後でcsvファイルから抽出したい特定の変数に対応する列番号のリストを返す関数を作成しました。変数名は で指定しstate_aggregate_vars
ます。
import csv
import numpy
def compute_countyStats(state_aggregate, year, state_aggregate_vars, listCounties, county_var, int_obese, int_healthy, int_refuse): :
f = open(state_aggregate, 'r')
readit = csv.reader(f)
headers = readit.next()
use_cols = []
for name in state_aggregate_vars:
use_cols.append(headers.index(name))
return use_cols
county_data = numpy.genfromtxt(f, dtype=float, delimiter=',', names = state_aggregate_vars, filling_values= -1,
usecols= use_cols, usemask=False)
sorted_array = county_data(numpy.argsort(county_data, axis= headers.index(county_var))
for code in listCounties:
temp = []
for entry in sorted_array:
if entry[0] == code:
temp.append(float(entry[1]))
else:
continue
percent_healthy = numpy.true_divide(temp.count(int_healthy),num_obs)
percent_obese = numpy.true_divide(temp.count(int_obese),num_obs)
percent_refused = numpy.true_divide(temp.count(int_refuse),num_obs)
county_stats[code] = year, code, percent_healthy, percent_obese, percent_refused,
return county_stats
次に、以下を使用してこの関数を呼び出します。
state_aggregate = "Aggregate_test90.csv"
year = 1990
state_aggregate_vars = ['_BMI90', 'AGE90', 'CTYCODE90', 'IYEAR90', 'SEX90', '_RFOBESE90']
listCounties = [31, 43, 163, 32, 167, 97]
county_var = 'CTYCODE90'
int_obese = 2
int_healthy = 1
int_refuse = 0
test = compute_countyStats(state_aggregate, year, state_aggregate_vars, listCounties, county_var, int_obese, int_healthy, int_refuse)
これが私のエラーです:
SyntaxError: invalid syntax in line 6:
for name in state_aggregate_vars:
何がうまくいかないのですか?
これが私のものpython -V
です:
Python 2.7.3 -- EPD 7.3-2 (32-bit)