Add logarithmic scale

bnp_pdf_statement_parser.py

@@ -7,6 +7,7 @@ import subprocess
 import re
 import matplotlib.pyplot as plt
 import matplotlib.ticker as ticker
+from datetime import datetime
 
 path = f'/home/benjamin/Desktop/bens_folder/bazaar/documents/bnp/bank_statements/'
 
@@ -38,12 +39,16 @@ PRINT_TRANSACTIONS = False
 
 totalMonthlyDebits = []
 totalMonthlyCredits = []
+firstDatetime = None
+lastDatetime = None
 for folder in sorted(os.listdir()):
     for file in sorted(os.listdir(folder)):
         #folder = '2022'
         #file = '20220321.pdf'
         filePath = f'{folder}/{file}'
         print(filePath)
+        if firstDatetime is None:
+            firstDatetime = file
         content = getTextFromPdf(filePath)
         lines = content.splitlines()
         started = False
@@ -91,17 +96,42 @@ for folder in sorted(os.listdir()):
                     comment += [line]
         #break
     #break
+lastDatetime = file
 
 fig, ax = plt.subplots()
 plt.title('Monthly debits and credits')
 plt.xlabel('Date')
 plt.ylabel('€')
 ALPHA = 0.5
-xTicks = range(len(totalMonthlyDebits))
+
+def getMonthIndex(aDatetimeStr):
+    aDatetime = datetime.strptime(aDatetimeStr, '%Y%m%d.pdf')
+    return aDatetime.year * 12 + aDatetime.month
+
+'''
+print(firstDatetime)
+print(lastDatetime)
+exit(1)
+'''
+#print(getMonthIndex(firstDatetime))
+#print(getMonthIndex(lastDatetime))
+xTicks = range(getMonthIndex(firstDatetime), getMonthIndex(lastDatetime) + 1)
+#print(len(xTicks))
+#print(len(totalMonthlyDebits))
 plt.bar(xTicks, totalMonthlyDebits, alpha = ALPHA, label = 'Debit')
 plt.bar(xTicks, totalMonthlyCredits, alpha = ALPHA, label = 'Credit')
 plt.legend()
 
+plt.yscale('log')
 ax.yaxis.set_major_formatter(ticker.StrMethodFormatter('{x:,}'))
 
+def getMonthName(monthIndex):
+    return datetime((monthIndex - 1) // 12, 1 + (monthIndex - 1) % 12, 1).strftime('%b %Y')
+
+ticksLabels = [getMonthName(monthIndex) for monthIndex in xTicks]
+plt.xticks(xTicks, ticksLabels, rotation = 90)
+#plt.tight_layout()
+# How to show the horizontal lines for subticks?
+plt.grid(axis = 'y')
+
 plt.show()