Develop Reference

How to write a function that runs certain SQL on certain columns in a PySpark dataframe?

I wrote some code and have this as output. The left side is basically the columns of a dataframe that I'm working with, and the right side is the SQL query that needs to be run on that particular column.
Now I want to write a function that runs the queries on the right on the columns on the left and display the output.
The first picture is basically the values of the 'Column' and 'Query' columns of another dataframe. I used .collect() methods to retrieve those values.
This seemed like a simple problem but I'm still stuck at it. Any idea how to do it?

Using a subset of your data
data_ls = [
('maxpulse', 'select count(*) from {table} where {col} is null'),
('duration', 'select round((count(distinct {col}) / count({col})) * 100) from {table}')
]
data_sdf = spark.sparkContext.parallelize(data_ls).toDF(['column', 'query'])
# +--------+-----------------------------------------------------------------------+
# |column |query |
# +--------+-----------------------------------------------------------------------+
# |maxpulse|select count(*) from {table} where {col} is null |
# |duration|select round((count(distinct {col}) / count({col})) * 100) from {table}|
# +--------+-----------------------------------------------------------------------+
Approach 1: Using UDF
def createQuery(query_string, column_name=None, table_name=None):
if column_name is not None and table_name is None:
fnlquery = query_string.format(col=column_name, table='{table}')
elif column_name is None and table_name is not None:
fnlquery = query_string.format(col='{col}', table=table_name)
elif column_name is not None and table_name is not None:
fnlquery = query_string.format(col=column_name, table=table_name)
else:
fnlquery = query_string
return fnlquery
createQueryUDF = func.udf(createQuery, StringType())
data_sdf. \
withColumn('final_query', createQueryUDF('query', 'column')). \
select('final_query'). \
show(truncate=False)
# +-----------------------------------------------------------------------------+
# |final_query |
# +-----------------------------------------------------------------------------+
# |select count(*) from {table} where maxpulse is null |
# |select round((count(distinct duration) / count(duration)) * 100) from {table}|
# +-----------------------------------------------------------------------------+
Approach 2: Using regexp_replace() sql function
data_sdf. \
withColumn('final_query', func.expr('regexp_replace(query, "[\{]col[\}]", column)')). \
select('final_query'). \
show(truncate=False)
# +-----------------------------------------------------------------------------+
# |final_query |
# +-----------------------------------------------------------------------------+
# |select count(*) from {table} where maxpulse is null |
# |select round((count(distinct duration) / count(duration)) * 100) from {table}|
# +-----------------------------------------------------------------------------+
Similar approach can be used to replace '{table}' with a table name. The final queries from the final_query field can then be collected (using .collect()) and used further to run sql queries.
query_list = data_sdf. \
withColumn('final_query', func.expr('regexp_replace(query, "[\{]col[\}]", column)')). \
select('final_query'). \
rdd.map(lambda x: x.final_query). \
collect()
# ['select count(*) from {table} where maxpulse is null',
# 'select round((count(distinct duration) / count(duration)) * 100) from {table}']
# run the queries by iterating over the list
for query in query_list:
spark.sql(query)

You can put column names and queries to a dictionary:
dct = {'column_name': 'SELECT * FROM table WHERE {col} IS NULL'}
for k, v in dct.items():
q = v.format(col = k)
# spark.sql(q)
print(q)
Output:
SELECT * FROM table WHERE column_name IS NULL

