</td>\n      <td>1608102.0</td>\n      <td>10803363.0</td>\n    </tr>\n    <tr>\n      <th>Seattle, WA</th>\n      <td>1187459.0</td>\n      <td>4906617.0</td>\n      <td>276241.0</td>\n      <td>1446404.0</td>\n      <td>1383381.0</td>\n    </tr>\n    <tr>\n      <th>Orlando, FL</th>\n      <td>2751766.0</td>\n      <td>3259437.0</td>\n      <td>2926725.0</td>\n      <td>5300777.0</td>\n      <td>2000013.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"id":"189f9886-2689-4bb1-bb83-8bb62d43be6d","cell_type":"markdown","source":"Our data is now in the right format for a stacked bar plot showing passenger counts. To make this visualization, we call the `plot()` method on the previous result and specify that we want horizontal bars (`kind='barh'`) and that the different airlines should be stacked (`stacked=True`). Note that since we have the destinations sorted in descending order, Atlanta will be plotted on the bottom, so we call `invert_yaxis()` on the `Axes` object returned by `plot()` to flip the order:"},{"metadata":{"trusted":true},"id":"a166c5b1-974e-41a5-b9ca-33e1b8e9cad5","cell_type":"code","source":"from matplotlib import ticker\n\nax = pivot[top_airlines.sort_index().index].plot(\n    kind='barh', stacked=True, \n    title='2019 Passenger Totals\\n(source: BTS)'\n)\nax.invert_yaxis() # put destinations with more passengers on top\n\n# formatting\nax.set(xlabel='number of passengers', ylabel='destination')\nax.legend(title='carrier')\n\n# shows x-axis in millions instead of scientific notation\nax.xaxis.set_major_formatter(ticker.EngFormatter())\n\n# removes the top and right lines from the figure to make it less boxy\nfor spine in ['top', 'right']:\n    ax.spines[spine].set_visible(False)","execution_count":9,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{},"id":"dd459250-46a4-430f-9fcf-8ab9f688f140","cell_type":"markdown","source":"One interesting thing to notice from the previous result is that Seattle is a top 10 destination, yet the top 5 carriers don't appear to be contributing as much to it as the rest of the destination cities, which are pretty much in the same order with the exception of Los Angeles. This could cause some confusion, so let's add in another stacked bar called `Other` that contains the passenger totals for all airlines not in the top 5. Since we calculated the `All` column when we created the pivot table, all we have to do here is add a column to our filtered data that contains the `All` column minus the top 5 airlines' passenger totals summed together. The plotting code only needs to be modified to shift the legend further out:"},{"metadata":{"trusted":true},"id":"7ba9f8c4-ed77-49b8-8627-85a11180b3c8","cell_type":"code","source":"ax = pivot[top_airlines.sort_index().index].assign(\n    Other=lambda x: pivot.All - x.sum(axis=1)\n).plot(\n    kind='barh', stacked=True, \n    title='2019 Passenger Totals\\n(source: BTS)'\n)\nax.invert_yaxis()\n\n# formatting\nax.set(xlabel='number of passengers', ylabel='destination')\nax.xaxis.set_major_formatter(ticker.EngFormatter())\n\n# shift legend to not cover the bars\nax.legend(title='carrier', bbox_to_anchor=(0.7, 0), loc='lower left')\n\nfor spine in ['top', 'right']:\n    ax.spines[spine].set_visible(False)","execution_count":10,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{},"id":"8044a1ad-2973-4f32-b42c-224a036fe1fb","cell_type":"markdown","source":"We can now clearly see that Atlanta had the most passengers arriving in 2019 and that flights from Delta Air Lines were the biggest contributor. But, we can do better by representing market share as the percentage of all passengers arriving in each destination city. In order to do that, we need to modify our pivot table by dividing each airline's passenger counts by the `All` column:"},{"metadata":{"trusted":true},"id":"df9fa688-3fec-4cbd-a4c4-cf153fcfd471","cell_type":"code","source":"normalized_pivot = \\\n    pivot[top_airlines.sort_index().index].apply(lambda x: x / pivot.All)\nnormalized_pivot","execution_count":11,"outputs":[{"output_type":"execute_result","execution_count":11,"data":{"text/plain":"unique_carrier_name    American Airlines Inc.  