def plot_all(self):
path = "./data/samsung_contest/data_tansformed.csv"
df = load_samsung(path)
reg_cols = [
'c02_사망자수',
'c03_사상자수',
'c04_중상자수',
'c05_경상자수',
'c06_부상신고자수',
]
label_encoder_cols = []
for k in df.columns:
if '_label' in k:
label_encoder_cols += [k]
onehot_col = []
for k in df.columns:
if '_onehot' in k:
onehot_col += [k]
x_cols = reg_cols + onehot_col
origin_cols = [
'c00_주야',
'c01_요일',
'c02_사망자수',
'c03_사상자수',
'c04_중상자수',
'c05_경상자수',
'c06_부상신고자수',
'c07_발생지시도',
'c08_발생지시군구',
'c09_사고유형_대분류',
'c10_사고유형_중분류',
'c11_법규위반',
'c12_도로형태_대분류',
'c13_도로형태',
'c14_당사자종별_1당_대분류',
'c15_당사자종별_2당_대분류',
]
# pprint(label_encoder_cols)
# pprint(onehot_col)
# pprint(x_cols)
# pprint(origin_cols)
plot = PlotTools()
for key in origin_cols:
# plot.dist(df, key, title=f'dist_{key}')
plot.count(df, key, title=f'count_{key}')
for a_key in origin_cols:
for b_key in origin_cols:
try:
plot.count(df, a_key, b_key, title=f'count_{a_key}_groupby_{b_key}')
except BaseException as e:
print(a_key, b_key, e)
class df_plotterMixIn:
def __init__(self):
self.plot = PlotTools()
def plot_all(self, df, df_Xs_keys, df_Ys_key):
self._df_cols_plot(df, df_Xs_keys, df_Ys_key)
@deco_exception_catch
def _plot_dist(self,
df: DF,
col_key: str,
partial_df: DF,
series: Series,
Xs_keys: list,
Ys_key: list,
path=None):
title = f'{col_key}_plot_dist'
self.plot.dist(df, col_key, title=title, path=f"./matplot/{title}.png")
@deco_exception_catch
def _plot_count(self,
df: DF,
col_key: str,
partial_df: DF,
series: Series,
Xs_keys: list,
Ys_key: list,
path=None):
title = f'{col_key}_plot_count_bar'
self.plot.count(df,
col_key,
title=title,
path=f"./matplot/{title}.png")
@deco_exception_catch
def _plot_violin(self,
df: DF,
col_key: str,
partial_df: DF,
series: Series,
Xs_keys: list,
Ys_key: list,
path=None):
title = f'{col_key}_plot_violin'
self.plot.violin_plot(df,
col_key,
Ys_key,
path=f"./matplot/{title}_1.png",
title=title)
self.plot.violin_plot(df,
Ys_key,
col_key,
path=f"./matplot/{title}_2.png",
title=title)
@deco_exception_catch
def _plot_joint2d(self,
df: DF,
col_key: str,
partial_df: DF,
series: Series,
Xs_keys: list,
Ys_key: list,
path=None):
title = f'{col_key}_plot_joint2d'
self.plot.joint_2d(df,
col_key,
Ys_key,
path=f"./matplot/{title}.png",
title=title)
@deco_exception_catch
def _plot_dist_groupby(self,
df: DF,
col_key: str,
partial_df: DF,
series: Series,
Xs_keys: list,
Ys_key: list,
path=None):
title = f'{col_key}_plot_dist_groupby'
self.plot.dist_groupby(df,
Ys_key,
col_key,
df,
title=title,
path=f"./matplot/{title}.png")
self.plot.dist_groupby(df,
col_key,
Ys_key,
df,
title=title,
path=f"./matplot/{title}.png")
def _df_cols_plot(self, df, df_Xs_keys, df_Ys_key):
with JobPool() as pool:
for key in df_Xs_keys:
col = df[[key]]
series = df[key]
args = (df, key, col, series, df_Xs_keys, df_Ys_key)
pool.apply_async(self._plot_dist, args=args)
pool.apply_async(self._plot_count, args=args)
pool.apply_async(self._plot_violin, args=args)
pool.apply_async(self._plot_joint2d, args=args)
class DF_PlotTools(LoggerMixIn):
def __init__(self, df, y_key, n_job=7, path=None):
super().__init__()
self.plot = PlotTools()
self.n_job = n_job
self.df = df
self.y_key = y_key
self.path = path
if self.path is None:
self.path = "./plot_outs"
def plot_all(self, ):
with JobPool(self.n_job) as pool:
keys = self.df.keys()
df = self.df
# plot dist
for key in keys:
args = [df, key]
pool.apply_async(self.plot_dist, args)
# plot count
for key in keys:
args = [df, key]
pool.apply_async(self.plot_countbar, args)
# plot violin
for key in keys:
args = [df, key, self.y_key]
pool.apply_async(self.plot_violin, args)
args = [df, self.y_key, key]
pool.apply_async(self.plot_violin, args)
# plot_joint2d
for key in keys:
args = [df, key, self.y_key]
pool.apply_async(self.plot_joint2d, args)
args = [df, self.y_key, key]
pool.apply_async(self.plot_joint2d, args)
# plot countbar_groupby
for a_key in keys:
args = [df, a_key, self.y_key]
pool.apply_async(self.plot_count_groupby, args)
@deco_exception_catch
def plot_dist(self, df: DF, col_key: str, title=None):
if title is None:
title = f'{col_key}_plot_dist'
self.plot.dist(df, col_key, title=title, path=f"./matplot/{title}.png")
@deco_exception_catch
def plot_countbar(self, df: DF, col_key: str, title=None):
if title is None:
title = f'{col_key}_plot_count_bar'
self.plot.count(df,
col_key,
title=title,
path=f"./matplot/{title}.png")
@deco_exception_catch
def plot_violin(self, df: DF, a_col, b_col, title=None):
if title is None:
title = f'{a_col}_{b_col}_plot_violin'
self.plot.violin_plot(df,
a_col,
b_col,
path=f"./matplot/{title}.png",
title=title)
@deco_exception_catch
def plot_joint2d(self, df: DF, a_col, b_col, title=None):
if title is None:
title = f'{a_col}_{b_col}_plot_joint2d'
self.plot.joint_2d(df,
a_col,
b_col,
path=f"./matplot/{title}.png",
title=title)
@deco_exception_catch
def plot_dist_groupby(self, df: DF, a_col, groupby_cols, title=None):
if title is None:
title = f'{a_col}_groupby_{groupby_cols}_plot_dist_groupby'
self.plot.dist_groupby(df,
a_col,
groupby_cols,
title=title,
path=f"./matplot/{title}.png")
@deco_exception_catch
def plot_count_groupby(self, df: DF, a_col, groupby_cols, title=None):
if title is None:
title = f'{a_col}_groupby_{groupby_cols}_count'
self.plot.count(df,
a_col,
groupby_cols,
title=title,
path=f"./matplot/{title}.png")
@deco_exception_catch
def plot_violin_groupby(self,
df: DF,
a_col,
b_col,
groupby_cols,
title=None):
if title is None:
title = f'{a_col}_{b_col}_groupby_{groupby_cols}_violin'
self.plot.violin_plot(df,
a_col,
b_col,
groupby_cols,
title=title,
path=f"./matplot/{title}.png")