Browse Source

updates

master
Yutsuo 2 years ago
parent
commit
f993402f5b
  1. 98
      nb_account_etl.ipynb
  2. 2209
      nb_credit_card_etl.ipynb
  3. 3088
      nb_lab.ipynb
  4. 12
      queries.sql

98
nb_account_etl.ipynb

@ -2,43 +2,16 @@
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# import csv\n",
"\n",
"# with open(\"./documents/extrato.csv\", newline=\"\", encoding=\"latin\") as csvfile:\n",
"# spamreader = csv.reader(csvfile)\n",
"# for row in spamreader:\n",
"# print(\", \".join(row))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"# import csv\n",
"\n",
"# with open(\"./documents/extrato.csv\", newline=\"\", encoding=\"latin\") as csvfile:\n",
"# spamreader = csv.reader(csvfile)\n",
"# csv_list = list(spamreader)\n",
"\n",
"# print(csv_list[1:])\n",
"# print(csv_list[1:][0])\n",
"# print(csv_list[1:][0][0])\n",
"# print(csv_list[1:][0][0].split(sep=\"/\"))\n",
"# print(csv_list[1:][0][0].split(sep=\"/\")[0])\n",
"\n",
"# for item in csv_list[1:]:\n",
"# print(item)"
"insert_query = \"INSERT IGNORE INTO default.TRANSACTION (ID, TDATE, ACCOUNT_ID, MEMO, COUNTRY, OUTFLOW, INFLOW, OWNER_ID, INSTALLMENT_NR, INSTALLMENT_TT, BILL, CREATED, UPDATED) VALUES ( %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s )\""
]
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
@ -78,6 +51,7 @@
" else:\n",
" tInstallmentNr = None\n",
" tInstallmentTt = None\n",
" tBill = \"CC\"\n",
" tCreated = str(datetime.now(tz=None))\n",
" tUpdated = None\n",
"\n",
@ -98,26 +72,28 @@
" tOwner,\n",
" tInstallmentNr,\n",
" tInstallmentTt,\n",
" tBill,\n",
" tCreated,\n",
" tUpdated,\n",
" )\n",
" )\n",
"\n",
" print(\"DONE\")\n",
" return insert_bulk"
]
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"insert_query = \"INSERT IGNORE INTO default.TRANSACTION (ID, TDATE, ACCOUNT_ID, MEMO, COUNTRY, OUTFLOW, INFLOW, OWNER_ID, INSTALLMENT_NR, INSTALLMENT_TT, CREATED, UPDATED) VALUES ( %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s )\""
"# Test\n",
"# build_account_input(\"./documents/extrato-30d.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@ -144,7 +120,17 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"# Test\n",
"# db_insert(build_account_input(\"./documents/extrato-30d.csv\"))"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
@ -164,14 +150,52 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"executor(): Error\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1ADDF0>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1ADDF0>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1D61E0>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1D77D0>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BAD26C00>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1D5820>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1D5820>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1708F0>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1D5820>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC137B00>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC208200>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC23FFB0>\n",
"DONE!\n",
"DONE\n",
"CONNECTED! <mysql.connector.connection_cext.CMySQLConnection object at 0x000001A7BC1D5880>\n",
"DONE!\n",
"EXECUTOR COMPLETED.\n"
]
}

2209
nb_credit_card_etl.ipynb

File diff suppressed because one or more lines are too long

3088
nb_lab.ipynb

File diff suppressed because it is too large Load Diff

12
queries.sql

@ -5,3 +5,15 @@ TRUNCATE TABLE `default`.`TRANSACTION`;
UPDATE `TRANSACTION` SET MEMO = TRIM(MEMO)
ALTER TABLE `default`.SUBCATEGORY MODIFY COLUMN UPDATED datetime ON UPDATE CURRENT_TIMESTAMP NULL;
SELECT * FROM `default`.`TRANSACTION` t WHERE INSTALLMENT_TT IS NOT NULL;
SELECT * FROM `default`.`TRANSACTION` t WHERE t.ID NOT IN default.CATEGORIZED_TRANSACTIONS.ID;
SELECT *
FROM TRANSACTION t
LEFT JOIN CATEGORIZED_TRANSACTIONS ct
ON t.ID = ct.TRANSACTION_ID
WHERE ct.TRANSACTION_ID IS NULL;
SELECT * FROM default.TRANSACTION t LEFT JOIN default.CATEGORIZED_TRANSACTIONS ct ON t.ID = ct.TRANSACTION_ID WHERE ct.TRANSACTION_ID IS NULL;
Loading…
Cancel
Save