Implement category renaming

.gitignore

@@ -1,4 +1,5 @@
 .idea/
 __pycache__/
 venv/
-build/
+build/
+banking_breakdown.egg-info

MANIFEST.in

@@ -0,0 +1,6 @@
+include banking_breakdown/ui/main_window.ui
+include banking_breakdown/ui/warning.png
+include banking_breakdown/document_builder/.latexmkrc
+include banking_breakdown/document_builder/Dockerfile.alpine
+include banking_breakdown/document_builder/report.tex
+include banking_breakdown/document_builder/common.tex

banking_breakdown/__main__.py

@@ -1,6 +1,5 @@
-from banking_breakdown import document_builder
-from banking_breakdown import statement_parser
-from banking_breakdown import ui
+from banking_breakdown import ui, regex_categorizer, statement_parser, \
+    document_builder
 
 import argparse
 
@@ -10,6 +9,9 @@ def categorize_func(args):
 
     df = pd.read_csv(args.i, delimiter=args.d)
 
+    if args.f is not None:
+        df = regex_categorizer.assign_categories(df, args.f)
+
     import signal
     signal.signal(signal.SIGINT, signal.SIG_DFL)
 
@@ -17,7 +19,8 @@ def categorize_func(args):
 
 
 def report_func(args):
-    print("Report")
+    report_data = statement_parser.parse_statement(args.i)
+    document_builder.build_document(args.o, report_data)
 
 
 #
@@ -45,7 +48,10 @@ def main():
     report_parser = subparsers.add_parser("report")
     report_parser.set_defaults(func=report_func)
     report_parser.add_argument('-i', required=True,
-                               help="CSV output file from categorization step")
+                               help="CSV file containing bank statement data (output file of categorization step)")
+    report_parser.add_argument('-o', required=False,
+                               help="Output directory ('build' by default)",
+                               default='build')
 
     args = parser.parse_args()
 

banking_breakdown/document_builder.py

@@ -1,36 +0,0 @@
-import subprocess
-import os
-import shutil
-from banking_breakdown import types
-
-
-def _copy_resources():
-    os.makedirs(os.path.dirname("build/report.tex"), exist_ok=True)
-    shutil.copyfile("res/report.tex", "build/report.tex")
-    shutil.copyfile("res/.latexmkrc", "build/.latexmkrc")
-
-
-def _serialize_report_data(report_data: types.ReportData):
-    report_data.net_income.to_csv('build/net_income.csv', index=False)
-    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():
-    subprocess.call("docker build . -f res/Dockerfile.alpine"
-                    " -t banking-breakdown",
-                    shell=True)
-    subprocess.call("docker run --rm -u `id -u`:`id -g`"
-                    " -v $(realpath .):/project"
-                    " -w /project/build banking-breakdown"
-                    " latexmk -pdf report.tex",
-                    shell=True)
-
-
-def build_document(report_data: types.ReportData):
-    _copy_resources()
-    _serialize_report_data(report_data)
-    _compile_document()

banking_breakdown/document_builder/__init__.py

@@ -0,0 +1,48 @@
+import subprocess
+import os
+import shutil
+from banking_breakdown import types
+
+import banking_breakdown.document_builder
+
+from importlib import resources
+
+
+def _copy_resources(build_dir: str):
+    res_prefix = resources.files(banking_breakdown.document_builder)
+
+    os.makedirs(os.path.dirname(f"{build_dir}/report.tex"), exist_ok=True)
+
+    shutil.copyfile(f"{res_prefix}/report.tex", f"{build_dir}/report.tex")
+    shutil.copyfile(f"{res_prefix}/common.tex", f"{build_dir}/common.tex")
+    shutil.copyfile(f"{res_prefix}/.latexmkrc", f"{build_dir}/.latexmkrc")
+
+
+def _serialize_report_data(build_dir: str, report_data: types.ReportData):
+    report_data.net_income.to_csv(f'{build_dir}/net_income.csv', index=False)
+    report_data.category_overview.to_csv(f'{build_dir}/category_overview.csv',
+                                         index=False)
+    report_data.expenses_by_category.to_csv(f'{build_dir}/expenses_by_category.csv',
+                                            index=False)
+    report_data.total_value.to_csv(f'{build_dir}/total_value.csv', index=False)
+    report_data.detailed_balance.to_csv(f'{build_dir}/detailed_balance.csv',
+                                        index=False)
+
+
+def _compile_document(build_dir):
+    res_prefix = resources.files(banking_breakdown.document_builder)
+
+    subprocess.call(f"docker build . -f {res_prefix}/Dockerfile.alpine"
+                    " -t banking-breakdown",
+                    shell=True)
+    subprocess.call("docker run --rm -u `id -u`:`id -g`"
+                    " -v $(realpath .):/project"
+                    f" -w /project/{build_dir} banking-breakdown"
+                    " latexmk -pdf report.tex",
+                    shell=True)
+
+
+def build_document(build_dir: str, report_data: types.ReportData):
+    _copy_resources(build_dir)
+    _serialize_report_data(build_dir, report_data)
+    _compile_document(build_dir)

