Add expense-by-category figure

banking_breakdown/__main__.py

@@ -1,6 +1,5 @@
-from banking_breakdown import document_builder
+from banking_breakdown import ui, regex_categorizer, statement_parser, \
-from banking_breakdown import statement_parser
+    document_builder
-from banking_breakdown import ui
 
 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(report_data)
 
 
 #

banking_breakdown/document_builder.py

@@ -14,6 +14,8 @@ 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.expenses_by_category.to_csv('build/expenses_by_category.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)

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 +6,104 @@ import re
 import numpy as np
 
 
-# def _read_regex_dict(regex_file: str = "res/category_regexes.json"):
+def _escape_string(to_escape: str):
-#     with open(regex_file, 'r') as f:
+    return to_escape.translate(str.maketrans({"&": r"\&"}))
-#         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 get_stripped_statement(filename: str) -> pd.DataFrame:
+def _compute_total_balance(df: pd.DataFrame) -> pd.DataFrame:
-    # df = pd.read_csv(filename, delimiter=';', decimal=",")
+    stripped_df = pd.DataFrame(
-    df = pd.read_csv(filename, delimiter=';')
+        {'t': df["t"], 'value': df["balance"]})
-    df["Valutadatum"] = (pd.to_datetime(df["Valutadatum"], format='%d.%m.%Y')
-                         .dt.strftime('%Y-%m-%d'))
 
-    result = pd.DataFrame({'t': df["Valutadatum"],
+    stripped_df.index = stripped_df['t']
-                           'other party': df["Name Zahlungsbeteiligter"],
+    gb = stripped_df.groupby(pd.Grouper(freq='M'))
-                           'value': df["Betrag"],
+
-                           'balance': df["Saldo nach Buchung"],
+    result = gb.tail(1)['value'].reset_index()
-                           'category': [''] * len(df["Valutadatum"]),
-                           'description': df["Buchungstext"],
-                           'purpose': df["Verwendungszweck"]
-                           })
 
     return result
+
+
+def _compute_net_income(df: pd.DataFrame) -> pd.DataFrame:
+    stripped_df = pd.DataFrame({'t': df["t"], 'value': df["value"]})
+
+    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:
+    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]
+    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['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/test.json

@@ -0,0 +1,5 @@
+{
+  "asdf": [
+    "Kinemic"
+  ]
+}

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

res/report.tex

@@ -212,5 +212,97 @@
 \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}