optiflow/util.py at main · pschillo/optiflow · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
# %%
# setup
import pandas as pd
import random
from datetime import datetime

def create_flight_data():

    ## %%
    # load original flight data set, skipping description in first 7 lines
    FAA_df = pd.read_csv('Detailed_Statistics_Departures.csv', skiprows=7, nrows=100)
    FAA_LAX_df = pd.read_csv('Detailed_Statistics_Departures_LAX.csv', skiprows=7, nrows=100)

    ## %%
    # inspect
    #FAA_df.head()
    #FAA_LAX_df.head()

    ## %%
    # clean data

    # drop N/A from relevant columns
    FAA_df = FAA_df.dropna(axis=0,subset=['Carrier Code', 'Flight Number'])
    FAA_LAX_df = FAA_LAX_df.dropna(axis=0,subset=['Carrier Code', 'Flight Number'])

    # convert column 'Flight Number'
    FAA_df['Flight Number'] = FAA_df['Flight Number'].astype('int')
    FAA_LAX_df['Flight Number'] = FAA_LAX_df['Flight Number'].astype('int')

    ## %%
    # create flight data datatrame

    # estimate
    Terminals = ['Terminal 1', 'Terminal 2']
    GatesTerminal1 = ['A1', 'A2', 'A3', 'A4']
    GatesTerminal2 = ['B1', 'B2', 'B3', 'B4']

    flight_data_df = pd.DataFrame(columns=['Code', 'Date (MM/DD/YYYY)', 'Departure', 'Terminal', 'Gate', 'BoardingStarts'])
    flight_data_df['Code'] = FAA_df['Carrier Code'].astype(str) + FAA_df['Flight Number'].astype(str)
    flight_data_df['Departure'] = FAA_df['Scheduled departure time']
    flight_data_df['Date (MM/DD/YYYY)'] = FAA_df['Date (MM/DD/YYYY)']
    flight_data_df['Destination'] = FAA_df['Destination Airport']
    flight_data_df['Origin'] = "GRR"

    for i in range(len(flight_data_df['Departure'])):
        flight_data_df['BoardingStarts'][i] = datetime.strptime(flight_data_df['Departure'][i], '%H:%M') - datetime.strptime("00:30", '%H:%M')

    flight_data_LAX_df = pd.DataFrame(columns=['Code', 'Date (MM/DD/YYYY)', 'Departure', 'Terminal', 'Gate', 'BoardingStarts'])
    flight_data_LAX_df['Code'] = FAA_df['Carrier Code'].astype(str) + FAA_df['Flight Number'].astype(str)
    flight_data_LAX_df['Departure'] = FAA_df['Scheduled departure time']
    flight_data_LAX_df['Date (MM/DD/YYYY)'] = FAA_df['Date (MM/DD/YYYY)']
    flight_data_LAX_df['Destination'] = FAA_LAX_df['Destination Airport']
    flight_data_LAX_df['Origin'] = "LAX"

    for i in range(len(flight_data_LAX_df['Departure'])):
        flight_data_LAX_df['BoardingStarts'][i] = datetime.strptime(flight_data_LAX_df['Departure'][i], '%H:%M') - datetime.strptime("00:30", '%H:%M')

    # fill
    for i in range(len(flight_data_df['Departure'])):
        flight_data_df['Terminal'][i] = random.choice(Terminals)

        if flight_data_df['Terminal'][i] == 'Terminal 1':
            flight_data_df['Gate'][i] = random.choice(GatesTerminal1)
        elif flight_data_df['Terminal'][i] == 'Terminal 2':
            flight_data_df['Gate'][i] = random.choice(GatesTerminal2)
        else: flight_data_df['Gate'][i] = 'unknown'

    for i in range(len(flight_data_LAX_df['Departure'])):
        flight_data_LAX_df['Terminal'][i] = random.choice(Terminals)

        if flight_data_LAX_df['Terminal'][i] == 'Terminal 1':
            flight_data_LAX_df['Gate'][i] = random.choice(GatesTerminal1)
        elif flight_data_LAX_df['Terminal'][i] == 'Terminal 2':
            flight_data_LAX_df['Gate'][i] = random.choice(GatesTerminal2)
        else: flight_data_LAX_df['Gate'][i] = 'unknown'

    flight_data_df = pd.concat([flight_data_df,flight_data_LAX_df])

    return flight_data_df

# estimate security
def estimate_time_security(time, time_df, airport):

    time = time
    data = time_df
    airport = airport

    # convert time format
    time = str(time)
    hours = time[:2]

    # check airport
    if airport == "GRR":
        data.drop(data[data['Identifier'] != "GRR"].index)
    else:
        data.drop(data[data['Identifier'] == "GRR"].index)

    mean_idx = data.index[data['Time_From'] == float(hours)][0]
    mean = float(data['Security'][mean_idx])

    security = random.gauss(mu=mean,sigma=0.5)

    return abs(security)

def estimate_time_checkin(time, time_df, airport):

    time = time
    data = time_df
    airport = airport

    # convert time format
    time = str(time)
    hours = time[:2]

    # check airport
    if airport == "GRR":
        data.drop(data[data['Identifier'] != "GRR"].index)
    else:
        data.drop(data[data['Identifier'] == "GRR"].index)

    mean_idx = data.index[data['Time_From'] == float(hours)][0]
    mean = float(data['Check-In'][mean_idx])

    security = random.gauss(mu=mean,sigma=0.8)

    return abs(security)

# %%