banking_breakdown/document_builder/common.tex

@@ -0,0 +1,317 @@
+% Author: Andreas Tsouchlos
+%
+% Collection of useful commands and definitions
+%
+% ||====================================================================||
+% ||                               WARNING                              ||
+% ||====================================================================||
+% || The following packages have to be included before using this file: ||
+% ||      amsmath                                                       ||
+% ||      pgfplots                                                      ||
+% ||====================================================================||
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% Math Symbols %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+\DeclareMathOperator*{\argmin}{\arg\!\min}
+\DeclareMathOperator*{\argmax}{\arg\!\max}
+\DeclareMathOperator\sign{sign}
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% Data Manipulation %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%
+% Filters for Pgfplots
+% Source: https://tex.stackexchange.com/a/58563 (modified)
+%
+
+\pgfplotsset{
+    discard if/.style 2 args={
+        x filter/.append code={
+            \edef\tempa{\thisrow{#1}}
+            \edef\tempb{#2}
+            \ifx\tempa\tempb
+                \def\pgfmathresult{inf}
+            \fi
+        }
+    },
+    discard if not/.style 2 args={
+        x filter/.append code={
+            \edef\tempa{\thisrow{#1}}
+            \edef\tempb{#2}
+            \ifx\tempa\tempb
+            \else
+                \def\pgfmathresult{inf}
+            \fi
+        }
+    },
+    discard if gt/.style 2 args={
+        x filter/.append code={
+            \edef\tempa{\thisrow{#1}}
+            \edef\tempb{#2}
+            \ifdim\tempa pt > \tempb pt
+                \def\pgfmathresult{inf}
+            \fi
+        }
+    },
+    discard if lt/.style 2 args={
+        x filter/.append code={
+            \edef\tempa{\thisrow{#1}}
+            \edef\tempb{#2}
+            \ifdim\tempa pt < \tempb pt
+                \def\pgfmathresult{inf}
+            \fi
+        }
+    }
+}
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% Graphics & Plotting %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%
+% Colors
+%
+
+% KIT Colors
+
+\definecolor{kit-green100}{rgb}{0,.59,.51}
+\definecolor{kit-green70}{rgb}{.3,.71,.65}
+\definecolor{kit-green50}{rgb}{.50,.79,.75}
+\definecolor{kit-green30}{rgb}{.69,.87,.85}
+\definecolor{kit-green15}{rgb}{.85,.93,.93}
+\definecolor{KITgreen}{rgb}{0,.59,.51}
+
+\definecolor{KITpalegreen}{RGB}{130,190,60}
+\colorlet{kit-maigreen100}{KITpalegreen}
+\colorlet{kit-maigreen70}{KITpalegreen!70}
+\colorlet{kit-maigreen50}{KITpalegreen!50}
+\colorlet{kit-maigreen30}{KITpalegreen!30}
+\colorlet{kit-maigreen15}{KITpalegreen!15}
+
+\definecolor{KITblue}{rgb}{.27,.39,.66}
+\definecolor{kit-blue100}{rgb}{.27,.39,.67}
+\definecolor{kit-blue70}{rgb}{.49,.57,.76}
+\definecolor{kit-blue50}{rgb}{.64,.69,.83}
+\definecolor{kit-blue30}{rgb}{.78,.82,.9}
+\definecolor{kit-blue15}{rgb}{.89,.91,.95}
+
+\definecolor{KITyellow}{rgb}{.98,.89,0}
+\definecolor{kit-yellow100}{cmyk}{0,.05,1,0}
+\definecolor{kit-yellow70}{cmyk}{0,.035,.7,0}
+\definecolor{kit-yellow50}{cmyk}{0,.025,.5,0}
+\definecolor{kit-yellow30}{cmyk}{0,.015,.3,0}
+\definecolor{kit-yellow15}{cmyk}{0,.0075,.15,0}
+
+\definecolor{KITorange}{rgb}{.87,.60,.10}
+\definecolor{kit-orange100}{cmyk}{0,.45,1,0}
+\definecolor{kit-orange70}{cmyk}{0,.315,.7,0}
+\definecolor{kit-orange50}{cmyk}{0,.225,.5,0}
+\definecolor{kit-orange30}{cmyk}{0,.135,.3,0}
+\definecolor{kit-orange15}{cmyk}{0,.0675,.15,0}
+
+\definecolor{KITred}{rgb}{.63,.13,.13}
+\definecolor{kit-red100}{cmyk}{.25,1,1,0}
+\definecolor{kit-red70}{cmyk}{.175,.7,.7,0}
+\definecolor{kit-red50}{cmyk}{.125,.5,.5,0}
+\definecolor{kit-red30}{cmyk}{.075,.3,.3,0}
+\definecolor{kit-red15}{cmyk}{.0375,.15,.15,0}
+
+\definecolor{KITpurple}{RGB}{160,0,120}
+\colorlet{kit-purple100}{KITpurple}
+\colorlet{kit-purple70}{KITpurple!70}
+\colorlet{kit-purple50}{KITpurple!50}
+\colorlet{kit-purple30}{KITpurple!30}
+\colorlet{kit-purple15}{KITpurple!15}
+
+\definecolor{KITcyanblue}{RGB}{80,170,230}
+\colorlet{kit-cyanblue100}{KITcyanblue}
+\colorlet{kit-cyanblue70}{KITcyanblue!70}
+\colorlet{kit-cyanblue50}{KITcyanblue!50}
+\colorlet{kit-cyanblue30}{KITcyanblue!30}
+\colorlet{kit-cyanblue15}{KITcyanblue!15}
+
+% Matplotlib Colors
+
+\definecolor{Mpl1}{HTML}{1f77b4}
+\definecolor{Mpl2}{HTML}{ff7f0e}
+\definecolor{Mpl3}{HTML}{2ca02c}
+\definecolor{Mpl4}{HTML}{d62728}
+\definecolor{Mpl5}{HTML}{9467bd}
+\definecolor{Mpl6}{HTML}{8c564b}
+\definecolor{Mpl7}{HTML}{e377c2}
+\definecolor{Mpl8}{HTML}{7f7f7f}
+\definecolor{Mpl9}{HTML}{bcbd22}
+\definecolor{Mpl10}{HTML}{17becf}
+
+%
+% Color Schemes
+%
+
+% Define colormaps
+
+\pgfplotsset{
+	colormap={mako}{
+		rgb=(0.18195582, 0.11955283, 0.23136943)
+		rgb=(0.25307401, 0.23772973, 0.48316271)
+		rgb=(0.21607792, 0.39736958, 0.61948028)
+		rgb=(0.20344718, 0.56074869, 0.65649508)
+		rgb=(0.25187832, 0.71827158, 0.67872193)
+		rgb=(0.54578602, 0.8544913, 0.69848331)
+	},
+	colormap={rocket}{
+		rgb=(0.20973515, 0.09747934, 0.24238489)
+		rgb=(0.43860848, 0.12177004, 0.34119475)
+		rgb=(0.67824099, 0.09192342, 0.3504148)
+		rgb=(0.8833417, 0.19830556, 0.26014181)
+		rgb=(0.95381595, 0.46373781, 0.31769923)
+		rgb=(0.96516917, 0.70776351, 0.5606593)
+	},
+	colormap={cividis}{
+		rgb=(0.130669, 0.231458, 0.43284)
+		rgb=(0.298421, 0.332247, 0.423973)
+		rgb=(0.42512, 0.431334, 0.447692)
+		rgb=(0.555393, 0.537807, 0.471147)
+		rgb=(0.695985, 0.648334, 0.440072)
+		rgb=(0.849223, 0.771947, 0.359729)
+	},
+	colormap={cel}{
+		color=(KITred!90!black);
+		color=(kit-blue100);
+ 		color=(kit-green70);
+		color=(kit-yellow70!80!kit-orange70);
+	},
+	colormap={matplotlib}{
+		% Source: https://github.com/matplotlib/matplotlib/blob/e5a85f960b2d47eac371cff709b830d52c36d267/lib/matplotlib/_cm.py#L1114
+        rgb=(0.2298057,   0.298717966, 0.753683153)
+        rgb=(0.26623388,  0.353094838, 0.801466763)
+        rgb=(0.30386891,  0.406535296, 0.84495867 )
+        rgb=(0.342804478, 0.458757618, 0.883725899)
+        rgb=(0.38301334,  0.50941904,  0.917387822)
+        rgb=(0.424369608, 0.558148092, 0.945619588)
+        rgb=(0.46666708,  0.604562568, 0.968154911)
+        rgb=(0.509635204, 0.648280772, 0.98478814 )
+        rgb=(0.552953156, 0.688929332, 0.995375608)
+        rgb=(0.596262162, 0.726149107, 0.999836203)
+        rgb=(0.639176211, 0.759599947, 0.998151185)
+        rgb=(0.681291281, 0.788964712, 0.990363227)
+        rgb=(0.722193294, 0.813952739, 0.976574709)
+        rgb=(0.761464949, 0.834302879, 0.956945269)
+        rgb=(0.798691636, 0.849786142, 0.931688648)
+        rgb=(0.833466556, 0.860207984, 0.901068838)
+        rgb=(0.865395197, 0.86541021,  0.865395561)
+        rgb=(0.897787179, 0.848937047, 0.820880546)
+        rgb=(0.924127593, 0.827384882, 0.774508472)
+        rgb=(0.944468518, 0.800927443, 0.726736146)
+        rgb=(0.958852946, 0.769767752, 0.678007945)
+        rgb=(0.96732803,  0.734132809, 0.628751763)
+        rgb=(0.969954137, 0.694266682, 0.579375448)
+        rgb=(0.966811177, 0.650421156, 0.530263762)
+        rgb=(0.958003065, 0.602842431, 0.481775914)
+        rgb=(0.943660866, 0.551750968, 0.434243684)
+        rgb=(0.923944917, 0.49730856,  0.387970225)
+        rgb=(0.89904617,  0.439559467, 0.343229596)
+        rgb=(0.869186849, 0.378313092, 0.300267182)
+        rgb=(0.834620542, 0.312874446, 0.259301199)
+        rgb=(0.795631745, 0.24128379,  0.220525627)
+        rgb=(0.752534934, 0.157246067, 0.184115123)
+        rgb=(0.705673158, 0.01555616,  0.150232812)
+	}
+}
+
+% Define cycle lists
+
+\pgfplotscreateplotcyclelist{mako}{%
+	[samples of colormap={4} of mako]%
+}
+\pgfplotscreateplotcyclelist{rocket}{%
+	[samples of colormap={4} of rocket]%
+}
+\pgfplotscreateplotcyclelist{cividis}{%
+	[samples of colormap={4} of cividis]%
+}
+\pgfplotscreateplotcyclelist{viridis}{%
+	[samples of colormap={4} of viridis]%
+}
+\pgfplotscreateplotcyclelist{cel}{%
+	[samples of colormap={4} of cel]%
+}
+\pgfplotscreateplotcyclelist{matplotlib}{%
+	{Mpl1},{Mpl2},{Mpl3},{Mpl4}
+}
+
+% Define 'scolX' colors
+
+\makeatletter
+
+\def\extractcolormapcolor#1#2{%
+	\expandafter\pgfplotscolormapaccess\expandafter[\pgfplotspointmetatransformedrange]%
+		[1.0]%
+		{#2}%
+		{\pgfkeysvalueof{/pgfplots/colormap name}}%
+	\def\pgfplots@loc@TMPb{\pgfutil@definecolor{#1}{\csname pgfpl@cm@\pgfkeysvalueof{/pgfplots/colormap name}@colspace\endcsname}}%
+	\expandafter\pgfplots@loc@TMPb\expandafter{\pgfmathresult}%
+}%
+
+\def\getcolorbyvalue#1{
+	\csname pgfpl@cm@\pgfkeysvalueof{/pgfplots/colormap name}@colspace\endcsname
+}
+
+\makeatother
+
+\def\setschemecolorsfrommap{
+	\extractcolormapcolor{scol0}{0}
+	\extractcolormapcolor{scol1}{333}
+	\extractcolormapcolor{scol2}{666}
+	\extractcolormapcolor{scol3}{1000}
+}
+
+\newcommand{\setschemecolorsmanually}[4]{
+	\colorlet{scol0}{#1}
+	\colorlet{scol1}{#2}
+	\colorlet{scol2}{#3}
+	\colorlet{scol3}{#4}
+}
+
+% Define color schemes
+
+\pgfplotsset{
+	/pgfplots/colorscheme/cel/.style={
+		colormap name={cel},
+		cycle list name={cel},
+		/utils/exec={\setschemecolorsfrommap},
+	},
+	/pgfplots/colorscheme/rocket/.style={
+		colormap name={rocket},
+		cycle list name={rocket},
+		/utils/exec={\setschemecolorsfrommap},
+	},
+	/pgfplots/colorscheme/viridis/.style={
+		colormap name={viridis},
+		cycle list name={viridis},
+		/utils/exec={\setschemecolorsfrommap},
+	},
+	/pgfplots/colorscheme/mako/.style={
+		colormap name={mako},
+		cycle list name={mako},
+		/utils/exec={\setschemecolorsfrommap},
+	},
+	/pgfplots/colorscheme/cividis/.style={
+		colormap name={cividis},
+		cycle list name={cividis},
+		/utils/exec={\setschemecolorsfrommap},
+	},
+	/pgfplots/colorscheme/matplotlib/.style={
+		colormap name={matplotlib},
+		cycle list name={matplotlib},
+		/utils/exec={\setschemecolorsmanually{Mpl1}{Mpl2}{Mpl3}{Mpl4}},
+	},
+}
+

