Merge pull request #19 from bsuman79/master

changed absolute path to ../data

analysis/analysis.py

@@ -1,9 +1,9 @@
 import pandas as pd
 import numpy as np
+import os
 
 
-
-def mwrd(directory='/Users/thoughtworker/chicago-river-sewage/data/', file='mwrd_rain_measurements.csv'):
+def mwrd(directory='../data/', file='mwrd_rain_measurements.csv'):
    data= pd.read_csv(directory+file, na_values='na')
    print data.shape[0]
    location= list(set(data.ix[0:,3]))
@@ -30,19 +30,58 @@ def mwrd(directory='/Users/thoughtworker/chicago-river-sewage/data/', file='mwrd
    print data_new.shape
    np.savetxt(file, data_new,fmt='%s', delimiter=",")
 
-def clean_water(directory='/Users/thoughtworker/chicago-river-sewage/data/',file='clean-waterway-measurements.csv'):
+def clean_water(directory='../data/',file='clean-waterway-measurements.csv'):
     data=pd.read_csv(directory+file, na_values='na')
     np.savetxt(file, data,fmt='%s', delimiter=",")
 
-def cso():
-   directory='/Users/thoughtworker/chicago-river-sewage/data/'
-   cso_file='cso_events_timestamped.csv'
+def cso(directory='../data/', file='cso_events_timestamped.csv', file1='ssmma_mwrd_merge_cleanedup.csv'):
+    readdata= pd.read_csv(directory+file1, na_values='na')    
+    loc=list(readdata['TARP Connection'])
+    lat=list(readdata['LAT_DEC'])
+    lng=list(readdata['LON_CONV'])
+    latitude,longitude={},{}
+    for key, val in zip(loc, lat):
+       latitude[key]=val
+    for key, val in zip(loc,lng):
+       longitude[key]= val
+    #print len(latitude), len(longitude) 
+    ct=0
+    fw=open('jnk.csv','w')
+    fw1=open('nocoord.csv','w')
+    with open(directory+file,"r") as f:
+      for line in f:
+         lsplit=line.split(",")
+         if len(lsplit)==4 and "(" not in lsplit[0]:
+            try:
+              print>>fw, '%s,%s,%s,%s,%s'%(lsplit[0], lsplit[-2],lsplit[-1], latitude[lsplit[0]],longitude[lsplit[0]])
+              ct+=1
+            except KeyError:
+              print>>fw1, '%s,%s,%s,%s,%s'%(lsplit[0], lsplit[-2],lsplit[-1], 'nan','nan') 
+              ct+=1   
+         if len(lsplit)!=4 and "(" in lsplit[0]: 
+            tmp=line.split("),")[0].split("(")[1].split(",")[0] 
+            try: 
+              print>>fw, '%s,%s,%s,%s,%s'%(tmp,lsplit[-2],lsplit[-1],latitude[tmp],longitude[tmp])
+              ct+=1
+            except KeyError:
+              print>>fw1, '%s,%s,%s,%s,%s'%(tmp,lsplit[-2],lsplit[-1],'nan','nan')
+              ct+=1     
+         if len(lsplit)!=4 and "(" not in lsplit[0]:
+             try:
+               print>>fw, '%s,%s,%s,%s,%s'%(lsplit[0], lsplit[-2],lsplit[-1], latitude[lsplit[0]],longitude[lsplit[0]])
+               ct+=1
+             except KeyError:
+                 print>>fw1, '%s,%s,%s,%s,%s'%(lsplit[0], lsplit[-2],lsplit[-1], 'nan','nan')
+                 ct+=1                
+    print ct                  
+    fw.close()
+    os.system('mv jnk.csv '+ file)
+
 
-   cso_data= pd.read_csv(directory+cso_file, na_values='na')
-   print cso_data.shape
+
 
 
 if __name__=="__main__":
     mwrd()
-    #cso()
-    #clean_water()
+    cso()
+    clean_water()