Return Missing Rows from Python SQL Query

Is there anyway i can compare two different databases (postgresl, sql server) and return the missing rows? I am missing one row in the postgresql table that is not in the sql server one and have no clue how to return that answer to me.
I have two connections opened for postgresql (bpo_table_results) and for sql server(rps_table_results)
postgresql table:
date count amount
1/1/21 500 1,234,654.12
sql server table:
date count amount
1/1/21 500 1,234,654.12
1/2/21 4541 3,457,787.24
expected results:
The row in the amount of 3,457,787.24 is missing from your posgresql table.
code:
def queryRPS(sql_server_conn, sql_server_cursor):
rps_item_count_l = []
rps_icl_amt_l = []
rps_table_q_2 = f"""select * from rps..sendfile where processingdate = '{cd}' and datasetname like '%ICL%' """
rps_table_results = sql_server_cursor.execute(rps_table_q_2).fetchall()
for row in rps_table_results:
rps_item_count = row[16]
rps_item_count_l.append(rps_item_count)
rps_icl_amt = row[18]
rps_icl_amt_l.append(rps_icl_amt)
def queryBPO(postgres_conn, postgres_cursor,rps_item_count_l, rps_icl_amt_l):
bpo_results_l = []
rps_results_l = []
for rps_count, rps_amount in zip(rps_item_count_l, rps_icl_amt_l):
rps_amount_f = str(rps_amount).rstrip('0')
rps_amount_f = ("{:,}".format(float(rps_amount_f)))
bpo_icl_awk_q_2 = """select * from ppc_data.icl_awk where num_items = '%s' and
file_total = '%s' """ % (str(rps_count), str(rps_amount_f))
postgres_cursor.execute(bpo_icl_awk_q_2)
bpo_table_results = postgres_cursor.fetchall()
rps_table_q_2 = f"""select * from rps..sendfile where processingdate = '{cd}' and datasetname like '%ICL%' """
rps_table_results = sql_server_cursor.execute(rps_table_q_2).fetchall()
rps_item_count_l, rps_icl_amt_l = queryRPS(sql_server_conn, sql_server_cursor)
queryBPO(postgres_conn, postgres_cursor, rps_item_count_l, rps_icl_amt_l)

Speeding up insertion of point data from netcdf

I've got this netcdf of weather data (one of thousands that require postgresql ingestion). I'm currently capable of inserting each band into a postgis-enabled table at a rate of about 20-23 seconds per band. (for monthly data, there is also daily data that i have yet to test.)
I've heard of different ways of speeding this up using COPY FROM, removing the gid, using ssds, etc... but I'm new to python and have no idea how to store the netcdf data to something I could use COPY FROM or what the best route might be.
If anyone has any other ideas on how to speed this up, please share!
Here is the ingestion script
import netCDF4, psycopg2, time
# Establish connection
db1 = psycopg2.connect("host=localhost dbname=postgis_test user=********** password=********")
cur = db1.cursor()
# Create Table in postgis
print(str(time.ctime()) + " CREATING TABLE")
try:
cur.execute("DROP TABLE IF EXISTS table_name;")
db1.commit()
cur.execute(
"CREATE TABLE table_name (gid serial PRIMARY KEY not null, thedate DATE, thepoint geometry, lon decimal, lat decimal, thevalue decimal);")
db1.commit()
print("TABLE CREATED")
except:
print(psycopg2.DatabaseError)
print("TABLE CREATION FAILED")
rawvalue_nc_file = 'netcdf_file.nc'
nc = netCDF4.Dataset(rawvalue_nc_file, mode='r')
nc.variables.keys()
lat = nc.variables['lat'][:]
lon = nc.variables['lon'][:]
time_var = nc.variables['time']
dtime = netCDF4.num2date(time_var[:], time_var.units)
newtime = [fdate.strftime('%Y-%m-%d') for fdate in dtime]
rawvalue = nc.variables['tx_max'][:]
lathash = {}
lonhash = {}
entry1 = 0
entry2 = 0
lattemp = nc.variables['lat'][:].tolist()
for entry1 in range(lat.size):
lathash[entry1] = lattemp[entry1]
lontemp = nc.variables['lon'][:].tolist()
for entry2 in range(lon.size):
lonhash[entry2] = lontemp[entry2]
for timestep in range(dtime.size):
print(str(time.ctime()) + " " + str(timestep + 1) + "/180")
for _lon in range(lon.size):
for _lat in range(lat.size):
latitude = round(lathash[_lat], 6)
longitude = round(lonhash[_lon], 6)
thedate = newtime[timestep]
thevalue = round(float(rawvalue.data[timestep, _lat, _lon] - 273.15), 3)
if (thevalue > -100):
cur.execute("INSERT INTO table_name (thedate, thepoint, thevalue) VALUES (%s, ST_MakePoint(%s,%s,0), %s)",(thedate, longitude, latitude, thevalue))
db1.commit()
cur.close()
db1.close()
print(" Done!")

