Compare commits
No commits in common. "c745d23ab87fc53b6e3a94041ad23a68dd62225b" and "1dab0d748f7b43f43b3fe1679ad9f6c3fcdce855" have entirely different histories.
c745d23ab8
...
1dab0d748f
@ -1,9 +1,34 @@
|
||||
import pandas as pd
|
||||
from banking_breakdown import document_builder
|
||||
from banking_breakdown import statement_parser
|
||||
import subprocess
|
||||
import os
|
||||
import shutil
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from banking_breakdown import types
|
||||
import numpy as np
|
||||
|
||||
|
||||
def main():
|
||||
report_data = statement_parser.parse_statement("res/banking_statement_2023.csv")
|
||||
categories = ["A", "B", "C", "D", "E", "F", "G"]
|
||||
values = np.array([10, 12, 53, 12, 90, 23, 32])
|
||||
values = values / values.sum() * 100
|
||||
|
||||
total_value = np.random.normal(size=10) + 4
|
||||
net_income = np.diff(total_value)
|
||||
|
||||
category_overview_df = pd.DataFrame(
|
||||
{"category": categories, "value": values.astype('int32')})
|
||||
t = np.linspace(0, total_value.size, total_value.size)
|
||||
total_value_df = pd.DataFrame({"t": t, "value": total_value})
|
||||
t = np.linspace(0, net_income.size, net_income.size)
|
||||
net_income_df = pd.DataFrame({"t": t, "value": net_income})
|
||||
|
||||
report_data = types.ReportData(category_overview=category_overview_df,
|
||||
net_income=net_income_df,
|
||||
total_value=total_value_df)
|
||||
|
||||
document_builder.build_document(report_data)
|
||||
|
||||
|
||||
|
||||
@ -15,8 +15,6 @@ def _serialize_report_data(report_data: types.ReportData):
|
||||
report_data.category_overview.to_csv('build/category_overview.csv',
|
||||
index=False)
|
||||
report_data.total_value.to_csv('build/total_value.csv', index=False)
|
||||
report_data.detailed_balance.to_csv('build/detailed_balance.csv',
|
||||
index=False)
|
||||
|
||||
|
||||
def _compile_document():
|
||||
|
||||
@ -1,80 +0,0 @@
|
||||
import typing
|
||||
import pandas as pd
|
||||
from banking_breakdown import types
|
||||
import json
|
||||
import re
|
||||
import numpy as np
|
||||
|
||||
|
||||
def _read_regex_dict(regex_file: str = "res/category_regexes.json"):
|
||||
with open(regex_file, 'r') as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def _tag_with_category(df: pd.DataFrame) -> pd.DataFrame:
|
||||
regex_dict = _read_regex_dict()
|
||||
|
||||
return df
|
||||
|
||||
|
||||
def _compute_total_balance(df: pd.DataFrame) -> pd.DataFrame:
|
||||
stripped_df = pd.DataFrame(
|
||||
{'t': df["Buchungstag"], 'value': df["Saldo nach Buchung"]})
|
||||
|
||||
stripped_df.index = stripped_df['t']
|
||||
gb = stripped_df.groupby(pd.Grouper(freq='M'))
|
||||
|
||||
result = gb.tail(1)['value'].reset_index()
|
||||
#result['t'] = result['t'].apply(lambda dt: dt.replace(day=1))
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def _compute_net_income(df: pd.DataFrame) -> pd.DataFrame:
|
||||
stripped_df = pd.DataFrame({'t': df["Buchungstag"], 'value': df["Betrag"]})
|
||||
|
||||
result = stripped_df.resample(rule='M', on="t").sum().reset_index()
|
||||
#result['t'] = result['t'].apply(lambda dt: dt.replace(day=1))
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def _compute_category_overview(df: pd.DataFrame) -> pd.DataFrame:
|
||||
categories = ["A", "B", "C", "D", "E", "F", "G"]
|
||||
values = np.array([10, 12, 53, 12, 90, 23, 32])
|
||||
values = values / values.sum() * 100
|
||||
values = np.round(values, decimals=1)
|
||||
values[-1] += 100 - np.sum(values)
|
||||
|
||||
category_overview_df = pd.DataFrame(
|
||||
{"category": categories, "value": values})
|
||||
|
||||
return category_overview_df
|
||||
|
||||
|
||||
def _compute_detailed_balance(df: pd.DataFrame) -> pd.DataFrame:
|
||||
return pd.DataFrame({'t': df["Buchungstag"],
|
||||
'value': df["Saldo nach Buchung"]})
|
||||
|
||||
|
||||