banking_breakdown/document_builder/report.tex

@@ -22,7 +22,7 @@
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
 
-\input{../lib/latex-common/common.tex}
+\input{common.tex}
 \pgfplotsset{colorscheme/rocket}
 
 
@@ -38,13 +38,13 @@
 \newcommand{\slice}[6]{
 	\pgfmathparse{0.5*#1+0.5*#2}
 	\let\midangle\pgfmathresult
-	
+
 	% slice
 	\fill[thick,color=#5] (0,0) -- (#1:1) arc (#1:#2+1:1) -- (0,0);
-	
+
 	% outer label
 	\node[label=\midangle:#4] at (\midangle:1) {};
-	
+
 	% inner label
 	\pgfmathparse{min((#2-#1-10)/110*(-0.3),0)}
 	\let\temp\pgfmathresult
@@ -58,13 +58,13 @@
 \newcounter{pieSliceB}
 \newcommand{\pie}[1]{
 	% Count elements
-	\setcounter{pieElem}{0}% 
+	\setcounter{pieElem}{0}%
 	\foreach\pieElem in {#1}{\stepcounter{pieElem}}%
 	\edef\numElements{\arabic{pieElem}}
 
 	% Draw pie chart
-	\setcounter{pieSliceA}{0}% 
-	\setcounter{pieSliceB}{0}% 
+	\setcounter{pieSliceA}{0}%
+	\setcounter{pieSliceB}{0}%
 	\foreach \xi/\t [count=\xk from 0] in {#1} {
 		% Get colors
 		\pgfmathparse{1000 / (\numElements - 1) * \xk}
@@ -81,16 +81,16 @@
 
 \newcommand{\csvPie}[1]{
 	% Count elements
-	\setcounter{pieElem}{0}% 
+	\setcounter{pieElem}{0}%
 	\csvreader[head to column names]{#1}{}{%
 		\stepcounter{pieElem}
 	}
 	\edef\numElements{\arabic{pieElem}}
 
