From 42d305be78ef3eeba16e7ec62782ca4dd7214056 Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 13:18:11 +0000
Subject: [PATCH 01/15] first iteration

---
 .coveragerc                     |   2 +
 README.md                       |  35 ++++++-
 cloud_function/main.py          |  21 ++++
 cloud_function/model.py         | 167 ++++++++++++++++++++++++++++++++
 cloud_function/query.py         | 145 +++++++++++++++++++++++++++
 cloud_function/repository.py    | 123 +++++++++++++++++++++++
 cloud_function/requirements.txt |   3 +
 cloud_function/services.py      |  20 ++++
 tests/__init__.py               |  21 ++++
 tests/conftest.py               |  44 +++++++++
 tests/data/cashflows.py         |  11 +++
 tests/test_model.py             | 131 +++++++++++++++++++++++++
 tests/test_services.py          |  32 ++++++
 13 files changed, 754 insertions(+), 1 deletion(-)
 create mode 100644 .coveragerc
 create mode 100644 cloud_function/main.py
 create mode 100644 cloud_function/model.py
 create mode 100644 cloud_function/query.py
 create mode 100644 cloud_function/repository.py
 create mode 100644 cloud_function/requirements.txt
 create mode 100644 cloud_function/services.py
 create mode 100644 tests/__init__.py
 create mode 100644 tests/conftest.py
 create mode 100644 tests/data/cashflows.py
 create mode 100644 tests/test_model.py
 create mode 100644 tests/test_services.py

