File size: 8,417 Bytes
44a9dbf 5472b6c 44a9dbf 5472b6c ae03dcd 5472b6c 44a9dbf 5472b6c 44a9dbf 5472b6c 44a9dbf 5472b6c 44a9dbf 5472b6c 44a9dbf 5472b6c 44a9dbf 5472b6c 44a9dbf c5fa079 5472b6c 44a9dbf c5fa079 5472b6c c5fa079 5472b6c c5fa079 5472b6c 44a9dbf 5472b6c 44a9dbf 5472b6c ae03dcd 5472b6c 44a9dbf ae03dcd 44a9dbf 5472b6c ae03dcd |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 |
import csv
import os
import argparse
import pandas as pd
from utilities.anonymize import (
get_cities_list,
get_abbreviation_dict_correction,
reformat_to_report,
anonymize_analyzer,
anonymize_engine,
add_space_to_comma_endpoint,
get_list_not_deidentify,
config_deidentify,
)
from utilities.translate import get_translation_dict_correction, translate_report
from utilities.convert import (
convert_df_no_header,
convert_df,
convert_json,
convert_list_phenogenius,
convert_pdf_to_text,
)
from utilities.extract_hpo import add_biometrics, extract_hpo
from utilities.get_model import get_models, get_nlp_marian
import gc
def main():
print("Code Starting")
MarianText, _, _ = translate_report(
Report,
Last_name,
First_name,
nlp_fr,
marian_fr_en,
dict_correction,
dict_abbreviation_correction,
)
MarianText_report = reformat_to_report(MarianText, nlp_fr)
del MarianText
print("Translation and De-identification")
(
MarianText_anonymize_report_analyze,
analyzer_results_return,
_,
_,
) = anonymize_analyzer(
MarianText_report, analyzer, proper_noun, Last_name, First_name
)
print(MarianText_anonymize_report_analyze)
MarianText_anonymize_report_engine = anonymize_engine(
MarianText_report, analyzer_results_return, engine, nlp_fr
)
MarianText_anonymize_report_engine_modif = pd.DataFrame(
[x for x in MarianText_anonymize_report_engine.split("\n")]
)
MarianText_anonymize_report_engine_df = MarianText_anonymize_report_engine_modif
with open(
os.path.join(args.result_dir, "Reports", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_translated_and_deindentified_report.txt",
"w",
) as file:
file.write(
convert_df_no_header(MarianText_anonymize_report_engine_df).decode("utf-8")
)
print(
"Text file created successfully : "
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_translated_and_deindentified_report.txt"
)
print("Summarization")
MarianText_anonymized_reformat_space = add_space_to_comma_endpoint(
MarianText_anonymize_report_engine, nlp_fr
)
MarianText_anonymized_reformat_biometrics, _ = add_biometrics(
MarianText_anonymized_reformat_space, nlp_fr
)
clinphen, clinphen_unsafe = extract_hpo(MarianText_anonymized_reformat_biometrics)
del MarianText_anonymize_report_engine
del MarianText_anonymized_reformat_space
del MarianText_anonymized_reformat_biometrics
clinphen_unsafe_check_raw = clinphen_unsafe
clinphen_unsafe_check_raw["To keep in list"] = False
clinphen_unsafe_check_raw["Confidence on extraction"] = "low"
del clinphen_unsafe
clinphen["Confidence on extraction"] = "high"
clinphen["To keep in list"] = True
cols = [
"HPO ID",
"Phenotype name",
"To keep in list",
"No. occurrences",
"Earliness (lower = earlier)",
"Confidence on extraction",
"Example sentence",
]
clinphen_all = pd.concat([clinphen, clinphen_unsafe_check_raw]).reset_index()
clinphen_all = clinphen_all[cols]
clinphen_df = clinphen_all
clinphen_df_without_low_confidence = clinphen_df[
clinphen_df["To keep in list"] == True
]
del clinphen
del clinphen_unsafe_check_raw
gc.collect()
with open(
os.path.join(args.result_dir, "TSV", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_summarized_report.tsv",
"w",
) as file:
file.write(convert_df(clinphen_df).decode("utf-8"))
print(
"Tsv file created successfully : "
+ os.path.join(args.result_dir, "TSV", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_summarized_report.tsv"
)
with open(
os.path.join(args.result_dir, "JSON", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_summarized_report.json",
"w",
) as file:
file.write(convert_json(clinphen_df_without_low_confidence))
print(
"JSON file created successfully : "
+ os.path.join(args.result_dir, "JSON", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_summarized_report.json"
)
with open(
os.path.join(args.result_dir, "TXT", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_summarized_report.txt",
"w",
) as file:
file.write(convert_list_phenogenius(clinphen_df_without_low_confidence))
print(
"Text file created successfully : "
+ os.path.join(args.result_dir, "TXT", "")
+ Report_id
+ "_"
+ Last_name
+ "_"
+ First_name
+ "_summarized_report.txt"
)
if __name__ == "__main__":
print("Welcome to the Clinfly app")
parser = argparse.ArgumentParser(description="Description of clinfly arguments")
parser.add_argument(
"--file",
type=str,
help="the input file which contains the visits informations",
required=True,
)
parser.add_argument(
"--language",
choices=["fr", "es", "de"],
type=str,
help="The language of the input : fr, es , de",
required=True,
)
parser.add_argument(
"--model_dir",
default=os.path.expanduser("~"),
type=str,
help="The directory where the models will be downloaded.",
)
parser.add_argument(
"--result_dir",
default="Results",
type=str,
help="The directory where the results will be placed.",
)
args = parser.parse_args()
if not os.path.exists(args.model_dir):
os.makedirs(args.model_dir)
if not os.path.exists(args.result_dir):
os.makedirs(args.result_dir)
if not os.path.exists(os.path.join(args.result_dir, "Reports")):
os.makedirs(os.path.join(args.result_dir, "Reports"))
if not os.path.exists(os.path.join(args.result_dir, "TSV")):
os.makedirs(os.path.join(args.result_dir, "TSV"))
if not os.path.exists(os.path.join(args.result_dir, "JSON")):
os.makedirs(os.path.join(args.result_dir, "JSON"))
if not os.path.exists(os.path.join(args.result_dir, "TXT")):
os.makedirs(os.path.join(args.result_dir, "TXT"))
print("Language chosen :", args.language)
models_status = get_models(args.language, args.model_dir)
dict_correction = get_translation_dict_correction()
dict_abbreviation_correction = get_abbreviation_dict_correction()
proper_noun = get_list_not_deidentify()
cities_list = get_cities_list()
analyzer, engine = config_deidentify(cities_list)
nlp_fr, marian_fr_en = get_nlp_marian(args.language)
file_name = args.file
Report_id: str
Last_name: str
First_name: str
Report: str
if os.path.isfile(args.file):
with open(file_name, 'r') as fichier:
for ligne in fichier:
elements = ligne.strip().split('\t')
Report_id, Last_name, First_name, text_or_link = elements
print("Report_id:", Report_id)
print("Last_name:", Last_name)
print("First_name:", First_name)
if os.path.exists(text_or_link):
if text_or_link.lower().endswith('.pdf'):
print(f"Processing PDF file: {text_or_link}")
Report = convert_pdf_to_text(text_or_link)
else:
print(f"Unsupported file type. Please provide a link to a PDF files.")
else:
Report = text_or_link
print("Report:", Report)
main()
print()
else:
print("Input is not a file. Please provide a valid input.")
|