 	% Draw pie chart
-	\setcounter{pieElem}{0}% 
-	\setcounter{pieSliceA}{0}% 
-	\setcounter{pieSliceB}{0}% 
+	\setcounter{pieElem}{0}%
+	\setcounter{pieSliceA}{0}%
+	\setcounter{pieSliceB}{0}%
 	\csvreader[head to column names]{#1}{}{%
 		% Get colors
 		\pgfmathparse{1000 / (\numElements - 1) * \thepieElem}
@@ -157,7 +157,7 @@
 			]
 				% Dummy plot to set x axis ticks
 				\addplot[draw=none]
-					table[col sep=comma, x=t, y=value]
+					table[col sep=comma, x=t, y=net]
 						{net_income.csv};
 
 				% Dummy plot to set x axis scale
@@ -165,11 +165,17 @@
 					table[col sep=comma, x=t, y expr=0]
 						{detailed_balance.csv};
 
-				\addplot[ybar, color=scol2, fill=scol2, line width=1pt]
-					table[col sep=comma, x=t, y=value, discard if lt={value}{0}]
+				\addplot[ybar, bar width=0.4cm, draw=none, fill=scol2!30, line width=1pt]
+					table[col sep=comma, x=t, y=income]
 						{net_income.csv};
-				\addplot[ybar, color=scol0, fill=scol0, line width=1pt]
-					table[col sep=comma, x=t, y=value, discard if gt={value}{0}]
+				\addplot[ybar, bar width=0.4cm, draw=none, fill=scol0!30, line width=1pt]
+					table[col sep=comma, x=t, y=expenses]
+						{net_income.csv};
+                \addplot[ybar, bar width=0.3cm, draw=none, fill=scol0, line width=1pt]
+					table[col sep=comma, x=t, y=net, discard if gt={net}{0}]
+						{net_income.csv};
+                \addplot[ybar, bar width=0.3cm, draw=none, fill=scol2, line width=1pt]
+					table[col sep=comma, x=t, y=net, discard if lt={net}{0}]
 						{net_income.csv};
 			\end{axis}
 		\end{tikzpicture}
@@ -211,6 +217,105 @@
 	\caption{Development of account balance over time}
 \end{figure}
 
+\begin{figure}
+	\centering
+
+	
+	\csvautotabular{net_income.csv}
+\end{figure}
+
+
+\begin{figure}[H]
+	\centering
+
+	% Read table
+	\pgfplotstableread[col sep=comma]{expenses_by_category.csv}\expbycattable
+	\pgfplotstablegetcolsof{\expbycattable}
+	\pgfmathtruncatemacro\NumCols{\pgfplotsretval-1}
+
+	\begin{subfigure}[c]{\textwidth}
+		\centering
+
+		\begin{tikzpicture}
+			\begin{axis}[
+				stack plots=y,
+				area style,
+				date coordinates in=x,
+				width=\textwidth,
+				height=0.375\textwidth,
+				xticklabel=\month.\shortyear{\year},
+				xtick=data,
+				enlargelimits=false,
+				xticklabel style={
+					rotate=60,
+					anchor=near xticklabel,
+				},
+				legend columns=5,
+				legend style={at={(0.5,-0.6)},anchor=south},
+				ylabel={Expenses in €},
+				ymin=0,
+			]
+				% For each
+				\pgfplotsinvokeforeach{0,...,\NumCols/2 -1}{
+					% Define color
+					\pgfmathparse{1000 / (\NumCols/2 -1) * #1}
+					\extractcolormapcolor{tempcol#1}{\pgfmathresult}
+
+					% Add plot
+					\addplot+[tempcol#1]
+						table[col sep=comma, x=t, y index=#1]
+							{\expbycattable} \closedcycle;
+
+					% Add legend entry (https://tex.stackexchange.com/a/405018)
+					\pgfplotstablegetcolumnnamebyindex{#1}\of{\expbycattable}\to\pgfplotsretval
+					\expandafter\addlegendentry\expandafter{\pgfplotsretval}
+				}
+			\end{axis}
+		\end{tikzpicture}
+	\end{subfigure}\\[1em]
+	\begin{subfigure}[c]{\textwidth}
+		\centering
+
+		\begin{tikzpicture}
+			\begin{axis}[
+				stack plots=y,
+				area style,
+				date coordinates in=x,
+				width=\textwidth,
+				height=0.375\textwidth,
+				xticklabel=\month.\shortyear{\year},
+				xtick=data,
+				enlargelimits=false,
+				xticklabel style={
+					rotate=60,
+					anchor=near xticklabel,
+				},
+				legend columns=5,
+				legend style={at={(0.5,-0.6)},anchor=south},
+				ylabel={Expenses in €},
+				ymin=0,
+			]
+				% For each
+				\pgfplotsinvokeforeach{\NumCols/2,...,\NumCols-1}{
+					% Define color
+					\pgfmathparse{1000 * (#1 - \NumCols/2) / (\NumCols-1 - \NumCols/2)}
+					\extractcolormapcolor{tempcol#1}{\pgfmathresult}
+
+					% Add plot
+					\addplot+[tempcol#1]
+						table[col sep=comma, x=t, y index=#1]
+							{\expbycattable} \closedcycle;
+
+					% Add legend entry (https://tex.stackexchange.com/a/405018)
+					\pgfplotstablegetcolumnnamebyindex{#1}\of{\expbycattable}\to\pgfplotsretval
+					\expandafter\addlegendentry\expandafter{\pgfplotsretval}
+				}
+			\end{axis}
+		\end{tikzpicture}
+	\end{subfigure}
+
+	\caption{Expenses by category}
+\end{figure}
 
 \end{document}
 

banking_breakdown/regex_categorizer.py

@@ -0,0 +1,54 @@
+import pandas as pd
+import json
+
+
+def _is_str_column(s: pd.Series):
+    """Check if the type of a pandas DataFrame column is str.
+
+    Taken from https://stackoverflow.com/a/67001213/3433817.
+    """
+    if isinstance(s.dtype, pd.StringDtype):
+        # The series was explicitly created as a string series (Pandas>=1.0.0)
+        return True
+    elif s.dtype == 'object':
+        # Object series, check each value
+        return all((v is None) or isinstance(v, str) for v in s)
+    else:
+        return False
+
+
+def _read_regex_dict(regex_file: str):
+    with open(regex_file, 'r') as f:
+        return json.load(f)
+
+
+def assign_categories(df: pd.DataFrame, regex_file: str) -> pd.DataFrame:
+    if 'category' not in df.columns:
+        df['category'] = [' '] * len(df.index)
+
+    regex_dict = _read_regex_dict(regex_file)
+
+    df = df.fillna('')
+
+    for column in df.columns:
+        if not _is_str_column(df[column]):
+            continue
+
+        for category in regex_dict:
+            for regex in regex_dict[category]:
+                matched = df[column].str.contains(regex, regex=True)
+                df.loc[matched, 'category'] = category
+
+    return df
+
+
+def main():
+    df = pd.read_csv('../res/bank_statement_2023_categorized.csv')
+
+    df = assign_categories(df, regex_file='../res/regexes.json')
+
+    print(df['category'])
+
+
+if __name__ == "__main__":
+    main()

