question1.py 6.11 KB
Newer Older
Tianyang's avatar
Tianyang committed
1
2
3
import numpy as np
import matplotlib.pyplot as plt
from functools import reduce
Tianyang's avatar
Tianyang committed
4
from database_pre1 import connection
Tianyang's avatar
Tianyang committed
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
import matplotlib.pyplot as plt


table_variable = ['station varchar',
        'year',
        'season',
        'month',
        'day',
        'hour',
        'minute',
        'lon',
        'lat',
		'tmpf',
		'dwpf',
		'relh',
		'drct',
		'sknt',
		'p01i',
		'alti',
		'mslp',
		'vsby',
		'gust',
		'skyc1',
		'skyc2',
		'skyc3',
		'skyc4',
		'skyl1',
		'skyl2',
		'skyl3',
		'skyl4',
		'wxcodes',
		'ice_accretion_1hr',
		'ice_accretion_3hr',
		'ice_accretion_6hr',
		'peak_wind_gust',
		'peak_wind_drct',
		'peak_wind_time',
		'feel',
		'metar']

def add (x,y):
    return x+y

def fmax(x,y):
    return max(x,y)

def fmin(x,y):
    return min(x,y)

#caculate mean, max, min reduce
#input [count,mean,max,min]
def reduceFonction (x,y):
    result = []
    fonctions = {0:'add',1:'add',2:'fmax',3:'fmin'}
    for i in range(4):
        result.append(reduce(eval(fonctions.get(i)),[x[i],y[i]]))
    return result

#input [valeur] -> [count,mean,max,min]
def mapFonction1 (x):
    return [1,x,x,x]

#input [count,mean,max,min] -> [mean,max,min]
def mapFonction2 (x):
    return [x[1]/x[0],x[2],x[3]]

Tianyang's avatar
Tianyang committed
71
#Test if it is a Nan
Tianyang's avatar
Tianyang committed
72
73
74
75
def testNan (x):
    test = x != x
    return test

Tianyang's avatar
Tianyang committed
76
#Map reduce fonction
Tianyang's avatar
Tianyang committed
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
def mapReduce_mmm(data,timeNB,targetNB):
    results = dict()
    for row in data.result():
        if timeNB == 1:
            data_time = row[timeNB]
        elif timeNB == 2:
            data_time = (row[timeNB-1],row[timeNB])
        elif timeNB == 3:
            data_time = (row[timeNB-2],row[timeNB-1],row[timeNB])
        else:
            assert 1==2, "Doesn\'t exits!"
        data_target = row[targetNB]
        if testNan(data_time) or testNan(data_target):
            continue
        if results.get(data_time) is None:
            results[data_time] = mapFonction1(data_target)
        else:
            mapresult = mapFonction1(data_target)
            results[data_time] = reduceFonction(mapresult,results[data_time])
    for eachTime in results:
        results[eachTime] = mapFonction2(results[eachTime])
    return results

Tianyang's avatar
Tianyang committed
100
#Zip the values in 3 list, one by one
Tianyang's avatar
Tianyang committed
101
102
103
104
105
106
107
def zipValues (values):
    result = [[],[],[]]
    for i in range(3):
        for each in values:
            result[i].append(each[i])
    return result

