parsebudget.py

import csv


CSVFILE='2018H1.csv'# TL:DR:
#Spending money:
# -,Personal.Recreation.Social,28.37
# -,Groceries,45.32
#Getting money:
# +,Income.Job,420.69
#Being subsidized:
# *,Gas,25.00
#Administrative corrections (e.g., chargebacks, canceled checks, etc):
# %,Personal,17.00


with open(CSVFILE) as f:
	#TODO large budget file support
	og=[e for e in csv.reader(f)]

budget=dict()

for t,c,v in og:
	if t not in budget:
		budget[t]=list()
	budget[t].append( (c,int(float(v)*100 + 0.4999)) )


cat_sep=['Personal.*', 'Personal.Technology', 'Personal.Recreation.Social', 'Personal.Recreation']

budg2=dict()

def handle_item(t, c, v, budg2=budg2):
	if t=='-':
		if not c in budg2:
			budg2[c]=0
		budg2[c]+=v
	elif t=='+':
		pass
	elif t=='*' or t=='%':
		if not c in budg2:
			budg2[c]=0
		budg2[c]-=v
	else:
		raise NotImplementedError

def check_is_match(cat, cat_sep):
	temp_cat=cat.split('.')[::-1]
	
	for element in cat_sep.split('.'):
		if len(temp_cat):
			# Still items yet to pop
			# Compare next item of cat_sep with next item of cat
			if element != temp_cat.pop():
				# MISMATCH, kill it
				return False
		else:
			#len==0, but for-loop is still running,
			#therefore cat was shorter than cat_sep
			return False
	# The for-loop exited, so cat_sep was shorter or equal
	# -AND all items tested matched
	return True

for t,l in budget.items():
	for c,v in l:
		for c_s in cat_sep:
			if check_is_match(c, c_s):
				handle_item(t,c_s,v,budg2)
				break
		else:
			handle_item(t,c.split('.')[0],v,budg2)

labels=[]
values=[]

for c,v in budg2.items():
	labels.append(c)
	values.append(v/100)

import plotly.offline
import plotly.graph_objs

trace = plotly.graph_objs.Pie(labels=labels, values=values)
plotly.offline.plot([trace],filename='out.html')