banking_breakdown/statement_parser.py

@@ -6,94 +6,117 @@ 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["Valutadatum"], '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()
-#
-#     return result
-#
-#
-# def _compute_net_income(df: pd.DataFrame) -> pd.DataFrame:
-#     stripped_df = pd.DataFrame({'t': df["Valutadatum"], 'value': df["Betrag"]})
-#
-#     stripped_df.index = stripped_df['t']
-#     gb = stripped_df.groupby(pd.Grouper(freq='M'))
-#
-#     result = gb["value"].sum().reset_index()
-#     return result
-#
-#
-# def _compute_category_overview(df: pd.DataFrame) -> pd.DataFrame:
-#     categories = ["Social life", "Other", "Food", "Hobbies",
-#                   "Rent \\& Utilities", "Education", "Transportation"]
-#     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["Valutadatum"],
-#                          'value': df["Saldo nach Buchung"]})
-#
-#
-# def parse_statement(filename: str) -> types.ReportData:
-#     df = pd.read_csv(filename, delimiter=';', decimal=",")
-#     df["Valutadatum"] = pd.to_datetime(df["Valutadatum"], 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/bank_statement_2023.csv")
-#
-#
-# if __name__ == "__main__":
-#     main()
+def _escape_string(to_escape: str):
+    return to_escape.translate(str.maketrans({"&": r"\&"}))
 
 
-def get_stripped_statement(filename: str) -> pd.DataFrame:
-    # df = pd.read_csv(filename, delimiter=';', decimal=",")
-    df = pd.read_csv(filename, delimiter=';')
-    df["Valutadatum"] = (pd.to_datetime(df["Valutadatum"], format='%d.%m.%Y')
-                         .dt.strftime('%Y-%m-%d'))
+def _compute_total_balance(df: pd.DataFrame) -> pd.DataFrame:
+    stripped_df = pd.DataFrame(
+        {'t': df["t"], 'value': df["balance"]})
 
-    result = pd.DataFrame({'t': df["Valutadatum"],
-                           'other party': df["Name Zahlungsbeteiligter"],
-                           'value': df["Betrag"],
-                           'balance': df["Saldo nach Buchung"],
-                           'category': [''] * len(df["Valutadatum"]),
-                           'description': df["Buchungstext"],
-                           'purpose': df["Verwendungszweck"]
-                           })
+    stripped_df.index = stripped_df['t']
+    gb = stripped_df.groupby(pd.Grouper(freq='M'))
+
+    result = gb.tail(1)['value'].reset_index()
 
     return result
+
+
+def _compute_net_income(df: pd.DataFrame) -> pd.DataFrame:
+    df.index = df['t']
+    income_df = df.loc[df['value'] > 0]
+    expenses_df = df.loc[df['value'] < 0]
+
+    income_df = income_df.groupby(pd.Grouper(freq='M'))[
+        'value'].sum().reset_index().round(decimals=2)
+    expenses_df = expenses_df.groupby(pd.Grouper(freq='M'))[
+        'value'].sum().reset_index().round(decimals=2)
+
+    t = income_df['t']
+    income = income_df['value'].round(decimals=2)
+    expenses = expenses_df['value'].round(decimals=2)
+    net = (income + expenses).round(decimals=2)
+
+    result_df = pd.DataFrame(
+        {'t': t, 'income': income, 'expenses': expenses, 'net': net})
+
+    return result_df
+
+
+def _compute_category_overview(df: pd.DataFrame) -> pd.DataFrame:
+    df = df.loc[df['value'] < 0]
+    df = df.drop('t', axis=1)
+    df = df.groupby(['category']).sum().reset_index()
+    values = (df['value'] / df['value'].sum() * 100).to_numpy()
+    values[-1] += 100 - np.sum(values)
+    values = np.round(values, decimals=1)
+    categories = [_escape_string(category) for category in df['category']]
+
+    category_overview_df = pd.DataFrame(
+        {"category": categories, "value": values})
+
+    category_overview_df = category_overview_df.sort_values('value',
+                                                            ascending=False)
+
+    return category_overview_df
+
+
+def _compute_expenses_by_category(complete_df: pd.DataFrame) -> pd.DataFrame:
+    complete_df = complete_df.loc[complete_df['value'] < 0].copy()
+    complete_df['value'] = -complete_df['value']
+    complete_df.index = complete_df['t']
+
+    complete_gb = complete_df.groupby(pd.Grouper(freq='M'))
+
+    categories = complete_df['category'].unique()
+    data_dict = {category: [] for category in categories}
+
+    for (month_date, month_df) in complete_gb:
+        month_df = month_df.drop('t', axis=1).reset_index().drop('t', axis=1)
+
+        category_df = month_df.groupby(['category']).sum().reset_index()
+
+        for _, row in category_df.iterrows():
+            data_dict[row['category']].append(row['value'])
+
+        non_listed = list(set(categories) - set(category_df['category']))
+        for category in non_listed:
+            data_dict[category].append(0)
+
+    result = pd.DataFrame(data_dict)
+    result = result.reindex(result.mean().sort_values(ascending=False).index,
+                            axis=1)
+    result = result.round(decimals=2)
+    result['t'] = complete_gb.tail(1).drop('t', axis=1).reset_index()['t']
+
+    return result
+
+
+def _compute_detailed_balance(df: pd.DataFrame) -> pd.DataFrame:
+    return pd.DataFrame({'t': df["t"],
+                         'value': df["balance"]})
+
+
+def parse_statement(filename: str) -> types.ReportData:
+    df = pd.read_csv(filename)
+    df["t"] = pd.to_datetime(df["t"], format='%Y-%m-%d')
+
+    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)
+    expenses_by_category_df = _compute_expenses_by_category(df)
+
+    return types.ReportData(category_overview_df,
+                            expenses_by_category_df,
+                            net_income_df,
+                            total_balance_df,
+                            detailed_balance_df, )
+
+
+def main():
+    report_data = parse_statement("../res/bank_statement_2023_categorized.csv")
+
+
+if __name__ == "__main__":
+    main()

banking_breakdown/types.py

@@ -5,6 +5,7 @@ import pandas as pd
 @dataclass
 class ReportData:
     category_overview: pd.DataFrame
+    expenses_by_category: pd.DataFrame
     net_income: pd.DataFrame
     total_value: pd.DataFrame
     detailed_balance: pd.DataFrame

banking_breakdown/ui/custom_ui_items.py

@@ -4,8 +4,11 @@ from PyQt6.QtGui import QPixmap, QAction
 from PyQt6.QtWidgets import QHBoxLayout, QLabel, QMenu, QInputDialog, \
     QMessageBox
 
