GOR Helper Demo

In [1]:

%%capture
# load the magic extension and imports
%reload_ext nextcode
import pandas as pd
import GOR_query_helper as GQH
%env LOG_QUERY=1

project = "matthew_sampson_hg38"
%env GOR_API_PROJECT={project}

Basic addition, deletions, and overwrite of definitions.¶

In [2]:

qh = GQH.GOR_Query_Helper()
qh.add("def #d1# = 2;")
qh.add("create #c1# = norrows 2 | calc rand random();")
print(qh.defs())
print('Now delete')
qh.delete('#d1#')
print(qh.defs())
print('Now add twice to demonstrate overwrite and now without a semicolon')
qh.add("def #d1# = 1  ")
qh.add("def #d1# = 1+1  ")
print(qh.defs())

def #d1# = 2;
create #c1# = norrows 2 | calc rand random();

Now delete
create #c1# = norrows 2 | calc rand random();

Now add twice to demonstrate overwrite and now without a semicolon
create #c1# = norrows 2 | calc rand random();
def #d1# = 1+1;

Clone multiple queries over to a new query helper, e.g. to work on another branch of the query.¶

In [3]:

qh2 = GQH.GOR_Query_Helper()
qh2.add_many(qh.defs())
print('Here are the cloned defs.')
print(qh2.defs())
print('Now add anoter create statement')
mydefs = qh2.add('create c2 = gor #genes# | top 2')
print(mydefs)

Here are the cloned defs.
create #c1# = norrows 2 | calc rand random();
def #d1# = 1+1;

Now add anoter create statement
create #c1# = norrows 2 | calc rand random();
def #d1# = 1+1;
create c2 = gor #genes# | top 2;

Use the definitons to run a query using the GOR magic-syntax.¶

In [4]:

mydefs = qh.defs()
print(mydefs)

create #c1# = norrows 2 | calc rand random();
def #d1# = 1+1;

In [5]:

%%gor
$mydefs
def #d2# = 2;
norrows 2 | calc d1 #d1# | calc d2 #d2#

Query ran in 0.27 sec
Query fetched 2 rows in 0.01 sec (total time 0.29 sec)
                                             

Out[5]:

	RowNum	d1	d2
0	0	2	2
1	1	2	2

In [8]:

mydefs2 = qh2.defs()

In [9]:

%%gor mypandaframe <<
$mydefs2
gor [c2] | calc dummy #d1# | multimap -cartesian [#c1#]

Query ran in 0.09 sec
Query fetched 4 rows in 0.02 sec (total time 0.11 sec)
                                             

In [10]:

mypandaframe.describe()

Out[10]:

	gene_start	gene_end	dummy	RowNum	rand
count	4.000000	4.000000	4.0	4.00000	4.000000
mean	13135.500000	21989.500000	2.0	0.50000	0.203145
std	1463.582932	8753.207431	0.0	0.57735	0.010190
min	11868.000000	14409.000000	2.0	0.00000	0.194320
25%	11868.000000	14409.000000	2.0	0.00000	0.194320
50%	13135.500000	21989.500000	2.0	0.50000	0.203145
75%	14403.000000	29570.000000	2.0	1.00000	0.211970
max	14403.000000	29570.000000	2.0	1.00000	0.211970

In [ ]:

mypandaframe

In [11]:

import nextcode
qs = nextcode.get_service("queryserver")

In [12]:

myquery = f"""{qh.defs()}
nor [#c1#]"""
print(myquery)

create #c1# = norrows 2 | calc rand random();
def #d1# = 1+1;

nor [#c1#]

In [13]:

qs.execute(myquery).dataframe()

Out[13]:

	RowNum	rand
0	0	0.21197
1	1	0.19432

In [ ]: