Run computations and export data

import decentriq_platform as dq
user_email = "@@ YOUR EMAIL HERE @@"
api_token = "@@ YOUR TOKEN HERE @@"

client = dq.create_client(user_email, api_token)
enclave_specs = dq.enclave_specifications.latest()

Setup Script

If you want to test this functionality and don't have a clean room already set up, you can use this script to create an appropriate environment to test the rest of this guide with.

import decentriq_platform as dq
from decentriq_platform.analytics import *

USER_EMAIL = "@@ YOUR EMAIL HERE @@"
API_TOKEN = "@@ YOUR TOKEN HERE @@"

client = dq.create_client(USER_EMAIL, API_TOKEN)

builder = AnalyticsDcrBuilder(client=client)
builder.\
    with_name("My DCR").\
    with_owner(USER_EMAIL).\
    with_description("My test DCR")

builder.add_node_definition(
    RawDataNodeDefinition(name="input_data_node", is_required=True)
)

columns = [
    Column(
        name="name",
        format_type=FormatType.STRING,
        is_nullable=False,
    ),
    Column(
        name="salary",
        format_type=FormatType.FLOAT,
        is_nullable=False,
    ),
]


builder.add_node_definition(
    TableDataNodeDefinition(
        name="salary_data", columns=columns, is_required=True
    )
)

my_script_content = b"""
with open("/input/input_data_node", "r") as input_file:
    input_data = input_file.read()
with open("/output/uppercase.txt", "w") as output_file:
    output_file.write(input_data.upper())
"""
builder.add_node_definition(
    PythonComputeNodeDefinition(
        name="uppercase_text_node",
        script=my_script_content,
        dependencies=["input_data_node"]
    )
)

my_query_content = """
    SELECT SUM(salary) FROM salary_data
"""
builder.add_node_definition(
    SqliteComputeNodeDefinition(
        name="sum_salary",
        query=my_query_content,
        dependencies=["salary_data"]
    )
)

builder.add_participant(
    USER_EMAIL,
    data_owner_of=["input_data_node", "salary_data"],
    analyst_of=["uppercase_text_node", "sum_salary"]
)

dcr_definition = builder.build()
dcr = client.publish_analytics_dcr(dcr_definition)

import io

data = io.BytesIO("""Alice,10.0
Bob,5.0
John,14.0
""".encode())
data_node = dcr.get_node("salary_data")
data_node.upload_and_publish_dataset(data, key=dq.Key(), name="my_salary_data.csv")

data = io.BytesIO(b"hello world")
data_node = dcr.get_node("input_data_node")
data_node.upload_and_publish_dataset(data, dq.Key(), "my-data.txt")

DCR_ID = dcr.id
print(DCR_ID)

Run and retrieve tabular computation results

Computations that take a table as input and return a table as output are SQL and Synthetic data.

import decentriq_platform as dq

user_email = "@@ YOUR EMAIL HERE @@"
api_token = "@@ YOUR TOKEN HERE @@"
DCR_ID = "@@ YOUR ANALYTICS DCR ID HERE @@"

client = dq.create_client(user_email, api_token)
dcr = client.retrieve_analytics_dcr(DCR_ID)
sql_node = dcr.get_node("sum_salary")
results_csv = sql_node.run_computation_and_get_results_as_string()

print("Computation result:\n\n", results_csv)

Run and retrieve script computation results

Python and R computation nodes may take any input and produce any point. The download results are a zip file. The zip file will contain the contents of the entire /output directory.

import decentriq_platform as dq

user_email = "@@ YOUR EMAIL HERE @@"
api_token = "@@ YOUR TOKEN HERE @@"

client = dq.create_client(user_email, api_token)
dcr = client.retrieve_analytics_dcr(DCR_ID)
python_node = dcr.get_node("uppercase_text_node")
results = python_node.run_computation_and_get_results_as_zip()
result_txt = results.read("uppercase.txt").decode()

print("Computation result:\n\n", result_txt)

Run and retrieve tabular computation results​

Run and retrieve script computation results​

Run and retrieve tabular computation results

Run and retrieve script computation results