Merge branch 'development' of https://github.com/ajschofield/de-project-bentley into test/transform-lambda

2 files changed, 474 insertions, 0 deletions

diff --git a/src/transform_lambda/dataframes.py b/src/transform_lambda/dataframes.py
new file mode 100644
index 0000000..2a46bd6
--- /dev/null
+++ b/src/transform_lambda/dataframes.py
@@ -0,0 +1,257 @@
+import pandas as pd
+from bs4 import BeautifulSoup
+import requests
+
+# Table names:
+# fact_sales_order
+# fact_purchase_orders
+# fact_payment
+# dim_transaction
+# dim_staff
+# dim_payment_type
+# dim_location
+# dim_design
+# dim_date
+# dim_currency
+# dim_counterparty
+
+
+# no test, same as fact_payment
+def create_fact_sales_order(dict_of_df):
+    df_sales = dict_of_df["sales_order"]
+    df_sales.index.name = "sales_record_id"
+
+    df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date
+    df_sales["created_time"] = (
+        df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_sales["last_updated_date"] = (
+        df_sales["last_updated"].astype("datetime64[ns]").dt.date
+    )
+    df_sales["last_updated_time"] = (
+        df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_sales["agreed_delivery_date"] = pd.to_datetime(
+        df_sales["agreed_delivery_date"], format="%Y-%m-%d"
+    )
+    df_sales["agreed_payment_date"] = pd.to_datetime(
+        df_sales["agreed_payment_date"], format="%Y-%m-%d"
+    )
+    df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1)
+
+    df_sales.reset_index(inplace=True)
+    return df_sales
+
+    df_sales["created_date"] = df_sales["created_at"].astype("datetime64[ns]").dt.date
+    df_sales["created_time"] = (
+        df_sales["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_sales["last_updated_date"] = (
+        df_sales["last_updated"].astype("datetime64[ns]").dt.date
+    )
+    df_sales["last_updated_time"] = (
+        df_sales["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_sales["agreed_delivery_date"] = pd.to_datetime(
+        df_sales["agreed_delivery_date"], format="%Y-%m-%d"
+    )
+    df_sales["agreed_payment_date"] = pd.to_datetime(
+        df_sales["agreed_payment_date"], format="%Y-%m-%d"
+    )
+    df_sales = df_sales.drop(labels=["created_at", "last_updated"], axis=1)
+    df_sales.reset_index(inplace=True)
+    return df_sales
+
+
+# no test, same as fact_payment
+
+
+def create_fact_purchase_orders(dict_of_df):
+    df_po = dict_of_df["purchase_order"]
+    df_po.index.name = "purchase_record_id"
+    df_po["created_date"] = df_po["created_at"].astype("datetime64[ns]").dt.date
+    df_po["created_time"] = (
+        df_po["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_po["last_updated_date"] = df_po["last_updated"].astype("datetime64[ns]").dt.date
+    df_po["last_updated_time"] = (
+        df_po["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_po["agreed_delivery_date"] = pd.to_datetime(
+        df_po["agreed_delivery_date"], format="%Y-%m-%d"
+    )
+    df_po["agreed_payment_date"] = pd.to_datetime(
+        df_po["agreed_payment_date"], format="%Y-%m-%d"
+    )
+    df_po = df_po.drop(labels=["created_at", "last_updated"], axis=1)
+    df_po.reset_index(inplace=True)
+    return df_po
+
+
+# test passed
+
+
+def create_fact_payment(dict_of_df):
+    df_payment = dict_of_df["payment"]
+    df_payment.index.name = "payment_record_id"
+    df_payment["created_date"] = (
+        df_payment["created_at"].astype("datetime64[ns]").dt.date
+    )
+    df_payment["created_time"] = (
+        df_payment["created_at"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_payment["last_updated_date"] = (
+        df_payment["last_updated"].astype("datetime64[ns]").dt.date
+    )
+    df_payment["last_updated_time"] = (
+        df_payment["last_updated"].astype("datetime64[ns]").dt.floor("s").dt.time
+    )
+    df_payment["payment_date"] = pd.to_datetime(
+        df_payment["payment_date"], format="%Y-%m-%d"
+    )
+    df_payment = df_payment.drop(labels=["created_at", "last_updated"], axis=1)
+
+    df_payment.reset_index(inplace=True)
+    return df_payment
+
+
+# test passed
+
+
+def create_dim_transaction(dict_of_df):
+    df_transaction = dict_of_df["transaction"].drop(
+        labels=["created_at", "last_updated"], axis=1
+    )
+    return df_transaction
+
+
+# test passed
+
+
+def create_dim_location(dict_of_df):
+    df_loc = (
+        dict_of_df["address"]
