def post_process_instruction(df_instruction, df_request, df_post,
survey_item_prefix):
for i, row in df_instruction.iterrows():
if df_post.empty == False:
last_row = df_post.iloc[-1]
if last_row['text'] != row['text']:
if 'QItem' in df_request.QuestionElement.unique():
rowqitem = df_request[df_request['QuestionElement'] ==
'QItem']
item_name = adjust_item_name(
rowqitem['QuestionElementNr'].values[0],
rowqitem['item_name'].values[0])
else:
item_name = row['item_name']
if df_post.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
data = {
'survey_item_ID': survey_item_id,
'Study': row['Study'],
'module': row['module'],
'item_type': row['item_type'],
'item_name': item_name,
'item_value': row['item_value'],
'text': row['text']
}
df_post = df_post.append(data, ignore_index=True)
else:
if 'QItem' in df_request.QuestionElement.unique():
rowqitem = df_request[df_request['QuestionElement'] == 'QItem']
item_name = adjust_item_name(
rowqitem['QuestionElementNr'].values[0],
rowqitem['item_name'].values[0])
else:
item_name = row['item_name']
if df_post.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
data = {
'survey_item_ID': survey_item_id,
'Study': row['Study'],
'module': row['module'],
'item_type': row['item_type'],
'item_name': item_name,
'item_value': row['item_value'],
'text': row['text']
}
df_post = df_post.append(data, ignore_index=True)
return df_post
def preprocess_instruction_segment(row, df_questionnaire, survey_item_prefix,
splitter):
"""
Extracts and processes the instruction segments from the input file.
Args:
param1 row (pandas dataframe object): dataframe row being currently analyzed.
param2 df_questionnaire (pandas dataframe): pandas dataframe to store questionnaire data.
param3 survey_item_prefix (string): prefix of survey_item_ID.
param4 splitter (NLTK object): NLTK object for sentence segmentation instantiated in accordance to the language.
Returns:
updated df_questionnaire with new valid instruction segments.
"""
raw_item = replace_abbreviations_and_fills(row['text'])
sentences = splitter.tokenize(raw_item)
for sentence in sentences:
if df_questionnaire.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(survey_item_prefix)
data = {
"survey_item_ID": survey_item_id,
'Study': survey_item_prefix[:-1],
'module': retrieve_module_from_item_name(row['name']),
'item_type': 'INSTRUCTION',
'item_name': row['name'],
'item_value': None,
'text': sentence
}
df_questionnaire = df_questionnaire.append(data, ignore_index=True)
return df_questionnaire
def questionnaire_post_processing(df_with_intro, survey_item_prefix):
ut.reset_initial_sufix()
df_post = pd.DataFrame(columns=[
'survey_item_ID', 'Study', 'module', 'item_type', 'item_name',
'item_value', 'text'
])
unique_item_names = df_with_intro.item_name.unique()
for unique_item_name in unique_item_names:
df_by_item_name = df_with_intro[df_with_intro['item_name'] ==
unique_item_name]
df_instruction = df_by_item_name[df_by_item_name['item_type'] ==
'INSTRUCTION']
df_introduction = df_by_item_name[df_by_item_name['item_type'] ==
'INTRODUCTION']
df_request = df_by_item_name[df_by_item_name['item_type'] == 'REQUEST']
df_response = df_by_item_name[df_by_item_name['item_type'] ==
'RESPONSE']
del df_response['QuestionElement']
if df_instruction.empty == False:
df_post = post_process_instruction(df_instruction, df_request,
df_post, survey_item_prefix)
if df_introduction.empty == False:
for i, row in df_introduction.iterrows():
if 'QItem' in df_request.QuestionElement.unique():
rowqitem = df_request[df_request['QuestionElement'] ==
'QItem']
item_name = adjust_item_name(
rowqitem['QuestionElementNr'].values[0],
rowqitem['item_name'].values[0])
else:
item_name = row['item_name']
if df_post.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
data = {
'survey_item_ID': survey_item_id,
'Study': row['Study'],
'module': row['module'],
'item_type': row['item_type'],
'item_name': item_name,
'item_value': row['item_value'],
'text': row['text']
}
df_post = df_post.append(data, ignore_index=True)
df_post = post_process_request_response(df_request, df_response,
df_post, survey_item_prefix)
return df_post
def process_request(df, row, survey_item_prefix, item_name, module, splitter):
"""
Processes request segments.