If you're certain most of the time is spent in PostgreSQL, and not in any other code of your own, you may want to look at the fast execution helpers, namely cur.execute_values() in your case.
Also, you may want to make sure you're in a transaction, so the database doesn't fall back to an autocommit mode. ("If you do not issue a BEGIN command, then each individual statement has an implicit BEGIN and (if successful) COMMIT wrapped around it.")
Something like this could do the trick -- not tested though.
for timestep in range(dtime.size):
print(str(time.ctime()) + " " + str(timestep + 1) + "/180")
values = []
cur.execute("BEGIN")
for _lon in range(lon.size):
for _lat in range(lat.size):
latitude = round(lathash[_lat], 6)
longitude = round(lonhash[_lon], 6)
thedate = newtime[timestep]
thevalue = round(
float(rawvalue.data[timestep, _lat, _lon] - 273.15), 3
)
if thevalue > -100:
values.append((thedate, longitude, latitude, thevalue))
psycopg2.extras.execute_values(
cur,
"INSERT INTO table_name (thedate, thepoint, thevalue) VALUES %s",
values,
template="(%s, ST_MakePoint(%s,%s,0), %s)"
)
db1.commit()

read_sql query returns an empty dataframe after I pass parameters as a dict in python pandas

I am trying to parameterize some parts of a SQL Query using the below dictionary:
query_params = dict(
{'target':'status',
'date_from':'201712',
'date_to':'201805',
'drform_target':'NPA'
})
sql_data_sample = str("""select *
from table_name
where dt = %(date_to)s
and %(target)s in (%(drform_target)s)
----------------------------------------------------
union all
----------------------------------------------------
(select *,
from table_name
where dt = %(date_from)s
and %(target)s in ('ACT')
order by random() limit 50000);""")
df_data_sample = pd.read_sql(sql_data_sample,con = cnxn,params = query_params)
However this returns a dataframe with no records at all. I am not sure what the error is since no error is being thrown.
df_data_sample.shape
Out[7]: (0, 1211)
The final PostgreSql query would be:
select *
from table_name
where dt = '201805'
and status in ('NPA')
----------------------------------------------------
union all
----------------------------------------------------
(select *
from table_name
where dt = '201712'
and status in ('ACT')
order by random() limit 50000);-- This part of random() is only for running it on my local and not on server.
Below is a small sample of data for replication. The original data has more than a million records and 1211 columns
service_change_3m service_change_6m dt grp_m2 status
0 -2 201805 $50-$75 NPA
0 0 201805 < $25 NPA
0 -1 201805 $175-$200 ACT
0 0 201712 $150-$175 ACT
0 0 201712 $125-$150 ACT
-1 1 201805 $50-$75 NPA
Can someone please help me with this?
UPDATE:
Based on suggestion by #shmee.. I am finally using :
target = 'status'
query_params = dict(
{
'date_from':'201712',
'date_to':'201805',
'drform_target':'NPA'
})
sql_data_sample = str("""select *
from table_name
where dt = %(date_to)s
and {0} in (%(drform_target)s)
----------------------------------------------------
union all
----------------------------------------------------
(select *,
from table_name
where dt = %(date_from)s
and {0} in ('ACT')
order by random() limit 50000);""").format(target)
df_data_sample = pd.read_sql(sql_data_sample,con = cnxn,params = query_params)

Yes, I am quite confident that your issue results from trying to set column names in your query via parameter binding (and %(target)s in ('ACT')) as mentioned in the comments.
This results in your query restricting the result set to records where 'status' in ('ACT') (i.e. Is the string 'status' an element of a list containing only the string 'ACT'?). This is, of course, false, hence no record gets selected and you get an empty result.
This should work as expected:
import psycopg2.sql
col_name = 'status'
table_name = 'public.churn_data'
query_params = {'date_from':'201712',
'date_to':'201805',
'drform_target':'NPA'
}
sql_data_sample = """select *
from {0}
where dt = %(date_to)s
and {1} in (%(drform_target)s)
----------------------------------------------------
union all
----------------------------------------------------
(select *
from {0}
where dt = %(date_from)s
and {1} in ('ACT')
order by random() limit 50000);"""
sql_data_sample = sql.SQL(sql_data_sample).format(sql.Identifier(table_name),
sql.Identifier(col_name))
df_data_sample = pd.read_sql(sql_data_sample,con = cnxn,params = query_params)

How to use python to ETL between databases?

