Spaces:
Running
Running
Vu Minh Chien
commited on
Commit
·
06d9f7d
1
Parent(s):
5a202c5
change predict rule
Browse files- Dockerfile +2 -2
- routes/predict.py +118 -109
- validate_optimization.py +2 -2
Dockerfile
CHANGED
@@ -28,8 +28,8 @@ COPY requirements.txt .
|
|
28 |
RUN --mount=type=secret,id=BITBUCKET_APP_PW,mode=0444,required=true \
|
29 |
git clone https://vumichien:$(cat /run/secrets/BITBUCKET_APP_PW)@bitbucket.org/dtm-partners/meisai-check-ai.git && \
|
30 |
cd meisai-check-ai && \
|
31 |
-
git checkout
|
32 |
-
git pull origin
|
33 |
cd ..
|
34 |
|
35 |
# Cài đặt dependencies
|
|
|
28 |
RUN --mount=type=secret,id=BITBUCKET_APP_PW,mode=0444,required=true \
|
29 |
git clone https://vumichien:$(cat /run/secrets/BITBUCKET_APP_PW)@bitbucket.org/dtm-partners/meisai-check-ai.git && \
|
30 |
cd meisai-check-ai && \
|
31 |
+
git checkout staging && \
|
32 |
+
git pull origin staging && \
|
33 |
cd ..
|
34 |
|
35 |
# Cài đặt dependencies
|
routes/predict.py
CHANGED
@@ -21,8 +21,14 @@ from mapping_lib.sub_subject_and_name_data_mapper import SubSubjectAndNameDataMa
|
|
21 |
from mapping_lib.sub_subject_location_data_mapper import SubSubjectLocationDataMapper
|
22 |
from mapping_lib.abstract_similarity_mapper import AbstractSimilarityMapper
|
23 |
from mapping_lib.name_and_abstract_mapper import NameAndAbstractDataMapper
|
24 |
-
from mapping_lib.
|
25 |
-
from mapping_lib.
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
|
27 |
from config import UPLOAD_DIR, OUTPUT_DIR
|
28 |
from models import (
|
@@ -65,6 +71,21 @@ async def predict(
|
|
65 |
# Load input data
|
66 |
start_time = time.time()
|
67 |
df_input_data = pd.read_csv(input_file_path)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
# Ensure basic columns exist with default values
|
70 |
basic_columns = {
|
@@ -83,9 +104,8 @@ async def predict(
|
|
83 |
if col not in df_input_data.columns:
|
84 |
df_input_data[col] = default_value
|
85 |
|
86 |
-
#
|
87 |
try:
|
88 |
-
# Subject mapping
|
89 |
if sentence_service.df_subject_map_data is not None:
|
90 |
subject_similarity_mapper = SubjectSimilarityMapper(
|
91 |
cached_embedding_helper=sentence_service.subject_cached_embedding_helper,
|
@@ -93,35 +113,29 @@ async def predict(
|
|
93 |
)
|
94 |
|
95 |
list_input_subject = df_input_data["科目"].unique()
|
96 |
-
df_subject_data = pd.DataFrame(
|
97 |
|
98 |
-
subject_similarity_mapper.
|
99 |
|
100 |
-
output_subject_map = dict(
|
101 |
-
|
102 |
-
|
103 |
-
df_input_data
|
104 |
-
output_subject_map
|
105 |
-
)
|
106 |
-
df_input_data["出力_科目"] = df_input_data["科目"].map(
|
107 |
-
output_subject_map
|
108 |
-
)
|
109 |
|
110 |
except Exception as e:
|
111 |
print(f"Error processing SubjectSimilarityMapper: {e}")
|
112 |
raise HTTPException(status_code=500, detail=str(e))
|
113 |
|
|
|
114 |
try:
|
115 |
-
# Standard subject mapping
|
116 |
if sentence_service.df_standard_subject_map_data is not None:
|
117 |
standard_subject_data_mapper = StandardSubjectDataMapper(
|
118 |
df_map_data=sentence_service.df_standard_subject_map_data
|
119 |
)
|
120 |
df_output_data = standard_subject_data_mapper.map_data(
|
121 |
-
df_input_data=df_input_data,
|
122 |
-
input_key_columns=["出力_科目"],
|
123 |
-
in_place=True,
|
124 |
)
|
|
|
125 |
else:
|
126 |
df_output_data = df_input_data.copy()
|
127 |
|
@@ -130,131 +144,127 @@ async def predict(
|
|
130 |
# Continue with original data if standard subject mapping fails
|
131 |
df_output_data = df_input_data.copy()
|
132 |
|
|
|
133 |
try:
|
134 |
-
# Sub subject mapping
|
135 |
if sentence_service.df_sub_subject_map_data is not None:
|
136 |
sub_subject_similarity_mapper = SubSubjectSimilarityMapper(
|
137 |
cached_embedding_helper=sentence_service.sub_subject_cached_embedding_helper,
|
138 |
df_map_data=sentence_service.df_sub_subject_map_data,
|
139 |
)
|
140 |
-
|
141 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
)
|
143 |
-
df_output_data
|
144 |
|
145 |
except Exception as e:
|
146 |
print(f"Error processing SubSubjectSimilarityMapper: {e}")
|
147 |
raise HTTPException(status_code=500, detail=str(e))
|
148 |
|
149 |
-
|
150 |
try:
|
151 |
-
# Name mapping
|
152 |
if sentence_service.df_name_map_data is not None:
|
153 |
name_sentence_mapper = NameSimilarityMapper(
|
154 |
cached_embedding_helper=sentence_service.name_cached_embedding_helper,
|
155 |
df_map_data=sentence_service.df_name_map_data,
|
156 |
)
|
157 |
-
name_sentence_mapper.
|
|
|
158 |
|
159 |
except Exception as e:
|
160 |
print(f"Error processing NameSimilarityMapper: {e}")
|
161 |
raise HTTPException(status_code=500, detail=str(e))
|
162 |
-
try:
|
163 |
-
sub_subject_location_mapper = SubSubjectLocationDataMapper()
|
164 |
-
sub_subject_location_mapper.map_location(df_output_data)
|
165 |
-
except Exception as e:
|
166 |
-
print(f"Error processing SubSubjectLocationDataMapper: {e}")
|
167 |
-
raise HTTPException(status_code=500, detail=str(e))
|
168 |
|
|
|
169 |
try:
|
170 |
-
# Sub subject and name mapping
|
171 |
if sentence_service.df_sub_subject_and_name_map_data is not None:
|
172 |
-
|
173 |
df_map_data=sentence_service.df_sub_subject_and_name_map_data
|
174 |
)
|
175 |
-
|
176 |
|
177 |
except Exception as e:
|
178 |
print(f"Error processing SubSubjectAndNameDataMapper: {e}")
|
179 |
raise HTTPException(status_code=500, detail=str(e))
|
180 |
|
|
|
181 |
try:
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
for col in ["標準科目", "摘要グループ", "確定", "摘要", "備考"]:
|
203 |
-
if col in df_output_data.columns:
|
204 |
-
df_output_data[col] = df_output_data[col].astype(str).fillna("")
|
205 |
|
|
|
|
|
|
|
206 |
abstract_similarity_mapper = AbstractSimilarityMapper(
|
207 |
cached_embedding_helper=sentence_service.abstract_cached_embedding_helper,
|
208 |
df_map_data=sentence_service.df_abstract_map_data,
|
209 |
)
|
210 |
-
abstract_similarity_mapper.