diff --git a/.coveragerc b/.coveragerc
new file mode 100644
index 0000000..3dbfbb4
--- /dev/null
+++ b/.coveragerc
@@ -0,0 +1,2 @@
+[run]
+omit = tests/*
\ No newline at end of file
diff --git a/README.md b/README.md
index a07dd40..1db2a20 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,35 @@
 # irr_calculator
-Python solution that calculates irr for a set of accounts
+## Introduction
+Python solution that calculates irr for a set of entities.
+
+## Execution
+On this section you will find how to run the code locally.
+
+### Python environment
+To execute the solution with your machine you will need an environment with python 3.10.0 and the libraries listed in 
+requirements.txt. In case you do not have such environment, you can create it as follows with conda:
+ 
+```
+conda create -n [] python=3.10.0 pip
+pip install -r cloud_function/requirements.txt
+```
+
+### Testing
+
+To execute the Python tests use next command on the CLI:
+
+```commandline
+python -m pytest -vv
+```
+
+It is needed a _.env_ file with the next settings:
+
+```
+PROJECT=
+SOURCE_TABLE=
+DESTINATION_TABLE=
+DATASET=
+```
+
+You will also need to provide a Service Account credentials or to use a user account with the right permissions to 
+interact with BigQuery.
\ No newline at end of file
diff --git a/cloud_function/main.py b/cloud_function/main.py
new file mode 100644
index 0000000..a79183d
--- /dev/null
+++ b/cloud_function/main.py
@@ -0,0 +1,21 @@
+from cloud_function import repository, services
+
+
+def func_entry_point(event, context):
+    """
+    Entry point for the application. This function initializes a BigQuery repository connector and invokes the
+    IRR pipeline.
+
+    Args:
+         event: The dictionary with data specific to this type of event. The `@type` field maps to
+                `type.googleapis.com/google.pubsub.v1.PubsubMessage`. The `data` field maps to the PubsubMessage data
+                in a base64-encoded string. The `attributes` field maps to the PubsubMessage attributes
+                if any is present.
+         context: Metadata of triggering event including `event_id` which maps to the PubsubMessage
+                  messageId, `timestamp` which maps to the PubsubMessage publishTime, `event_type` which maps to
+                  `google.pubsub.topic.publish`, and `resource` which is a dictionary that describes the service
+                  API endpoint pubsub.googleapis.com, the triggering topic's name, and the triggering event type
+                  `type.googleapis.com/google.pubsub.v1.PubsubMessage`.
+    """
+    bq_repository = repository.BiqQueryRepository()
+    services.irr_pipeline(bq_repository)
diff --git a/cloud_function/model.py b/cloud_function/model.py
new file mode 100644
index 0000000..853185a
--- /dev/null
+++ b/cloud_function/model.py
@@ -0,0 +1,167 @@
+from dataclasses import dataclass
+import datetime as dt
+import numpy_financial as npf
+
+@dataclass(frozen=True)
+class Cashflow:
+    """
+    A data class representing a cashflow entry. This class is used to store information about a cashflow,
+    including the date, inflow, outflow, value, and entity name. The class is frozen to ensure immutability.
+
+    Attributes:
+        date (datetime.datetime): The date of the cashflow.
+        inflow (float): The inflow amount.
+        outflow (float): The outflow amount.
+        value (float): The net value.
+        entity_name (str): The name of the associated entity.
+    """
+    date: dt.datetime
+    inflow: float
+    outflow: float
+    value: float
+    entity_name: str
+
+    def __gt__(self, other):
+        if self.date is None:
+            return False
+        elif other.date is None:
+            return True
+        else:
+            return self.date > other.date
+
+
+@dataclass(frozen=True)
+class Irr:
+    """
+    A data class representing Internal Rate of Return (IRR) data for a specific entity. This class is used to store
+    information about IRR, including the date, monthly IRR value, and entity name. The class is frozen to ensure
+    immutability.
+
+    Attributes:
+        date (datetime.datetime): The date of the IRR calculation.
+        value (float): The monthly IRR value.
+        entity_name (str): The name of the associated entity.
+    Properties:
+        value_annual (float): Calculate the annualized IRR value based on the monthly value.
+    Methods:
+        to_dict(): Convert the IRR data to a dictionary for serialization.
+    """
+    date: dt.datetime
+    value: float
+    entity_name: str
+
+    @property
+    def value_annual(self):
+        """
+        Calculate the annualized IRR value based on the monthly value.
+
+        Returns:
+            float: The annualized IRR value (rounded to 4 decimal places).
+        """
+        return round(((1 + self.value) ** 12) - 1, 4)
+
+    def to_dict(self) -> dict:
+        """
+        Convert the IRR data to a dictionary for serialization.
+
+        Returns:
+            dict: A dictionary representation of the IRR data.
+        """
+        return {
+            'date': self.date.strftime('%Y-%m-%d'),
+            'irr_monthly': self.value,
+            'irr_annual': self.value_annual,
+            'entity_name': self.entity_name
+        }
+
+
+class Entity:
+    """
+    A class representing an entity with associated cashflows and calculated Internal Rate of Return (IRR) data.
+
+    Args:
+        entity_name (str): The name of the entity.
+    Attributes:
+        entity_name (str): The name of the entity.
+        sorted_cashflows (list[Cashflow]): A list of sorted Cashflow objects for the entity.
+        irrs (list[Irr]): A list of calculated IRR data.
+    Methods:
+        add_cashflow(cashflow: Cashflow): Add a Cashflow to the entity's list of cashflows.
+        calculate_irr(): Calculate IRR data based on the entity's cashflows.
+    """
+    def __init__(self, entity_name: str):
+        self.entity_name: str = entity_name
+        self.sorted_cashflows: list[Cashflow] = []
+        self.irrs: list[Irr] = []
+
+    def add_cashflow(self, cashflow: Cashflow):
+        """
+        Add a Cashflow to the entity's list of cashflows and ensure the list remains sorted by date.
+
+        Args:
+            cashflow (Cashflow): The Cashflow to add.
+        """
+        self.sorted_cashflows.append(cashflow)
+        self.sorted_cashflows = sorted(self.sorted_cashflows)
+
+    def calculate_irr(self):
+        """
+        Calculate IRR data based on the entity's sorted cashflows. This method calculates IRR based on cashflows and
+        stores the results in the 'irrs' attribute.
+
+        If there are not enough cashflows for calculation, a message is printed.
+        """
+        self.irrs = []
+        if self.sorted_cashflows.__len__() < 2:
+            print(f"Not enough values for {self.entity_name}")
+            # raise Exception("Not enough values")
+            # todo: make this to be logged
+        else:
+            periodic_cashflow = [self.sorted_cashflows[0].outflow - self.sorted_cashflows[0].inflow]
+            for cashflow in self.sorted_cashflows[1:]:
+                periodic_cashflow.append(cashflow.value + cashflow.outflow - cashflow.inflow)
+                self.irrs.append(Irr(cashflow.date, round(npf.irr(periodic_cashflow), 4), self.entity_name))
+                periodic_cashflow[-1] = cashflow.outflow - cashflow.inflow
+
+    def __eq__(self, other):
+        if not isinstance(other, Entity):
+            return False
+        return self.entity_name == other.entity_name
+
+    def __hash__(self):
+        return hash(self.entity_name)
+
+
+def allocate_cashflows_to_entities(cashflows: list[Cashflow], entities: dict[str: Entity]):
+    """
+    Allocate cashflows to entities based on the entity names.
+
+    Args:
+        cashflows (list[Cashflow]): A list of Cashflow objects to be allocated to entities.
+        entities (dict[str, Entity]): A dictionary of entities where keys are entity names, and values are Entity
+                                      objects.
+    Returns:
+        dict[str, Entity]: A dictionary of entities with updated cashflow data.
+    """
+    for cashflow in cashflows:
+        entities[cashflow.entity_name].add_cashflow(cashflow)
+    # todo: get an except catcher for KeyError!?
+
+    return entities
+
+
+def entities_collection_creation(cashflows: list[Cashflow]) -> dict[str: Entity]:
+    """
+    Create a collection of entities based on the provided list of cashflows.
+
+    Args:
+        cashflows (list[Cashflow]): A list of Cashflow objects from which entities will be created.
+    Returns:
+        dict[str, Entity]: A dictionary of entities with entity names as keys and corresponding Entity objects.
+    """
+    entities = {}
+    entity_names = tuple([cashflow.entity_name for cashflow in cashflows])
+    for entity_name in entity_names:
+        entities[entity_name] = Entity(entity_name)
+
+    return entities
diff --git a/cloud_function/query.py b/cloud_function/query.py
new file mode 100644
index 0000000..c81810d
--- /dev/null
+++ b/cloud_function/query.py
@@ -0,0 +1,145 @@
+ACCOUNT_LEVEL_QUERY = """
+WITH
+  max_date AS (
+  SELECT
+    MAX(month_start) AS max_date
+  FROM
+    `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio` ),
+  monthly_periodic_cashflows AS (
+  SELECT
+    acc.account_name,
+    DATE_ADD(gla.date, INTERVAL 1 DAY) AS date,
+    CASE
+      WHEN gla.end_balance_amount_pounds > 0 THEN CASE
+      WHEN acc.account_currency = 'Pound' THEN gla.end_balance_amount_pounds
+    ELSE
+    gla.end_balance_amount_euros
+  END
+    ELSE
+    0
+  END
+    AS inflow,
+    CASE
+      WHEN gla.end_balance_amount_pounds < 0 THEN CASE
+      WHEN acc.account_currency = 'Pound' THEN - gla.end_balance_amount_pounds
+    ELSE
+    - gla.end_balance_amount_euros
+  END
+    ELSE
+    0
+  END
+    AS outflow
+  FROM
+    `poetic-dock-367718.dw_accounting.accounts` acc
+  INNER JOIN
+    `poetic-dock-367718.dw_accounting.gl_monthly_periodic_snapshot` gla
+  ON
+    gla.account_id = acc.account_id
+  WHERE
+    acc.account_family = 'Stock Market'
+    AND gla.ledger_book_name = 'Accounting App')
+SELECT
+  ass.account_name AS entity_name,
+  ass.month_start AS date,
+  CASE
+    WHEN ass.account_currency = 'Pound' THEN ass.end_balance_amount_pounds
+  ELSE
+  ass.end_balance_amount_euros
+END
+  AS value,
+  COALESCE(pas.inflow, 0) AS inflow,
+  COALESCE(pas.outflow,0) AS outflow
+FROM
+  `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio` ass
+LEFT JOIN
+  monthly_periodic_cashflows pas
+ON
+  ass.month_start = pas.date
+  AND ass.account_name = pas.account_name
+CROSS JOIN
+  max_date md
+WHERE
+  ass.account_family = 'Stock Market'
+  AND ass.month_start <= md.max_date
+  AND ass.month_start NOT IN ('2023-06-01',
+    '2023-07-01',
+    '2023-08-01',
+    '2023-09-01',
+    '2023-10-01')
+  AND NOT ( ass.account_name = 'DeGiro - IPCO' AND ass.month_start = '2019-04-01' )
+UNION ALL
+SELECT
+  ass.account_name AS entity_name,
+  pas.date,
+  CASE
+    WHEN ass.account_currency = 'Pound' THEN ass.end_balance_amount_pounds
+  ELSE
+  ass.end_balance_amount_euros
+END
+  AS value,
+  COALESCE(pas.inflow, 0) AS inflow,
+  COALESCE(pas.outflow,0) AS outflow
+FROM (
+  SELECT
+    *
+  FROM
+    `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio`
+  WHERE
+    month_start = '2023-05-01'
+    AND account_family = 'Stock Market' ) ass
+RIGHT JOIN (
+  SELECT
+    acc.account_name,
+    DATE_ADD(gla.date, INTERVAL 1 DAY) AS date,
+    CASE
+      WHEN gla.end_balance_amount_pounds > 0 THEN CASE
+      WHEN acc.account_currency = 'Pound' THEN gla.end_balance_amount_pounds
+    ELSE
+    gla.end_balance_amount_euros
+  END
+    ELSE
+    0
+  END
+    AS inflow,
+    CASE
+      WHEN gla.end_balance_amount_pounds < 0 THEN CASE
+      WHEN acc.account_currency = 'Pound' THEN - gla.end_balance_amount_pounds
+    ELSE
+    - gla.end_balance_amount_euros
+  END
+    ELSE
+    0
+  END
+    AS outflow
+  FROM
+    `poetic-dock-367718.dw_accounting.accounts` acc
+  INNER JOIN
+    `poetic-dock-367718.dw_accounting.gl_monthly_periodic_snapshot` gla
+  ON
+    gla.account_id = acc.account_id
+  WHERE
+    acc.account_family = 'Stock Market'
+    AND gla.ledger_book_name = 'Accounting App'
+    AND DATE_ADD(gla.date, INTERVAL 1 DAY) IN ('2023-06-01',
+      '2023-07-01',
+      '2023-08-01',
+      '2023-09-01',
+      '2023-10-01')) pas
+ON
+  ass.account_name = pas.account_name
+INNER JOIN (
+  SELECT
+    account_name,
+    MIN(month_start) AS min_date,
+    MAX(month_start) AS max_date
+  FROM
+    `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio`
+  WHERE
+    account_family = 'Stock Market'
+  GROUP BY
+    account_name) md
+ON
+  md.account_name = pas.account_name
+  AND pas.date <= md.max_date
+  AND pas.date >= md.min_date;
+"""
\ No newline at end of file
diff --git a/cloud_function/repository.py b/cloud_function/repository.py
new file mode 100644
index 0000000..2547fee
--- /dev/null
+++ b/cloud_function/repository.py
@@ -0,0 +1,123 @@
+from abc import ABC, abstractmethod
+from google.cloud import bigquery
+from cloud_function import model
+
+
+class AbstractRepository(ABC):
+    """
+    An abstract base class for repository interfaces that define methods to interact with a data source.
+
+    Subclasses of AbstractRepository are expected to implement these methods to handle data retrieval and storage.
+
+    Methods:
+        get_cashflows: Abstract method for retrieving cashflows from the repository.
+        load_irrs: Abstract method for loading Internal Rate of Return (IRR) data into the repository.
+    """
+    @abstractmethod
+    def get_cashflows(self) -> list[model.Cashflow]:
+        """
+        Abstract method for retrieving cashflows from the repository.
+
+        Returns:
+            A list of Cashflow objects representing the cashflows.
+
+        Raises:
+            NotImplementedError: This method should be implemented by concrete subclasses.
+        """
+        raise NotImplementedError
+
+    @abstractmethod
+    def load_irrs(self, entities: dict[str: model.Entity]):
+        """
+        Abstract method for loading Internal Rate of Return (IRR) data into the repository.
+
+        Args:
+            entities (dict): A dictionary of Entity objects for which IRR data will be loaded.
+                The dictionary maps entity IDs to Entity objects.