Using psycopg2, I'm able to select data from a table in one PostgreSQL database connection and INSERT it into a table in a second PostgreSQL database connection.
However, I'm only able to do it by setting the exact feature I want to extract, and writing out separate variables for each column I'm trying to insert.
Does anyone know of a good practice for either:
moving an entire table between databases, or
iterating through features while not having to declare variables for every column you want to move
or...?
Here's the script I'm currently using where you can see the selection of a specific feature, and the creation of variables (it works, but this is not a practical method):
import psycopg2
connDev = psycopg2.connect("host=host1 dbname=dbname1 user=postgres password=*** ")
connQa = psycopg2.connect("host=host2 dbname=dbname2 user=postgres password=*** ")
curDev = connDev.cursor()
curQa = connQa.cursor()
sql = ('INSERT INTO "tempHoods" (nbhd_name, geom) values (%s, %s);')
curDev.execute('select cast(geom as varchar) from "CCD_Neighborhoods" where nbhd_id = 11;')
tempGeom = curDev.fetchone()
curDev.execute('select nbhd_name from "CCD_Neighborhoods" where nbhd_id = 11;')
tempName = curDev.fetchone()
data = (tempName, tempGeom)
curQa.execute (sql, data)
#commit transactions
connDev.commit()
connQa.commit()
#close connections
curDev.close()
curQa.close()
connDev.close()
connQa.close()
One other note is that python allows the ability to explicitly work with SQL functions / data type casting, which for us is important as we work with the GEOMETRY data type. Above you can see I'm casting it to TEXT then dumping it into an existing geometry column in the source table - this will work with MSSQL Server, which is a huge feature in the geospatial community...

In your solution (your solution and your question have a different order of statements) change the lines which start with 'sql = ' and the loop before '#commit transactions' comment to
sql_insert = 'INSERT INTO "tempHoods" (nbhd_id, nbhd_name, typology, notes, geom) values '
sql_values = ['(%s, %s, %s, %s, %s)']
data_values = []
# you can make this larger if you want
# ...try experimenting to see what works best
batch_size = 100
sql_stmt = sql_insert + ','.join(sql_values*batch_size) + ';'
for i, row in enumerate(rows, 1):
data_values += row[:5]
if i % batch_size == 0:
curQa.execute (sql_stmt , data_values )
data_values = []
if (i % batch_size != 0):
sql_stmt = sql_insert + ','.join(sql_values*(i % batch_size)) + ';'
curQa.execute (sql_stmt , data_values )
BTW, I don't think you need to commit. You don't begin any transactions. So there should not be any need to commit them. Certainly, you don't need to commit a cursor if all you did was a bunch of selects on it.

Here's my updated code based on Dmitry's brilliant solution:
import psycopg2
connDev = psycopg2.connect("host=host1 dbname=dpspgisdev user=postgres password=****")
connQa = psycopg2.connect("host=host2 dbname=dpspgisqa user=postgres password=****")
curDev = connDev.cursor()
curQa = connQa.cursor()
print "Truncating Source"
curQa.execute('delete from "tempHoods"')
connQa.commit()
#Get Data
curDev.execute('select nbhd_id, nbhd_name, typology, notes, cast(geom as varchar) from "CCD_Neighborhoods";') #cast geom to varchar and insert into geometry column!
rows = curDev.fetchall()
sql_insert = 'INSERT INTO "tempHoods" (nbhd_id, nbhd_name, typology, notes, geom) values '
sql_values = ['(%s, %s, %s, %s, %s)'] #number of columns selecting / inserting
data_values = []
batch_size = 1000 #customize for size of tables...
sql_stmt = sql_insert + ','.join(sql_values*batch_size) + ';'
for i, row in enumerate(rows, 1):
data_values += row[:5] #relates to number of columns (%s)
if i % batch_size == 0:
curQa.execute (sql_stmt , data_values )
connQa.commit()
print "Inserting..."
data_values = []
if (i % batch_size != 0):
sql_stmt = sql_insert + ','.join(sql_values*(i % batch_size)) + ';'
curQa.execute (sql_stmt, data_values)
print "Last Values..."
connQa.commit()
# close connections
curDev.close()
curQa.close()
connDev.close()
connQa.close()