We Keep Coding

Delete values from db2 table if exist in schema in Python

i want to ask for a little help about my problem. I have sql query that get all the tables from some schema and put those tables in a list in Python. For example:
tablesList = ['TABLE1','TABLE2',...]
After i get this list of tables that i want i go one more time through each table in a for loop for example:
for t in range(len(tables)):
table = tables[t]
...
#here i want to check if this table exist in some db2 schema and if exist delete content
#of this table, otherwise go with next table check and don't delete content
Query for checking will be:
sql = """SELECT COUNT(*) FROM SYSIBM.SYSTABLES
WHERE TYPE = 'T'
AND CREATOR = 'MY_SCHEMA'
AND NAME = '{table}';""".format(table = table)
cursor.execute(sql)
rows_count = cursor.fetchone()
if rows_count is None:
pass
else:
delete...

How to upsert pandas DataFrame to PostgreSQL table?

I've scraped some data from web sources and stored it all in a pandas DataFrame. Now, in order harness the powerful db tools afforded by SQLAlchemy, I want to convert said DataFrame into a Table() object and eventually upsert all data into a PostgreSQL table. If this is practical, what is a workable method of going about accomplishing this task?

Update: You can save yourself some typing by using this method.
If you are using PostgreSQL 9.5 or later you can perform the UPSERT using a temporary table and an INSERT ... ON CONFLICT statement:
import sqlalchemy as sa
# …
with engine.begin() as conn:
# step 0.0 - create test environment
conn.exec_driver_sql("DROP TABLE IF EXISTS main_table")
conn.exec_driver_sql(
"CREATE TABLE main_table (id int primary key, txt varchar(50))"
)
conn.exec_driver_sql(
"INSERT INTO main_table (id, txt) VALUES (1, 'row 1 old text')"
)
# step 0.1 - create DataFrame to UPSERT
df = pd.DataFrame(
[(2, "new row 2 text"), (1, "row 1 new text")], columns=["id", "txt"]
)
# step 1 - create temporary table and upload DataFrame
conn.exec_driver_sql(
"CREATE TEMPORARY TABLE temp_table AS SELECT * FROM main_table WHERE false"
)
df.to_sql("temp_table", conn, index=False, if_exists="append")
# step 2 - merge temp_table into main_table
conn.exec_driver_sql(
"""\
INSERT INTO main_table (id, txt)
SELECT id, txt FROM temp_table
ON CONFLICT (id) DO
UPDATE SET txt = EXCLUDED.txt
"""
)
# step 3 - confirm results
result = conn.exec_driver_sql("SELECT * FROM main_table ORDER BY id").all()
print(result) # [(1, 'row 1 new text'), (2, 'new row 2 text')]

I have needed this so many times, I ended up creating a gist for it.
The function is below, it will create the table if it is the first time persisting the dataframe and will update the table if it already exists:
import pandas as pd
import sqlalchemy
import uuid
import os
def upsert_df(df: pd.DataFrame, table_name: str, engine: sqlalchemy.engine.Engine):
"""Implements the equivalent of pd.DataFrame.to_sql(..., if_exists='update')
(which does not exist). Creates or updates the db records based on the
dataframe records.
Conflicts to determine update are based on the dataframes index.
This will set unique keys constraint on the table equal to the index names
1. Create a temp table from the dataframe
2. Insert/update from temp table into table_name
Returns: True if successful
"""
# If the table does not exist, we should just use to_sql to create it
if not engine.execute(
f"""SELECT EXISTS (
SELECT FROM information_schema.tables
WHERE table_schema = 'public'
AND table_name = '{table_name}');
"""
).first()[0]:
df.to_sql(table_name, engine)
return True
# If it already exists...
temp_table_name = f"temp_{uuid.uuid4().hex[:6]}"
df.to_sql(temp_table_name, engine, index=True)
index = list(df.index.names)
index_sql_txt = ", ".join([f'"{i}"' for i in index])
columns = list(df.columns)
headers = index + columns
headers_sql_txt = ", ".join(
[f'"{i}"' for i in headers]
) # index1, index2, ..., column 1, col2, ...
# col1 = exluded.col1, col2=excluded.col2
update_column_stmt = ", ".join([f'"{col}" = EXCLUDED."{col}"' for col in columns])
# For the ON CONFLICT clause, postgres requires that the columns have unique constraint
query_pk = f"""
ALTER TABLE "{table_name}" DROP CONSTRAINT IF EXISTS unique_constraint_for_upsert;
ALTER TABLE "{table_name}" ADD CONSTRAINT unique_constraint_for_upsert UNIQUE ({index_sql_txt});
"""
engine.execute(query_pk)
# Compose and execute upsert query
query_upsert = f"""
INSERT INTO "{table_name}" ({headers_sql_txt})
SELECT {headers_sql_txt} FROM "{temp_table_name}"
ON CONFLICT ({index_sql_txt}) DO UPDATE
SET {update_column_stmt};
"""
engine.execute(query_upsert)
engine.execute(f"DROP TABLE {temp_table_name}")
return True