+
+        Raises:
+            NotImplementedError: This method should be implemented by concrete subclasses.
+        """
+        raise NotImplementedError
+
+
+class BiqQueryRepository(AbstractRepository):
+    """
+    A concrete implementation of the AbstractRepository for interacting with Google BigQuery.
+    This repository class is designed to retrieve cashflows and load Internal Rate of Return (IRR) data into
+    Google BigQuery.
+
+    Args:
+        project (str, optional): The Google Cloud project ID. If not specified, the default project is used.
+
+    Attributes:
+        client (bigquery.Client): The Google BigQuery client instance.
+        cashflow_source (str): The SQL source query for cashflows.
+        irr_destination (str): The destination table for IRR data.
+
+    Methods:
+        get(query: str) -> bigquery.table.RowIterator: Execute a SQL query and return the results.
+        get_cashflows() -> list[model.Cashflow]: Retrieve cashflow data and convert it to Cashflow objects.
+        load_table_from_json(data: list[dict], destination: str, job_config: bigquery.job.load.LoadJobConfig):
+            Load data from a list of dictionaries into a BigQuery table.
+        load_irrs(entities: dict[str, model.Entity]): Load IRR data from a dictionary of Entity objects.
+    """
+    def __init__(self, project=None):
+        self.client = bigquery.Client(project=project)
+        self.cashflow_source = "SELECT * FROM dw_accounting.cashflows"
+        self.irr_destination = "publishing.entity_irrs"
+
+    def get(self, query: str) -> bigquery.table.RowIterator:
+        """
+        Execute a SQL query and return the results as a RowIterator.
+
+        Args:
+            query (str): The SQL query to execute.
+
+        Returns:
+            bigquery.table.RowIterator: An iterator for the query results.
+        """
+        query_job = self.client.query(query)
+        rows = query_job.result()
+
+        return rows
+
+    def get_cashflows(self) -> list[model.Cashflow]:
+        """
+        Retrieve cashflow data and convert it into a list of Cashflow objects.
+
+        Returns:
+            list[model.Cashflow]: A list of Cashflow objects representing the cashflows.
+        """
+        cashflows = []
+        for row in self.get(self.cashflow_source):
+            cashflows.append(model.Cashflow(row.date, row.inflow, row.outflow, row.value, row.entity_name))
+
+        return cashflows
+
+    def load_table_from_json(self, data: list[dict], destination: str, job_config: bigquery.job.load.LoadJobConfig):
+        """
+        Load data from a list of dictionaries into a BigQuery table.
+
+        Args:
+            data (list[dict]): The data to load as a list of dictionaries.
+            destination (str): The destination table in BigQuery.
+            job_config (bigquery.job.load.LoadJobConfig): Job configuration for the load operation.
+        """
+        load_job = self.client.load_table_from_json(data, destination, job_config=job_config)
+        load_job.result()
+
+    def load_irrs(self, entities: dict[str: model.Entity]):
+        """
+        Load IRR data from a dictionary of Entity objects into BigQuery. This method extracts IRR data from Entity
+        objects and loads it into the specified BigQuery destination table.
+
+        Args:
+            entities (dict): A dictionary of Entity objects where the keys are entity IDs.
+        """
+        irrs = [irr.to_dict() for entity in entities.values() for irr in entity.irrs]
+        job_config = bigquery.LoadJobConfig(
+            write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
+            source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
+        )
+        self.load_table_from_json(irrs, self.irr_destination, job_config)
diff --git a/cloud_function/requirements.txt b/cloud_function/requirements.txt
new file mode 100644
index 0000000..ff902cd
--- /dev/null
+++ b/cloud_function/requirements.txt
@@ -0,0 +1,3 @@
+numpy-financial==1.0.0
+google-cloud-bigquery==3.13.0
+python-dotenv==0.14.0
\ No newline at end of file
diff --git a/cloud_function/services.py b/cloud_function/services.py
new file mode 100644
index 0000000..c668547
--- /dev/null
+++ b/cloud_function/services.py
@@ -0,0 +1,20 @@
+from cloud_function.repository import AbstractRepository
+from cloud_function import model
+
+
+def irr_pipeline(repository: AbstractRepository):
+    """
+    Perform an Internal Rate of Return (IRR) data pipeline. The pipeline retrieves cashflows, creates entities,
+    allocates cashflows to entities, calculates IRRs, and loads IRR data into the repository.
+
+    Args:
+        repository (AbstractRepository): The repository for data retrieval and storage.
+    """
+    cashflows = repository.get_cashflows()
+    entities = model.entities_collection_creation(cashflows)
+    entities = model.allocate_cashflows_to_entities(cashflows, entities)
+
+    for entity in entities.values():
+        entity.calculate_irr()
+
+    repository.load_irrs(entities)
\ No newline at end of file
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..47d406f
--- /dev/null
+++ b/tests/__init__.py
@@ -0,0 +1,21 @@
+import os
+from dotenv import load_dotenv
+
+
+def env_var_loader(file_name, file_path=None):
+    """ Method that allows to load env variables in local from a file.
+    Args:
+        file_name: path to file with environment variables
+        file_path: path to the file, if it is not provided it is assumed that the file is in the root of the project
+        """
+    if file_path:
+        env_path = os.path.join(file_path, file_name)
+    else:
+        wd = os.getcwd()
+        env_path = os.path.join(wd, file_name)
+
+    if os.path.isfile(env_path):
+        load_dotenv(dotenv_path=env_path)
+
+
+env_var_loader('tests/.env')
diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..af7c58d
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,44 @@
+import pytest
+from cloud_function.repository import BiqQueryRepository
+import os
+from tests.data.cashflows import CASHFLOWS
+from google.cloud import bigquery
+
+
+@pytest.fixture(scope='session')
+def bq_repository():
+    """
+    Fixture that returns instance of BiqQueryRepository()
+
+    Returns:
+        instance of BiqQueryRepository()
+    """
+    bq_repository = BiqQueryRepository(project=os.environ['PROJECT'])
+    bq_repository.cashflow_source = f"SELECT * FROM {os.environ['DATASET']}.{os.environ['SOURCE_TABLE']}"
+    bq_repository.irr_destination = os.environ['DATASET'] + '.' + os.environ['DESTINATION_TABLE']
+
+    return bq_repository
+
+
+@pytest.fixture(scope='function')
+def repository_with_cashflows(bq_repository):
+    """
+    Fixture that creates a cashflow table on destination BigQuery project. Also load data into table.
+
+    Args:
+        bq_repository: instance of BiqQueryRepository()
+
+    Returns:
+        instance of BiqQueryRepository() where a cashflow table has been created
+    """
+    job_config = bigquery.LoadJobConfig(
+        write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
+        source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
+    )
+    bq_repository.client.create_dataset(os.environ['DATASET'], exists_ok=True)
+    bq_repository.load_table_from_json(CASHFLOWS, os.environ['DATASET'] + '.' + os.environ['SOURCE_TABLE'], job_config)
+
+    yield bq_repository
+
+    bq_repository.client.delete_table(os.environ['DATASET'] + '.' + os.environ['SOURCE_TABLE'])
+    bq_repository.client.delete_table(os.environ['DATASET'] + '.' + os.environ['DESTINATION_TABLE'])
diff --git a/tests/data/cashflows.py b/tests/data/cashflows.py
new file mode 100644
index 0000000..25b427c
--- /dev/null
+++ b/tests/data/cashflows.py
@@ -0,0 +1,11 @@
+import datetime as dt
+
+CASHFLOWS = [
+    {'date': '2022-01-01', 'inflow': 1000, 'outflow': 0, 'value': 1000, 'entity_name': 'Test Account 1'},
+    {'date': '2022-02-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
+    {'date': '2022-03-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
+    {'date': '2022-04-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
+    {'date': '2022-05-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
+    {'date': '2022-03-01', 'inflow': 1000, 'outflow': 0, 'value': 1000, 'entity_name': 'Test Account 2'},
+    {'date': '2022-04-01', 'inflow': 0, 'outflow': 0, 'value': 1100, 'entity_name': 'Test Account 2'},
+]
diff --git a/tests/test_model.py b/tests/test_model.py
new file mode 100644
index 0000000..a7216a3
--- /dev/null
+++ b/tests/test_model.py
@@ -0,0 +1,131 @@
+from cloud_function import model
+import datetime as dt
+import pytest
+
+
+def test_sort_for_cashflow():
+    """
+    GIVEN a list of elements for value object Cashflow
+    WHEN this list is sorted [sorted()]
+    THEN the Cashflow instances has to be sorted by date from older to newer
+    """
+    cashflow1 = model.Cashflow(dt.datetime(2022, 1, 1), 1000, 0, 0, 'test entity')
+    cashflow2 = model.Cashflow(dt.datetime(2023, 2, 1), 0, 100, 1000, 'test entity')
+    cashflow3 = model.Cashflow(dt.datetime(1998, 3, 1), 0, 100, 1000, 'test entity')
+
+    assert sorted([cashflow1, cashflow2, cashflow3]) == [cashflow3, cashflow1, cashflow2]
+
+
+def test_sort_for_cashflow_none_cases():
+    """
+    GIVEN a collection of cashflows which one has None as date
+    WHEN those cashflows are sorted
+    THEN cashflow with None as date should be listed first
+    """
+    cashflow1 = model.Cashflow(None, 1000, 0, 0, 'test entity')
+    cashflow2 = model.Cashflow(dt.datetime(2023, 2, 1), 0, 100, 1000, 'test entity')
+
+    assert sorted([cashflow1, cashflow2]) == [cashflow1, cashflow2]
+    assert sorted([cashflow2, cashflow1]) == [cashflow1, cashflow2]
+
+
+def test_allocate():
+    """
+    GIVEN an entity
+    WHEN cashflows are added to entity (Entity.add_cashflow())
+    THEN cashflow collection of entity object (Entity.sorted_cashflows) are updated to include
+         this cashflow and are sorted
+    """
+    entity_name = 'test entity'
+    cashflow1 = model.Cashflow(dt.datetime(2022, 1, 1), 100, 100, 100, entity_name)
+    cashflow2 = model.Cashflow(dt.datetime(2023, 1, 2), 1000, 1000, 1000, entity_name)
+    entity = model.Entity(entity_name)
+    entities = {entity_name: entity}
+
+    model.allocate_cashflows_to_entities([cashflow2, cashflow1], entities)
+
+    assert entity.sorted_cashflows == [cashflow1, cashflow2]
+
+
+def test_calculate_irrs():
+    """
+    GIVEN an entity with a collection of cashflows
+    WHEN Internal Rate of Return (irr or dcf, Discounted Cash Flow) is calculated (Entity.calculate_irr())
+    THEN irrs has to be calculated producing expected results
+    """
+    entity_name = 'test account'
+    entity = model.Entity(entity_name)
+    entities = {entity_name: entity}
+
+    model.allocate_cashflows_to_entities(
+        [
+            model.Cashflow(dt.datetime(2022, 1, 1), 1000, 0, 0, entity_name),
+            model.Cashflow(dt.datetime(2022, 2, 1), 0, 100, 1000, entity_name),
+            model.Cashflow(dt.datetime(2022, 3, 1), 0, 100, 1000, entity_name)
+        ],
+        entities)
+
+    entities[entity_name].calculate_irr()
+
+    assert entities[entity_name].irrs == [
+        model.Irr(dt.datetime(2022, 2, 1), 0.1, entity_name),
+        model.Irr(dt.datetime(2022, 3, 1), 0.1, entity_name)
+    ]
+
+
+@pytest.mark.parametrize(
+    "value, expected_result",
+    [
+        (1, 4095),
+        (-1, -1),
+        (0.01, 0.1268)
+     ]
+)
+def test_cashflow_value_annual(value, expected_result):
+    """
+    GIVEN an Internal Rate of Return with a monthly value
+    WHEN calling Irr.value_annual
+    THEN the annualised irr value has to be returned
+    """
+    irr = model.Irr(dt.datetime(2022, 2, 1), value, 'test - account')
+
+    assert irr.value_annual == expected_result
+
+
+def test_irr_to_dict():
+    """
+    GIVEN an Internal Rate of Return
+    WHEN it is converted to dict
+    THEN check that the return is the expected value
+    """
+    irr = model.Irr(dt.datetime(2022, 2, 1), 1, 'test - account')
+
+    assert irr.to_dict() == {
+        'date': '2022-02-01', 'irr_monthly': 1, 'irr_annual': 4095, 'entity_name': 'test - account'
+    }
+
+
+def test_entity_equality():
+    """
+    GIVEN 2 entities
+    WHEN they have the same entity name
+    THEN they are equal
+    """
+    entity_name = 'test entity'
+    entity1 = model.Entity(entity_name)
+    entity2 = model.Entity(entity_name)
+
+    assert entity1 == entity2
+
+
+def test_entity_inequality():
+    """
+    GIVEN 2 entities
+    WHEN they have different entity name
+    THEN they are different
+    """
+    entity1 = model.Entity('test entity')
+    entity2 = model.Entity('other')
+
+    assert not entity1 == entity2
+    assert not entity1 == 1
diff --git a/tests/test_services.py b/tests/test_services.py
new file mode 100644
index 0000000..c9e8a93
--- /dev/null
+++ b/tests/test_services.py
@@ -0,0 +1,32 @@
+import os
+from cloud_function import services
+from google.cloud.bigquery.table import Row
+import datetime as dt
+
+
+def test_irr_pipeline(repository_with_cashflows):
+    """
+    GIVEN some cashflows on bq
+    WHEN they are processed by irr_pipeline() service
+    THEN the expected results should be populated into the correct destination table
+    """
+    services.irr_pipeline(repository_with_cashflows)
+
+    results = repository_with_cashflows.get(
+        f"SELECT * FROM {os.environ['DATASET']}.{os.environ['DESTINATION_TABLE']} ORDER BY entity_name, date"
+    )
+    expected_results = [
+        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 2, 1)),
+            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
+        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 3, 1)),
+            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
+        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 4, 1)),
+            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
+        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 5, 1)),
+            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
+        Row(('Test Account 2', 0.1, 2.1384, dt.date(2022, 4, 1)),
+            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3})
+    ]
+
+    for result, expected_result in zip(results, expected_results):
+        assert result == expected_result
\ No newline at end of file

