Shume shume keq data input. Done!

convert.py

@@ -3,6 +3,7 @@ from os import listdir
 from os.path import isfile, join
 from docx.api import Document
 from enum import Enum
+from datetime import datetime
 
 
 class Klinika(Enum):
@@ -12,7 +13,7 @@ class Klinika(Enum):
 
 
 def convert(klinika: str):
-    print(klinika)
+    print(f"Filloi {klinika} me {datetime.now()}")
     columns = []
     filtered_columns = []
     docx_path = './Word/'
@@ -26,6 +27,14 @@ def convert(klinika: str):
     for path in list_paths:
         document = Document(path)
         for table in document.tables:
+            if "urgjenca_2016.docx" in path:
+                grid = table._tbl.find("w:tblGrid", table._tbl.nsmap)
+                for cell in table.column_cells(2):
+                    cell._tc.getparent().remove(cell._tc)
+                col_elem = grid[2]
+                grid.remove(col_elem)
+                print(f"U FSHI PAVIONI")
+
             for cell in table.rows[0].cells:
                 columns.append(cell.text.strip().replace('\n', ' '))
             RowA = table.rows[0]
@@ -34,16 +43,17 @@ def convert(klinika: str):
             for row in table.rows:
                 text = [cell.text for cell in row.cells]
                 df = df.append([text], ignore_index=True)
-        print(f'{path} Done')
+        print(f"Mbaroi {path} me {datetime.now()}")
 
     for word in columns:
         if word not in filtered_columns:
             filtered_columns.append(word)
     print(f'{len(filtered_columns)} Columns found')
     print('writing to excel...')
+    print(f"Perfundoi {klinika} me {datetime.now()}")
     df.columns = filtered_columns
     excel_path = join(xlsx_path, f"raw_{klinika}_2016-2019.xlsx")
     df.to_excel(excel_path, index=False)
 
 
-convert(Klinika.OBS.value)
+convert(Klinika.URGJENCA.value)

llogarit_moshen.py

@@ -37,7 +37,7 @@ def konverto_data(datat: str, i: int):
     # i +=1
     datat_pattern = "%d/%m/%y"
     try:
-        if "2572/81" in datat or datat == "?" or datat == "nan" or datat == "Pensionist" or datat == "15/13/92" or datat == "29/2/94":
+        if "2572/81" in datat or datat == "?" or datat == "nan" or datat == "Pensionist" or datat == "15/13/92" or datat == "29/2/94" or datat == "20/0/81" or "Colicaabdpd" in datat or "2379/11" in datat or "2710/44" in datat or "31/4/56" in datat or "11/1/199" in datat or "27/7/889" in datat or "31/9/84" in datat:
             df.iat[i, df.columns.get_loc('MOSHA')] = "ERROR"
             df.iat[i, df.columns.get_loc('ERROR')] = datat
             return ""
@@ -53,7 +53,6 @@ def konverto_data(datat: str, i: int):
             return "DEKLARUAR"
         if datat.endswith('/'):
             datat = datat[:-1]
-            print(datat)
         datat = datat.split('/')
         if len(datat) == 1:
             datat.insert(0, '1')
@@ -65,14 +64,17 @@ def konverto_data(datat: str, i: int):
         if (len(datat)) > 2:
             if datat[2] in ['1', '2', '3', '4', '5', '6', '7', '8', '9']:
                 datat[2] = f"0{datat[2]}"
-            if int(datat[2]) > 99:
-                datat_pattern = "%d/%m/%Y"
-            # Detyrohem te bej nje supozim qe nuk ka datelindje 1919 e poshte, bazuar mbi datat e shtrimit qe jane max 2019
-            elif int(datat[2]) > 19 and int(datat[2]) < 100:
-                datat[2] = f"19{datat[2]}"
-                datat_pattern = "%d/%m/%Y"
-            else:
-                datat_pattern = "%d/%m/%y"
+            try:
+                if int(datat[2]) > 99:
+                    datat_pattern = "%d/%m/%Y"
+                # Detyrohem te bej nje supozim qe nuk ka datelindje 1919 e poshte, bazuar mbi datat e shtrimit qe jane max 2019
+                elif int(datat[2]) > 19 and int(datat[2]) < 100:
+                    datat[2] = f"19{datat[2]}"
+                    datat_pattern = "%d/%m/%Y"
+                else:
+                    datat_pattern = "%d/%m/%y"
+            except:
+                print(i, datat)
         datat = "/".join(datat)
         try:
             datat = datetime.strptime(datat, datat_pattern)
@@ -92,6 +94,7 @@ def pastro_string(datat: str, i: int):
     datat = datat.replace(" ", "")
     datat = datat.replace(".", "/")
     datat = datat.replace("'", "")
+
     datat = konverto_data(datat, i)
     return datat
 
@@ -120,11 +123,18 @@ for index, row in df.iterrows():
     datelindja_korigj.append(datelindja)
     i += 1
 
+
 df.insert(len(df.columns), "DT_SHTRIMI_KORIGJ", data_shtri_korigj)
 df.insert(len(df.columns), "DATELINDJA_KORIGJ", datelindja_korigj)
 
+df.drop(columns=df.columns[0], axis=1, inplace=True)
 df.drop(columns=df.columns[0], axis=1, inplace=True)
 
+cols = df.columns.tolist() 
+index = cols.index('MOSHA')
+del cols[index]
+cols.insert(3,'MOSHA')
+df = df[cols]
 current_GMT = time.gmtime()
 ts = calendar.timegm(current_GMT)