my CSV contains information about individuals and their date of death and their area of death. I am also using geopy to locate this area. This part is working i think but I don't really want to have the individuals but I want the total bodycount per incident per day and per area. So it gives me a CSV with information about the number of deaths, the geolocation, the date, and the area/province it happened in. Here is a snippet of my csv:
rowid,Name,Status,Sex,Province,Area,Date_of_Death,Cause_of_Death
1,Hasan Ali Saad al-Hareeri ,Civilian,Adult - Male,Daraa,Sawara,2015-12-10,Warplane shelling
2,Riham Adnan Swais ,Civilian,Adult - Female,Homs,Telbeiseh,2015-12-10,Shelling
3,Ammar Ahmad al-Njoam ,Civilian,Adult - Male,Aleppo,Jarablus,2015-12-10,Explosion
4,Yaseen Slaiman al-Salkhadi ,Civilian,Adult - Male,Daraa,Jassim,2015-12-10,Warplane shelling
5,Ayman Noman Qanatra ,Civilian,Adult - Male,Daraa,Jassim,2015-12-10,Warplane shelling
6,Abdul Kareem Mohammad al-Tamki ,Civilian,Adult - Male,Daraa,Sheikh Miskeen,2015-12-10,Warplane shelling
7,Ahmad Mohammad al-Tamki ,Civilian,Child - Male,Daraa,Sheikh Miskeen,2015-12-10,Warplane shelling
8,Hamze Mohammad al-Tamki ,Civilian,Adult - Male,Daraa,Sheikh Miskeen,2015-12-10,Warplane shelling
12,Ahmad Ibraheem al-Sayed Omar ,Civilian,Adult - Male,Aleppo,,2015-12-10,Warplane shelling
13,Unidentified ,Civilian,Child - Male,Aleppo,Kafrnaya,2015-12-10,Warplane shelling
14,Unidentified 1 ,Civilian,Adult - Female,Aleppo,Bazzaa,2015-12-10,Warplane shelling
15,Unidentified 2 ,Civilian,Child - Male,Aleppo,Bazzaa,2015-12-10,Warplane shelling
16,Unidentified 3 ,Civilian,Child - Male,Aleppo,Bazzaa,2015-12-10,Warplane shelling
17,Mohammad Ahmad al-Farhoud ,Civilian,Adult - Male,Idlib,Telminis,2015-12-10,Shooting
23,wife of Faisal al-Ahmad al-Khaleefe ,Civilian,Adult - Female,Deir Ezzor,Qourieh,2015-12-10,Warplane shelling
24,Unidentified ,Civilian,Adult - Male,Deir Ezzor,Takaya,2015-12-10,Kidnapping - Execution
25,Unidentified 1 ,Civilian,Adult - Male,Deir Ezzor,Tabya Jazera village,2015-12-10,Kidnapping - Execution
26,Unidentified 2 ,Civilian,Adult - Male,Deir Ezzor,Tabya Jazera village,2015-12-10,Kidnapping - Execution
27,Unidentified 3 ,Civilian,Adult - Male,Deir Ezzor,Tabya Jazera village,2015-12-10,Kidnapping - Execution
28,Unidentified 4 ,Civilian,Adult - Male,Deir Ezzor,Tabya Jazera village,2015-12-10,Kidnapping - Execution
29,Unidentified 5 ,Civilian,Adult - Male,Deir Ezzor,Tabya Jazera village,2015-12-10,Kidnapping - Execution
32,Amoun Murad ,Civilian,Adult - Female,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
33,Kafa Mezweq ,Civilian,Adult - Female,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
34,Hala Mohammad ,Civilian,Adult - Female,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
35,Ahmad Mezweq ,Civilian,Child - Male,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
36,Ahlam Mezweq ,Civilian,Child - Female,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
37,Adnan Hussain Haj Kheder ,Civilian,Child - Male,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
38,Wife of Hussain Haj Kheder ,Civilian,Adult - Female,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
39,daughter of Hussain Haj Kheder 1 ,Civilian,Child - Female,Idlib,Jisr Shagour: Mraand,2015-12-09,Warplane shelling
40,Muhammad Muhammad al-Aoutani ,Civilian,Adult - Male,Damascus Suburbs,Hamouria,2015-12-09,Warplane shelling
41,Ibrahim al-Shami ,Civilian,Adult - Male,Damascus Suburbs,Hamouria,2015-12-09,Warplane shelling
Here is my code
import csv