From f901416f5616acfb86e4eaa1aee2f6c413b3856c Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 16:06:28 +0000
Subject: [PATCH 02/15] formatted with black

---
 cloud_function/model.py      |  34 +++++---
 cloud_function/query.py      | 145 -----------------------------------
 cloud_function/repository.py |  23 ++++--
 cloud_function/services.py   |   2 +-
 tests/__init__.py            |  12 +--
 tests/conftest.py            |  28 ++++---
 tests/data/cashflows.py      |  56 ++++++++++++--
 tests/test_model.py          |  51 ++++++------
 tests/test_services.py       |  32 +++++---
 9 files changed, 167 insertions(+), 216 deletions(-)
 delete mode 100644 cloud_function/query.py

diff --git a/cloud_function/model.py b/cloud_function/model.py
index 853185a..6f14527 100644
--- a/cloud_function/model.py
+++ b/cloud_function/model.py
@@ -2,6 +2,7 @@
 import datetime as dt
 import numpy_financial as npf
 
+
 @dataclass(frozen=True)
 class Cashflow:
     """
@@ -15,6 +16,7 @@ class Cashflow:
         value (float): The net value.
         entity_name (str): The name of the associated entity.
     """
+
     date: dt.datetime
     inflow: float
     outflow: float
@@ -46,6 +48,7 @@ class Irr:
     Methods:
         to_dict(): Convert the IRR data to a dictionary for serialization.
     """
+
     date: dt.datetime
     value: float
     entity_name: str
@@ -68,10 +71,10 @@ def to_dict(self) -> dict:
             dict: A dictionary representation of the IRR data.
         """
         return {
-            'date': self.date.strftime('%Y-%m-%d'),
-            'irr_monthly': self.value,
-            'irr_annual': self.value_annual,
-            'entity_name': self.entity_name
+            "date": self.date.strftime("%Y-%m-%d"),
+            "irr_monthly": self.value,
+            "irr_annual": self.value_annual,
+            "entity_name": self.entity_name,
         }
 
 
@@ -89,6 +92,7 @@ class Entity:
         add_cashflow(cashflow: Cashflow): Add a Cashflow to the entity's list of cashflows.
         calculate_irr(): Calculate IRR data based on the entity's cashflows.
     """
+
     def __init__(self, entity_name: str):
         self.entity_name: str = entity_name
         self.sorted_cashflows: list[Cashflow] = []
@@ -117,10 +121,20 @@ def calculate_irr(self):
             # raise Exception("Not enough values")
             # todo: make this to be logged
         else:
-            periodic_cashflow = [self.sorted_cashflows[0].outflow - self.sorted_cashflows[0].inflow]
+            periodic_cashflow = [
+                self.sorted_cashflows[0].outflow - self.sorted_cashflows[0].inflow
+            ]
             for cashflow in self.sorted_cashflows[1:]:
-                periodic_cashflow.append(cashflow.value + cashflow.outflow - cashflow.inflow)
-                self.irrs.append(Irr(cashflow.date, round(npf.irr(periodic_cashflow), 4), self.entity_name))
+                periodic_cashflow.append(
+                    cashflow.value + cashflow.outflow - cashflow.inflow
+                )
+                self.irrs.append(
+                    Irr(
+                        cashflow.date,
+                        round(npf.irr(periodic_cashflow), 4),
+                        self.entity_name,
+                    )
+                )
                 periodic_cashflow[-1] = cashflow.outflow - cashflow.inflow
 
     def __eq__(self, other):
@@ -132,7 +146,9 @@ def __hash__(self):
         return hash(self.entity_name)
 
 
-def allocate_cashflows_to_entities(cashflows: list[Cashflow], entities: dict[str: Entity]):
+def allocate_cashflows_to_entities(
+    cashflows: list[Cashflow], entities: dict[str:Entity]
+):
     """
     Allocate cashflows to entities based on the entity names.
 
@@ -150,7 +166,7 @@ def allocate_cashflows_to_entities(cashflows: list[Cashflow], entities: dict[str
     return entities
 
 
-def entities_collection_creation(cashflows: list[Cashflow]) -> dict[str: Entity]:
+def entities_collection_creation(cashflows: list[Cashflow]) -> dict[str:Entity]:
     """
     Create a collection of entities based on the provided list of cashflows.
 
