add display script, fix critical cleanup bug, first exports

.gitignore

@@ -7,3 +7,4 @@ NONE
 data/
 log_importer
 secrets.py
+share/

cleanup_script.py

@@ -1,34 +1,28 @@
 #!/usr/bin/env python3
 import argparse
 import csv
-import sys
-import json
 import logging
-import requests
-import hashlib
-import io
-import datetime
-import pandas as pd
 from rich import progress
 from rich.logging import RichHandler
 from rich.console import Console
 from rich.traceback import install
 install(show_locals=True, locals_max_length=150, locals_max_string=300)
 global YEARS
-YEARS = [2020, 2021, 2022, 2023, 2024]
+YEARS = [2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
 global INFLATION_RATES
+#Harmonisierter Verbraucherpreisindex des statistischen Bundesamts
 INFLATION_RATES = {
-        2014: 0.8,
-        2015: 0.7,
-        2016: 0.4,
-        2017: 1.7,
-        2018: 1.9,
-        2019: 1.4,
-        2020: 0.4,
-        2021: 3.2,
-        2022: 8.7,
-        2023: 6.0,
-        2024: 2.5,
+        2014: 0.008,
+        2015: 0.007,
+        2016: 0.004,
+        2017: 0.017,
+        2018: 0.019,
+        2019: 0.014,
+        2020: 0.004,
+        2021: 0.032,
+        2022: 0.087,
+        2023: 0.060,
+        2024: 0.025,
         }
 
 class Company:
@@ -78,11 +72,8 @@ class Company:
 
     def calculate_all_tax(self) -> None:
         """Calculate tax for all relevant years."""
-        self.calculate_tax(2020)
-        self.calculate_tax(2021)
-        self.calculate_tax(2022)
-        self.calculate_tax(2023)
-        self.calculate_tax(2024)
+        for year in YEARS:
+            self.calculate_tax(year)
 
     def calculate_tax(self, year: int) -> None:
         """Calculate simple tax from provided values."""
@@ -111,14 +102,7 @@ class Company:
 
     def write(self) -> None:
         """Write the current dataset to CSV"""
-        with open(self.report.output) as out_csv:
-            try:
-                output_reader = pd.read_csv(out_csv)
-                bvd_id = output_reader["bvd_id"]
-                if not self.cleaned_data.get("bvd_id") in bvd_id:
-                    self.writer.writerow(self.cleaned_data)
-            except pd.errors.EmptyDataError:
-                    self.writer.writerow(self.cleaned_data)
+        self.writer.writerow(self.cleaned_data)
 
 
 class dataimport:

display_script.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+from pandas import read_csv
+import matplotlib.pyplot as plt
+import matplotlib.ticker as mtick
+import matplotlib as mpl
+mpl.rcParams['figure.dpi'] = 1200
+import numpy as np
+import pathlib
+
+class display:
+    def __init__(self, filename) -> None:
+        """Start the actual import process. Seperates process and setup."""
+        with open(filename, mode='r', encoding='utf-8-sig', newline='') as csv_file:
+            reader = read_csv(csv_file)
+            plt.style.use('_mpl-gallery')
+            for style in ["nom", "real", "realeff"]:
+                fig, ax = plt.subplots(figsize=(12, 6))
+                ob1 = np.asarray(reader[f"{style}tax2014"].dropna())
+                ob2 = np.asarray(reader[f"{style}tax2015"].dropna())
+                ob3 = np.asarray(reader[f"{style}tax2016"].dropna())
+                ob4 = np.asarray(reader[f"{style}tax2017"].dropna())
+                ob5 = np.asarray(reader[f"{style}tax2018"].dropna())
+                ob6 = np.asarray(reader[f"{style}tax2019"].dropna())
+                ob7 = np.asarray(reader[f"{style}tax2020"].dropna())
+                ob8 = np.asarray(reader[f"{style}tax2021"].dropna())
+                ob9 = np.asarray(reader[f"{style}tax2022"].dropna())
+                ob10 = np.asarray(reader[f"{style}tax2023"].dropna())
+                ob11 = np.asarray(reader[f"{style}tax2024"].dropna())
+                x = [ob1, ob2, ob3, ob4, ob5, ob6, ob7, ob8, ob9, ob10, ob11]
+                ax.boxplot(x, positions=[2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024], patch_artist=True,
+                           showmeans=False, showfliers=False,
+                    medianprops={"color": "white", "linewidth": 0.5},
+                    boxprops={"facecolor": "C0", "edgecolor": "white",
+                              "linewidth": 0.5},
+                    whiskerprops={"color": "C0", "linewidth": 1.5},
+                    capprops={"color": "C0", "linewidth": 1.5})
+                ax.yaxis.set_major_formatter(mtick.PercentFormatter(1,0))
+                plt.show()
+
+
+display(pathlib.Path('/home/user/bachelorarbeit_importer/data/', 'cleaned_st2.csv'))

export_cleaned.csv

@@ -0,0 +1 @@
+bvd_id,name,gv2014,gn2014,st2014,ek2014,nomtax2014,realtax2014,realefftax2014,gv2015,gn2015,st2015,ek2015,nomtax2015,realtax2015,realefftax2015,gv2016,gn2016,st2016,ek2016,nomtax2016,realtax2016,realefftax2016,gv2017,gn2017,st2017,ek2017,nomtax2017,realtax2017,realefftax2017,gv2018,gn2018,st2018,ek2018,nomtax2018,realtax2018,realefftax2018,gv2019,gn2019,st2019,ek2019,nomtax2019,realtax2019,realefftax2019,gv2020,gn2020,st2020,ek2020,nomtax2020,realtax2020,realefftax2020,gv2021,gn2021,st2021,ek2021,nomtax2021,realtax2021,realefftax2021,gv2022,gn2022,st2022,ek2022,nomtax2022,realtax2022,realefftax2022,gv2023,gn2023,st2023,ek2023,nomtax2023,realtax2023,realefftax2023,gv2024,gn2024,st2024,ek2024,nomtax2024,realtax2024,realefftax2024

pgpass

@@ -1 +0,0 @@
-denkena-consulting.com:5432:bachelorarbeit:bachelorarbeit_w:TWVn2kDqhtGOXN+1qb0Nfb/PLjQI4a22/xtIGv/T2kpf

requirements.txt

@@ -3,19 +3,27 @@ binapy==0.8.0
 certifi==2025.1.31
 cffi==1.17.1
 charset-normalizer==3.4.1
+contourpy==1.3.2
 cryptography==44.0.1
+cycler==0.12.1
+fonttools==4.58.2
 furl==2.1.3
 idna==3.10
 jwskate==0.11.1
+kiwisolver==1.4.8
 markdown-it-py==3.0.0
+matplotlib==3.10.3
 mdurl==0.1.2
 numpy==2.3.0
 orderedmultidict==1.0.1
+packaging==25.0
 pandas==2.3.0
+pillow==11.2.1
 psycopg==3.2.9
 psycopg-pool==3.2.6
 pycparser==2.22
 Pygments==2.19.1
+pyparsing==3.2.3
 python-dateutil==2.9.0.post0
 pytz==2025.2
 requests==2.32.3