Little change

question1.py

@@ -68,10 +68,12 @@ def mapFonction1 (x):
 def mapFonction2 (x):
     return [x[1]/x[0],x[2],x[3]]
 
+#Test if it is a Nan
 def testNan (x):
     test = x != x
     return test
 
+#Map reduce fonction
 def mapReduce_mmm(data,timeNB,targetNB):
     results = dict()
     for row in data.result():
@@ -95,7 +97,7 @@ def mapReduce_mmm(data,timeNB,targetNB):
         results[eachTime] = mapFonction2(results[eachTime])
     return results
 
-
+#Zip the values in 3 list, one by one
 def zipValues (values):
     result = [[],[],[]]
     for i in range(3):
@@ -103,7 +105,7 @@ def zipValues (values):
             result[i].append(each[i])
     return result
 
-
+#Fonction 1: the history courbe graph
 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)
@@ -134,7 +136,8 @@ def drawCourbe_history(session,time,target,timeNB,targetNB,espace):
         for label in ax.get_xticklabels()[::6]:
             label.set_visible(True)
     plt.legend(bbox_to_anchor=(1.0, 1), loc=1, borderaxespad=0.)
-    plt.savefig("Projet-NF26/test.png")
+    plt.savefig("Projet-NF26/question1.png")
+    print ("Generate successfully")
 
 
 def checkNBvariable (x):
@@ -150,11 +153,11 @@ def checkNBvariable (x):
 
 def drawCourbe_season(session,season,target,targetNB,espace):
     data = session.execute_async("select * from caitiany.database_espace where station = '%s'"%espace )
+    #We do the same map reduce as fonction 1 by fixing the time as season
     results = mapReduce_mmm(data,2,targetNB)
     results = seprateSeason(results,season)
     keys = list(results.keys())
     values = list(results.values())
-    print(values)
     zipped_result = zipValues(values)
     for each in keys:
         index_each = keys.index(each)
@@ -170,10 +173,11 @@ def drawCourbe_season(session,season,target,targetNB,espace):
     plt.ylabel(target)
     plt.grid(True)
     plt.legend(bbox_to_anchor=(1.0, 1), loc=1, borderaxespad=0.)
-    plt.savefig("Projet-NF26/test.png")
-
+    plt.savefig("Projet-NF26/question1_season.png")
+    print ("Generate successfully")
 
 
+#Choose the data of the season we want
 def seprateSeason (results,season):
     output = dict()
     for each in results:
@@ -185,13 +189,20 @@ def seprateSeason (results,season):
 
 if __name__ == "__main__":
     session = connection()
-    espace = input("Please enter what station you want to search:  ")
-    #time = input("Per which kind of time:  ")
-    target = input("Which value do you want to check:  ")
-    #timeNB = checkNBvariable(time)
-    targetNB = checkNBvariable(target)
-    #drawCourbe_history(session,time,target,timeNB,targetNB,espace)
-
-    #Season check
-    season = input("Please enter which season you want to search:  ")
-    drawCourbe_season(session,season,target,targetNB,espace)
+    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)

question3.py

@@ -5,6 +5,44 @@ from database_pre3 import connection
 import matplotlib.pyplot as plt
 import re
 import folium
+import random
+
+
+table_variable = [
+    'date',
+    'lon',
+    'lat',
+    'station',
+    'alti',
+    'drct',
+    'dwpf', 
+    'feel',
+    'gust',
+    'ice_accretion_1hr',
+    'ice_accretion_3hr',
+    'ice_accretion_6hr',
+    'metar',
+    'mslp',
+    'p01i',
+    'peak_wind_drct',
+    'peak_wind_gust',
+    'peak_wind_time',
+    'relh',
+    'sknt',
+    'skyc1',
+    'skyc2',
+    'skyc3',
+    'skyc4',
+    'skyl1',
+    'skyl2',
+    'skyl3',
+    'skyl4',
+    'tmpf',
+    'vsby',
+    'wxcodes']
+
+
+
 
 def add (x,y):
     return x+y
@@ -96,29 +134,41 @@ def map2_kmeans(x):
 
 
 def MapnewCentre(x):
-    return x[1]/x[0]
+    if x[0] != 0:
+        return x[1]/x[0]
+    else:
+        return 0
 