|
211 |
-
|
212 |
-
print(f"DEBUG: AbstractSimilarityMapper completed successfully")
|
213 |
|
214 |
except Exception as e:
|
215 |
print(f"Error processing AbstractSimilarityMapper: {e}")
|
216 |
print(f"DEBUG: Full error traceback:")
|
217 |
-
import traceback
|
218 |
-
|
219 |
traceback.print_exc()
|
220 |
# Don't raise the exception, continue processing
|
221 |
print(f"DEBUG: Continuing without AbstractSimilarityMapper...")
|
222 |
|
|
|
223 |
try:
|
224 |
-
# Name and abstract mapping
|
225 |
if sentence_service.df_name_and_subject_map_data is not None:
|
226 |
name_and_abstract_mapper = NameAndAbstractDataMapper(
|
227 |
df_map_data=sentence_service.df_name_and_subject_map_data
|
228 |
)
|
229 |
-
df_output_data =
|
|
|
|
|
|
|
230 |
|
231 |
except Exception as e:
|
232 |
print(f"Error processing NameAndAbstractDataMapper: {e}")
|
233 |
raise HTTPException(status_code=500, detail=str(e))
|
234 |
|
|
|
235 |
try:
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
cached_embedding_helper=sentence_service.unit_cached_embedding_helper,
|
240 |
-
df_map_data=sentence_service.df_unit_map_data,
|
241 |
-
)
|
242 |
-
unit_mapper.predict_input_optimized(df_input_data=df_output_data)
|
243 |
-
|
244 |
-
except Exception as e:
|
245 |
-
print(f"Error processing UnitMapper: {e}")
|
246 |
-
raise HTTPException(status_code=500, detail=str(e))
|
247 |
-
|
248 |
-
try:
|
249 |
-
# Standard name mapping
|
250 |
-
if sentence_service.df_standard_name_map_data is not None:
|
251 |
-
standard_name_mapper = StandardNameMapper(
|
252 |
-
df_map_data=sentence_service.df_standard_name_map_data
|
253 |
-
)
|
254 |
-
df_output_data = standard_name_mapper.map_data(df_output_data)
|
255 |
-
|
256 |
except Exception as e:
|
257 |
-
print(f"Error processing
|
258 |
raise HTTPException(status_code=500, detail=str(e))
|
259 |
|
260 |
# Create output columns and ensure they have proper values
|
@@ -286,7 +296,6 @@ async def predict(
|
|
286 |
for col, default_value in required_columns.items():
|
287 |
if col not in df_output_data.columns:
|
288 |
df_output_data[col] = default_value
|
289 |
-
|
290 |
# Map output columns to match Excel structure
|
291 |
# 出力_中科目 mapping - use the standard sub-subject from sub-subject mapper
|
292 |
if "出力_中科目" in df_output_data.columns:
|
@@ -331,26 +340,26 @@ async def predict(
|
|
331 |
print(f"Available columns after processing: {list(df_output_data.columns)}")
|
332 |
|
333 |
# Final check and fallback for missing output columns
|
334 |
-
if (
|
335 |
-
|
336 |
-
|
337 |
-
):
|
338 |
-
|
339 |
-
|
340 |
-
if (
|
341 |
-
|
342 |
-
|
343 |
-
):
|
344 |
-
|
345 |
-
|
346 |
-
if (
|
347 |
-
|
348 |
-
|
349 |
-
):
|
350 |
-
|
351 |
-
|
352 |
-
if "出力_確率度" not in df_output_data.columns:
|
353 |
-
|
354 |
|
355 |
# Define output columns in exact order as shown in Excel
|
356 |
output_columns = [
|
@@ -511,14 +520,14 @@ async def predict_raw(
|
|
511 |
try:
|
512 |
# Unit mapping
|
513 |
if sentence_service.df_unit_map_data is not None:
|
514 |
-
unit_mapper =
|
515 |
cached_embedding_helper=sentence_service.unit_cached_embedding_helper,
|
516 |
df_map_data=sentence_service.df_unit_map_data,
|
517 |
)
|
518 |
unit_mapper.predict_input(df_input_data=df_input_data)
|
519 |
|
520 |
except Exception as e:
|
521 |
-
print(f"Error processing
|
522 |
raise HTTPException(status_code=500, detail=str(e))
|
523 |
|
524 |
# Ensure required columns exist
|
|
|
21 |
from mapping_lib.sub_subject_location_data_mapper import SubSubjectLocationDataMapper
|
22 |
from mapping_lib.abstract_similarity_mapper import AbstractSimilarityMapper
|
23 |
from mapping_lib.name_and_abstract_mapper import NameAndAbstractDataMapper
|
24 |
+
from mapping_lib.unit_mapper import UnitMapper
|
25 |
+
from mapping_lib.base_dictionary_mapper import BaseDictionaryMapper
|
26 |
+
from common_lib.data_utilities import fillna_with_space
|
27 |
+
from common_lib.string_utilities import (
|
28 |
+
preprocess_text,
|
29 |
+
ConversionType,
|
30 |
+
ConversionSettings,
|
31 |
+
)
|
32 |
|
33 |
from config import UPLOAD_DIR, OUTPUT_DIR
|
34 |
from models import (
|
|
|
71 |
# Load input data
|
72 |
start_time = time.time()
|
73 |
df_input_data = pd.read_csv(input_file_path)
|
74 |
+
|
75 |
+
# Preprocess data like in meisai-check-ai/predict.py
|
76 |
+
df_input_data["元名称"] = df_input_data["名称"]
|
77 |
+
df_input_data["名称"] = df_input_data["名称"].apply(
|
78 |
+
lambda x: (
|
79 |
+
preprocess_text(
|
80 |
+
x,
|
81 |
+
convert_kana=ConversionType.Z2H,
|
82 |
+
convert_alphabet=ConversionType.Z2H,
|
83 |
+
convert_digit=ConversionType.Z2H,
|
84 |
+
)
|
85 |
+
if pd.notna(x)
|
86 |
+
else ""
|
87 |
+
)
|
88 |
+
)
|
89 |
|
90 |
# Ensure basic columns exist with default values
|
91 |
basic_columns = {
|
|
|
104 |
if col not in df_input_data.columns:
|
105 |
df_input_data[col] = default_value
|
106 |
|
107 |
+
# SubjectSimilarityMapper
|
108 |
try:
|
|
|
109 |
if sentence_service.df_subject_map_data is not None:
|
110 |
subject_similarity_mapper = SubjectSimilarityMapper(
|
111 |
cached_embedding_helper=sentence_service.subject_cached_embedding_helper,
|
|
|
113 |
)
|
114 |
|
115 |
list_input_subject = df_input_data["科目"].unique()
|
116 |
+
df_subject_data = pd.DataFrame(list_input_subject, columns=["科目"])
|
117 |
|
118 |
+
subject_similarity_mapper.predict_input(df_input_data=df_subject_data)
|
119 |
|
120 |
+
output_subject_map = dict(zip(df_subject_data["科目"], df_subject_data["出力_科目"]))
|
121 |
+
df_input_data["標準科目"] = df_input_data["科目"].map(output_subject_map)
|
122 |
+
df_input_data["出力_科目"] = df_input_data["標準科目"]
|
123 |
+
fillna_with_space(df_input_data)
|
|
|
|
|
|
|
|
|
|
|
124 |
|
125 |
except Exception as e:
|
126 |
print(f"Error processing SubjectSimilarityMapper: {e}")
|
127 |
raise HTTPException(status_code=500, detail=str(e))
|
128 |
|
129 |
+
# StandardSubjectDataMapper
|
130 |
try:
|
|
|
131 |
if sentence_service.df_standard_subject_map_data is not None:
|
132 |