+import banking_breakdown.ui
 from banking_breakdown.ui.pandas_model import PandasModel
 
+from importlib import resources
+
 
 class WarningItem(QHBoxLayout):
     """Item appearing at top of Window with warning icon."""
@@ -14,7 +17,8 @@ class WarningItem(QHBoxLayout):
         super(WarningItem, self).__init__()
 
         self._warningIcon = QLabel()
-        pixmap = QPixmap("res/warning.png")
+        pixmap_path = f"{resources.files(banking_breakdown.ui)}/warning.png"
+        pixmap = QPixmap(pixmap_path)
         self._warningIcon.setPixmap(pixmap)
 
         self._label = QLabel(text)
@@ -35,16 +39,16 @@ class HeaderContextMenu(QMenu):
     """Context menu appearing when right-clicking the header of the QTableView.
     """
 
-    def __init__(self, column, pandas_model: PandasModel, callback=None,
+    def __init__(self, column_index, pandas_model: PandasModel, callback=None,
                  parent=None):
         super(HeaderContextMenu, self).__init__()
 
-        self._column = column
         self._pandas_model = pandas_model
         self._callback = callback
 
+        self._column_index = column_index
         self._column_text \
-            = self._pandas_model.headerData(self._column,
+            = self._pandas_model.headerData(self._column_index,
                                             Qt.Orientation.Horizontal)
 
         # Define assign action
@@ -85,9 +89,11 @@ class HeaderContextMenu(QMenu):
             return
 
         if (new_name != self._column_text) and (new_name != ''):
-            df = self._pandas_model.get_dataframe()
-            df = df.rename(columns={self._column_text: new_name})
-            self._pandas_model.set_dataframe(df)
+            try:
+                self._pandas_model.rename_column(self._column_text, new_name)
+            except:
+                QMessageBox.warning(self, "No action performed",
+                                    "An error occurred.")
 
             if self._callback:
                 self._callback()
@@ -98,10 +104,7 @@ class HeaderContextMenu(QMenu):
                                       f" column '{self._column_text}'?")
 
         if button == QMessageBox.StandardButton.Yes:
-            df = self._pandas_model.get_dataframe()
-            df = df.iloc[:, [j for j, c
-                             in enumerate(df.columns) if j != self._column]]
-            self._pandas_model.set_dataframe(df)
+            self._pandas_model.delete_column_by_index(self._column_index)
 
             if self._callback:
                 self._callback()
@@ -112,21 +115,14 @@ class HeaderContextMenu(QMenu):
                    if column != self._column_text]
 
         other_name, flag = QInputDialog.getItem(self, "Switch column position",
-                                                f"Switch position of colum"
-                                                f" '{self._column_text}' with:",
+                                                f"Switch position of colum "
+                                                f"'{self._column_text}' with:",
                                                 columns, editable=False)
 
         if not flag:
             return
 
-        column_titles = list(df.columns)
-        index1, index2 = column_titles.index(
-            self._column_text), column_titles.index(other_name)
-        column_titles[index1], column_titles[index2] \
-            = column_titles[index2], column_titles[index1]
-
-        df = df.reindex(columns=column_titles)
-        self._pandas_model.set_dataframe(df)
+        self._pandas_model.switch_columns(self._column_text, other_name)
 
         if self._callback:
             self._callback()
@@ -139,14 +135,12 @@ class HeaderContextMenu(QMenu):
         if not flag:
             return
 
-        df = self._pandas_model.get_dataframe()
         try:
-            df[self._column_text] \
-                = pd.to_datetime(df[self._column_text], format=date_format)
+            self._pandas_model.assign_date_column(self._column_text,
+                                                  date_format)
         except:
             QMessageBox.warning(self, "No action performed",
                                 "An error occurred.")
-        self._pandas_model.set_dataframe(df)
 
         if self._callback:
             self._callback()
@@ -160,19 +154,12 @@ class HeaderContextMenu(QMenu):
         if not flag:
             return
 
-        df = self._pandas_model.get_dataframe()
-
         try:
-            if decimal_sep == ',':
-                df[self._column_text] \
-                    = df[self._column_text].str.replace(',', '.').astype(float)
-            else:
-                df[self._column_text] = df[self._column_text].astype(float)
+            self._pandas_model.assign_float_column(self._column_text,
+                                                   decimal_sep)
         except:
             QMessageBox.warning(self, "No action performed",
                                 "An error occurred.")
 
-        self._pandas_model.set_dataframe(df)
-
         if self._callback:
             self._callback()

banking_breakdown/ui/main_window.py

@@ -6,15 +6,19 @@ from PyQt6.QtGui import QAction
 from PyQt6.QtWidgets import QMainWindow, QPushButton, QVBoxLayout, \
     QTableView, QInputDialog, QMessageBox, QFileDialog, QListWidget
 
+import banking_breakdown.ui
 from banking_breakdown.ui.pandas_model import PandasModel
 from banking_breakdown.ui.custom_ui_items import WarningItem, HeaderContextMenu
 
 
+from importlib import resources
+
 class MainWindow(QMainWindow):
     def __init__(self):
         super(MainWindow, self).__init__()
 
-        uic.loadUi("res/main_window.ui", self)
+        ui_path = f"{resources.files(banking_breakdown.ui)}/main_window.ui"
+        uic.loadUi(ui_path, self)
         self.setContentsMargins(9, 9, 9, 9)
 
         self._warnings = []
@@ -25,6 +29,8 @@ class MainWindow(QMainWindow):
             = self.findChild(QVBoxLayout, "warningLayout")
         self._create_button \
             = self.findChild(QPushButton, "createCategoryButton")
+        self._rename_button \
+            = self.findChild(QPushButton, "renameCategoryButton")
         self._delete_button \
             = self.findChild(QPushButton, "deleteCategoryButton")
         self._apply_button \
@@ -38,18 +44,24 @@ class MainWindow(QMainWindow):
         self._action_save \
             = self.findChild(QAction, "actionSave")
 
+        # Set scrolling behavior
+
+        self._table_view.horizontalScrollBar().setSingleStep(10)
+        self._table_view.verticalScrollBar().setSingleStep(10)
+
         # Set up QTableView model
 
         self._pandas_model = PandasModel(self)
-        self._proxyModel = QSortFilterProxyModel(self)
-        self._proxyModel.setSourceModel(self._pandas_model)
-        self._table_view.setModel(self._proxyModel)
-        self._proxyModel.setDynamicSortFilter(True)
-        self._proxyModel.setSortRole(Qt.ItemDataRole.EditRole)
+        self._proxy_model = QSortFilterProxyModel(self)
+        self._proxy_model.setSourceModel(self._pandas_model)
+        self._table_view.setModel(self._proxy_model)
+        self._proxy_model.setSortRole(Qt.ItemDataRole.EditRole)
+        self._proxy_model.setDynamicSortFilter(False)
 