Here is my code for bulk insert & insert on conflict update query for postgresql from pandas dataframe:
Lets say id is unique key for both postgresql table and pandas df and you want to insert and update based on this id.
import pandas as pd
from sqlalchemy import create_engine, text
engine = create_engine(postgresql://username:pass#host:port/dbname)
query = text(f"""
INSERT INTO schema.table(name, title, id)
VALUES {','.join([str(i) for i in list(df.to_records(index=False))])}
ON CONFLICT (id)
DO UPDATE SET name= excluded.name,
title= excluded.title
""")
engine.execute(query)
Make sure that your df columns must be same order with your table.
EDIT 1:
Thanks to Gord Thompson's comment, I realized that this query won't work if there is single quote in columns. Therefore here is a fix if there is single quote in columns:
import pandas as pd
from sqlalchemy import create_engine, text
df.name = df.name.str.replace("'", "''")
df.title = df.title.str.replace("'", "''")
engine = create_engine(postgresql://username:pass#host:port/dbname)
query = text("""
INSERT INTO author(name, title, id)
VALUES %s
ON CONFLICT (id)
DO UPDATE SET name= excluded.name,
title= excluded.title
""" % ','.join([str(i) for i in list(df.to_records(index=False))]).replace('"', "'"))
engine.execute(query)

Consider this function if your DataFrame and SQL Table contain the same column names and types already.
Advantages:
Good if you have a long dataframe to insert. (Batching)
Avoid writing long sql statement in your code.
Fast
.
from sqlalchemy import Table
from sqlalchemy.engine.base import Engine as sql_engine
from sqlalchemy.dialects.postgresql import insert
from sqlalchemy.ext.automap import automap_base
import pandas as pd
def upsert_database(list_input: pd.DataFrame, engine: sql_engine, table: str, schema: str) -> None:
if len(list_input) == 0:
return None
flattened_input = list_input.to_dict('records')
with engine.connect() as conn:
base = automap_base()
base.prepare(engine, reflect=True, schema=schema)
target_table = Table(table, base.metadata,
autoload=True, autoload_with=engine, schema=schema)
chunks = [flattened_input[i:i + 1000] for i in range(0, len(flattened_input), 1000)]
for chunk in chunks:
stmt = insert(target_table).values(chunk)
update_dict = {c.name: c for c in stmt.excluded if not c.primary_key}
conn.execute(stmt.on_conflict_do_update(
constraint=f'{table}_pkey',
set_=update_dict)
)

If you already have a pandas dataframe you could use df.to_sql to push the data directly through SQLAlchemy
from sqlalchemy import create_engine
#create a connection from Postgre URI
cnxn = create_engine("postgresql+psycopg2://username:password#host:port/database")
#write dataframe to database
df.to_sql("my_table", con=cnxn, schema="myschema")

How can I handle errors inside of a for loop inside of a cx_Oracle connection?

here's a run down of what I'd like to do: I have a list of table names, and I want to run sql against an oracle database and pull back the table name and row count for every table in my table list. However, not every table name in my list of table names is necessarily actually in the database. This causes my code to throw a database error. What I would like to do, is whenever I come to a table name that is not in the database, I create a dataframe that contains the table name and instead of count(*), there's some text that says 'table not found', or something similar. At the end of the loop I'm concatenating all of the dataframes into one dataframe. The overall goal here is to validate that certain tables exist and that they have the expected row counts.
query_list=[]
df_List=[]
connstr= '%s/%s#%s' %(username, password, server)
conn = cx_Oracle.connect(connstr)
with conn:
query_list = ["SELECT '%s' as tbl, count(*) FROM %s." %(elm, database) +elm for elm in table_list]
df_List = [pd.read_sql(elm,conn) for elm in query_list]
df = pd.concat(df_List)