Args:
param1 df (pandas dataframe): dataframe to store processed questionnaire data.
param2 row (pandas dataframe row): row of dataframe with contents of the input
file being analyzed in outer loop.
param3 survey_item_prefix (string): prefix of survey_item_ID.
param4 item_name (string): item_name metadata parameter, retrieved in previous steps.
param5 module (string): module metadata parameter, retrieved in previous steps.
param6 splitter (NLTK object): sentence segmentation from NLTK library.
Returns:
a pandas dataframe with preprocessed request segments.
"""
request = row['Request for answer text']
study, country_language = get_country_language_and_study_info(
survey_item_prefix)
if request != '.' and isinstance(request, str):
request = clean_text(request)
sentences = splitter.tokenize(request)
for sentence in sentences:
if sentence != '...':
if df.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
if check_if_segment_is_instruction(sentence, country_language):
item_type = 'INSTRUCTION'
else:
item_type = 'REQUEST'
data = {
'survey_item_ID': survey_item_id,
'Study': study,
'module': module,
'item_type': item_type,
'item_name': item_name,
'item_value': None,
'text': sentence
}
df = df.append(data, ignore_index=True)
return df
def extract_wis_data(df, df_questionnaire, study):
"""
Extracts and preprocesses WIS data from df, attibuting MCSQ metadata (and also harmonizing metadata e.g. item names, item types, when necessary).
Args:
param1 df (pandas dataframe): the input data in a dataframe representation.
param2 df_questionnaire (pandas dataframe): a dataframe to hold the processed questionnaire data.
param3 study (string): the name of the study, embedded in the WIS export filename.
Returns:
the df_questionnaire (pandas dataframe) with the preprocessed data.
"""
survey_item_prefix_source = instantiate_survey_item_prefix(study, 'source')
survey_item_prefix_eng = instantiate_survey_item_prefix(study, 'en_GB')
survey_item_prefix_fre = instantiate_survey_item_prefix(study, 'fr_FR')
survey_item_prefix_por = instantiate_survey_item_prefix(study, 'pt_PT')
survey_item_prefix_rus = instantiate_survey_item_prefix(study, 'ru_RU')
survey_item_prefix_ger = instantiate_survey_item_prefix(study, 'de_DE')
survey_item_prefix_spa = instantiate_survey_item_prefix(study, 'es_ES')
survey_item_prefix_nor = instantiate_survey_item_prefix(study, 'no_NO')
survey_item_prefix_cze = instantiate_survey_item_prefix(study, 'cs_CZ')
df['NEXT_ITEM_TYPE'] = df['ITEM_TYPE'].shift(-1)
flag = 0
for i, row in df.iterrows():
if isinstance(
row['PAGE'],
str) and row['PAGE'] != 'ALERT_1' and row['PAGE'] != 'ALERT_2':
item_name = simplify_item_name(
row['UNIQUE IDENTIFIER (PER SURVEY)'])
item_value = row['VALUES of VAR']
wis_item_type = row['ITEM_TYPE']
item_type = harmonize_item_type(wis_item_type)
if str(
row['source']
) != 'TRANSLATION IN TASK_API' and 'NO TRANSLATION' not in str(
row['en_GB']):
if isinstance(row['source'], str) or isinstance(
row['source'], int):
if wis_item_type == 'matrix question' and row[
'NEXT_ITEM_TYPE'] != 'matrix option':
if flag == 0:
count = 0
flag = 1
else:
count = count + 1
df_questionnaire.iloc[
-1,
df_questionnaire.columns.get_loc(
'item_name')] = item_name + '_' + str(count)
df['item_name'] = df[
'UNIQUE IDENTIFIER (PER SURVEY)'].replace(
to_replace=row['LAST_ITEM_NAME'],
value=item_name + '_introD')
df_by_item_name = df[
df['UNIQUE IDENTIFIER (PER SURVEY)'] ==
row['UNIQUE IDENTIFIER (PER SURVEY)']]
df_by_item_name_responses = df_by_item_name[
df_by_item_name['ITEM_TYPE'] == 'matrix option']
if df_questionnaire.empty:
survey_item_id_source = ut.get_survey_item_id(
survey_item_prefix_source)
else:
survey_item_id_source = ut.update_survey_item_id(
survey_item_prefix_source)
data = {
'Study':
study,
'module':
row['PAGE'],
'item_type':
item_type,
'wis_item_type':
wis_item_type,
'item_name':
item_name + '_' + str(count),
'item_value':
item_value,
'ENG_SOURCE_survey_item_ID':
survey_item_id_source,
'ENG_SOURCE_text':
row['source'],
'ENG_GB_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_eng),
'ENG_GB_text':
row['en_GB'],
'FRE_FR_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_fre),
'FRE_FR_text':
row['fr_FR'],
'POR_PT_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_por),
'POR_PT_text':
row['pt_PT'],
'RUS_RU_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_rus),
'RUS_RU_text':
row['ru_RU'],
'GER_DE_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_ger),
'GER_DE_text':
row['de_DE'],
'SPA_ES_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_spa),
'SPA_ES_text':
row['es_ES'],
'NOR_NO_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_nor),