         # Set event handlers
 
         self._create_button.clicked.connect(self._handle_create_click)
+        self._rename_button.clicked.connect(self._handle_rename_click)
         self._delete_button.clicked.connect(self._handle_delete_click)
         self._clear_button.clicked.connect(self._handle_clear_click)
         self._apply_button.clicked.connect(self._handle_apply_click)
@@ -99,6 +111,13 @@ class MainWindow(QMainWindow):
                                len(col))
                 self._table_view.setColumnWidth(i, max_char * 10)
 
+    def _assign_category_to_selected_transactions(self, category: str):
+        indexes = self._table_view.selectionModel().selectedRows()
+        row_indices = [self._table_view.model().mapToSource(index).row()
+                       for index in indexes]
+
+        self._pandas_model.assign_category(category, row_indices)
+
     #
     # List data updates
     #
@@ -108,13 +127,11 @@ class MainWindow(QMainWindow):
             self._list_widget.addItem(category)
 
     def _update_categories_from_dataframe(self):
-        df = self._pandas_model.get_dataframe()
-
-        df_categories = df['category'].unique()
+        df_categories = self._pandas_model.get_categories()
         current_categories = [self._list_widget.item(x).text() for x
                               in range(self._list_widget.count())]
-
         missing = list(set(df_categories) - set(current_categories))
+
         self._add_categories([category for category
                               in missing if category != ' '])
 
@@ -133,19 +150,19 @@ class MainWindow(QMainWindow):
             warning_item.hide()
             self._warning_layout.removeItem(warning_item)
 
-        df = self._pandas_model.get_dataframe()
+        columns = self._pandas_model.get_columns()
 
-        if 't' not in df.columns:
+        if 't' not in columns:
             self._add_warning_item(
                 "The column 't' does not exist. Please rename the column"
                 " containing the dates of the transactions to 't'.")
 
-        if 'value' not in df.columns:
+        if 'value' not in columns:
             self._add_warning_item(
                 "The column 'value' does not exist. Please rename the column"
                 " containing the values of the transactions to 'value'.")
 
-        if 'balance' not in df.columns:
+        if 'balance' not in columns:
             self._add_warning_item(
                 "The column 'balance' does not exist. Please rename the column"
                 " containing the balance after each transaction to 'balance'")
@@ -157,11 +174,30 @@ class MainWindow(QMainWindow):
     def _handle_header_right_click(self, pos):
         column = self._table_view.horizontalHeader().logicalIndexAt(pos)
 
-        context = HeaderContextMenu(parent=self, column=column,
+        context = HeaderContextMenu(parent=self, column_index=column,
                                     pandas_model=self._pandas_model,
                                     callback=self._dataframe_update_callback)
         context.exec(self.sender().mapToGlobal(pos))
 
+    def _handle_rename_click(self):
+        selected_item = self._list_widget.currentItem()
+
+        new_name, flag = QInputDialog.getText(self, "Rename category",
+                                              "New name:",
+                                              text=selected_item.text())
+        if not flag:
+            return
+
+        current_items = [self._list_widget.item(x).text() for x
+                         in range(self._list_widget.count())]
+
+        if new_name not in current_items:
+            self._pandas_model.rename_category(selected_item.text(), new_name)
+            selected_item.setText(new_name)
+        else:
+            QMessageBox.warning(self, "No action performed",
+                                f"Category '{new_name}' already exists.")
+
     def _handle_create_click(self):
         new_name, flag = QInputDialog.getText(self, "Create category",
                                               "New category:",
@@ -179,37 +215,25 @@ class MainWindow(QMainWindow):
                                 f"Category '{new_name}' already exists.")
 
     def _handle_delete_click(self):
-        selected_item = self._list_widget.selectedItems()[0]
+        selected_item = self._list_widget.currentItem()
 
         button = QMessageBox.question(self, "Delete category",
                                       f"Are you sure you want to delete"
                                       f" category '{selected_item.text()}'?")
 
         if button == QMessageBox.StandardButton.Yes:
+            self._pandas_model.delete_category(selected_item.text())
             self._list_widget.takeItem(self._list_widget.row(selected_item))
-            df = self.get_statement_data()
-            df.loc[df['category'] == selected_item.text(), 'category'] = ' '
 
     def _handle_clear_click(self):
-        self._assign_category(' ')
-
-    def _assign_category(self, category: str):
-        indexes = self._table_view.selectionModel().selectedRows()
-
-        row_indices = [self._table_view.model().mapToSource(index).row()
-                       for index in indexes]
-
-        df = self._pandas_model.get_dataframe()
-        df.loc[row_indices, 'category'] = category
-
-        self._pandas_model.set_dataframe(df)
+        self._assign_category_to_selected_transactions(' ')
 
     def _handle_apply_click(self):
         category = self._list_widget.selectedItems()[0].text()
-        self._assign_category(category)
+        self._assign_category_to_selected_transactions(category)
 
     def _handle_item_double_click(self, item):
-        self._assign_category(item.text())
+        self._assign_category_to_selected_transactions(item.text())
 
     def _handle_save(self):
         filename, _ = QFileDialog.getSaveFileName(self, 'Save File')
@@ -243,9 +267,16 @@ class MainWindow(QMainWindow):
         else:
             self._apply_button.setEnabled(False)
 
+    def _check_enable_rename_button(self):
+        if (len(self._list_widget.selectedItems()) > 0):
+            self._rename_button.setEnabled(True)
+        else:
+            self._rename_button.setEnabled(False)
+
     def _handle_list_selection_changed(self):
         self._check_enable_delete_button()
         self._check_enable_apply_button()
+        self._check_enable_rename_button()
 
     def _handle_table_selection_changed(self):
         self._check_enable_clear_button()

banking_breakdown/ui/main_window.ui

@@ -60,6 +60,36 @@
              </property>
             </widget>
            </item>
+           <item>
+            <widget class="QPushButton" name="renameCategoryButton">
+             <property name="enabled">
+              <bool>false</bool>
+             </property>
+             <property name="toolTip">
+              <string>Rename selected category</string>
+             </property>
+             <property name="text">
+              <string>Rename</string>
+             </property>
+            </widget>
+           </item>
+          </layout>
+         </item>
+         <item>
+          <layout class="QHBoxLayout" name="horizontalLayout_4">
+           <item>
+            <spacer name="horizontalSpacer">
+             <property name="orientation">
+              <enum>Qt::Horizontal</enum>
+             </property>
+             <property name="sizeHint" stdset="0">
+              <size>
+               <width>40</width>
+               <height>20</height>
+              </size>
+             </property>
+            </spacer>
+           </item>
            <item>
             <widget class="QPushButton" name="deleteCategoryButton">
              <property name="enabled">
@@ -80,6 +110,9 @@
            <property name="sizeAdjustPolicy">
             <enum>QAbstractScrollArea::AdjustToContents</enum>
            </property>
+           <property name="sortingEnabled">
+            <bool>true</bool>
+           </property>
           </widget>
          </item>
          <item>
@@ -123,12 +156,24 @@
         <layout class="QVBoxLayout" name="verticalLayout">
          <item>
           <widget class="QTableView" name="transactionTableView">
+           <property name="autoScroll">
+            <bool>false</bool>
+           </property>
            <property name="selectionBehavior">
             <enum>QAbstractItemView::SelectRows</enum>
            </property>
+           <property name="verticalScrollMode">
+            <enum>QAbstractItemView::ScrollPerPixel</enum>
+           </property>
+           <property name="horizontalScrollMode">
+            <enum>QAbstractItemView::ScrollPerPixel</enum>
+           </property>
            <property name="sortingEnabled">
             <bool>true</bool>
            </property>
+           <attribute name="horizontalHeaderShowSortIndicator" stdset="0">
+            <bool>true</bool>
+           </attribute>
            <attribute name="horizontalHeaderStretchLastSection">
             <bool>true</bool>
            </attribute>