from geopy.geocoders import GoogleV3
geolocator = GoogleV3() #here some parameters are needed
lookups = {}
valueCounter = 0
init= True
with open('151213_Martyrs_filtered_civilian_2015_with_country.csv', 'rb') as csvinput:
with open('151213_output_martyrs_final.csv', 'w') as csvoutput:
output_fieldnames = ['Value','Country','Province','Area','Date_of_Death','Cause_of_Death','Latitude','Longitude']
writer = csv.DictWriter(csvoutput, delimiter=',', fieldnames=output_fieldnames)
reader = csv.DictReader(csvinput)
for row in reader:
if init == True :
prevProvince = row['Province']
prevArea = row['Area']
prevDate = row['Date_of_Death']
prevCause = row['Cause_of_Death']
init = False
if prevArea == row['Area'] and prevCause == row['Cause_of_Death'] and prevDate['Date_of_Death']:
valueCounter +=1
if row['Province'].split(' ', 1) == 'Damascus':
rowProv = "Damascus"
else:
rowProv = row['Province']
#here you have to replace the dict item by your csv column names
query = ','.join(str(x) for x in (rowProv, row['Area']))
try:
address, (latitude, longitude) = lookups[query]
except KeyError: # new lookup
try:
query = ','.join(str(x) for x in (rowProv, rowProv))
address, (latitude, longitude) = lookups[query]
# print('lookup')
except KeyError: # search
try:
query = ','.join(str(x) for x in (rowProv, row['Area']))
address, (latitude, longitude) = geolocator.geocode(query)
except: # error
query = ','.join(str(x) for x in (rowProv, rowProv))
address, (latitude, longitude) = geolocator.geocode(query)
lookups[query] = address, (latitude, longitude)
print(query)
else: #write down and save previous Row data
output_row = {}
output_row['Value'] = valueCounter
output_row['Province'] = prevProvince
output_row['Area'] = prevArea
output_row['Date_of_Death'] = prevDate
output_row['Cause_of_Death'] = prevCause
output_row['Latitude'] = latitude
output_row['Longitude'] = longitude
writer.writerow(output_row)
prevProvince = row['Province']
prevArea = row['Area']
prevDate = row['Date_of_Death']
prevCause = row['Cause_of_Death']
valueCounter = 1
if row['Province'].split(' ', 1) == 'Damascus':
rowProv = "Damascus"
else:
rowProv = row['Province']
#here you have to replace the dict item by your csv column names
query = ','.join(str(x) for x in (rowProv, row['Area']))
try:
address, (latitude, longitude) = lookups[query]
except KeyError: # new lookup
try:
query = ','.join(str(x) for x in (rowProv, rowProv))
address, (latitude, longitude) = lookups[query]
# print('lookup')
except KeyError: # search
try:
query = ','.join(str(x) for x in (rowProv, row['Area']))
address, (latitude, longitude) = geolocator.geocode(query)
except: # error
query = ','.join(str(x) for x in (rowProv, rowProv))
address, (latitude, longitude) = geolocator.geocode(query)
lookups[query] = address, (latitude, longitude)
print(query)
What am I not seeing because it is not working?
Terminal gives me this message
Test_stackoverflow_cached Ian$ python geopy_script_bodycount.py
Traceback (most recent call last):
File "geopy_script_bodycount.py", line 22, in <module>
if prevArea == row['Area'] and prevCause == row['Cause_of_Death'] and prevDate['Date_of_Death']:
TypeError: string indices must be integers, not str
I am not sure what you are trying to do in that line, but the problem is in the one mentioned in by the trace:
if prevArea == row['Area'] and prevCause == row['Cause_of_Death'] and prevDate['Date_of_Death']:
Here prevDate is a string, not a dictionary like the row variable. You probably want to compare it something, like in the other clauses.