'NOR_NO_text':
row['no_NO'],
'CZE_CZ_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_cze),
'CZE_CZ_text':
row['cs_CZ']
}
df_questionnaire = df_questionnaire.append(
data, ignore_index=True)
for i, row in df_by_item_name_responses.iterrows():
survey_item_id_source = ut.update_survey_item_id(
survey_item_prefix_source)
item_name = simplify_item_name(
row['UNIQUE IDENTIFIER (PER SURVEY)'])
item_value = row['VALUES of VAR']
wis_item_type = row['ITEM_TYPE']
item_type = harmonize_item_type(wis_item_type)
data = {
'Study':
study,
'module':
row['PAGE'],
'item_type':
item_type,
'wis_item_type':
wis_item_type,
'item_name':
item_name + '_' + str(count),
'item_value':
item_value,
'ENG_SOURCE_survey_item_ID':
survey_item_id_source,
'ENG_SOURCE_text':
row['source'],
'ENG_GB_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_eng),
'ENG_GB_text':
row['en_GB'],
'FRE_FR_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_fre),
'FRE_FR_text':
row['fr_FR'],
'POR_PT_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_por),
'POR_PT_text':
row['pt_PT'],
'RUS_RU_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_rus),
'RUS_RU_text':
row['ru_RU'],
'GER_DE_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_ger),
'GER_DE_text':
row['de_DE'],
'SPA_ES_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_spa),
'SPA_ES_text':
row['es_ES'],
'NOR_NO_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_nor),
'NOR_NO_text':
row['no_NO'],
'CZE_CZ_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_cze),
'CZE_CZ_text':
row['cs_CZ']
}
df_questionnaire = df_questionnaire.append(
data, ignore_index=True)
else:
flag = 0
if df_questionnaire.empty:
survey_item_id_source = ut.get_survey_item_id(
survey_item_prefix_source)
else:
survey_item_id_source = ut.update_survey_item_id(
survey_item_prefix_source)
data = {
'Study':
study,
'module':
row['PAGE'],
'item_type':
item_type,
'wis_item_type':
wis_item_type,
'item_name':
item_name,
'item_value':
item_value,
'ENG_SOURCE_survey_item_ID':
survey_item_id_source,
'ENG_SOURCE_text':
row['source'],
'ENG_GB_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_eng),
'ENG_GB_text':
row['en_GB'],
'FRE_FR_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_fre),
'FRE_FR_text':
row['fr_FR'],
'POR_PT_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_por),
'POR_PT_text':
row['pt_PT'],
'RUS_RU_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_rus),
'RUS_RU_text':
row['ru_RU'],
'GER_DE_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_ger),
'GER_DE_text':
row['de_DE'],
'SPA_ES_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_spa),
'SPA_ES_text':
row['es_ES'],
'NOR_NO_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_nor),
'NOR_NO_text':
row['no_NO'],
'CZE_CZ_survey_item_ID':
ut.get_survey_item_id(survey_item_prefix_cze),
'CZE_CZ_text':
row['cs_CZ']
}
df_questionnaire = df_questionnaire.append(
data, ignore_index=True)
return df_questionnaire
def post_process_request_response(df_request, df_response, df_post,
survey_item_prefix):
for i, row in df_request.iterrows():
if df_post.empty == False:
last_row = df_post.iloc[-1]
if last_row['text'] != row['text']:
if 'QItem' in df_request.QuestionElement.unique():
item_name = adjust_item_name(row['QuestionElementNr'],
row['item_name'])
else:
item_name = row['item_name']
if df_post.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
data = {
'survey_item_ID': survey_item_id,
'Study': row['Study'],
'module': row['module'],
'item_type': row['item_type'],
'item_name': item_name,
'item_value': row['item_value'],
'text': row['text']
}
df_post = df_post.append(data, ignore_index=True)
if df_response.empty == False:
if row['QuestionElement'] == 'QItem':
for i, response_row in df_response.iterrows():
data = {
'survey_item_ID':
ut.update_survey_item_id(survey_item_prefix),
'Study':
response_row['Study'],
'module':
response_row['module'],
'item_type':
response_row['item_type'],
'item_name':
item_name,
'item_value':
response_row['item_value'],
'text':
response_row['text']
}
df_post = df_post.append(data, ignore_index=True)
else:
if 'QItem' in df_request.QuestionElement.unique():
item_name = adjust_item_name(row['QuestionElementNr'],
row['item_name'])
else:
item_name = row['item_name']
if df_post.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(survey_item_prefix)
data = {
'survey_item_ID': survey_item_id,
'Study': row['Study'],
'module': row['module'],
'item_type': row['item_type'],
'item_name': item_name,
'item_value': row['item_value'],
'text': row['text']
}
df_post = df_post.append(data, ignore_index=True)
if df_response.empty == False:
if row['QuestionElement'] == 'QItem':
for i, response_row in df_response.iterrows():
data = {
'survey_item_ID':
ut.update_survey_item_id(survey_item_prefix),
'Study':
response_row['Study'],
'module':
response_row['module'],
'item_type':
response_row['item_type'],
'item_name':
item_name,
'item_value':
response_row['item_value'],
'text':
response_row['text']
}
df_post = df_post.append(data, ignore_index=True)
if df_response.empty == False:
last_row = df_post.iloc[-1]
if last_row['item_type'] != 'RESPONSE':
for i, response_row in df_response.iterrows():
data = {
'survey_item_ID':
ut.update_survey_item_id(survey_item_prefix),
'Study': response_row['Study'],
'module': response_row['module'],
'item_type': response_row['item_type'],
'item_name': last_row['item_name'],
'item_value': response_row['item_value'],
'text': response_row['text']
}
df_post = df_post.append(data, ignore_index=True)
return df_post
def main(filename):
extract_source = 0
"""
Parse the input XML file by filename
"""
file = str(filename)
tree = ET.parse(file)
root = tree.getroot()
"""
Create a dictionary containing parent-child relations of the parsed tree
"""
parent_map = dict((c, p) for p in tree.getiterator() for c in p)
ess_questions_instructions = root.findall('.//questionnaire/questions')
ess_answers = root.findall('.//questionnaire/answers')
ess_showcards = root.findall('.//questionnaire/showcards')
df_questionnaire, survey_item_prefix, study, country_language, splitter = set_initial_structures(
filename, extract_source)
ess_special_answer_categories = instantiate_special_answer_category_object(
country_language)
if 'GER_AT' in filename:
ess_special_answer_categories.refuse[0] = 'Verweigert'
ess_special_answer_categories.dont_know[0] = 'Weiß nicht'
if 'GER_CH' in filename:
ess_special_answer_categories.refuse[0] = 'Antwort verweigert'
ess_special_answer_categories.dont_know[0] = 'Weiss nicht'
if 'GER_DE' in filename:
ess_special_answer_categories.refuse[0] = 'Antwort verweigert'
if 'NOR_NO' in filename:
ess_special_answer_categories.refuse[0] = 'Nekter'
df_question_instruction = pd.DataFrame(
columns=['answer_id', 'item_name', 'item_type', 'text'])
df_answers = pd.DataFrame(
columns=['answer_id', 'item_name', 'text', 'item_value'])
item_value = None
df_question_instruction = process_question_instruction_node(
ess_questions_instructions, df_question_instruction, parent_map,
splitter, country_language, extract_source)
df_answers = process_answer_node(ess_answers, df_answers, parent_map,
ess_special_answer_categories,
extract_source)
unique_item_names_question_instruction = df_question_instruction.item_name.unique(
)
for unique_item_name in unique_item_names_question_instruction:
df_question_instruction_by_item_name = df_question_instruction[
df_question_instruction['item_name'].str.lower() ==
unique_item_name.lower()]
df_answers_by_item_name = df_answers[
df_answers['item_name'].str.lower() == unique_item_name.lower()]
module = retrieve_item_module(unique_item_name, study)
last_item_name = ''
for i, row in df_question_instruction_by_item_name.iterrows():
item_name = row['item_name']
if item_name == 'Instruction' or item_name == 'Intro':
item_name = last_item_name
if 'Row ' not in item_name and item_name != 'CI' and item_name != 'outro' and 'istration Note' not in item_name and item_name != 'box':
if df_questionnaire.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
if check_if_segment_is_instruction(row['text'],
country_language):
item_type = 'INSTRUCTION'
else:
item_type = row['item_type']
data = {
'survey_item_ID': survey_item_id,
'Study': study,
'module': module,
'item_type': item_type,
'item_name': item_name,
'item_value': None,
'text': row['text']
}
df_questionnaire = df_questionnaire.append(data,
ignore_index=True)
last_item_name = item_name
if df_answers_by_item_name.empty == False:
for j, row in df_answers_by_item_name.iterrows():
if row['item_value'] == 'None':
item_value = None
else:
item_value = row['item_value']
data = {
'survey_item_ID':
ut.update_survey_item_id(survey_item_prefix),
'Study': study,
'module': module,
'item_type': row['item_type'],
'item_name': item_name,
'item_value': item_value,
'text': row['text']
}
df_questionnaire = df_questionnaire.append(data,
ignore_index=True)
# df_question_instruction.to_csv('questions.csv', encoding='utf-8-sig', index=False)
# df_answers.to_csv('answers.csv', encoding='utf-8-sig', index=False)
df_questionnaire.to_csv(survey_item_prefix[:-1] + '.csv',
encoding='utf-8-sig',
sep='\t',
index=False)
def process_question_segment(raw_item, survey_item_prefix, study, item_name,
df_questionnaire, splitter, country_language):
"""
Extracts and processes the question segments from a raw item.