standard_subject_data_mapper = StandardSubjectDataMapper(
|
133 |
df_map_data=sentence_service.df_standard_subject_map_data
|
134 |
)
|
135 |
df_output_data = standard_subject_data_mapper.map_data(
|
136 |
+
df_input_data=df_input_data, input_key_columns=["出力_科目"], in_place=True
|
|
|
|
|
137 |
)
|
138 |
+
fillna_with_space(df_output_data)
|
139 |
else:
|
140 |
df_output_data = df_input_data.copy()
|
141 |
|
|
|
144 |
# Continue with original data if standard subject mapping fails
|
145 |
df_output_data = df_input_data.copy()
|
146 |
|
147 |
+
# SubSubjectSimilarityMapper
|
148 |
try:
|
|
|
149 |
if sentence_service.df_sub_subject_map_data is not None:
|
150 |
sub_subject_similarity_mapper = SubSubjectSimilarityMapper(
|
151 |
cached_embedding_helper=sentence_service.sub_subject_cached_embedding_helper,
|
152 |
df_map_data=sentence_service.df_sub_subject_map_data,
|
153 |
)
|
154 |
+
df_input_sub_subject = df_output_data[
|
155 |
+
["科目", "標準科目", "出力_科目", "中科目", "分類"]
|
156 |
+
].drop_duplicates()
|
157 |
+
sub_subject_similarity_mapper.predict_input(df_input_data=df_input_sub_subject)
|
158 |
+
|
159 |
+
sub_subject_map_key_columns = ["科目", "標準科目", "出力_科目", "中科目", "分類"]
|
160 |
+
sub_subject_map_data_columns = [
|
161 |
+
"出力_基準中科目",
|
162 |
+
"出力_中科目類似度",
|
163 |
+
"出力_中科目",
|
164 |
+
"外部・内部区分",
|
165 |
+
]
|
166 |
+
|
167 |
+
sub_subject_data_mapper = BaseDictionaryMapper(
|
168 |
+
df_input_sub_subject, sub_subject_map_key_columns, sub_subject_map_data_columns
|
169 |
+
)
|
170 |
+
sub_subject_data_mapper.map_data(
|
171 |
+
df_input_data=df_output_data,
|
172 |
+
input_key_columns=sub_subject_map_key_columns,
|
173 |
+
in_place=True,
|
174 |
)
|
175 |
+
fillna_with_space(df_output_data)
|
176 |
|
177 |
except Exception as e:
|
178 |
print(f"Error processing SubSubjectSimilarityMapper: {e}")
|
179 |
raise HTTPException(status_code=500, detail=str(e))
|
180 |
|
181 |
+
# NameSimilarityMapper
|
182 |
try:
|
|
|
183 |
if sentence_service.df_name_map_data is not None:
|
184 |
name_sentence_mapper = NameSimilarityMapper(
|
185 |
cached_embedding_helper=sentence_service.name_cached_embedding_helper,
|
186 |
df_map_data=sentence_service.df_name_map_data,
|
187 |
)
|
188 |
+
name_sentence_mapper.predict_input(df_input_data=df_output_data)
|
189 |
+
fillna_with_space(df_output_data)
|
190 |
|
191 |
except Exception as e:
|
192 |
print(f"Error processing NameSimilarityMapper: {e}")
|
193 |
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
|
|
|
|
|
|
|
|
|
194 |
|
195 |
+
# SubSubjectAndNameDataMapper
|
196 |
try:
|
|
|
197 |
if sentence_service.df_sub_subject_and_name_map_data is not None:
|
198 |
+
sub_subject_and_name_data_mapper = SubSubjectAndNameDataMapper(
|
199 |
df_map_data=sentence_service.df_sub_subject_and_name_map_data
|
200 |
)
|
201 |
+
sub_subject_and_name_data_mapper.map_data(df_input_data=df_output_data)
|
202 |
|
203 |
except Exception as e:
|
204 |
print(f"Error processing SubSubjectAndNameDataMapper: {e}")
|
205 |