Delta Air Lines Inc.  \\\ndest_city_name                                                        \nAtlanta, GA                          0.026301              0.734253   \nChicago, IL                          0.191118              0.031905   \nNew York, NY                         0.121673              0.236063   \nLos Angeles, CA                      0.164905              0.151454   \nDallas/Fort Worth, TX                0.680815              0.032545   \nDenver, CO                           0.045111              0.050834   \nHouston, TX                          0.035278              0.025793   \nSan Francisco, CA                    0.070985              0.077498   \nSeattle, WA                          0.047339              0.195605   \nOrlando, FL                          0.111241              0.131764   \n\nunique_carrier_name    JetBlue Airways  Southwest Airlines Co.  \\\ndest_city_name                                                   \nAtlanta, GA                   0.007096                0.084644   \nChicago, IL                   0.004762                0.185294   \nNew York, NY                  0.168329                0.031185   \nLos Angeles, CA               0.022765                0.112960   \nDallas/Fort Worth, TX         0.002323                     NaN   \nDenver, CO                    0.005431                0.276253   \nHouston, TX                   0.003085                0.228749   \nSan Francisco, CA             0.025653                0.057672   \nSeattle, WA                   0.011013                0.057662   \nOrlando, FL                   0.118314                0.214285   \n\nunique_carrier_name    United Air Lines Inc.  \ndest_city_name                                \nAtlanta, GA                         0.008666  \nChicago, IL                         0.244400  \nNew York, NY                        0.022650  \nLos Angeles, CA                     0.117427  \nDallas/Fort Worth, TX               0.019590  \nDenver, CO                          0.316312  \nHouston, TX                         0.396927  \nSan Francisco, CA                   0.387443  \nSeattle, WA                         0.055149  \nOrlando, FL                         0.080851  ","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>unique_carrier_name</th>\n      <th>American Airlines Inc.</th>\n      <th>Delta Air Lines Inc.</th>\n      <th>JetBlue Airways</th>\n      <th>Southwest Airlines Co.</th>\n      <th>United Air Lines Inc.</th>\n    </tr>\n    <tr>\n      <th>dest_city_name</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Atlanta, GA</th>\n      <td>0.026301</td>\n      <td>0.734253</td>\n      <td>0.007096</td>\n      <td>0.084644</td>\n      <td>0.008666</td>\n    </tr>\n    <tr>\n      <th>Chicago, IL</th>\n      <td>0.191118</td>\n      <td>0.031905</td>\n      <td>0.004762</td>\n      <td>0.185294</td>\n      <td>0.244400</td>\n    </tr>\n    <tr>\n      <th>New York, NY</th>\n      <td>0.121673</td>\n      <td>0.236063</td>\n      <td>0.168329</td>\n      <td>0.031185</td>\n      <td>0.022650</td>\n    </tr>\n    <tr>\n      <th>Los Angeles, CA</th>\n      <td>0.164905</td>\n      <td>0.151454</td>\n      <td>0.022765</td>\n      <td>0.112960</td>\n      <td>0.117427</td>\n    </tr>\n    <tr>\n      <th>Dallas/Fort Worth, TX</th>\n      <td>0.680815</td>\n      <td>0.032545</td>\n      <td>0.002323</td>\n      <td>NaN</td>\n      <td>0.019590</td>\n    </tr>\n    <tr>\n      <th>Denver, CO</th>\n      <td>0.045111</td>\n      <td>0.050834</td>\n      <td>0.005431</td>\n      <td>0.276253</td>\n      <td>0.316312</td>\n    </tr>\n    <tr>\n      <th>Houston, TX</th>\n      <td>0.035278</td>\n      <td>0.025793</td>\n      <td>0.003085</td>\n      <td>0.228749</td>\n      <td>0.396927</td>\n    </tr>\n    <tr>\n      <th>San Francisco, CA</th>\n      <td>0.070985</td>\n      <td>0.077498</td>\n      <td>0.025653</td>\n      <td>0.057672</td>\n      <td>0.387443</td>\n    </tr>\n    <tr>\n      <th>Seattle, WA</th>\n      <td>0.047339</td>\n      <td>0.195605</td>\n      <td>0.011013</td>\n      <td>0.057662</td>\n      <td>0.055149</td>\n    </tr>\n    <tr>\n      <th>Orlando, FL</th>\n      <td>0.111241</td>\n      <td>0.131764</td>\n      <td>0.118314</td>\n      <td>0.214285</td>\n      <td>0.080851</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"id":"84cf0751-0f7f-401e-b495-233d3fe49909","cell_type":"markdown","source":"Before plotting, we will also sort the bars by the total market share of the top 5 carriers. Viewing this information as percentages gives us a better idea of which carriers dominate which markets: Delta has by far the largest share of Atlanta and American Airlines has over 60% of Dallas/Fort Worth, while United has strong footholds in several markets:"},{"metadata":{"trusted":true},"id":"c88b53af-d232-4e7a-89e0-88b0a53dcf4f","cell_type":"code","source":"# determine sort order\nmarket_share_sorted = normalized_pivot.sum(axis=1).sort_values()\n\nax = normalized_pivot.loc[market_share_sorted.index,:].plot(\n    kind='barh', stacked=True, xlim=(0, 1), \n    title='2019 Market Share\\n(source: BTS)'\n)\n\n# formatting\nax.set(xlabel='percentage of all passengers', ylabel='destination')\nax.legend(title='carrier', bbox_to_anchor=(0.7, 0), loc='lower left')\n\n# show x-axis as percentages\nax.xaxis.set_major_formatter(ticker.PercentFormatter(xmax=1))\n\nfor spine in ['top', 'right']:\n    ax.spines[spine].set_visible(False)","execution_count":12,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{},"id":"61d2d72e-0c16-44bf-b464-791fc04161e8","cell_type":"markdown","source":"As we noticed earlier, Seattle sticks out. The top 5 carriers have more than 50% combined market share for 9 out of the top 10 destinations, but not for Seattle. Using our pivot table, we can see that Alaska Airlines is the top carrier for Seattle:"},{"metadata":{"trusted":true},"id":"dd94bc5e-b539-425c-8258-46f775c6c063","cell_type":"code","source":"pivot.loc['Seattle, WA', :].nlargest(6)","execution_count":13,"outputs":[{"output_type":"execute_result","execution_count":13,"data":{"text/plain":"unique_carrier_name\nAll                       25084302.0\nAlaska Airlines Inc.       9637977.0\nDelta Air Lines Inc.       4906617.0\nHorizon Air                2454491.0\nSouthwest Airlines Co.     1446404.0\nUnited Air Lines Inc.      1383381.0\nName: Seattle, WA, dtype: float64"},"metadata":{}}]},{"metadata":{},"id":"2fc809c4-572c-4a0f-8d4a-decef0016b4d","cell_type":"markdown","source":"Now, it's your turn.\n\nIn this article, we explored just a few of the many powerful features in the `pandas` library that make data analysis easier. While we only used a small subset of the columns, this dataset is packed with information that can be analyzed using a pivot table: try looking into origin cities, freight/mail carriers, or even flight distance.\n\nBe sure to check out my upcoming ODSC Europe 2021 training session, \"[Introduction to Data Analysis Using Pandas](https://odsc.com/speakers/introduction-to-data-analysis-using-pandas/)\", from 1:30-4:30 PM BST June 10, 2021, for an in-depth introduction to `pandas`. Or pick up my book,  \"[Hands-On Data Analysis with Pandas](https://www.amazon.com/Hands-Data-Analysis-Pandas-visualization-dp-1800563450/dp/1800563450/)\", for a thorough exploration of the `pandas` library using real-world datasets, along with `matplotlib`, `seaborn`, and `scikit-learn`."}],"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.8.8","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":5}