def authCurves(self, network, orgs=None, dests=None, flights=None, cabins=None, bcs=None, date_ranges=None): """ Plots AUTH curves for some subset of the data. AUTH is stated at the level of a cabin-booking class. AUTH changes with time starting from the opening of ticket sales and ending close to departure. Note that you only have to look at two booking classes (BC) for purpose of overbooking: Y class for Y cabin and J class for J cabin. This is because those classes always have the maximum AUTH among all classes in a cabin at a given point of time (they are at the top in hierarchy). """ df = network.f.getDrillDown(orgs=orgs, dests=dests, flights=flights, cabins=cabins, bcs=bcs, date_ranges=date_ranges) fltbk = network.f.getUniqueFlightsAndBookings(df) plt.figure() for g, d in fltbk: AUTH = np.array(d.sort(columns='KEYDAY', ascending=False)['AUTH']) KEYDAY = np.array(-d.sort(columns='KEYDAY', ascending=False)['KEYDAY']) plt.plot(KEYDAY, AUTH) title = Utils.createTitleForFeatures(orgs,dests,flights,cabins,bcs,date_ranges) plt.title(title) plt.xlabel('-KEYDAY') plt.ylabel('AUTH') plt.show()
def bookingCurves(self, network, orgs=None, dests=None, flights=None, cabins=None, bcs=None, date_ranges=None): """ Plots booking curves for some subset of the data. A booking curve tracks the number of seats booked over time, starting from the opening of ticket sales and ending close to departure """ df = network.f.getDrillDown(orgs=orgs, dests=dests, flights=flights, cabins=cabins, bcs=bcs, date_ranges=date_ranges) fltbk = network.f.getUniqueFlightsAndBookings(df) plt.figure() for g, d in fltbk: BKD = list(d.sort(columns='KEYDAY', ascending=False)['BKD']) KEYDAY = list(-d.sort(columns='KEYDAY', ascending=False)['KEYDAY']) ID = d['DATE'].first BC = d['BC'].first plt.plot(KEYDAY, BKD) title = Utils.createTitleForFeatures(orgs,dests,flights,cabins,bcs,date_ranges) plt.title(title) plt.xlabel('-KEYDAY') plt.ylabel('BKD') plt.show()
def overbookingCurves(self, network, orgs=None, dests=None, flights=None, cabins=None, bcs=None, date_ranges=None, normalized=True): """ Plots overbooking curves for some subset of the data. Overbooking is defined where AUTH > CAP. We plot overbooking as a ratio between AUTH and CAP. Overbooking varies with time. """ df = network.f.getDrillDown(orgs=orgs, dests=dests, flights=flights, cabins=cabins, bcs=bcs, date_ranges=date_ranges) fltbk = network.f.getUniqueFlightsAndBookings(df) plt.figure() if normalized: for g, d in fltbk: # normalized AUTH == OVERBOOKED AUTH = np.array(d.sort(columns='KEYDAY', ascending=False)['AUTH']) # ignore time series that are not overbooked if not Utils.isOverbooked(AUTH): continue KEYDAY = np.array(-d.sort(columns='KEYDAY', ascending=False)['KEYDAY']) plt.plot(KEYDAY, AUTH) else: for g, d in fltbk: AUTH = np.array(d.sort(columns='KEYDAY', ascending=False)['AUTH']) CAP = float(d.iloc[0]['CAP']) OVRBKD = AUTH/CAP # ignore time series that are not overbooked if not Utils.isOverbooked(OVRBKD): continue KEYDAY = np.array(-d.sort(columns='KEYDAY', ascending=False)['KEYDAY']) plt.plot(KEYDAY, OVRBKD) title = Utils.createTitleForFeatures(orgs,dests,flights,cabins,bcs,date_ranges) plt.title(title) plt.xlabel('-KEYDAY') plt.ylabel('Percentage Overbooked: AUTH / CAP') plt.show()
