-
Notifications
You must be signed in to change notification settings - Fork 0
/
analyze.py
180 lines (157 loc) · 5.92 KB
/
analyze.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import os
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from pandas import DataFrame
from datetime import datetime
from config import logger, settings
sns.set_style("whitegrid")
def get_plot_filename(workdir: str, filename: str):
return os.path.join(workdir, filename)
class Analyzer:
def __init__(self) -> None:
self.workdir = settings["workdir"]
self.plotdir = os.path.join(self.workdir, "plots")
def read_excel(self):
excel_name = settings["expenses_excel_filename"]
filepath = os.path.join(self.workdir, excel_name)
logger.debug(f"Reading excel {filepath}")
df: DataFrame = pd.read_excel(
filepath,
converters={"Date & time": pd.to_datetime},
index_col="Date & time",
)
# df.loc[:, "YearMonth"] = df.index.to_period("M")
df.loc[:, "Year"] = df.index.year
df.loc[:, "Month"] = df.index.month
return df
def plot_total_expenses(self, df: DataFrame):
logger.info("Starting total expenses")
g = sns.catplot(
x="Year",
y="Amount",
col="Category",
data=df,
estimator=sum,
col_wrap=4,
ci=None,
kind="bar",
)
g.fig.subplots_adjust(top=0.92)
g.fig.suptitle(f"Total Expenses by Category", fontsize=20)
plt.savefig(get_plot_filename(self.plotdir, f"Total Expenses by Category"))
plt.close()
def plot_monthly_balance(self, df: DataFrame, year: int):
logger.info("Starting total expenses/ingress by month")
sns.barplot(
x="Month",
y="Amount",
hue="Type",
data=df,
estimator=sum,
ci=None,
)
plt.title(f"Monthly Balance - {year}", fontsize=14)
plt.savefig(get_plot_filename(self.plotdir, f"{year}_Monthly Balance"))
plt.close()
def plot_by_category(self, df: DataFrame, year: int):
logger.info(f"{year} - Starting plots by category")
excluded_cols = settings["category_filters"]
for idx, exc_col in enumerate(excluded_cols):
cat_df = df.loc[~df["Category"].isin(exc_col)]
g = sns.catplot(
x="Month",
y="Amount",
col="Category",
data=cat_df,
kind="bar",
col_wrap=4,
estimator=sum,
ci=None,
)
g.fig.subplots_adjust(top=0.92)
g.fig.suptitle(f"Expenses by category - {year}", fontsize=20)
plt.savefig(
get_plot_filename(
self.plotdir, f"{year}_Expenses by Category and Month - {idx}"
)
)
plt.close()
def plot_monthly(self, df: DataFrame, year: int):
logger.info(f"{year} - Starting monthly plots")
year_dir = os.path.join(self.plotdir, str(year))
os.makedirs(year_dir, exist_ok=True)
for month in df["Month"].unique().tolist():
logger.info(f"Processing month {month}")
df_month = df.loc[df["Month"] == month]
g = sns.catplot(
data=df_month,
x="Category",
y="Amount",
kind="bar",
estimator=sum,
ci=None,
height=8,
aspect=1,
)
g.fig.suptitle(f"Expenses {year}-{month}")
g.ax.tick_params(axis="x", labelrotation=45)
plt.savefig(get_plot_filename(year_dir, f"{year}_{month:02d}_Expenses"))
plt.close()
df_j = (
df_month.groupby(["Category"])["Amount"]
.sum()
.round(2)
.sort_values(ascending=False)
)
pie, _ = plt.subplots(figsize=[10, 6])
labels = df_j.keys()
_, l, p = plt.pie(
x=df_j,
autopct="%.1f%%",
explode=[0.01] * len(labels),
labels=labels,
pctdistance=0.65,
)
[t.set_rotation(0) for t in p]
[t.set_fontsize(12) for t in p]
[t.set_fontsize(12) for t in l]
plt.axis("equal")
plt.title(f"Expenses by category {year}-{month}", fontsize=14)
plt.legend(df_j)
pie.savefig(
get_plot_filename(year_dir, f"{year}_{month:02d}_Expenses_by_category")
)
plt.close()
def summary(self):
df = self.read_excel()
df_expenses = df.loc[df["Type"] == "Expense"]
df_ingress = df.loc[df["Type"] == "Ingress"]
expenses_year = df_expenses.groupby("Year")["Amount"].sum()
ingress_year = df_ingress.groupby("Year")["Amount"].sum()
summary = pd.concat(
[expenses_year, ingress_year], axis=1, keys=["Expenses", "Ingress"]
)
summary.fillna(0, inplace=True)
summary["Savings"] = summary["Ingress"] - summary["Expenses"]
summary["Savings %"] = (
(summary["Ingress"] - summary["Expenses"]) / summary["Ingress"] * 100
)
logger.info("Total balance \n%s", summary)
return df, df_expenses, df_ingress
def start(self):
logger.info("Starting analyser")
df, df_expenses, df_ingress = self.summary()
self.plot_total_expenses(df_expenses)
for year in df_expenses.loc[:, "Year"].unique().tolist():
if year != datetime.now().year:
continue
logger.info(f"Analyzing {year}")
year_expenses_df = df_expenses.loc[df_expenses["Year"] == year]
year_df = df.loc[df["Year"] == year]
self.plot_monthly_balance(year_df, year)
self.plot_by_category(year_expenses_df, year)
self.plot_monthly(year_expenses_df, year)
if __name__ == "__main__":
analyzer = Analyzer()
analyzer.start()