def create(self, file_path: str) -> None:
(ggplot(self._data, aes(x="pattern", y="count", label="fraction")) +
geom_bar(stat="identity", fill="#1e4f79") +
geom_text(va='bottom', size=24, format_string='{:.1%}') +
scale_x_discrete(limits=self._data["pattern"]) +
scale_y_continuous(labels=comma_format(), expand=[0.1, 0]) +
ggtitle("Design Pattern Counts") + xlab("Design Pattern") +
ylab("Count") + theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32),
axis_text_x=element_text(rotation=45, ha="right"))).save(
file_path, width=24, height=8)
def test_empty_breaks():
x = []
assert custom_format()(x) == []
assert comma_format()(x) == []
assert currency_format()(x) == []
assert percent_format()(x) == []
assert scientific_format()(x) == []
assert date_format()(x) == []
assert mpl_format()(x) == []
assert log_format()(x) == []
assert timedelta_format()(x) == []
def test_empty_breaks():
x = []
assert custom_format()(x) == []
assert comma_format()(x) == []
assert currency_format()(x) == []
assert percent_format()(x) == []
assert scientific_format()(x) == []
assert date_format()(x) == []
assert mpl_format()(x) == []
assert log_format()(x) == []
assert timedelta_format()(x) == []
def create(self, file_path: str) -> None:
(ggplot(self._data, aes(x="category", y="count", label="percent")) +
geom_bar(stat="identity", fill="#1e4f79") +
geom_text(va='bottom', size=24) +
scale_x_discrete(limits=self._data["category"]) +
scale_y_continuous(labels=comma_format(), expand=[0.1, 0]) +
ggtitle("Classes per Category") + xlab("Category") +
ylab("Number of Classes") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32),
axis_text_x=element_text(rotation=45, ha="right"))).save(
file_path, width=7, height=7)
def create(self, file_path: str) -> None:
(ggplot(self._data, aes("value")) +
geom_histogram(bins=100, fill="#1e4f79") +
facet_wrap(facets="variable", scales="free", ncol=3) +
scale_x_continuous(trans=asinh_trans(), labels=asinh_labels) +
scale_y_continuous(labels=comma_format()) +
ggtitle("Distributions of QMOOD Quality Attributes") +
xlab("Quality Attribute Value") + ylab("Number of Projects") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32),
subplots_adjust={
"wspace": 0.35,
"hspace": 0.35
})).save(file_path, width=24, height=12)
def create(self, file_path: str) -> None:
(ggplot(self._data, aes("loc")) +
geom_histogram(bins=100, fill="#1e4f79") +
facet_grid(facets="category ~ .", scales='free_y') +
scale_x_continuous(trans=asinh_trans(), labels=asinh_labels) +
scale_y_continuous(labels=comma_format())
#+ scale_y_continuous(labels=lambda l: ["%.2f%%" % (v * 100 / len(self._data)) for v in l])
+ ggtitle("Class Sizes") + xlab("Lines of Code") +
ylab("Number of Classes") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32), subplots_adjust={"hspace": 0.1
})).save(file_path,
width=8,
height=18)
def create(self, file_path: str) -> None:
(ggplot(self._data, aes("value")) +
geom_histogram(bins=100, fill="#1e4f79") +
facet_wrap(facets="variable", scales="free", ncol=3) + xlim(0, 1) +
scale_y_continuous(labels=comma_format()) +
ggtitle("Intensity of Design Pattern Use") +
xlab("Percentage of Classes Participating in Design Pattern") +
ylab("Number of Projects") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32),
axis_title_y=element_text(margin={"r": 40}),
subplots_adjust={
"wspace": 0.3,
"hspace": 0.5
})).save(file_path, width=24, height=24)
def test_comma_format():
x = [1000, 2, 33000, 400]
result = comma_format()(x)
assert result == ['1,000', '2', '33,000', '400']
result_df['거래금액'] = pd.to_numeric(result_df['거래금액'])
result_df['도로명시군구코드'] = pd.to_numeric(result_df['도로명시군구코드'], downcast='integer')
result_df = pd.merge(left=result_df,
right=gu_code_data,
left_on='도로명시군구코드',
right_on='코드').drop('코드', axis=1)
result_df['년월'] = result_df['년'] + result_df['월']
result_df['년월'] = result_df['년월'].map(lambda x : datetime.datetime.strptime(x, '%Y%m'))
chart_df = result_df.groupby(['년월', '구'])['거래금액'].agg('sum')
chart_df = chart_df.reset_index()
chart_df['거래금액'] = chart_df['거래금액'] * 0.0001
chart_df = chart_df.query('년월 != "2019-07-01"') # 19년 6월 실거래가 아직 일부만 반영되어 제외
#%%
# 그래프 그리기
(ggplot(data=chart_df, mapping=aes(x = '년월', y = '거래금액', color='구'))
+ geom_line()
+ scale_x_datetime(breaks=date_breaks('6 months'), labels=date_format('%Y%m'))
+ scale_y_continuous(breaks=list(range(0, 20000, 2500)),labels = comma_format())
+ labs(x='기간', y='거래금액 (단위:억원)', color='')
+ theme(text=element_text(family='Malgun Gothic'))
)
#%%
# 피벗 돌려서 파일로 저장하기
trade_vol_df = chart_df.pivot(index='년월', columns='구', values='거래금액')
trade_vol_df.to_csv(file_path + 'apt_trade_vol_data.csv', encoding='euc-kr')
def test_comma_format():
x = [1000, 2, 33000, 400]
result = comma_format()(x)
assert result == ['1,000', '2', '33,000', '400']