diff --git a/cloud_function/query.py b/cloud_function/query.py
deleted file mode 100644
index c81810d..0000000
--- a/cloud_function/query.py
+++ /dev/null
@@ -1,145 +0,0 @@
-ACCOUNT_LEVEL_QUERY = """
-WITH
-  max_date AS (
-  SELECT
-    MAX(month_start) AS max_date
-  FROM
-    `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio` ),
-  monthly_periodic_cashflows AS (
-  SELECT
-    acc.account_name,
-    DATE_ADD(gla.date, INTERVAL 1 DAY) AS date,
-    CASE
-      WHEN gla.end_balance_amount_pounds > 0 THEN CASE
-      WHEN acc.account_currency = 'Pound' THEN gla.end_balance_amount_pounds
-    ELSE
-    gla.end_balance_amount_euros
-  END
-    ELSE
-    0
-  END
-    AS inflow,
-    CASE
-      WHEN gla.end_balance_amount_pounds < 0 THEN CASE
-      WHEN acc.account_currency = 'Pound' THEN - gla.end_balance_amount_pounds
-    ELSE
-    - gla.end_balance_amount_euros
-  END
-    ELSE
-    0
-  END
-    AS outflow
-  FROM
-    `poetic-dock-367718.dw_accounting.accounts` acc
-  INNER JOIN
-    `poetic-dock-367718.dw_accounting.gl_monthly_periodic_snapshot` gla
-  ON
-    gla.account_id = acc.account_id
-  WHERE
-    acc.account_family = 'Stock Market'
-    AND gla.ledger_book_name = 'Accounting App')
-SELECT
-  ass.account_name AS entity_name,
-  ass.month_start AS date,
-  CASE
-    WHEN ass.account_currency = 'Pound' THEN ass.end_balance_amount_pounds
-  ELSE
-  ass.end_balance_amount_euros
-END
-  AS value,
-  COALESCE(pas.inflow, 0) AS inflow,
-  COALESCE(pas.outflow,0) AS outflow
-FROM
-  `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio` ass
-LEFT JOIN
-  monthly_periodic_cashflows pas
-ON
-  ass.month_start = pas.date
-  AND ass.account_name = pas.account_name
-CROSS JOIN
-  max_date md
-WHERE
-  ass.account_family = 'Stock Market'
-  AND ass.month_start <= md.max_date
-  AND ass.month_start NOT IN ('2023-06-01',
-    '2023-07-01',
-    '2023-08-01',
-    '2023-09-01',
-    '2023-10-01')
-  AND NOT ( ass.account_name = 'DeGiro - IPCO' AND ass.month_start = '2019-04-01' )
-UNION ALL
-SELECT
-  ass.account_name AS entity_name,
-  pas.date,
-  CASE
-    WHEN ass.account_currency = 'Pound' THEN ass.end_balance_amount_pounds
-  ELSE
-  ass.end_balance_amount_euros
-END
-  AS value,
-  COALESCE(pas.inflow, 0) AS inflow,
-  COALESCE(pas.outflow,0) AS outflow
-FROM (
-  SELECT
-    *
-  FROM
-    `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio`
-  WHERE
-    month_start = '2023-05-01'
-    AND account_family = 'Stock Market' ) ass
-RIGHT JOIN (
-  SELECT
-    acc.account_name,
-    DATE_ADD(gla.date, INTERVAL 1 DAY) AS date,
-    CASE
-      WHEN gla.end_balance_amount_pounds > 0 THEN CASE
-      WHEN acc.account_currency = 'Pound' THEN gla.end_balance_amount_pounds
-    ELSE
-    gla.end_balance_amount_euros
-  END
-    ELSE
-    0
-  END
-    AS inflow,
-    CASE
-      WHEN gla.end_balance_amount_pounds < 0 THEN CASE
-      WHEN acc.account_currency = 'Pound' THEN - gla.end_balance_amount_pounds
-    ELSE
-    - gla.end_balance_amount_euros
-  END
-    ELSE
-    0
-  END
-    AS outflow
-  FROM
-    `poetic-dock-367718.dw_accounting.accounts` acc
-  INNER JOIN
-    `poetic-dock-367718.dw_accounting.gl_monthly_periodic_snapshot` gla
-  ON
-    gla.account_id = acc.account_id
-  WHERE
-    acc.account_family = 'Stock Market'
-    AND gla.ledger_book_name = 'Accounting App'
-    AND DATE_ADD(gla.date, INTERVAL 1 DAY) IN ('2023-06-01',
-      '2023-07-01',
-      '2023-08-01',
-      '2023-09-01',
-      '2023-10-01')) pas
-ON
-  ass.account_name = pas.account_name
-INNER JOIN (
-  SELECT
-    account_name,
-    MIN(month_start) AS min_date,
-    MAX(month_start) AS max_date
-  FROM
-    `poetic-dock-367718.publishing.monthly_periodic_asset_portfolio`
-  WHERE
-    account_family = 'Stock Market'
-  GROUP BY
-    account_name) md
-ON
-  md.account_name = pas.account_name
-  AND pas.date <= md.max_date
-  AND pas.date >= md.min_date;
-"""
\ No newline at end of file
diff --git a/cloud_function/repository.py b/cloud_function/repository.py
index 2547fee..b1e75e6 100644
--- a/cloud_function/repository.py
+++ b/cloud_function/repository.py
@@ -13,6 +13,7 @@ class AbstractRepository(ABC):
         get_cashflows: Abstract method for retrieving cashflows from the repository.
         load_irrs: Abstract method for loading Internal Rate of Return (IRR) data into the repository.
     """
+
     @abstractmethod
     def get_cashflows(self) -> list[model.Cashflow]:
         """
@@ -27,7 +28,7 @@ def get_cashflows(self) -> list[model.Cashflow]:
         raise NotImplementedError
 
     @abstractmethod
-    def load_irrs(self, entities: dict[str: model.Entity]):
+    def load_irrs(self, entities: dict[str : model.Entity]):
         """
         Abstract method for loading Internal Rate of Return (IRR) data into the repository.
 
@@ -62,6 +63,7 @@ class BiqQueryRepository(AbstractRepository):
             Load data from a list of dictionaries into a BigQuery table.
         load_irrs(entities: dict[str, model.Entity]): Load IRR data from a dictionary of Entity objects.
     """
+
     def __init__(self, project=None):
         self.client = bigquery.Client(project=project)
         self.cashflow_source = "SELECT * FROM dw_accounting.cashflows"
@@ -91,11 +93,20 @@ def get_cashflows(self) -> list[model.Cashflow]:
         """
         cashflows = []
         for row in self.get(self.cashflow_source):
-            cashflows.append(model.Cashflow(row.date, row.inflow, row.outflow, row.value, row.entity_name))
+            cashflows.append(
+                model.Cashflow(
+                    row.date, row.inflow, row.outflow, row.value, row.entity_name
+                )
+            )
 
         return cashflows
 
-    def load_table_from_json(self, data: list[dict], destination: str, job_config: bigquery.job.load.LoadJobConfig):
+    def load_table_from_json(
+        self,
+        data: list[dict],
+        destination: str,
+        job_config: bigquery.job.load.LoadJobConfig,
+    ):
         """
         Load data from a list of dictionaries into a BigQuery table.
 
@@ -104,10 +115,12 @@ def load_table_from_json(self, data: list[dict], destination: str, job_config: b
             destination (str): The destination table in BigQuery.
             job_config (bigquery.job.load.LoadJobConfig): Job configuration for the load operation.
         """
-        load_job = self.client.load_table_from_json(data, destination, job_config=job_config)
+        load_job = self.client.load_table_from_json(
+            data, destination, job_config=job_config
+        )
         load_job.result()
 
-    def load_irrs(self, entities: dict[str: model.Entity]):
+    def load_irrs(self, entities: dict[str : model.Entity]):
         """
         Load IRR data from a dictionary of Entity objects into BigQuery. This method extracts IRR data from Entity
         objects and loads it into the specified BigQuery destination table.
diff --git a/cloud_function/services.py b/cloud_function/services.py
index c668547..3f606ef 100644
--- a/cloud_function/services.py
+++ b/cloud_function/services.py
@@ -17,4 +17,4 @@ def irr_pipeline(repository: AbstractRepository):
     for entity in entities.values():
         entity.calculate_irr()
 
-    repository.load_irrs(entities)
\ No newline at end of file
+    repository.load_irrs(entities)
diff --git a/tests/__init__.py b/tests/__init__.py
index 47d406f..25a0fc3 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -3,11 +3,13 @@
 
 
 def env_var_loader(file_name, file_path=None):
-    """ Method that allows to load env variables in local from a file.
+    """
+    Load environment variables from a specified file using python-dotenv.
+
     Args:
-        file_name: path to file with environment variables
-        file_path: path to the file, if it is not provided it is assumed that the file is in the root of the project
-        """
+        file_name (str): The name of the environment file.
+        file_path (str, optional): The path to the directory containing the environment file.
+    """
     if file_path:
         env_path = os.path.join(file_path, file_name)
     else:
@@ -18,4 +20,4 @@ def env_var_loader(file_name, file_path=None):
         load_dotenv(dotenv_path=env_path)
 
 
-env_var_loader('tests/.env')
+env_var_loader("tests/.env")
diff --git a/tests/conftest.py b/tests/conftest.py
index af7c58d..e16eb40 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -5,7 +5,7 @@
 from google.cloud import bigquery
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def bq_repository():
     """
     Fixture that returns instance of BiqQueryRepository()
@@ -13,14 +13,18 @@ def bq_repository():
     Returns:
         instance of BiqQueryRepository()
     """
-    bq_repository = BiqQueryRepository(project=os.environ['PROJECT'])
-    bq_repository.cashflow_source = f"SELECT * FROM {os.environ['DATASET']}.{os.environ['SOURCE_TABLE']}"
-    bq_repository.irr_destination = os.environ['DATASET'] + '.' + os.environ['DESTINATION_TABLE']
+    bq_repository = BiqQueryRepository(project=os.environ["PROJECT"])
+    bq_repository.cashflow_source = (
+        f"SELECT * FROM {os.environ['DATASET']}.{os.environ['SOURCE_TABLE']}"
+    )
+    bq_repository.irr_destination = (
+        os.environ["DATASET"] + "." + os.environ["DESTINATION_TABLE"]
+    )
 
     return bq_repository
 
 
-@pytest.fixture(scope='function')
+@pytest.fixture(scope="function")
 def repository_with_cashflows(bq_repository):
     """
     Fixture that creates a cashflow table on destination BigQuery project. Also load data into table.
@@ -35,10 +39,16 @@ def repository_with_cashflows(bq_repository):
         write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
         source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
     )
-    bq_repository.client.create_dataset(os.environ['DATASET'], exists_ok=True)
-    bq_repository.load_table_from_json(CASHFLOWS, os.environ['DATASET'] + '.' + os.environ['SOURCE_TABLE'], job_config)
+    bq_repository.client.create_dataset(os.environ["DATASET"], exists_ok=True)
+    bq_repository.load_table_from_json(
+        CASHFLOWS, os.environ["DATASET"] + "." + os.environ["SOURCE_TABLE"], job_config
+    )
 
     yield bq_repository
 
-    bq_repository.client.delete_table(os.environ['DATASET'] + '.' + os.environ['SOURCE_TABLE'])
-    bq_repository.client.delete_table(os.environ['DATASET'] + '.' + os.environ['DESTINATION_TABLE'])
+    bq_repository.client.delete_table(
+        os.environ["DATASET"] + "." + os.environ["SOURCE_TABLE"]
+    )
+    bq_repository.client.delete_table(
+        os.environ["DATASET"] + "." + os.environ["DESTINATION_TABLE"]
+    )
diff --git a/tests/data/cashflows.py b/tests/data/cashflows.py
index 25b427c..9cd4cd0 100644
--- a/tests/data/cashflows.py
+++ b/tests/data/cashflows.py
@@ -1,11 +1,53 @@
 import datetime as dt
 