Consider try/except handling to return query output or table not found output:
def get_table_count(sql, conn, elm):
try:
return pd.read_sql(sql, conn)
except:
return pd.DataFrame({'tbl': elm, 'note': 'table not found'}, index = [0])
with conn:
sql = "SELECT '{t}' as tbl, count(*) as table_count FROM {d}.{t}"
df_List = [get_table_count(sql.format(t = elm, d = database), conn, elm) \
for elm in table_list]
df = pd.concat(df_List, ignore_index = True)

Get a list of all the Table Names which are in the DB, then create a loop to query each Table to get the row count.
Here is a SQL statement to get a list of all Tables in an Oracle DB:
SQL:
SELECT DISTINCT TABLE_NAME FROM ALL_TAB_COLUMNS ORDER BY TABLE_NAME ASC;
Python (to make list of tables you want row counts for and which exist in the DB):
list(set(tables_that_exist_in_DB) - (set(tables_that_exist_in_DB) - set(list_of_tables_you_want)))

Get table name for field in database result in Python (PostgreSQL)

I'm trying to get table name for field in result set that I got from database (Python, Postgres). There is a function in PHP to get table name for field, I used it and it works so I know it can be done (in PHP). I'm looking for similar function in Python.
pg_field_table() function in PHP gets results and field number and "returns the name of the table that field belongs to". That is exactly what I need, but in Python.
Simple exaple - create tables, insert rows, select data:
CREATE TABLE table_a (
id INT,
name VARCHAR(10)
);
CREATE TABLE table_b (
id INT,
name VARCHAR(10)
);
INSERT INTO table_a (id, name) VALUES (1, 'hello');
INSERT INTO table_b (id, name) VALUES (1, 'world');
When using psycopg2 or sqlalchemy I got right data and right field names but without information about table name.
import psycopg2
query = '''
SELECT *
FROM table_a A
LEFT JOIN table_b B
ON A.id = B.id
'''
con = psycopg2.connect('dbname=testdb user=postgres password=postgres')
cur = con.cursor()
cur.execute(query)
data = cur.fetchall()
print('fields', [desc[0] for desc in cur.description])
print('data', data)
The example above prints field names. The output is:
fields ['id', 'name', 'id', 'name']
data [(1, 'hello', 1, 'world')]
I know that there is cursor.description, but it does not contain table name, just the field name.
What I need - some way to retrieve table names for fields in result set when using raw SQL to query data.
EDIT 1: I need to know if "hello" came from "table_a" or "table_b", both fields are named same ("name"). Without information about table name you can't tell in which table the value is.
EDIT 2: I know that there are some workarounds like SQL aliases: SELECT table_a.name AS name1, table_b.name AS name2 but I'm really asking how to retrieve table name from result set.
EDIT 3: I'm looking for solution that allows me to write any raw SQL query, sometimes SELECT *, sometimes SELECT A.id, B.id ... and after executing that query I will get field names and table names for fields in the result set.

It is necessary to query the pg_attribute catalog for the table qualified column names:
query = '''
select
string_agg(format(
'%%1$s.%%2$s as "%%1$s.%%2$s"',
attrelid::regclass, attname
) , ', ')
from pg_attribute
where attrelid = any (%s::regclass[]) and attnum > 0 and not attisdropped
'''
cursor.execute(query, ([t for t in ('a','b')],))
select_list = cursor.fetchone()[0]
query = '''
select {}
from a left join b on a.id = b.id
'''.format(select_list)
print cursor.mogrify(query)
cursor.execute(query)
print [desc[0] for desc in cursor.description]
Output:
select a.id as "a.id", a.name as "a.name", b.id as "b.id", b.name as "b.name"
from a left join b on a.id = b.id
['a.id', 'a.name', 'b.id', 'b.name']

Getting the id of the last record inserted for Postgresql SERIAL KEY with Python

I am using SQLAlchemy without the ORM, i.e. using hand-crafted SQL statements to directly interact with the backend database. I am using PG as my backend database (psycopg2 as DB driver) in this instance - I don't know if that affects the answer.
I have statements like this,for brevity, assume that conn is a valid connection to the database:
conn.execute("INSERT INTO user (name, country_id) VALUES ('Homer', 123)")
Assume also that the user table consists of the columns (id [SERIAL PRIMARY KEY], name, country_id)
How may I obtain the id of the new user, ideally, without hitting the database again?

