FDM_MiniProject/adr_operations.py at main · YuvinNP/FDM_MiniProject · 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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
import pandas as pd

# data_frame = pd.read_csv( 'cluster_hotel.csv' )
yearlist = []

# def toCSV(csv_file):
#     data_frame = pd.read_csv(csv_file)
#     return data_frame

import pandas as pd
data_frame = pd.read_csv('correct_cluster.csv')
yearlist = [int(2015), int(2016), int(2017)]

# def monthly_transaction_avg():
#     # data_frame = pd.read_csv(source_file)
#     print( 'Loading...................' )
#
#     averageList = []
#     sumList = []
#     data_frame_new = data_frame[[
#         'arrival_date_year', 'arrival_date_month', 'adr']]
#
#
#     # for index, row in data_frame_new.iterrows():
#     #     year = row['arrival_date_year']
#     #     if year not in yearlist:
#     #         yearlist.append( year )
#
#     dfList = []
#     # df = "df"
#     i = 1
#     for year in yearlist:
#         rows = []
#         for index, row in data_frame_new.iterrows():
#             y = row['arrival_date_year']
#             m = row['arrival_date_month']
#             adr = row['adr']
#             if y == int(year):
#                 rows.append( [int(y), m, adr] )
#         df = pd.DataFrame( rows, columns=['year', 'month', 'adr'] )
#         df.to_csv('year{}.csv'.format(i), index=False)
#         i = i + 1
#     print('Successfully Created')
#
# monthly_transaction_avg()


def readCsv(file):
    return pd.read_csv(file)

import pandas as pd
data_frame = pd.read_csv('correct_cluster.csv')
yearlist = [int(2015), int(2016), int(2017)]

def monthly_transaction_avg():
    averageList = []
    sumList = []
    dfList = []
    dfList.append( readCsv( 'year1.csv' ) )
    dfList.append( readCsv( 'year2.csv' ) )
    dfList.append( readCsv( 'year3.csv' ) )
    for dataframes in dfList:
        averageList.append( dataframes.groupby( ['year', 'month'], sort=False ).mean() )
        sumList.append( dataframes.groupby( ['year', 'month'], sort=False ).sum() )
    print( 'Loading...................' )
    return averageList, sumList

output2 = monthly_transaction_avg()


def dictionryOutput():
    adrDic = {}
    adrTotal = {}
    for i in output2[0]:
        # print(i)
        adrInDic = {}
        for j in range( len( i ) ):
            adrInDic[i.index.values[j][1]] = i['adr'].iloc[j]
        adrDic[i.index.values[0][0]] = adrInDic
    for i in output2[1]:
        # print(i)
        adrInTotal = {}
        for j in range( len( i ) ):
            adrInTotal[i.index.values[j][1]] = i['adr'].iloc[j]
        adrTotal[i.index.values[0][0]] = adrInTotal
    return adrDic, adrTotal

def financialYearPattern():
    adrDic = dictionryOutput()[0]
    adrTotalDic = dictionryOutput()[1]
    seasonalDic = {}
    internalDic = {}
    seasonalTotalDic = {}
    internalTotalDic = {}
    count1 = 1
    count2 = 1

    valueList = []

    for keys, values in adrDic.items():
        for i in values.keys():
            valueList.append(values[i])

    monthCount = len(valueList)
    incCount1 = 0
    incCount2 = 0

    for keys, values in adrDic.items():
        for i in values.keys():

            if i == 'June':
                keyVal = 'season' + str( count1 )
                internalDic[i] = values[i]
                incCount1 += 1
                seasonalDic[keyVal] = internalDic
                internalDic = {}
                # internalDic = {}
                count1 = count1 + 1
            else:
                incCount1 += 1
                internalDic[i] = values[i]

            if incCount1 == monthCount:
                keyVal = 'season' + str( count1 )
                internalDic[i] = values[i]
                incCount1 += 1
                seasonalDic[keyVal] = internalDic

    for keys, values in adrTotalDic.items():
        for i in values.keys():
            if i == 'June':
                keyVal = 'season' + str( count2 )
                internalTotalDic[i] = values[i]
                incCount2 += 1
                seasonalTotalDic[keyVal] = internalTotalDic
                internalTotalDic = {}
                count2 = count2 + 1
            else:
                incCount2 += 1
                internalTotalDic[i] = values[i]

            if incCount2 == 26:
                keyVal = 'season' + str( count2 )
                internalTotalDic[i] = values[i]
                incCount2 += 1
                seasonalTotalDic[keyVal] = internalTotalDic

    return seasonalDic, seasonalTotalDic

def annualDailyRateAvg():
    avgDic = {}

    season1 = list(financialYearPattern()[0]['season1'].values() )
    season2 = list(financialYearPattern()[0]['season2'].values() )

    months = list(financialYearPattern()[0]['season1'] )

    for i, j, month in zip( season1, season2, months ):
        avgDic[month] = (i + j) / 2

    return avgDic

def annualTotalRevAvg():
    avgDic = {}

    season1 = list(financialYearPattern()[1]['season1'].values() )
    season2 = list(financialYearPattern()[1]['season2'].values() )

    months = list(financialYearPattern()[1]['season1'] )

    for i, j, month in zip( season1, season2, months ):
        avgDic[month] = (i + j) / 2

    return avgDic

def yearList():
    return yearlist