import re
import csv
from automation import xytogeo
import pickle as cp
from auxilary import bin_assign,trim
Geo_dic ={}
with open('../../data/RPD__Part_I_Crime_14_Days.csv') as fin:
j=0
reader = csv.DictReader(fin)
for row in reader:
Geo_dic[(row["X"],row["Y"])] = xytogeo(row["X"],row["Y"])[:-3]
print j
j=j+1
# # if j>10:
# # break
#Geoid Dictionary
# Geo_dic = {}
# with open('../../data/dataset3.csv',"rb") as fin:
# reader = csv.DictReader(fin)
# for row in reader:
# Geo_dic [(row["X"],row["Y"])] = row["GeoID"]
for row in csv.reader(csvinput):
if row[0] == "X":
top_row = copy.copy(row)
#Finding necessary information to keep
time_ind= row.index("OccurredFrom_Time")
mon_ind= row.index("OccurredFrom_Date_Month")
yr_ind = row.index("Reported_Date_Year")
patrol_beat_ind = row.index("Patrol_Beat")
crimetype_ind = row.index("Statute_Text")
loctype_ind = row.index("Location_Type")
geobeat_ind = row.index("Geo_Beat")
geosec_ind = row.index("Geo_Section_Num")
row=row[:2]+["GeoID"]+[row[time_ind],row[mon_ind],row[yr_ind],row[patrol_beat_ind],row[crimetype_ind],row[loctype_ind],row[geobeat_ind],row[geosec_ind]]
#writing the necessary information and adding the binary datatype
writer.writerow(row+["IsLarceny","IsBurglary","IsMotor Vehicle Theft","IsRobbery","IsAggravated Assault","IsMurder","Ismor","Isnoon","Isnight"])
else:
if (row[0] and row[1]):
crm_text = row[crimetype_ind]
time_txt = int(row[time_ind])
ad_row= bin_assign(crm_text,time_txt)
row=row[:2]+[xytogeo(row[0],row[1])[:-3]]+[row[time_ind],row[mon_ind],row[yr_ind],row[patrol_beat_ind],row[crimetype_ind],row[loctype_ind],row[geobeat_ind],row[geosec_ind]]+ad_row
writer.writerow(row)
i=i+1
print i
# if i>10:
# break
row[time_ind], row[mon_ind], row[yr_ind],
row[patrol_beat_ind], row[crimetype_ind], row[loctype_ind],
row[geobeat_ind], row[geosec_ind]
]
#writing the necessary information and adding the binary datatype
writer.writerow(row + [
"IsLarceny", "IsBurglary", "IsMotor Vehicle Theft",
"IsRobbery", "IsAggravated Assault", "IsMurder", "Ismor",
"Isnoon", "Isnight"
])
else:
if (row[0] and row[1]):
crm_text = row[crimetype_ind]
time_txt = int(row[time_ind])
geoid = xytogeo(row[0], row[1])[:-3]
ad_row, dic = bin_assign(crm_text, time_txt, ratio, geoid)
ratio = dic
row = row[:2] + [geoid] + [
row[time_ind], row[mon_ind], row[yr_ind],
row[patrol_beat_ind], row[crimetype_ind],
row[loctype_ind], row[geobeat_ind], row[geosec_ind]
] + ad_row
writer.writerow(row)
i = i + 1
print i
# if i>10:
# break
csvoutput.close()
def get_paramforpredicition(X,Y): geoid = xytogeo(X,Y) near_loc = nearest(X,Y,geoid) params = Parameter_set[near_loc] return params
with open('../../data/RPD__Part_I_Crime_2011_to_Present.csv') as fin:
with open('../../data/dataset7.csv', 'wb') as csvfile:
j = 0
reader = csv.DictReader(fin)
fieldnames = ["X", "Y", "GeoID"]
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for row in reader:
j = j + 1
if (j > 56900 and j < 57400):
if (row["X"] and row["Y"]):
if j % 100 == 0:
print j
write_dic = {}
write_dic["X"] = row["X"]
write_dic["Y"] = row["Y"]
write_dic["GeoID"] = xytogeo(row["X"], row["Y"])[:-3]
writer.writerow(write_dic)
# for row in reader:
# if (row["X"] and row["Y"]):
# write_dic={}
# write_dic["X"] = row["X"]
# write_dic["Y"] = row["Y"]
# write_dic["GeoID"] = xytogeo(row["X"],row["Y"])[:-3]
# print write_dic
# writer.writerow(write_dic)
# # if j>10:
# # break