Tianyang's avatar
Tianyang committed
108
#Fonction 1: the history courbe graph
Tianyang's avatar
Tianyang committed
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
def drawCourbe_history(session,time,target,timeNB,targetNB,espace):
    data = session.execute_async("select * from caitiany.database_espace where station = '%s'"%espace )
    results = mapReduce_mmm(data,timeNB,targetNB)
    keys = list(results.keys())
    values = list(results.values())
    zipped_result = zipValues(values)
    if isinstance(keys[0],tuple):
        for each in keys:
            index_each = keys.index(each)
            each = list(each)
            if timeNB == 2:
                each[0] = str(each[0])
                keys[index_each] = ".".join(each)
            elif timeNB == 3:
                each[0] = str(each[0])
                each[2] = str(each[2])
                keys[index_each] = each[0] +'.'+ each[2]
    fig, ax = plt.subplots(1, 1)
    plt.plot(keys,zipped_result[0],'x-',label="mean")
    plt.plot(keys,zipped_result[1],'+-',label="max")
    plt.plot(keys,zipped_result[2],'b--',label="min")
    plt.xticks(keys, keys, rotation=45, fontsize=5)
    plt.ylabel(target)
    plt.grid(True)
    if timeNB == 3:
        for label in ax.get_xticklabels():
            label.set_visible(False)
        for label in ax.get_xticklabels()[::6]:
            label.set_visible(True)
    plt.legend(bbox_to_anchor=(1.0, 1), loc=1, borderaxespad=0.)
Tianyang's avatar
Tianyang committed
139
140
    plt.savefig("Projet-NF26/question1.png")
    print ("Generate successfully")
Tianyang's avatar
Tianyang committed
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155


def checkNBvariable (x):
    i=0
    for each in table_variable:
        if x == each:
            return i
        i += 1
    print ('Doesn\'t exist!!')




def drawCourbe_season(session,season,target,targetNB,espace):
    data = session.execute_async("select * from caitiany.database_espace where station = '%s'"%espace )
Tianyang's avatar
Tianyang committed
156
    #We do the same map reduce as fonction 1 by fixing the time as season
Tianyang's avatar
Tianyang committed
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
    results = mapReduce_mmm(data,2,targetNB)
    results = seprateSeason(results,season)
    keys = list(results.keys())
    values = list(results.values())
    zipped_result = zipValues(values)
    for each in keys:
        index_each = keys.index(each)
        each = list(each)
        each[0] = str(each[0])
        keys[index_each] = ".".join(each)

    fig, ax = plt.subplots(1, 1)
    plt.plot(keys,zipped_result[0],'x-',label="mean")
    plt.plot(keys,zipped_result[1],'+-',label="max")
    plt.plot(keys,zipped_result[2],'b--',label="min")
    plt.xticks(keys, keys, rotation=45, fontsize=5)
    plt.ylabel(target)
    plt.grid(True)
    plt.legend(bbox_to_anchor=(1.0, 1), loc=1, borderaxespad=0.)
Tianyang's avatar
Tianyang committed
176
177
    plt.savefig("Projet-NF26/question1_season.png")
    print ("Generate successfully")
Tianyang's avatar
Tianyang committed
178
179


Tianyang's avatar
Tianyang committed
180
#Choose the data of the season we want
Tianyang's avatar
Tianyang committed
181
182
183
184
185
186
187
188
189
190
191
def seprateSeason (results,season):
    output = dict()
    for each in results:
        if season in each:
            output[each] = results[each]
    return output



if __name__ == "__main__":
    session = connection()
Tianyang's avatar
Tianyang committed
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
    choice = int(input("Which kind of service do you want?\n1.Station history\n2.Check history by seasons\nYour choice: "))

    #if choice == 1, we will use the fonction 1
    if choice == 1:
        espace = input("Please enter which station you want to search [LEBZ,LETO,etc]:  ")
        time = input("By which kind of time [year,season,month,etc]:  ")
        target = input("Which indicator do you want to check [tmpf,dwpf,etc]:  ")
        timeNB = checkNBvariable(time)
        targetNB = checkNBvariable(target)
        drawCourbe_history(session,time,target,timeNB,targetNB,espace)
    else:
        #Fonction 2, the check according to the seasons
        espace = input("Please enter what station you want to search [LEBZ,LETO,etc]:  ")
        target = input("Which indicator do you want to check [tmpf,dwpf,etc]:  ")
        targetNB = checkNBvariable(target)
        season = input("Please enter which season you want to search [Spring,Summer,Autumn,Winter]:  ")
        drawCourbe_season(session,season,target,targetNB,espace)