 CASHFLOWS = [
-    {'date': '2022-01-01', 'inflow': 1000, 'outflow': 0, 'value': 1000, 'entity_name': 'Test Account 1'},
-    {'date': '2022-02-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
-    {'date': '2022-03-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
-    {'date': '2022-04-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
-    {'date': '2022-05-01', 'inflow': 0, 'outflow': 100, 'value': 1000, 'entity_name': 'Test Account 1'},
-    {'date': '2022-03-01', 'inflow': 1000, 'outflow': 0, 'value': 1000, 'entity_name': 'Test Account 2'},
-    {'date': '2022-04-01', 'inflow': 0, 'outflow': 0, 'value': 1100, 'entity_name': 'Test Account 2'},
+    {
+        "date": "2022-01-01",
+        "inflow": 1000,
+        "outflow": 0,
+        "value": 1000,
+        "entity_name": "Test Account 1",
+    },
+    {
+        "date": "2022-02-01",
+        "inflow": 0,
+        "outflow": 100,
+        "value": 1000,
+        "entity_name": "Test Account 1",
+    },
+    {
+        "date": "2022-03-01",
+        "inflow": 0,
+        "outflow": 100,
+        "value": 1000,
+        "entity_name": "Test Account 1",
+    },
+    {
+        "date": "2022-04-01",
+        "inflow": 0,
+        "outflow": 100,
+        "value": 1000,
+        "entity_name": "Test Account 1",
+    },
+    {
+        "date": "2022-05-01",
+        "inflow": 0,
+        "outflow": 100,
+        "value": 1000,
+        "entity_name": "Test Account 1",
+    },
+    {
+        "date": "2022-03-01",
+        "inflow": 1000,
+        "outflow": 0,
+        "value": 1000,
+        "entity_name": "Test Account 2",
+    },
+    {
+        "date": "2022-04-01",
+        "inflow": 0,
+        "outflow": 0,
+        "value": 1100,
+        "entity_name": "Test Account 2",
+    },
 ]
diff --git a/tests/test_model.py b/tests/test_model.py
index a7216a3..483cd87 100644
--- a/tests/test_model.py
+++ b/tests/test_model.py
@@ -9,11 +9,15 @@ def test_sort_for_cashflow():
     WHEN this list is sorted [sorted()]
     THEN the Cashflow instances has to be sorted by date from older to newer
     """
-    cashflow1 = model.Cashflow(dt.datetime(2022, 1, 1), 1000, 0, 0, 'test entity')
-    cashflow2 = model.Cashflow(dt.datetime(2023, 2, 1), 0, 100, 1000, 'test entity')
-    cashflow3 = model.Cashflow(dt.datetime(1998, 3, 1), 0, 100, 1000, 'test entity')
-
-    assert sorted([cashflow1, cashflow2, cashflow3]) == [cashflow3, cashflow1, cashflow2]
+    cashflow1 = model.Cashflow(dt.datetime(2022, 1, 1), 1000, 0, 0, "test entity")
+    cashflow2 = model.Cashflow(dt.datetime(2023, 2, 1), 0, 100, 1000, "test entity")
+    cashflow3 = model.Cashflow(dt.datetime(1998, 3, 1), 0, 100, 1000, "test entity")
+
+    assert sorted([cashflow1, cashflow2, cashflow3]) == [
+        cashflow3,
+        cashflow1,
+        cashflow2,
+    ]
 
 
 def test_sort_for_cashflow_none_cases():
@@ -22,8 +26,8 @@ def test_sort_for_cashflow_none_cases():
     WHEN those cashflows are sorted
     THEN cashflow with None as date should be listed first
     """
-    cashflow1 = model.Cashflow(None, 1000, 0, 0, 'test entity')
-    cashflow2 = model.Cashflow(dt.datetime(2023, 2, 1), 0, 100, 1000, 'test entity')
+    cashflow1 = model.Cashflow(None, 1000, 0, 0, "test entity")
+    cashflow2 = model.Cashflow(dt.datetime(2023, 2, 1), 0, 100, 1000, "test entity")
 
     assert sorted([cashflow1, cashflow2]) == [cashflow1, cashflow2]
     assert sorted([cashflow2, cashflow1]) == [cashflow1, cashflow2]
@@ -36,7 +40,7 @@ def test_allocate():
     THEN cashflow collection of entity object (Entity.sorted_cashflows) are updated to include
          this cashflow and are sorted
     """
-    entity_name = 'test entity'
+    entity_name = "test entity"
     cashflow1 = model.Cashflow(dt.datetime(2022, 1, 1), 100, 100, 100, entity_name)
     cashflow2 = model.Cashflow(dt.datetime(2023, 1, 2), 1000, 1000, 1000, entity_name)
     entity = model.Entity(entity_name)
@@ -53,7 +57,7 @@ def test_calculate_irrs():
     WHEN Internal Rate of Return (irr or dcf, Discounted Cash Flow) is calculated (Entity.calculate_irr())
     THEN irrs has to be calculated producing expected results
     """
-    entity_name = 'test account'
+    entity_name = "test account"
     entity = model.Entity(entity_name)
     entities = {entity_name: entity}
 
@@ -61,25 +65,21 @@ def test_calculate_irrs():
         [
             model.Cashflow(dt.datetime(2022, 1, 1), 1000, 0, 0, entity_name),
             model.Cashflow(dt.datetime(2022, 2, 1), 0, 100, 1000, entity_name),
-            model.Cashflow(dt.datetime(2022, 3, 1), 0, 100, 1000, entity_name)
+            model.Cashflow(dt.datetime(2022, 3, 1), 0, 100, 1000, entity_name),
         ],
-        entities)
+        entities,
+    )
 
     entities[entity_name].calculate_irr()
 
     assert entities[entity_name].irrs == [
         model.Irr(dt.datetime(2022, 2, 1), 0.1, entity_name),
-        model.Irr(dt.datetime(2022, 3, 1), 0.1, entity_name)
+        model.Irr(dt.datetime(2022, 3, 1), 0.1, entity_name),
     ]
 
 
 @pytest.mark.parametrize(
-    "value, expected_result",
-    [
-        (1, 4095),
-        (-1, -1),
-        (0.01, 0.1268)
-     ]
+    "value, expected_result", [(1, 4095), (-1, -1), (0.01, 0.1268)]
 )
 def test_cashflow_value_annual(value, expected_result):
     """
@@ -87,7 +87,7 @@ def test_cashflow_value_annual(value, expected_result):
     WHEN calling Irr.value_annual
     THEN the annualised irr value has to be returned
     """
-    irr = model.Irr(dt.datetime(2022, 2, 1), value, 'test - account')
+    irr = model.Irr(dt.datetime(2022, 2, 1), value, "test - account")
 
     assert irr.value_annual == expected_result
 
@@ -98,10 +98,13 @@ def test_irr_to_dict():
     WHEN it is converted to dict
     THEN check that the return is the expected value
     """
-    irr = model.Irr(dt.datetime(2022, 2, 1), 1, 'test - account')
+    irr = model.Irr(dt.datetime(2022, 2, 1), 1, "test - account")
 
     assert irr.to_dict() == {
-        'date': '2022-02-01', 'irr_monthly': 1, 'irr_annual': 4095, 'entity_name': 'test - account'
+        "date": "2022-02-01",
+        "irr_monthly": 1,
+        "irr_annual": 4095,
+        "entity_name": "test - account",
     }
 
 
@@ -111,7 +114,7 @@ def test_entity_equality():
     WHEN they have the same entity name
     THEN they are equal
     """
-    entity_name = 'test entity'
+    entity_name = "test entity"
     entity1 = model.Entity(entity_name)
     entity2 = model.Entity(entity_name)
 
@@ -124,8 +127,8 @@ def test_entity_inequality():
     WHEN they have different entity name
     THEN they are different
     """
-    entity1 = model.Entity('test entity')
-    entity2 = model.Entity('other')
+    entity1 = model.Entity("test entity")
+    entity2 = model.Entity("other")
 
     assert not entity1 == entity2
     assert not entity1 == 1
diff --git a/tests/test_services.py b/tests/test_services.py
index c9e8a93..69f6fc9 100644
--- a/tests/test_services.py
+++ b/tests/test_services.py
@@ -16,17 +16,27 @@ def test_irr_pipeline(repository_with_cashflows):
         f"SELECT * FROM {os.environ['DATASET']}.{os.environ['DESTINATION_TABLE']} ORDER BY entity_name, date"
     )
     expected_results = [
-        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 2, 1)),
-            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
-        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 3, 1)),
-            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
-        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 4, 1)),
-            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
-        Row(('Test Account 1', 0.1, 2.1384, dt.date(2022, 5, 1)),
-            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3}),
-        Row(('Test Account 2', 0.1, 2.1384, dt.date(2022, 4, 1)),
-            {'entity_name': 0, 'irr_monthly': 1, 'irr_annual': 2, 'date': 3})
+        Row(
+            ("Test Account 1", 0.1, 2.1384, dt.date(2022, 2, 1)),
+            {"entity_name": 0, "irr_monthly": 1, "irr_annual": 2, "date": 3},
+        ),
+        Row(
+            ("Test Account 1", 0.1, 2.1384, dt.date(2022, 3, 1)),
+            {"entity_name": 0, "irr_monthly": 1, "irr_annual": 2, "date": 3},
+        ),
+        Row(
+            ("Test Account 1", 0.1, 2.1384, dt.date(2022, 4, 1)),
+            {"entity_name": 0, "irr_monthly": 1, "irr_annual": 2, "date": 3},
+        ),
+        Row(
+            ("Test Account 1", 0.1, 2.1384, dt.date(2022, 5, 1)),
+            {"entity_name": 0, "irr_monthly": 1, "irr_annual": 2, "date": 3},
+        ),
+        Row(
+            ("Test Account 2", 0.1, 2.1384, dt.date(2022, 4, 1)),
+            {"entity_name": 0, "irr_monthly": 1, "irr_annual": 2, "date": 3},
+        ),
     ]
 
     for result, expected_result in zip(results, expected_results):
-        assert result == expected_result
\ No newline at end of file
+        assert result == expected_result