 
 
-def kmeans (data,targetNB):
-    #3centre with [point count, temprature centre]
-    centre = {0:[1,0],1:[1,0],2:[1,0]}
+def kmeans (data,targetNB,target):
     #cluster est pour stocler lat, lon de chaque point de chaque cluster
     cluster = [[],[],[]]
 
     result = mapReduce_kmeans(data,targetNB)
 
-    #mettre le premier 3 point comme le centres init
-    init_point_values = [result[i] for i in result.keys()][:3]
-    init_point_keys = [i for i in result.keys()][:3]
+    if len(result) < 3:
+        raise Exception ("We\'ve just searched less than 3 station!!")
+
+    #mettre ramdom 3 point comme le centres init
+    center1 = random.choice(list(result))
+    center2 = random.choice(list(result))
+    center3 = random.choice(list(result))
+    init_point_values = [result[center1],result[center2],result[center3]]
+    #init_point_values = [result[i] for i in result.keys()][:3]
+    init_point_keys = [center1,center2,center3]
+
+    #3centre with [point count, temprature centre]
+    centre = {0:[0,0],1:[0,0],2:[0,0]}
+    centre_new = {0:[0,0],1:[0,0],2:[0,0]}
 
     for key in centre.keys():
         centre[key] = [1,init_point_values[key]]
+        centre_new[key] = [1,init_point_values[key]]
         cluster[key].append(init_point_keys[key])
     
 
     #init the centre new and result new for mapreduce
-    centre_new = {0:[0,0],1:[0,0],2:[0,0]}
     result_new = dict()
     #When the number of point of cluster don't change,stop
     while True:
@@ -154,17 +204,20 @@ def kmeans (data,targetNB):
             break
         else:
             #caculate the new centre
-            print ('jasdlkjalsdkjalskd         ',cluster_nb_diff(centre_new,centre))
+            print ("Cluster number differ:  ",cluster_nb_diff(centre_new,centre))
+            print (centre_new)
             for eachculster in centre_new:
                 centre_new[eachculster][1] = MapnewCentre(centre_new[eachculster])
+            print("center new: ",centre_new)
+            print("center old: ",centre)
             centre = centre_new
             centre_new = {0:[0,0],1:[0,0],2:[0,0]}
             result_new = dict()
             cluster = [[],[],[]]
-    createMap(cluster)
+    createMap(cluster,result)
 
 
-def createMap (cluster):
+def createMap (cluster,result):
     mean_lat = 0
     count = 0
     for each in [cluster[0],cluster[1],cluster[2]]:
@@ -187,18 +240,33 @@ def createMap (cluster):
     i = 0
     for each in [cluster[0],cluster[1],cluster[2]]:
         for each_pos in each:
+            label = str(each_pos[2])+"\n"+""+target+":"+str(round(result[(each_pos[0],each_pos[1],each_pos[2])],2))
             folium.Marker([each_pos[1],each_pos[0]],
-                        popup=each_pos[2],
+                        popup=label,
                         icon=folium.Icon(color=color[i])).add_to(m)
         i +=1
     print(i)
     m.save("Projet-NF26/map.html")
+    print("Generate successfully")
+
+
 
+def checkNBvariable (x):
+    i=0
+    for each in table_variable:
+        if x == each:
+            return i
+        i += 1
+    print ('Doesn\'t exist!!')
 
 
 if __name__ == "__main__":
     session = connection()
-    start = '2008-12-19'
-    end = '2012-12-14'
+    start = input("Please enter the start time [form: AAAA-MM-DD (From 2008-1-1 to 2017-12-30)]:  ")
+    end = input("Please enter the end time [form: AAAA-MM-DD (From 2008-1-1 to 2017-12-30)]:  ")
+    target = input("Which indicator do you want to check [tmpf,dwpf,etc]:  ")
+    targetNB = checkNBvariable(target)
+    #start = '2008-12-19'
+    #end = '2012-12-14'
     data = session.execute_async("select * from caitiany.database_kmeans where date >= '%s' and date <= '%s' ALLOW FILTERING"%(start,end))
-    kmeans(data,4)
+    kmeans(data,targetNB,target)