raise HTTPException(status_code=500, detail=str(e))
|
206 |
|
207 |
+
# UnitMapper
|
208 |
try:
|
209 |
+
if sentence_service.df_unit_map_data is not None:
|
210 |
+
unit_similarity_mapper = UnitMapper(
|
211 |
+
cached_embedding_helper=sentence_service.unit_cached_embedding_helper,
|
212 |
+
df_map_data=sentence_service.df_unit_map_data,
|
213 |
+
)
|
214 |
+
unit_map_key_columns = ["単位"]
|
215 |
+
df_input_unit = df_input_data[unit_map_key_columns].drop_duplicates()
|
216 |
+
unit_similarity_mapper.predict_input(df_input_data=df_input_unit)
|
217 |
+
|
218 |
+
output_unit_data_columns = ["出力_基準単位", "出力_単位類似度", "出力_集計用単位", "出力_標準単位"]
|
219 |
+
unit_data_mapper = BaseDictionaryMapper(
|
220 |
+
df_input_unit, unit_map_key_columns, output_unit_data_columns
|
221 |
+
)
|
222 |
+
_ = unit_data_mapper.map_data(
|
223 |
+
df_input_data=df_output_data, input_key_columns=unit_map_key_columns, in_place=True
|
224 |
+
)
|
225 |
+
fillna_with_space(df_output_data)
|
226 |
+
except Exception as e:
|
227 |
+
print(f"Error processing UnitMapper: {e}")
|
228 |
+
raise HTTPException(status_code=500, detail=str(e))
|
|
|
|
|
|
|
229 |
|
230 |
+
# AbstractSimilarityMapper
|
231 |
+
try:
|
232 |
+
if sentence_service.df_abstract_map_data is not None:
|
233 |
abstract_similarity_mapper = AbstractSimilarityMapper(
|
234 |
cached_embedding_helper=sentence_service.abstract_cached_embedding_helper,
|
235 |
df_map_data=sentence_service.df_abstract_map_data,
|
236 |
)
|
237 |
+
abstract_similarity_mapper.predict_input(df_input_data=df_output_data)
|
|
|
|
|
238 |
|
239 |
except Exception as e:
|
240 |
print(f"Error processing AbstractSimilarityMapper: {e}")
|
241 |
print(f"DEBUG: Full error traceback:")
|
|
|
|
|
242 |
traceback.print_exc()
|
243 |
# Don't raise the exception, continue processing
|
244 |
print(f"DEBUG: Continuing without AbstractSimilarityMapper...")
|
245 |
|
246 |
+
# NameAndAbstractDataMapper
|
247 |
try:
|
|
|
248 |
if sentence_service.df_name_and_subject_map_data is not None:
|
249 |
name_and_abstract_mapper = NameAndAbstractDataMapper(
|
250 |
df_map_data=sentence_service.df_name_and_subject_map_data
|
251 |
)
|
252 |
+
df_output_data["出力_項目名"] = df_output_data["出力_標準名称"]
|
253 |
+
_ = name_and_abstract_mapper.map_data(df_output_data)
|
254 |
+
fillna_with_space(df_output_data)
|
255 |
+
df_output_data["出力_項目名(中科目抜き)"] = df_output_data["出力_項目名"]
|
256 |
|
257 |
except Exception as e:
|
258 |
print(f"Error processing NameAndAbstractDataMapper: {e}")
|
259 |
raise HTTPException(status_code=500, detail=str(e))
|
260 |
|
261 |
+
# SubSubjectLocationDataMapper
|
262 |
try:
|
263 |
+
sub_subject_location_mapper = SubSubjectLocationDataMapper()
|
264 |
+
sub_subject_location_mapper.map_location(df_output_data)
|
265 |
+
df_output_data["名称"] = df_output_data["元名称"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
266 |
except Exception as e:
|
267 |
+
print(f"Error processing SubSubjectLocationDataMapper: {e}")
|
268 |
