WIP about to plot with transaction precision

bnp_pdf_statement_parser.py

@@ -5,6 +5,7 @@ import matplotlib.pyplot as plt
 import matplotlib.ticker as ticker
 from datetime import datetime
 from utils import getDatetimeFromFileName, getMonthIndexSinceEpoch, getMonthNameFromMonthIndex, readPdfBankStatement
+import operator
 
 PATH = f'/home/benjamin/Desktop/bens_folder/bazaar/documents/bnp/bank_statements/'
 
@@ -16,30 +17,24 @@ MAIN_BANK_ACCOUNT = 'compte_de_cheques'
 
 debits = []
 credits_ = []
-# Precise bank account
 allTransactions = []
-
+monthlyTransactions = {}
-'''
-def appendTransactions(x):
-    global allTransactions
-    allTransactions += [x]
-'''
 
 def appendTransactions(transactions, bankAccount):
     global allTransactions
-    #print('Before')
-    #pprint(allTransactions)
     for transaction in transactions:
         transaction['bank account'] = bankAccount
         allTransactions += [transaction]
-    #print('After')
+        date = transaction['date'].replace(day = 1)
-    #pprint(allTransactions)
+        monthlyTransactions[date] = monthlyTransactions.get(date, []) + [transaction]
 
 for folder in os.listdir():
     if folder != MAIN_BANK_ACCOUNT:
         for file in os.listdir(folder):
             filePath = f'{folder}/{file}'
             print(filePath)
+            print(readPdfBankStatement(filePath))
+            exit(0)
             transactions = readPdfBankStatement(filePath)[3]
             appendTransactions(transactions, folder)
 
@@ -59,13 +54,21 @@ for folder in sorted(os.listdir()):
     #break
 
 from pprint import pprint
-#pprint(transactions)
-import operator
 allTransactions.sort(key = operator.itemgetter('date'))
 print(len(allTransactions))
 pprint(allTransactions)
 
-exit(0)
+sortedMonths = sorted(monthlyTransactions.keys())
+#pprint(sortedMonths)
+# debit or credit?
+totalMonthlyCredits = []
+totalMonthlyDebits = []
+totalMonthlyDifferences = []
+#totalMonthlyDebits = [[ for transaction in monthlyTransactions[month]] for month in sortedMonths]
+for month in sortedMonths:
+    #for transaction in monthlyTransactions[month]:
+    currentMonthlyTransactions = monthlyTransactions[month]
+    monthlyCredits = []
 
 fig, ax = plt.subplots()
 plt.title('Monthly debits and credits')
@@ -73,12 +76,12 @@ plt.xlabel('Date')
 plt.ylabel('€')
 ALPHA = 0.5
 
-xTicks = range(getMonthIndexSinceEpoch(firstDatetime), getMonthIndexSinceEpoch(lastDatetime) + 1)
+xTicks = range(getMonthIndexSinceEpoch(sortedMonths[0]), getMonthIndexSinceEpoch(sortedMonths[-1]) + 1)
 totalMonthlyAmountAndLabel = (
     #(totalMonthlyDebits, 'Debit'),
     #(totalMonthlyCredits, 'Credit'),
     (totalMonthlyDifferences, 'Difference'),
-    (totals, 'Total'),
+    #(totals, 'Total'),
 )
 for totalMonthlyAmount, totalMonthlyLabel in totalMonthlyAmountAndLabel:
     plt.bar(xTicks, totalMonthlyAmount, alpha = ALPHA, label = totalMonthlyLabel)

utils.py

@@ -78,6 +78,7 @@ def readPdfBankStatement(filePath):
                 break
             firstLineOfPaymentRegexMatch = FIRST_LINE_OF_PAYMENT_REGEX.match(line)
             if firstLineOfPaymentRegexMatch is not None:
+                print(line)
                 if date is not None:
                     transactions += [{
                         'date': getDateFollowing(date, initialDate),