# coding: utf-8
__author__ = 'ZFTurbo: https://kaggle.com/zfturbo'

import datetime
from heapq import nlargest
from operator import itemgetter
from collections import defaultdict
import numpy as np
import math
import matplotlib.pyplot as plt
from sklearn import svm, datasets, metrics
from sklearn.model_selection import KFold
from sklearn import preprocessing
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn import mixture
from sklearn.model_selection import cross_val_predict
from sklearn.linear_model import LogisticRegression

import pandas as pd


def run_solution():
    
    train = pd.read_csv("../input/train.csv",  nrows = 1000000, error_bad_lines=False)  
    test = pd.read_csv("../input/test.csv", nrows = 2000000,error_bad_lines=False)
    id_test = test['id']
    
    del train["date_time"]
    del train["srch_ci"]
    del train["srch_co"]
    del train["is_booking"]
    del train["cnt"]
    train = train.fillna(0)
    test = test.fillna(0)
    
    cluster = defaultdict(lambda: defaultdict(int))

    from sklearn.ensemble import RandomForestClassifier
    predictors = [c for c in train.columns if c not in ["hotel_cluster"]]
    clf = RandomForestClassifier(n_estimators=25, min_weight_fraction_leaf=0.1)
    #scores = cross_validation.cross_val_score(clf, train[predictors], train['hotel_cluster'], cv=3)
    clf.fit(train[predictors], train['hotel_cluster'])
    y_pred = clf.predict_proba(test[predictors])
    
    for i in range(len(id_test)):
        data = sorted(y_pred[i], reverse = True)[0:5]
        cluster[id_test[i]] = data    
    
    print('Preparing arrays...')
    f = open("../input/train.csv", "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))
    total = 0
    #count = 0

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

    print('Generate submission...')
    now = datetime.datetime.now()
    path = 'submission_' + str(now.strftime("%Y-%m-%d-%H-%M")) + '.csv'
    out = open(path, "w")
    f = open("../input/test.csv", "r")
    f.readline()
    total = 0
    out.write("id,hotel_cluster\n")

    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])

        if len(filled) != 5:
            d = cluster[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])

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

run_solution()