From 56e12af8fc35922252ed1023ba9d767d845027ee Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 18:01:16 +0000
Subject: [PATCH 03/15] added terraform code

---
 cloud_function/main.py       |  3 +-
 cloud_function/repository.py |  2 +-
 cloud_function/services.py   |  4 +-
 main.tf                      | 73 ++++++++++++++++++++++++++++++++++++
 tests/__init__.py            |  3 ++
 variables.tf                 | 27 +++++++++++++
 6 files changed, 108 insertions(+), 4 deletions(-)
 create mode 100644 main.tf
 create mode 100644 variables.tf

diff --git a/cloud_function/main.py b/cloud_function/main.py
index a79183d..bf941e0 100644
--- a/cloud_function/main.py
+++ b/cloud_function/main.py
@@ -1,4 +1,5 @@
-from cloud_function import repository, services
+import repository
+import services
 
 
 def func_entry_point(event, context):
diff --git a/cloud_function/repository.py b/cloud_function/repository.py
index b1e75e6..751137c 100644
--- a/cloud_function/repository.py
+++ b/cloud_function/repository.py
@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from google.cloud import bigquery
-from cloud_function import model
+import model
 
 
 class AbstractRepository(ABC):
diff --git a/cloud_function/services.py b/cloud_function/services.py
index 3f606ef..cb905bf 100644
--- a/cloud_function/services.py
+++ b/cloud_function/services.py
@@ -1,5 +1,5 @@
-from cloud_function.repository import AbstractRepository
-from cloud_function import model
+from repository import AbstractRepository
+import model
 
 
 def irr_pipeline(repository: AbstractRepository):
diff --git a/main.tf b/main.tf
new file mode 100644
index 0000000..01e4855
--- /dev/null
+++ b/main.tf
@@ -0,0 +1,73 @@
+provider "google" {
+  project = var.project_id
+  region  = var.region
+}
+
+resource "google_service_account" "default" {
+  account_id = var.service_account_name
+  display_name = "IRR Calculator Cloud Function SA"
+}
+
+resource "google_project_iam_member" "big_query_writer" {
+  project = var.project_id
+  role    = "roles/bigquery.dataEditor"
+  member  = "serviceAccount:${google_service_account.default.email}"
+}
+
+resource "google_project_iam_member" "big_query_jobUser" {
+  project = var.project_id
+  role    = "roles/bigquery.jobUser"
+  member  = "serviceAccount:${google_service_account.default.email}"
+}
+
+resource "google_storage_bucket" "source_code" {
+  name                        = "irr-calculator-source-code-location"
+  storage_class               = "STANDARD"
+  location                    = var.region
+  uniform_bucket_level_access = true
+}
+
+data "archive_file" "source" {
+  type        = "zip"
+  source_dir  = "${path.root}/cloud_function"
+  output_path = "${path.root}/zip_to_cloud_function.zip"
+}
+
+resource "google_storage_bucket_object" "zip" {
+  name   = "cloud-function-source-code-for-${var.cloud_function_name}.zip"
+  bucket = google_storage_bucket.source_code.name
+  source = data.archive_file.source.output_path
+}
+
+resource "google_pubsub_topic" "default" {
+  name = "cloud-function-${var.cloud_function_name}"
+}
+
+resource "google_cloud_scheduler_job" "default" {
+  name = "cloud-function-${var.cloud_function_name}"
+  description = "Scheduler to trigger the cloud function: ${var.cloud_function_name}"
+  schedule = "30 0 * * *"
+
+  pubsub_target {
+    topic_name = google_pubsub_topic.default.id
+    data = base64encode("Trigger Cloud Function")
+  }
+}
+
+resource "google_cloudfunctions_function" "irr_calculator" {
+  name                  = var.cloud_function_name
+
+  runtime               = "python310"
+  available_memory_mb   = 512
+  timeout               = 539
+  source_archive_bucket = google_storage_bucket.source_code.name
+  source_archive_object = google_storage_bucket_object.zip.name
+  entry_point           = var.function_entry_point
+  service_account_email = google_service_account.default.email
+  max_instances         = 1
+
+  event_trigger {
+    event_type = "google.pubsub.topic.publish"
+    resource   = google_pubsub_topic.default.name
+  }
+}
\ No newline at end of file
diff --git a/tests/__init__.py b/tests/__init__.py
index 25a0fc3..f93b7e1 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -1,5 +1,6 @@
 import os
 from dotenv import load_dotenv
+import sys
 
 
 def env_var_loader(file_name, file_path=None):
@@ -21,3 +22,5 @@ def env_var_loader(file_name, file_path=None):
 
 
 env_var_loader("tests/.env")
+
+sys.path.append(os.path.join(os.getcwd(), 'cloud_function'))
diff --git a/variables.tf b/variables.tf
new file mode 100644
index 0000000..6c5fb5b
--- /dev/null
+++ b/variables.tf
@@ -0,0 +1,27 @@
+variable "project_id" {
+  type        = string
+  description = "Name of the Google Project"
+}
+
+variable "region" {
+  type        = string
+  default     = "europe-west2"
+  description = "Location for the resources"
+}
+
+variable "cloud_function_name" {
+  type        = string
+  description = "Name of the ECB Api Caller Cloud Function"
+}
+
+variable "function_entry_point" {
+  type        = string
+  default     = "func_entry_point"
+  description = "Name of the function entry point for the Python solution at main.py"
+}
+
+
+variable "service_account_name" {
+  type        = string
+  description = "Name of the Service Account"
+}
\ No newline at end of file

From 3d66d687016e799244e42ac25fb152e4ad8861b1 Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:11:13 +0000
Subject: [PATCH 04/15] added github workflow for testing

---
 .github/workflows/pytest.yaml | 34 ++++++++++++++++++++++++++++++++++
 tests/__init__.py             | 10 +++++++++-
 2 files changed, 43 insertions(+), 1 deletion(-)
 create mode 100644 .github/workflows/pytest.yaml

diff --git a/.github/workflows/pytest.yaml b/.github/workflows/pytest.yaml
new file mode 100644
index 0000000..b896426
--- /dev/null
+++ b/.github/workflows/pytest.yaml
@@ -0,0 +1,34 @@
+name: Pytest
+
+on:
+  push:
+  pull_request:
+    branches:
+      - main
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10']
+      max-parallel: 1
+    env: # Or as an environment variable
+      PROJECT: ${{ secrets.PROJECT }}
+      SOURCE_TABLE: ${{ secrets.SOURCE_TABLE }}
+      DESTINATION_TABLE: ${{ secrets.DESTINATION_TABLE }}
+      DATASET: ${{ secrets.DATASET }}
+      SA_JSON: ${{ secrets.SA_JSON }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          python -m pip install pytest==7.4.3
+      - name: Test with pytest
+        run: |
+          python -m pytest -vv
diff --git a/tests/__init__.py b/tests/__init__.py
index f93b7e1..86bc523 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -20,7 +20,15 @@ def env_var_loader(file_name, file_path=None):
     if os.path.isfile(env_path):
         load_dotenv(dotenv_path=env_path)
 
-
+# load env vars
 env_var_loader("tests/.env")
 
+# load path to get python files
 sys.path.append(os.path.join(os.getcwd(), 'cloud_function'))
+
+# load sa if applicable
+if os.environ.get('SA_JSON'):
+    file_name = 'sa.json'
+    with open(file_name, 'r') as f:
+        f.write(os.environ['SA_JSON'])
+    os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = file_name

From 6538b6a5bf8085da933b249e6c5fad9ca5829692 Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:14:13 +0000
Subject: [PATCH 05/15] hotfix GitHub workflow

---
 .github/workflows/pytest.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/pytest.yaml b/.github/workflows/pytest.yaml
index b896426..d8a1db8 100644
--- a/.github/workflows/pytest.yaml
+++ b/.github/workflows/pytest.yaml
@@ -29,6 +29,7 @@ jobs:
           python -m pip install --upgrade pip
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
           python -m pip install pytest==7.4.3
+          python -m pip install python-dotenv==0.14.0
       - name: Test with pytest
         run: |
           python -m pytest -vv

From 8c5786c176451000af0c14bedc07a4af877168b3 Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:16:40 +0000
Subject: [PATCH 06/15] hotfix GitHub workflow 2

---
 tests/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/__init__.py b/tests/__init__.py
index 86bc523..62deea0 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -28,7 +28,7 @@ def env_var_loader(file_name, file_path=None):
 
