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)
def test_df(self):
if self._test_df is None:
path = path_join(path_head, 'test_kor.csv')
test_df = load_samsung(path)
test_df = add_col_num(test_df)
test_df = self.fill_rand(test_df)
test_df = self.fill_inference_able(test_df)
save_samsung(test_df, './test.csv')
self._test_df = test_df
return self._test_df
def transform_to_result(self, predict_df):
result_df = load_samsung(path_join(path_head, 'result_kor.csv'))
size = len(result_df)
predict_cols = list(predict_df.columns)
result_cols = [str.upper(a) for a in 'abcdefghijklmnopqrstuvwxyz']
result_cols = result_cols[:len(predict_cols)]
result_col_tp_result_col = dict(zip(result_cols, predict_cols))
for i in range(size):
a = result_df.loc[i, :]
row = int(a['열']) - 2
col = a['행']
predict_col = result_col_tp_result_col[col]
result_df.loc[i, '값'] = predict_df.loc[row, predict_col]
# print(row, col, type(row), type(col), predict_col)
return result_df
def fill_rand(self, test_df):
path = path_join(path_head, 'data_init.csv')
train_df = load_samsung(path)
train_df['id'] = [0] * len(train_df)
g = train_df.groupby(['c07_발생지시도', 'c08_발생지시군구'])['id'].count()
mapper = {}
for key, val in list(g.index):
if key not in mapper:
mapper[key] = [val]
else:
mapper[key] += [val]
city_to_city_sub = mapper
g = train_df.groupby('c07_발생지시도')['id'].count()
city = list(g.index)
g = train_df.groupby('c08_발생지시군구')['id'].count()
city_sub = list(g.index)
for idx in range(len(test_df)):
if self.is_nan(test_df.loc[idx, 'c00_주야']):
test_df.loc[idx, 'c00_주야'] = np.random.choice(['주간', '야간'], 1)[0]
elif self.is_nan(test_df.loc[idx, 'c01_요일']):
day = ['월', '화', '수', '목', '금', '토', '일']
test_df.loc[idx, 'c01_요일'] = np.random.choice(day, 1)[0]
elif self.is_nan(test_df.loc[idx, 'c07_발생지시도']) and self.is_nan(test_df.loc[idx, 'c08_발생지시군구']):
test_df.loc[idx, 'c07_발생지시도'] = np.random.choice(city, 1)[0]
test_df.loc[idx, 'c08_발생지시군구'] = np.random.choice(city_sub, 1)[0]
elif not self.is_nan(test_df.loc[idx, 'c07_발생지시도']) and self.is_nan(test_df.loc[idx, 'c08_발생지시군구']):
choice = city_to_city_sub[test_df.loc[idx, 'c07_발생지시도']]
test_df.loc[idx, 'c08_발생지시군구'] = np.random.choice(choice, 1)[0]
return test_df
def predict(self, cache=True):
test_df_trans = self.test_df_trans
clf_dicts = self.model
path = path_join(path_head, 'predict.csv')
if os.path.exists(path) and cache:
print('predict cache found, use cache')
df = load_samsung(path)
return df
print('predict')
for idx in range(len(test_df_trans)):
p_type = self.get_p_type(test_df_trans, idx)
p_type_str = str(p_type)
print(f'predict {idx}, {p_type_str}')
x_cols = list(self.x_cols)
for y_col in p_type:
x_cols.remove(y_col)
for y_col in p_type:
print(f'predict {y_col}')
x_df = DF(test_df_trans.loc[[idx], x_cols])
x_df = x_df.reset_index(drop=True)
clf = clf_dicts[p_type_str][y_col]
print(clf)
clf_name = 'XGBoostClf'
predict = clf.predict(x_df)[clf_name][0][0]
test_df_trans.loc[idx, y_col] = predict
print(f'predict = {predict}, at_df:{test_df_trans.loc[idx, y_col]}')
save_samsung(test_df_trans, path)
return test_df_trans
def test_bench(self):
predict_df = load_samsung(path_join(path_head, 'predict.csv'))
transformed_result_df = self.transform_to_result(predict_df)
save_samsung(transformed_result_df, path_join(path_head, 'result_predict.csv'))