The question segments are always between the {QUESTION} and {ANSWERS} tags,
for instance:
G2
{QUESTION}
Per a ell és important ser ric.
Vol tenir molts diners i coses cares.
{ANSWERS}
Se sembla molt a mi
Se sembla a mi
Se sembla una mica a mi
Se sembla poc a mi
No se sembla a mi
No se sembla gens a mi
Args:
param1 raw_item (list): raw survey item, retrieved in previous steps.
param2 survey_item_prefix (string): prefix of survey_item_ID.
param3 study (string): metadata parameter about study embedded in the file name.
param4 item_name (string): item_name metadata parameter, retrieved in previous steps.
param5 df_questionnaire (pandas dataframe): pandas dataframe to store questionnaire data.
param6 splitter (NLTK object): sentence segmentation from NLTK library.
param7 country_language (string): country_language metadata, embedded in file name.
Returns:
updated df_questionnaire when new valid question segments are included, or df_questionnaire in the same state it
was when no new valid question segments were included.
"""
print(raw_item)
index_question_tag = raw_item.index('{QUESTION}')
index_answer_tag = raw_item.index('{ANSWERS}')
question_segment = raw_item[index_question_tag + 1:index_answer_tag]
for item in question_segment:
item = clean_text(item)
item = expand_interviewer_abbreviations(item, country_language)
if item != '':
sentences = splitter.tokenize(item)
for sentence in sentences:
if df_questionnaire.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
if check_if_segment_is_instruction(sentence, country_language):
item_type = 'INSTRUCTION'
else:
item_type = 'REQUEST'
data = {
"survey_item_ID": survey_item_id,
'Study': study,
'module': retrieve_item_module(item_name, study),
'item_type': item_type,
'item_name': item_name,
'item_value': None,
'text': sentence
}
df_questionnaire = df_questionnaire.append(data,
ignore_index=True)
return df_questionnaire
def process_intro_segment(raw_item, survey_item_prefix, study, item_name,
df_questionnaire, splitter):
"""
Extracts and processes the introduction segments from a raw item.
The introduction segments are always between the item name and {QUESTION} tag,
for instance:
{INTRO}
Ara m'agradaria fer-li algunes preguntes sobre política i el govern.
B1
{QUESTION}
En quina mesura diria vostè que l'interessa la política?
Vostè diria que l'interessa...
{ANSWERS}
Molt
Bastant
Poc
Gens
Args:
param1 raw_item (list): raw survey item, retrieved in previous steps.
param2 survey_item_prefix (string): prefix of survey_item_ID.
param3 study (string): metadata parameter about study embedded in the file name.
param4 item_name (string): item_name metadata parameter, retrieved in previous steps.
param5 df_questionnaire (pandas dataframe): pandas dataframe to store questionnaire data.
param6 splitter (NLTK object): sentence segmentation from NLTK library.
Returns:
updated df_questionnaire when new valid introduction segments are included, or df_questionnaire in
the same state it was when no new valid introduction segments were included.
"""
index_intro_tag = raw_item.index('{INTRO}')
index_question_tag = raw_item.index('{QUESTION}')
intro_segment = raw_item[index_intro_tag + 1:index_question_tag]
for item in intro_segment:
item = clean_text(item)
if item != '':
sentences = splitter.tokenize(item)
for sentence in sentences:
if df_questionnaire.empty:
survey_item_id = ut.get_survey_item_id(survey_item_prefix)
else:
survey_item_id = ut.update_survey_item_id(
survey_item_prefix)
data = {
"survey_item_ID": survey_item_id,
'Study': study,
'module': retrieve_item_module(item_name, study),
'item_type': 'INTRODUCTION',
'item_name': item_name,
'item_value': None,
'text': sentence
}
df_questionnaire = df_questionnaire.append(data,
ignore_index=True)
return df_questionnaire