Expedia/BenchMark_Expedia_script.py at master · Behrang78/Expedia · 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
# code source:  https://www.kaggle.com/zfturbo/expedia-hotel-recommendations/leakage-solution/code

__author__ = 'ZFTurbo: https://kaggle.com/zfturbo'

import datetime
from heapq import nlargest
from operator import itemgetter
from collections import defaultdict

train_file = "/home/ml1/Downloads/Kaggle-Expedia/AnalyzedData/train.csv"
test_file  = "/home/ml1/Downloads/Kaggle-Expedia/AnalyzedData/test.csv"
output_path = "/home/ml1/Downloads/Kaggle-Expedia/AnalyzedData/"

def run_solution():
    print('Preparing arrays...')
    f = open(train_file, "r")
    f.readline()
    best_hotels_od_ulc = defaultdict(lambda: defaultdict(int))
    best_hotels_search_dest = defaultdict(lambda: defaultdict(int))
    best_hotels_search_dest1 = defaultdict(lambda: defaultdict(int))
    best_hotel_country = defaultdict(lambda: defaultdict(int))
    popular_hotel_cluster = defaultdict(int)
    total = 0

    # Calc counts
    while 1:
        line = f.readline().strip()
        total += 1

        if total % 10000000 == 0:
            print('Read {} lines...'.format(total))

        if line == '':
            break

        arr = line.split(",")
        book_year = int(arr[0][:4])
        user_location_city = arr[5]
        orig_destination_distance = arr[6]
        srch_destination_id = arr[16]
        is_booking = int(arr[18])
        hotel_country = arr[21]
        hotel_market = arr[22]
        hotel_cluster = arr[23]

        append_1 = 3 + 17*is_booking
        append_2 = 1 + 5*is_booking

        if user_location_city != '' and orig_destination_distance != '':
            best_hotels_od_ulc[(user_location_city, orig_destination_distance)][hotel_cluster] += 1

        if srch_destination_id != '' and hotel_country != '' and hotel_market != '' and book_year == 2014:
            best_hotels_search_dest[(srch_destination_id, hotel_country, hotel_market)][hotel_cluster] += append_1

        if srch_destination_id != '':
            best_hotels_search_dest1[srch_destination_id][hotel_cluster] += append_1

        if hotel_country != '':
            best_hotel_country[hotel_country][hotel_cluster] += append_2

        popular_hotel_cluster[hotel_cluster] += 1

    f.close()

    print('Generate submission...')
    now = datetime.datetime.now()
    path = output_path + 'submission_' + str(now.strftime("%Y-%m-%d-%H-%M")) + '.csv'
    out = open(path, "w")
    f = open(test_file, "r")
    f.readline()
    total = 0
    out.write("id,hotel_cluster\n")
    topclasters = nlargest(5, sorted(popular_hotel_cluster.items()), key=itemgetter(1))

    while 1:
        line = f.readline().strip()
        total += 1

        if total % 1000000 == 0:
            print('Write {} lines...'.format(total))

        if line == '':
            break

        arr = line.split(",")
        id = arr[0]
        user_location_city = arr[6]
        orig_destination_distance = arr[7]
        srch_destination_id = arr[17]
        hotel_country = arr[20]
        hotel_market = arr[21]

        out.write(str(id) + ',')
        filled = []

        s1 = (user_location_city, orig_destination_distance)
        if s1 in best_hotels_od_ulc:
            d = best_hotels_od_ulc[s1]
            topitems = nlargest(5, sorted(d.items()), key=itemgetter(1))
            for i in range(len(topitems)):
                if topitems[i][0] in filled:
                    continue
                if len(filled) == 5:
                    break
                out.write(' ' + topitems[i][0])
                filled.append(topitems[i][0])

        s2 = (srch_destination_id, hotel_country, hotel_market)
        if s2 in best_hotels_search_dest:
            d = best_hotels_search_dest[s2]
            topitems = nlargest(5, d.items(), key=itemgetter(1))
            for i in range(len(topitems)):
                if topitems[i][0] in filled:
                    continue
                if len(filled) == 5:
                    break
                out.write(' ' + topitems[i][0])
                filled.append(topitems[i][0])
        elif srch_destination_id in best_hotels_search_dest1:
            d = best_hotels_search_dest1[srch_destination_id]
            topitems = nlargest(5, d.items(), key=itemgetter(1))
            for i in range(len(topitems)):
                if topitems[i][0] in filled:
                    continue
                if len(filled) == 5:
                    break
                out.write(' ' + topitems[i][0])
                filled.append(topitems[i][0])

        if hotel_country in best_hotel_country:
            d = best_hotel_country[hotel_country]
            topitems = nlargest(5, d.items(), key=itemgetter(1))
            for i in range(len(topitems)):
                if topitems[i][0] in filled:
                    continue
                if len(filled) == 5:
                    break
                out.write(' ' + topitems[i][0])
                filled.append(topitems[i][0])

        for i in range(len(topclasters)):
            if topclasters[i][0] in filled:
                continue
            if len(filled) == 5:
                break
            out.write(' ' + topclasters[i][0])
            filled.append(topclasters[i][0])

        out.write("\n")
    out.close()
    print('Completed!')

run_solution()