raise HTTPException(status_code=500, detail=str(e))
|
269 |
|
270 |
# Create output columns and ensure they have proper values
|
|
|
296 |
for col, default_value in required_columns.items():
|
297 |
if col not in df_output_data.columns:
|
298 |
df_output_data[col] = default_value
|
|
|
299 |
# Map output columns to match Excel structure
|
300 |
# 出力_中科目 mapping - use the standard sub-subject from sub-subject mapper
|
301 |
if "出力_中科目" in df_output_data.columns:
|
|
|
340 |
print(f"Available columns after processing: {list(df_output_data.columns)}")
|
341 |
|
342 |
# Final check and fallback for missing output columns
|
343 |
+
# if (
|
344 |
+
# "出力_中科目" not in df_output_data.columns
|
345 |
+
# or df_output_data["出力_中科目"].eq("").all()
|
346 |
+
# ):
|
347 |
+
# df_output_data["出力_中科目"] = df_output_data.get("中科目", "")
|
348 |
+
|
349 |
+
# if (
|
350 |
+
# "出力_項目名" not in df_output_data.columns
|
351 |
+
# or df_output_data["出力_項目名"].eq("").all()
|
352 |
+
# ):
|
353 |
+
# df_output_data["出力_項目名"] = df_output_data.get("名称", "")
|
354 |
+
|
355 |
+
# if (
|
356 |
+
# "出力_単位" not in df_output_data.columns
|
357 |
+
# or df_output_data["出力_単位"].eq("").all()
|
358 |
+
# ):
|
359 |
+
# df_output_data["出力_単位"] = df_output_data.get("単位", "")
|
360 |
+
|
361 |
+
# if "出力_確率度" not in df_output_data.columns:
|
362 |
+
# df_output_data["出力_確率度"] = 0 # Default confidence score
|
363 |
|
364 |
# Define output columns in exact order as shown in Excel
|
365 |
output_columns = [
|
|
|
520 |
try:
|
521 |
# Unit mapping
|
522 |
if sentence_service.df_unit_map_data is not None:
|
523 |
+
unit_mapper = UnitMapper(
|
524 |
cached_embedding_helper=sentence_service.unit_cached_embedding_helper,
|
525 |
df_map_data=sentence_service.df_unit_map_data,
|
526 |
)
|
527 |
unit_mapper.predict_input(df_input_data=df_input_data)
|
528 |
|
529 |
except Exception as e:
|
530 |
+
print(f"Error processing UnitMapper: {e}")
|
531 |
raise HTTPException(status_code=500, detail=str(e))
|
532 |
|
533 |
# Ensure required columns exist
|
validate_optimization.py
CHANGED
@@ -25,7 +25,7 @@ class FileComparator:
|
|
25 |
'出力_中科目',
|
26 |
'出力_標準名称',
|
27 |
'出力_項目名',
|
28 |
-
'出力_
|
29 |
]
|
30 |
|
31 |
def load_original_data(self) -> pd.DataFrame:
|
@@ -236,7 +236,7 @@ def main():
|
|
236 |
"""Main function to compare two files"""
|
237 |
# File paths
|
238 |
original_file = "data/outputData_original.csv"
|
239 |
-
second_file = "data/
|
240 |
|
241 |
if not os.path.exists(original_file):
|
242 |
print(f"❌ Original file not found: {original_file}")
|
|
|
25 |
'出力_中科目',
|
26 |
'出力_標準名称',
|
27 |
'出力_項目名',
|
28 |
+
'出力_集計用単位'
|
29 |
]
|
30 |
|
31 |
def load_original_data(self) -> pd.DataFrame:
|
|
|
236 |
"""Main function to compare two files"""
|
237 |
# File paths
|
238 |
original_file = "data/outputData_original.csv"
|
239 |
+
second_file = "data/outputData_api.csv"
|
240 |
|
241 |
if not os.path.exists(original_file):
|
242 |
print(f"❌ Original file not found: {original_file}")
|