banking_breakdown/ui/pandas_model.py

@@ -1,7 +1,9 @@
+import typing
+
 import numpy
 import pandas as pd
 from PyQt6 import QtCore
-from PyQt6.QtCore import Qt, QModelIndex
+from PyQt6.QtCore import Qt, QModelIndex, QSortFilterProxyModel
 
 
 def _get_str_dataframe(df: pd.DataFrame) -> pd.DataFrame:
@@ -20,9 +22,10 @@ class PandasModel(QtCore.QAbstractTableModel):
 
         self._data = pd.DataFrame()
         self._data_str = pd.DataFrame()
-        self._horizontalHeaders = None
 
+    #
     # Overloaded functions
+    #
 
     def rowCount(self, parent=None):
         return len(self._data_str.values)
@@ -55,14 +58,120 @@ class PandasModel(QtCore.QAbstractTableModel):
                 and (role == Qt.ItemDataRole.DisplayRole)):
             return super().headerData(section, orientation, role)
 
-        return self._horizontalHeaders[section]
+        return self._data_str.columns[section]
 
-    # Other functions
+    #
+    # Manipulate categories
+    #
+
+    def assign_category(self, category, row_indices):
+        if 'category' not in self._data.columns:
+            self.create_column('category')
+
+        self._data.loc[row_indices, 'category'] = category
+        self._data_str = _get_str_dataframe(self._data)
+
+        for row_index in row_indices:
+            start_index = self.index(row_index, 0)
+            stop_index = self.index(row_index, len(self._data.columns) - 1)
+            self.dataChanged.emit(start_index, stop_index)
+
+    def delete_category(self, category):
+        if 'category' not in self._data.columns:
+            self.create_column('category')
+
+        row_indices = self._data.loc[self._data['category'] == category].index
+        self.assign_category(' ', row_indices)
+
+    def rename_category(self, old_name, new_name):
+        if 'category' not in self._data.columns:
+            self.create_column('category')
+
+        row_indices = self._data.loc[self._data['category'] == old_name].index
+        self.assign_category(new_name, row_indices)
+
+
+    def get_categories(self) -> typing.List[str]:
+        if 'category' not in self._data.columns:
+            self.create_column('category')
+
+        return self._data['category'].unique()
+
+    #
+    # Manipulate columns
+    #
+
+    def create_column(self, column, initial_value=' '):
+        self._data[column] = [initial_value] * len(self._data.index)
+        self._data_str = _get_str_dataframe(self._data)
+        self.layoutAboutToBeChanged.emit()
+        self.layoutChanged.emit()
+
+    def delete_column_by_index(self, column_index):
+        self._data \
+            = self._data.iloc[:, [j for j, c in enumerate(self._data.columns)
+                                  if j != column_index]]
+        self._data_str = _get_str_dataframe(self._data)
+
+        self.layoutAboutToBeChanged.emit()
+        self.layoutChanged.emit()
+
+    def rename_column(self, old_name, new_name):
+        if new_name in self._data.columns:
+            raise Exception(
+                f"A column with the name '{new_name}' already exists.")
+
+        self._data = self._data.rename(columns={old_name: new_name})
+        self._data_str = _get_str_dataframe(self._data)
+
+        column_index = self._data.columns.get_loc(new_name)
+        self.headerDataChanged.emit(Qt.Orientation.Horizontal,
+                                    column_index, column_index)
+
+    def switch_columns(self, column1, column2):
+        column_titles = list(self._data.columns)
+
+        index1, index2 \
+            = column_titles.index(column1), column_titles.index(column2)
+
+        column_titles[index1], column_titles[index2] \
+            = column_titles[index2], column_titles[index1]
+
+        self._data = self._data.reindex(columns=column_titles)
+        self._data_str = _get_str_dataframe(self._data)
+
+        self.layoutAboutToBeChanged.emit()
+        self.layoutChanged.emit()
+
+    def get_columns(self) -> typing.List[str]:
+        return list(self._data.columns)
+
+    def assign_float_column(self, column, decimal_sep):
+        if decimal_sep == ',':
+            self._data[column] \
+                = self._data[column].str.replace(',', '.').astype(float)
+        else:
+            self._data[column] = self._data[column].astype(float)
+
+        self._data_str = _get_str_dataframe(self._data)
+
+        column_index = self._data.columns.get_loc(column)
+        start_index = self.index(0, column_index)
+        stop_index = self.index(len(self._data.index), column_index)
+        self.dataChanged.emit(start_index, stop_index)
+
+    def assign_date_column(self, column, date_format):
+        self._data[column] \
+            = pd.to_datetime(self._data[column], format=date_format)
+        self._data_str = _get_str_dataframe(self._data)
+
+    #
+    # Directly access dataframe
+    #
 
     def set_dataframe(self, df):
         self._data = df
         self._data_str = _get_str_dataframe(df)
-        self._horizontalHeaders = list(df.columns)
 
         self.layoutAboutToBeChanged.emit()
         self.layoutChanged.emit()

requirements.txt

@@ -0,0 +1,4 @@
+numpy==1.26.3
+pandas==1.5.3
+PyQt6==6.6.1
+setuptools==69.0.3

setup.py

@@ -0,0 +1,20 @@
+import os
+from setuptools import setup
+
+
+with open('requirements.txt') as f:
+    required = f.read().splitlines()
+
+
+setup(
+   name='banking_breakdown',
+   version='1.0',
+   description='Visualize bank statements',
+   author='Andreas Tsouchlos',
+   packages=['banking_breakdown', 'banking_breakdown.ui', 'banking_breakdown.document_builder'],
+   install_requires=required,
+   package_data={'banking_breakdown.ui': ['main_window.ui', 'warning.png'],
+                 'banking_breakdown.document_builder': ['.latexmkrc', 'Dockerfile.alpine', 'report.tex', 'common.tex']},
+   include_package_data=True,
+)
+