Primera fase lista: Output CSV

action_flow/fase1_extract.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# # Imports
+
+# In[29]:
+
+
+import pandas as pd
+import os 
+import sys
+
+
+# In[30]:
+
+
+module_path = os.path.abspath(os.path.join('..'))
+
+# Add to sys.path if not already present
+if module_path not in sys.path:
+    sys.path.append(module_path)
+    print(module_path)
+
+from extraccion import agentes_entidades
+
+
+# # Variables
+
+# In[31]:
+
+
+INPUT_FOLDER = f"{module_path}/input/Preguntas Categoricas/"
+OUTPUT_FOLDER = f"{module_path}/output/fase1"
+FILES_TO_PROCESS = os.listdir(INPUT_FOLDER)
+DELIMITER = "|^"
+DIC_QUESTIONS = {
+    "Encuesta_MediaG01Q02.csv":agentes_entidades.extractor_pre_1
+    # COMPLETAR RESTO
+}
+
+
+# # Functions
+
+# In[32]:
+
+
+def extract_answers(answers):
+    answer_formated = ""
+    iterator_answers = answers.acciones
+    for item in iterator_answers:
+        answer_formated+=f"{item.accion}{DELIMITER}"
+    return answer_formated
+
+
+# In[33]:
+
+
+def format_answer(dataframe,function):
+    dataframe["respuestas_formato"] = None
+    for index, row in dataframe.iterrows():
+        answers = function (row['respuesta'])
+        answer_to_insert = extract_answers(answers)
+        dataframe.loc[index,'respuestas_formato'] = answer_to_insert
+
+
+# In[34]:
+
+
+def format_all_answers(Dic_questions):
+    for key,value in Dic_questions.items():
+        question_dataframe = pd.read_csv(INPUT_FOLDER+"/"+key)
+        format_answer(question_dataframe, value)
+        question_dataframe.to_csv(OUTPUT_FOLDER+"/"+key)
+
+
+# In[35]:
+
+
+format_all_answers(DIC_QUESTIONS)
+