 # load sa if applicable
 if os.environ.get('SA_JSON'):
-    file_name = 'sa.json'
+    file_name = 'temp/sa.json'
     with open(file_name, 'r') as f:
         f.write(os.environ['SA_JSON'])
     os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = file_name

From 114475c5f0bef768cc5d087ed4ec4cb264f9c110 Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:20:09 +0000
Subject: [PATCH 07/15] hotfix GitHub workflow 3

---
 tests/__init__.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tests/__init__.py b/tests/__init__.py
index 62deea0..ddfb54f 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -28,7 +28,7 @@ def env_var_loader(file_name, file_path=None):
 
 # load sa if applicable
 if os.environ.get('SA_JSON'):
-    file_name = 'temp/sa.json'
-    with open(file_name, 'r') as f:
-        f.write(os.environ['SA_JSON'])
+    file_name = 'sa.json'
+    with open(file_name, 'w') as f:
+        f.write(os.environ.get('SA_JSON'))
     os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = file_name

From 8ab691954d015fac67a71cc8024203da249e7fdd Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:21:54 +0000
Subject: [PATCH 08/15] hotfix GitHub workflow 4

---
 .github/workflows/pytest.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/pytest.yaml b/.github/workflows/pytest.yaml
index d8a1db8..bce3989 100644
--- a/.github/workflows/pytest.yaml
+++ b/.github/workflows/pytest.yaml
@@ -27,7 +27,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          if [ -f cloud_function/requirements.txt ]; then pip install -r cloud_function/requirements.txt; fi
           python -m pip install pytest==7.4.3
           python -m pip install python-dotenv==0.14.0
       - name: Test with pytest

From 4657c72ac9c9e3f27e9a267e4b5229dc833ec6ff Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:25:28 +0000
Subject: [PATCH 09/15] hotfix GitHub workflow 5

---
 tests/conftest.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index e16eb40..181b353 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -39,7 +39,8 @@ def repository_with_cashflows(bq_repository):
         write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
         source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
     )
-    bq_repository.client.create_dataset(os.environ["DATASET"], exists_ok=True)
+    if os.environ.get('SA_JSON'):
+        bq_repository.client.create_dataset(os.environ["DATASET"], exists_ok=True)
     bq_repository.load_table_from_json(
         CASHFLOWS, os.environ["DATASET"] + "." + os.environ["SOURCE_TABLE"], job_config
     )

From 23b382e997b8a37d85abedc7077f29035a76ad43 Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Thu, 9 Nov 2023 23:26:43 +0000
Subject: [PATCH 10/15] hotfix GitHub workflow 6

---
 tests/conftest.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index 181b353..845fbb5 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -39,7 +39,7 @@ def repository_with_cashflows(bq_repository):
         write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
         source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
     )
-    if os.environ.get('SA_JSON'):
+    if not os.environ.get('SA_JSON'):
         bq_repository.client.create_dataset(os.environ["DATASET"], exists_ok=True)
     bq_repository.load_table_from_json(
         CASHFLOWS, os.environ["DATASET"] + "." + os.environ["SOURCE_TABLE"], job_config

From 160f39e3001f2e809369c860387b232b15d6a28d Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Fri, 10 Nov 2023 17:11:49 +0000
Subject: [PATCH 11/15] adding README

---
 README.md | 67 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 53 insertions(+), 14 deletions(-)

diff --git a/README.md b/README.md
index 1db2a20..2ea4809 100644
--- a/README.md
+++ b/README.md
@@ -1,20 +1,37 @@
 # irr_calculator
-## Introduction
-Python solution that calculates irr for a set of entities.
+Python solution that calculates Internal Rate of Return (IRR) for a set of entities.
 
-## Execution
-On this section you will find how to run the code locally.
+## Internal Rate of Return (IRR)
 
-### Python environment
-To execute the solution with your machine you will need an environment with python 3.10.0 and the libraries listed in 
-requirements.txt. In case you do not have such environment, you can create it as follows with conda:
- 
-```
-conda create -n [] python=3.10.0 pip
-pip install -r cloud_function/requirements.txt
-```
+Internal Rate of Return (IRR) is a financial metric that calculates the profitability of an investment by 
+determining the Discount Rate at which the net present value (NPV) of the investment becomes zero. 
+In other words, IRR represents the interest rate at which the present value of cash inflows equals the present 
+value of cash outflows. The primary purpose of IRR is to assess the attractiveness of an investment opportunity.
 
-### Testing
+The IRR is calculated using the following formula:
+
+$`\[ NPV = \sum_{t=0}^{T} \frac{CF_t}{(1 + r)^t} \]`$
+
+Where:
+- \( NPV \) is the net present value of cash inflows and outflows.
+- \( T \) is the total number of periods.
+- \( CF_t \) is the cash flow in period \( t \).
+- \( r \) is the discount rate (IRR).
+
+The IRR is found by solving the NPV equation for \( r \) when \( NPV = 0 \). 
+
+## Terraform code
+The provided Terraform code automates the deployment of the python solution to calculate IRR as a 
+Cloud Function on Google Cloud Platform (GCP). It begins by configuring the necessary GCP provider settings, 
+such as the project ID and region. The code then creates a service account for the Cloud Function, 
+assigning it specific roles for interacting with BigQuery. 
+It also establishes a Cloud Storage bucket to store the Cloud Function's source code, archives the source code, 
+and uploads it to the designated bucket. Additionally, the configuration sets up a Pub/Sub topic and a 
+Cloud Scheduler job, allowing the Cloud Function to be triggered periodically. 
+Finally, it defines the Cloud Function itself. This Terraform setup streamlines the deployment process and 
+ensures a consistent environment for the IRR calculator on GCP.
+
+## Testing
 
 To execute the Python tests use next command on the CLI:
 
@@ -32,4 +49,26 @@ DATASET=
 ```
 
 You will also need to provide a Service Account credentials or to use a user account with the right permissions to 
-interact with BigQuery.
\ No newline at end of file
+interact with BigQuery.
+
+### Python environment
+To execute these tests within your machine you will need an environment with python 3.10.0 and the libraries listed in 
+requirements.txt. In case you do not have such environment, you can create it as follows with conda:
+ 
+```
+conda create -n [] python=3.10.0 pip
+pip install -r cloud_function/requirements.txt
+```
+
+You also need to install pytest==7.4.3 & python-dotenv==0.14.0
+
+## GitHub Workflow
+GitHub workflow automates Python testing for the project, triggered on every push  or pull requests to the main branch. 
+Operating on the latest Ubuntu environment, it employs a matrix strategy to test against Python 3.10. 
+The workflow initializes Python, installs project dependencies, including Pytest and Python-dotenv, 
+and executes Pytest. 
+Key environment variables, such as project details and service account JSON, are securely managed using GitHub Secrets. 
+
+
+
+

From 91be33f48ead6dee8049a367ed22fa26bdc8227a Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Fri, 10 Nov 2023 17:12:46 +0000
Subject: [PATCH 12/15] fix to readme

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 2ea4809..1fd6b5d 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ value of cash outflows. The primary purpose of IRR is to assess the attractivene
 
 The IRR is calculated using the following formula:
 
-$`\[ NPV = \sum_{t=0}^{T} \frac{CF_t}{(1 + r)^t} \]`$
+$`NPV = \sum_{t=0}^{T} \frac{CF_t}{(1 + r)^t}`$
 
 Where:
 - \( NPV \) is the net present value of cash inflows and outflows.

From f3903bc4717ce1e7e747b71f796f91b1e8ea329f Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Fri, 10 Nov 2023 17:14:33 +0000
Subject: [PATCH 13/15] fix to readme 2

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 1fd6b5d..ca5cd03 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ value of cash outflows. The primary purpose of IRR is to assess the attractivene
 
 The IRR is calculated using the following formula:
 
-$`NPV = \sum_{t=0}^{T} \frac{CF_t}{(1 + r)^t}`$
+$`NPV = \sum_{t=0}^T \frac{CF_t}{(1 + r)^t}`$
 
 Where:
 - \( NPV \) is the net present value of cash inflows and outflows.

From 901f93e24527ce2cc97d5591c89f938589be9a3d Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Fri, 10 Nov 2023 17:16:40 +0000
Subject: [PATCH 14/15] fix to readme 3

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index ca5cd03..eada67c 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ value of cash outflows. The primary purpose of IRR is to assess the attractivene
 
 The IRR is calculated using the following formula:
 
-$`NPV = \sum_{t=0}^T \frac{CF_t}{(1 + r)^t}`$
+$`NPV = ( \sum_{t=0}^T \frac{CF_t}{(1 + r)^t} )`$
 
 Where:
 - \( NPV \) is the net present value of cash inflows and outflows.

From d275dec3af45a230ada1fceac82d5fa3b601c6cd Mon Sep 17 00:00:00 2001
From: $Cuentas-AppServices <antjesben@gmail.com>
Date: Fri, 10 Nov 2023 17:20:00 +0000
Subject: [PATCH 15/15] fix to readme 4

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index eada67c..ca5cd03 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ value of cash outflows. The primary purpose of IRR is to assess the attractivene
 
 The IRR is calculated using the following formula:
 
-$`NPV = ( \sum_{t=0}^T \frac{CF_t}{(1 + r)^t} )`$
+$`NPV = \sum_{t=0}^T \frac{CF_t}{(1 + r)^t}`$
 
 Where:
 - \( NPV \) is the net present value of cash inflows and outflows.