From a2ca594f992e47abb7665f0b695785b69c05f4d7 Mon Sep 17 00:00:00 2001
From: Oliver <ovaningen@student.unimelb.edu.au>
Date: Sat, 24 Apr 2021 16:40:29 +1000
Subject: [PATCH] LGA health conditions: smoker, preobese, obesity and heart
disease
---
LGA_by_HEALTH.csv | 9 +++++++++
LGA_by_HEALTH.py | 13 +++++++++++++
SA2_to_LGA.py | 2 +-
3 files changed, 23 insertions(+), 1 deletion(-)
create mode 100644 LGA_by_HEALTH.csv
create mode 100644 LGA_by_HEALTH.py
diff --git a/LGA_by_HEALTH.csv b/LGA_by_HEALTH.csv
new file mode 100644
index 0000000..ccb3470
--- /dev/null
+++ b/LGA_by_HEALTH.csv
@@ -0,0 +1,9 @@
+LGA_CODE_2011,smokers,heart_disease,pre_obese,obese
+21890,12.1,6.6,30.1,19.3
+22670,14.5,9.1,28.1,16.8
+22750,12.2,7.9,32.5,16.6
+23110,11.8,8.1,30.4,21.3
+23810,24.4,5.6,36.6,22.0
+24330,15.7,3.9,34.9,11.9
+27350,14.3,7.0,23.5,12.1
+27450,8.9,6.7,33.1,16.4
diff --git a/LGA_by_HEALTH.py b/LGA_by_HEALTH.py
new file mode 100644
index 0000000..69cef3f
--- /dev/null
+++ b/LGA_by_HEALTH.py
@@ -0,0 +1,13 @@
+import pandas as pandas
+
+df = pandas.read_csv("datasets/2015_LGA_health_profiles.csv", dtype = "string")
+
+lgas = set(pandas.read_csv("PM10_to_LGA.csv", dtype = "string")["LGA_CODE_2011"].unique())
+
+df = df[df[" lga_code"].isin(lgas)]
+df = df.rename(columns = {" lga_code": "LGA_CODE_2011", "ppl_reporting_heart_disease_perc": "heart_disease",
+ " ppl_reporting_being_pre_obese_perc": "pre_obese", " ppl_reporting_being_obese_perc": "obese", " ppl_aged_over_18_who_are_current_smokers_perc": "smokers"})
+df = df.sort_values(["LGA_CODE_2011"])
+df = df.reindex(columns = ["LGA_CODE_2011", "smokers", "heart_disease", "pre_obese", "obese"])
+
+df.to_csv(path_or_buf = "LGA_by_HEALTH.csv", index = False)
\ No newline at end of file
diff --git a/SA2_to_LGA.py b/SA2_to_LGA.py
index d2ffa64..1ca4df0 100644
--- a/SA2_to_LGA.py
+++ b/SA2_to_LGA.py
@@ -5,7 +5,7 @@ df = pandas.read_csv("datasets/2011_SA2_to_LGA_vic.csv", dtype = "string")
# Keep only Victorian LGAs
#df = df[df["LGA_CODE_2011"].str[0] == "2"]
# Only ones in AQ_to_LGA.csv
-lgas = set(pandas.read_csv("AQ_to_LGA.csv", dtype = "string")["LGA_CODE_2011"].unique())
+lgas = set(pandas.read_csv("PM10_to_LGA.csv", dtype = "string")["LGA_CODE_2011"].unique())
print(lgas)
df = df[df["LGA_CODE_2011"].isin(lgas)]
--
GitLab