def clean_data():
data = acquisition()
# we get rid of rows with no price
data = data.dropna(subset=["price"])
# we want to analyse AVE prices so this is the only type of train we keep
# data["train_type"].value_counts()
data = data[data["train_type"] == "AVE"]
# As we want the Turista solo plaza H class is for people with a disability we delte all this rows as we want to analyse ordinary tickets to get a more realistic cost for the avg person
# data["train_class"].value_counts()
data = data[data["train_class"] != "TuristaSólo plaza H"]
# we are going to keep only the promo and flexible tickets, the most common type of fares
list_values = ["COD.PROMOCIONAL", "Mesa", "Promo +", "Grupos Ida", "4x100"]
for col in list_values:
data = data[data["fare"] != col]
# As we have decided to analyze only trips with origin in Madrid we drop the rest
data = data[data["origin"] == "MADRID"]
# data["destination"].value_counts()
return data
pylab.draw()
#Do acquisition
#Get 11ms of acquisition samples for fine frequency estimation
samplesPerCode = int(
round(settings.samplingFreq /
(settings.codeFreqBasis / settings.codeLength)))
acqSamples = getSamples.int8(settings.fileName, 11 * samplesPerCode,
settings.skipNumberOfBytes)
if settings.skipAcquisition:
print "\nLoading old acquisition results ...",
acqResults = pickle.load(open("acqResults.pickle", "rb"))
print "done"
else:
print "\nAcquiring satellites ...",
acqResults = acquisition(acqSamples, settings)
pickle.dump(acqResults, open("acqResults.pickle", "wb"))
# print "done"
if settings.plotAcquisition:
acqFigure = plotAcquisition(acqResults, settings)
pylab.draw()
#Do tracking
#Find if any satellites were acquired
acqSuccessful = False
#for i in settings.acqSatelliteList:
for i in range(32 - 1, -1, -1):
if acqResults[i][0] > settings.acqThreshold:
acqSuccessful = True
else: #if satellite wasn't found, pop it off the list
acqResults.pop(i)
if settings.plotSignal:
print "Plotting data", settings.fileName
probeFigure = probeData(settings)
pylab.draw()
#Do acquisition
#Get 11ms of acquisition samples for fine frequency estimation
samplesPerCode = int(round(settings.samplingFreq / (settings.codeFreqBasis / settings.codeLength)))
acqSamples = getSamples.int8(settings.fileName,11*samplesPerCode,settings.skipNumberOfBytes)
if settings.skipAcquisition:
print "\nLoading old acquisition results ...",
acqResults = pickle.load(open("acqResults.pickle","rb"))
print "done"
else:
print "\nAcquiring satellites ...",
acqResults = acquisition(acqSamples,settings)
pickle.dump(acqResults,open("acqResults.pickle","wb"))
# print "done"
if settings.plotAcquisition:
acqFigure = plotAcquisition(acqResults,settings)
pylab.draw()
#Do tracking
#Find if any satellites were acquired
acqSuccessful = False
#for i in settings.acqSatelliteList:
for i in range(32-1,-1,-1):
if acqResults[i][0] > settings.acqThreshold:
acqSuccessful = True
else: #if satellite wasn't found, pop it off the list
acqResults.pop(i)
threshold = 0.05
if len(sys.argv) > 1:
threshold = float(sys.argv[1])
firstCfg = Config("First")
secondCfg = Config("Second")
### Display title
print
print "\t\t\t\tProgramme" + Color.BOLD + " MAGELLI" + Color.NORMAL
### ETAPE 1: apprentissage sur un court texte
print
print "-" * 70
print Color.BOLD + "Entrez un texte de votre choix et terminez en tapant deux fois Entrée :" + Color.NORMAL
freq_bs = acquisition(firstCfg)
print Color.CYAN + "Fréquence des BACKSPACE: " + str(freq_bs) + Color.NORMAL
print "-" * 70
### ETAPE 2: écriture d'un deuxième texte (identique ou non)
print Color.BOLD + "Entrez un deuxième texte (identique ou non) et terminez en tapant deux fois Entrée :" + Color.NORMAL
freq_bs = acquisition(secondCfg)
print Color.CYAN + "Fréquence des BACKSPACE: " + str(freq_bs) + Color.NORMAL
print "-" * 70
print
### ETAPE 3: comparaison des deux (sensibilité variable)
inter = firstCfg.intersection(secondCfg)
sum = 0
i = 0
def postProcessing(*args, **kwargs):
nargin = len(args)
## Initialization =========================================================
print 'Starting processing...'
if nargin == 1:
settings = args[0]
fileNameStr = settings.fileName
elif nargin == 2:
fileNameStr, settings = args
if ~isinstance(fileNameStr, str):
raise TypeError('File name must be a string')
else:
raise Exception('Incorrect number of arguments')
try:
with open(fileNameStr, 'rb') as fid:
# If success, then process the data
# Move the starting point of processing. Can be used to start the
# signal processing at any point in the data record (e.g. good for long
# records or for signal processing in blocks).
fid.seek(settings.skipNumberOfBytes, 0)
## Acquisition ============================================================
# Do acquisition if it is not disabled in settings or if the variable
# acqResults does not exist.
if not settings.skipAcquisition or 'acqResults' not in globals():
# Find number of samples per spreading code
samplesPerCode = long(
round(settings.samplingFreq /
(settings.codeFreqBasis / settings.codeLength)))
# frequency estimation
data = np.fromfile(fid, settings.dataType, 11 * samplesPerCode)
print ' Acquiring satellites...'