def stackedBookingCurve(self, network, orgs=None, dests=None, flights=None, cabins=None, bcs=None, date_ranges=None): """ Generate a summative booking curve for a given flight. In order for this function to work properly the arguments must specify one specific flight (or a subset of the booking classes on a specific flight). Additionally, the network must have been create using a normalized data set. """ first_flights = network.f.getDrillDown(orgs=orgs, dests=dests, flights=flights, cabins=cabins, bcs=bcs, date_ranges=date_ranges) groupedByBookings = network.f.getUniqueFlightsAndBookings(first_flights) xvals = np.linspace(-1, 0, 101) # Increments of .01 from -1 -> 0 interps = None labels = [g[4] for g, d in groupedByBookings] for g, d in groupedByBookings: keydays = -d['KEYDAY'] booked = d['BKD'] yvals = network.interp(xvals, keydays, booked) if interps == None: interps = yvals else: interps = np.vstack((interps, yvals)) # interps is my matrix m, n = interps.shape interps_sum = np.zeros((m,n)) for i in range(m-1): for j in range(i+1, m): interps_sum[j] += interps[i] for i in range(m): plt.plot(xvals, interps_sum[i]) plt.legend(labels, loc=6, prop={'size': 14}) plt.title('Summative Booking Curve\n' + Utils.createTitleForFeatures(orgs, dests, flights, cabins, bcs, date_ranges)) plt.xlabel('Normalized Keyday') plt.ylabel('Normalized Booked') plt.show()
def overbookingVsCabinLoadFactor(self, network, orgs=None, dests=None, flights=None, cabins=None, bcs=None, date_ranges=None, normalized=True, subplots=True): """ Plots how overbooking varies with Cabin load factor. Final Cabin Load Factor for a particular flight booking class is binned into three separate categories: Overbooked: CLF > 1 Underbooked: CLF < .8 Optimumly booked: .8 < CLF < 1 """ df = network.f.getDrillDown(orgs=orgs, dests=dests, flights=flights, cabins=cabins, bcs=bcs, date_ranges=date_ranges) fltbk = network.f.getUniqueFlightsAndBookings(df) # TODO: allow for countFinalCabinLoadFactor to use normalized data CLF_dict = network.countFinalCabinLoadFactor() fig = plt.figure() # preparing to capture the legend handles legend_over = None legend_under = None legend_optimum = None n_over = 0 n_under = 0 n_optimum = 0 if normalized: for g, d in fltbk: # normalized AUTH == OVERBOOKED AUTH = np.array(d.sort(columns='KEYDAY', ascending=False)['AUTH']) # ignore time series that are not overbooked if not Utils.isOverbooked(AUTH): continue KEYDAY = np.array(-d.sort(columns='KEYDAY', ascending=False)['KEYDAY']) DATE = d.iloc[0]['DATE'] FLT = d.iloc[0]['FLT'] ORG = d.iloc[0]['ORG'] DES = d.iloc[0]['DES'] #TODO: See CLF_dict (above) CABIN_LOAD_FACTOR = CLF_dict[(DATE, FLT, ORG, DES)] if CABIN_LOAD_FACTOR > 1: plt.plot(KEYDAY, AUTH, 'r') elif CABIN_LOAD_FACTOR < .95: plt.plot(KEYDAY, AUTH, 'y') else: plt.plot(KEYDAY, AUTH, 'g') else: for g, d in fltbk: AUTH = np.array(d.sort(columns='KEYDAY', ascending=False)['AUTH']) CAP = float(d.iloc[0]['CAP']) OVRBKD = AUTH/CAP # ignore time series that are not overbooked if not Utils.isOverbooked(OVRBKD): continue KEYDAY = np.array(-d.sort(columns='KEYDAY', ascending=False)['KEYDAY']) DATE = d.iloc[0]['DATE'] FLT = d.iloc[0]['FLT'] ORG = d.iloc[0]['ORG'] DES = d.iloc[0]['DES'] CABIN_LOAD_FACTOR = CLF_dict[(DATE, FLT, ORG, DES)] if CABIN_LOAD_FACTOR > 1: plt.subplot(311) if subplots else None if not legend_over: legend_over, = plt.plot(KEYDAY, OVRBKD , 'r') else: plt.plot(KEYDAY, OVRBKD , 'r') n_over += 1 elif CABIN_LOAD_FACTOR < .95: plt.subplot(313) if subplots else None if not legend_under: legend_under, = plt.plot(KEYDAY, OVRBKD, 'y') else: plt.plot(KEYDAY, OVRBKD, 'y') n_under += 1 else: plt.subplot(312) if subplots else None if not legend_optimum: legend_optimum, = plt.plot(KEYDAY, OVRBKD, 'g') else: plt.plot(KEYDAY, OVRBKD, 'g') n_optimum += 1 title = Utils.createTitleForFeatures(orgs,dests,flights,cabins,bcs,date_ranges) plt.subplot(311) if subplots else None plt.suptitle(title) plt.xlabel('-KEYDAY') plt.ylabel('Percentage Overbooked: AUTH / CAP') plt.subplot(311) plt.ylim([.25,2]) plt.subplot(312) plt.ylim([.25,2]) plt.subplot(313) plt.ylim([.25,2]) plt.legend([legend_over, legend_optimum, legend_under], ["Cabin Load Factor > 1, n={}".format(n_over), "Optimum Cabin Load Factor,n={}".format(n_optimum), "Cabin Load Factor < .95, n={}".format(n_under) ]) plt.show()