def parse_statement(filename: str) -> types.ReportData:
|
||||
df = pd.read_csv(filename, delimiter=';', decimal=",")
|
||||
df["Buchungstag"] = pd.to_datetime(df["Buchungstag"], format='%d.%m.%Y')
|
||||
|
||||
category_overview_df = _compute_category_overview(df)
|
||||
total_balance_df = _compute_total_balance(df)
|
||||
net_income_df = _compute_net_income(df)
|
||||
detailed_balance_df = _compute_detailed_balance(df)
|
||||
|
||||
return types.ReportData(category_overview_df,
|
||||
net_income_df,
|
||||
total_balance_df,
|
||||
detailed_balance_df)
|
||||
|
||||
|
||||
def main():
|
||||
report_data = parse_statement("../res/banking_statement_2023.csv")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@ -7,4 +7,3 @@ class ReportData:
|
||||
category_overview: pd.DataFrame
|
||||
net_income: pd.DataFrame
|
||||
total_value: pd.DataFrame
|
||||
detailed_balance: pd.DataFrame
|
||||
|
||||
@ -4,7 +4,6 @@
|
||||
\usepackage{amsmath}
|
||||
\usepackage{pgfplots}
|
||||
\pgfplotsset{compat=newest}
|
||||
\usetikzlibrary{pgfplots.dateplot}
|
||||
|
||||
% Other packages
|
||||
\usepackage[a4paper, total={12cm, 25cm}]{geometry}
|
||||
@ -31,10 +30,6 @@
|
||||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||
|
||||
|
||||
\makeatletter
|
||||
\newcommand*\shortyear[1]{\expandafter\@gobbletwo\number\numexpr#1\relax}
|
||||
\makeatother
|
||||
|
||||
\newcommand{\slice}[6]{
|
||||
\pgfmathparse{0.5*#1+0.5*#2}
|
||||
\let\midangle\pgfmathresult
|
||||
@ -141,34 +136,15 @@
|
||||
|
||||
\begin{tikzpicture}
|
||||
\begin{axis}[
|
||||
date coordinates in=x,
|
||||
width=\textwidth,
|
||||
height=0.375\textwidth,
|
||||
ylabel={Net income in €},
|
||||
y label style={at={(-0.1,0.5)},anchor=south},
|
||||
xticklabel=\month.\shortyear{\year},
|
||||
xtick=data,
|
||||
xticklabel style={
|
||||
rotate=60,
|
||||
anchor=near xticklabel,
|
||||
},
|
||||
grid,
|
||||
enlarge x limits=0.03,
|
||||
]
|
||||
% Dummy plot to set x axis ticks
|
||||
\addplot[draw=none]
|
||||
table[col sep=comma, x=t, y=value]
|
||||
{net_income.csv};
|
||||
|
||||
% Dummy plot to set x axis scale
|
||||
\addplot[draw=none]
|
||||
table[col sep=comma, x=t, y=value]
|
||||
{detailed_balance.csv};
|
||||
|
||||
\addplot[ybar, color=scol2, fill=scol2, line width=1pt]
|
||||
\addplot+[ybar, color=scol2, fill=scol2, line width=1pt]
|
||||
table[col sep=comma, x=t, y=value, discard if lt={value}{0}]
|
||||
{net_income.csv};
|
||||
\addplot[ybar, color=scol0, fill=scol0, line width=1pt]
|
||||
\addplot+[ybar, color=scol0, fill=scol0, line width=1pt]
|
||||
table[col sep=comma, x=t, y=value, discard if gt={value}{0}]
|
||||
{net_income.csv};
|
||||
\end{axis}
|
||||
@ -179,31 +155,15 @@
|
||||
|
||||
\begin{tikzpicture}
|
||||
\begin{axis}[
|
||||
date coordinates in=x,
|
||||
width=\textwidth,
|
||||
height=0.375\textwidth,
|
||||
area style,
|
||||
ylabel={Total balance in €},
|
||||
y label style={at={(-0.1,0.5)},anchor=south},
|
||||
xticklabel=\month.\shortyear{\year},
|
||||
xtick=data,
|
||||
enlarge x limits=0.03,
|
||||
xticklabel style={
|
||||
rotate=60,
|
||||
anchor=near xticklabel,
|
||||
},
|
||||
grid,
|
||||
]
|
||||
% Dummy plot to set x axis ticks
|
||||
\addplot[draw=none]
|
||||
\addplot+[mark=none, color=scol1, line width=1pt]
|
||||
table[col sep=comma, x=t, y=value]
|
||||
{total_value.csv};
|
||||
|
||||
\addplot[scol3, mark=none, line width=1pt]
|
||||
table[col sep=comma, x=t, y=value]
|
||||
{detailed_balance.csv};
|
||||
\addplot[scol1, mark=none, line width=1pt]
|
||||
table[col sep=comma, x=t, y=value]
|
||||
{total_value.csv};
|
||||
{total_value.csv} \closedcycle;
|
||||
\end{axis}
|
||||
\end{tikzpicture}
|
||||
\end{subfigure}
|
||||
@ -211,6 +171,5 @@
|
||||
\caption{Development of account balance over time}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\end{document}
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user