acqResults = acquisition.acquisition(data, settings)
plotAcquisition.plotAcquisition(acqResults)
## Initialize channels and prepare for the run ============================
# Start further processing only if a GNSS signal was acquired (the
# field FREQUENCY will be set to 0 for all not acquired signals)
if np.any(acqResults.carrFreq):
channel = preRun.preRun(acqResults, settings)
preRun.showChannelStatus(channel, settings)
else:
# No satellites to track, exit
print 'No GNSS signals detected, signal processing finished.'
trackResults = None
## Track the signal =======================================================
startTime = datetime.datetime.now()
print ' Tracking started at %s' % startTime.strftime('%X')
try:
trackResults = np.load('trackingResults_python.npy')
except IOError:
trackResults, channel = tracking.tracking(
fid, channel, settings)
np.save('trackingResults_python', trackResults)
print ' Tracking is over (elapsed time %s s)' % (
datetime.datetime.now() - startTime).total_seconds()
# Auto save the acquisition & tracking results to a file to allow
# running the positioning solution afterwards.
print ' Saving Acq & Tracking results to file "trackingResults.mat"'
## Calculate navigation solutions =========================================
print ' Calculating navigation solutions...'
try:
navSolutions = np.load('navSolutions_python.npy')
except IOError:
navSolutions, eph = postNavigation.postNavigation(
trackResults, settings)
np.save('navSolutions_python', navSolutions)
print ' Processing is complete for this data block'
# return
# savemat('trackingResults_from_python',
# {'trackResults': trackResults,
# 'settings': settings,
# 'acqResults': acqResults,
# 'channel': channel,
# 'navSolutions': navSolutions})
## Plot all results ===================================================
print ' Plotting results...'
# TODO
# turn off tracking plots for now
if not settings.plotTracking:
plotTracking.plotTracking(range(settings.numberOfChannels),
trackResults, settings)
plotNavigation.plotNavigation(navSolutions, settings)
print 'Post processing of the signal is over.'
except IOError as e:
# Error while opening the data file.
print 'Unable to read file "%s": %s.' % (settings.fileName, e)
threshold = 0.05
if len(sys.argv) > 1 :
threshold = float(sys.argv[1])
firstCfg = Config("First")
secondCfg = Config("Second")
### Display title
print
print "\t\t\t\tProgramme" + Color.BOLD + " MAGELLI" + Color.NORMAL
### ETAPE 1: apprentissage sur un court texte
print
print "-"*70
print Color.BOLD + "Entrez un texte de votre choix et terminez en tapant deux fois Entrée :" + Color.NORMAL
freq_bs = acquisition(firstCfg)
print Color.CYAN + "Fréquence des BACKSPACE: " + str(freq_bs) + Color.NORMAL
print "-"*70
### ETAPE 2: écriture d'un deuxième texte (identique ou non)
print Color.BOLD + "Entrez un deuxième texte (identique ou non) et terminez en tapant deux fois Entrée :" + Color.NORMAL
freq_bs = acquisition(secondCfg)
print Color.CYAN + "Fréquence des BACKSPACE: " + str(freq_bs) + Color.NORMAL
print "-"*70
print
### ETAPE 3: comparaison des deux (sensibilité variable)
inter = firstCfg.intersection(secondCfg)
sum = 0
i = 0
analysis.male_female_ratio(df)
analysis.more_even_country(df)
analysis.profitable_work_field(df)
analysis.education_ratio(df)
else:
print('Not a valid number, try again with a choice from 1 to 6!')
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Prepare yourself for an analysis of the billionaires of 2018:')
requiredNamed = parser.add_argument_group('required named arguments')
requiredNamed.add_argument('-a', '--analysis', dest='type_of_analysis', default=None, choices=[1, 2, 3, 4, 5, 6], type=int, help="""1 - To know which country has maximum numbers of billionaires;
2 - To get the male to female ratio based on the total of dollars;
3 - To know which country has the greatest share in terms of total money held by its billionaires;
4 - To get the top 15 most profitable fields of work;
5 - To get the percentage of billionaires with studies;
6 - To get all the above""", required=True)
requiredNamed.add_argument('-e', '--email', dest='want_results', default=None, required=True, choices=['y', 'n'], type=str, help="""y - To receive an email with your results;
n - Otherwise""")
args = parser.parse_args()
print('Prepare yourself for an analysis of the billionaires of 2018!')
acquisition('df')
cleaning('df')
webscraping('df')
df = pd.read_csv('df')
main(args.type_of_analysis)
converting.extra_analysis()
converting.add_pdf(args.type_of_analysis)
sending_email(args.want_results)