You might be able to use the RETURNING clause of the INSERT statement like this:
result = conn.execute("INSERT INTO user (name, country_id) VALUES ('Homer', 123)
RETURNING *")
If you only want the resulting id:
result = conn.execute("INSERT INTO user (name, country_id) VALUES ('Homer', 123)
RETURNING id")
[new_id] = result.fetchone()

User lastrowid
result = conn.execute("INSERT INTO user (name, country_id) VALUES ('Homer', 123)")
result.lastrowid

Current SQLAlchemy documentation suggests
result.inserted_primary_key should work!

Python + SQLAlchemy
after commit, you get the primary_key column id (autoincremeted) updated in your object.
db.session.add(new_usr)
db.session.commit() #will insert the new_usr data into database AND retrieve id
idd = new_usr.usrID # usrID is the autoincremented primary_key column.
return jsonify(idd),201 #usrID = 12, correct id from table User in Database.

this question has been asked many times on stackoverflow and no answer I have seen is comprehensive. Googling 'sqlalchemy insert get id of new row' brings up a lot of them.
There are three levels to SQLAlchemy.
Top: the ORM.
Middle: Database abstraction (DBA) with Table classes etc.
Bottom: SQL using the text function.
To an OO programmer the ORM level looks natural, but to a database programmer it looks ugly and the ORM gets in the way. The DBA layer is an OK compromise. The SQL layer looks natural to database programmers and would look alien to an OO-only programmer.
Each level has it own syntax, similar but different enough to be frustrating. On top of this there is almost too much documentation online, very hard to find the answer.
I will describe how to get the inserted id AT THE SQL LAYER for the RDBMS I use.
Table: User(user_id integer primary autoincrement key, user_name string)
conn: Is a Connection obtained within SQLAlchemy to the DBMS you are using.
SQLite
======
insstmt = text(
'''INSERT INTO user (user_name)
VALUES (:usernm) ''' )
# Execute within a transaction (optional)
txn = conn.begin()
result = conn.execute(insstmt, usernm='Jane Doe')
# The id!
recid = result.lastrowid
txn.commit()
MS SQL Server
=============
insstmt = text(
'''INSERT INTO user (user_name)
OUTPUT inserted.record_id
VALUES (:usernm) ''' )
txn = conn.begin()
result = conn.execute(insstmt, usernm='Jane Doe')
# The id!
recid = result.fetchone()[0]
txn.commit()
MariaDB/MySQL
=============
insstmt = text(
'''INSERT INTO user (user_name)
VALUES (:usernm) ''' )
txn = conn.begin()
result = conn.execute(insstmt, usernm='Jane Doe')
# The id!
recid = conn.execute(text('SELECT LAST_INSERT_ID()')).fetchone()[0]
txn.commit()
Postgres
========
insstmt = text(
'''INSERT INTO user (user_name)
VALUES (:usernm)
RETURNING user_id ''' )
txn = conn.begin()
result = conn.execute(insstmt, usernm='Jane Doe')
# The id!
recid = result.fetchone()[0]
txn.commit()

result.inserted_primary_key
Worked for me. The only thing to note is that this returns a list that contains that last_insert_id.

Make sure you use fetchrow/fetch to receive the returning object
insert_stmt = user.insert().values(name="homer", country_id="123").returning(user.c.id)
row_id = await conn.fetchrow(insert_stmt)

For Postgress inserts from python code is simple to use "RETURNING" keyword with the "col_id" (name of the column which you want to get the last inserted row id) in insert statement at end
syntax -
from sqlalchemy import create_engine
conn_string = "postgresql://USERNAME:PSWD#HOSTNAME/DATABASE_NAME"
db = create_engine(conn_string)
conn = db.connect()
INSERT INTO emp_table (col_id, Name ,Age)
VALUES(3,'xyz',30) RETURNING col_id;
or
(if col_id column is auto increment)
insert_sql = (INSERT INTO emp_table (Name ,Age)
VALUES('xyz',30) RETURNING col_id;)
result = conn.execute(insert_sql)
[last_row_id] = result.fetchone()
print(last_row_id)
#output = 3
ex -