+        .drop(labels=["created_at", "last_updated"], axis=1)
+        .rename(columns={"address_id": "location_id"})
+    )
+    return df_loc
+
+
+def create_dim_counterparty(dict_of_df):
+    df_prefixed_address = (
+        dict_of_df["address"]
+        .drop(labels=["created_at", "last_updated"], axis=1)
+        .add_prefix("counterparty_legal_", axis=1)
+    )
+    df_cp = pd.merge(
+        dict_of_df["counterparty"],
+        df_prefixed_address,
+        left_on="legal_address_id",
+        right_on="counterparty_legal_address_id",
+        how="inner",
+    )
+    df_cp.drop(
+        columns=[
+            "legal_address_id",
+            "counterparty_legal_address_id",
+        ],
+        inplace=True,
+    )
+    return df_cp
+
+
+# test passed
+
+
+def create_dim_date(dict_of_df):
+    fact_dfs = [
+        create_fact_payment(dict_of_df),
+        create_fact_purchase_orders(dict_of_df),
+        create_fact_sales_order(dict_of_df),
+    ]
+    list_of_date_columns = []
+    for df in fact_dfs:
+        date_col_names = [
+            col_name for col_name in list(df.columns) if "_date" in col_name
+        ]
+        for col in date_col_names:
+            list_of_date_columns.append(df[col])
+    sr_date = pd.array(pd.concat(list_of_date_columns), dtype="datetime64[ns]")
+    df_date = pd.DataFrame(data=sr_date, columns=["date_id"])
+    df_date.drop_duplicates(inplace=True)
+    df_date["year"] = df_date["date_id"].dt.year
+    df_date["month"] = df_date["date_id"].dt.month
+    df_date["day"] = df_date["date_id"].dt.day
+    df_date["day_of_week"] = df_date["date_id"].dt.dayofweek
+    df_date["day_name"] = df_date["date_id"].dt.day_name()
+    df_date["month_name"] = df_date["date_id"].dt.month_name()
+    df_date["quarter"] = df_date["date_id"].dt.quarter
+    return df_date
+
+
+# tests passed
+
+
+def scrape_currency_names():
+    response = requests.get("https://www.xe.com/currency/").content
+    soup = BeautifulSoup(response, "html.parser")
+    currency = [
+        item.text for item in soup.findAll("a", attrs={"class": "sc-299dec64-6 fZPTSw"})
+    ]
+    sr = pd.Series(currency)
+    df_cur = sr.str.split(pat=" - ", expand=True).rename(
+        {0: "currency_code", 1: "currency_name"}, axis=1
+    )
+    return df_cur
+
+
+# tests passed
+
+
+def create_dim_currency(dict_of_df, names=scrape_currency_names()):
+    df_cur = dict_of_df["currency"].drop(labels=["created_at", "last_updated"], axis=1)
+    dim_cur = pd.merge(
+        df_cur, names, left_on="currency_code", right_on="currency_code", how="inner"
+    )
+    return dim_cur
+
+
+# tests passed
+
+
+def create_dim_payment_type(dict_of_df):
+    df_payment_type = dict_of_df["payment_type"]
+    dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]]
+    return dim_payment_type
+
+
+# tests passed
+
+
+def create_dim_design(dict_of_df):
+    df_design = dict_of_df["design"]
+    dim_design = df_design.loc[
+        :, ["design_id", "design_name", "file_name", "file_location"]
+    ]
+    return dim_design
+
+
+# tests passed
+
+
+def create_dim_staff(dict_of_df):
+    staff_department = pd.merge(
+        dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left"
+    )
+    dim_staff = staff_department.loc[
+        :,
+        [
+            "staff_id",
+            "first_name",
+            "last_name",
+            "department_name",
+            "location",
+            "email_address",
+        ],
+    ]
+    return dim_staff
diff --git a/src/transform_lambda/transform_lambda.py b/src/transform_lambda/transform_lambda.py
new file mode 100644
index 0000000..93b2284
--- /dev/null
+++ b/src/transform_lambda/transform_lambda.py
@@ -0,0 +1,217 @@
+import json
+import boto3
+import re
+import logging
+import pandas as pd
+import pyarrow as pa
+import pyarrow.parquet as pq
+from dataframes import *
+from botocore.exceptions import ClientError
+from pg8000.native import Connection, InterfaceError
+from datetime import datetime
+
+
+class DBConnectionException(Exception):
+    """Wraps pg8000.native Error or DatabaseError."""
+
+    def __init__(self, e):
+        """Initialise with provided error message."""
+        self.message = str(e)
+        super().__init__(self.message)
+
+
+logger = logging.getLogger(__name__)
+
+logging.basicConfig(
+    format="{asctime} - {levelname} - {message}",
+    style="{",
+    datefmt="%Y-%m-%d %H:%M",
+    level=logging.DEBUG,
+)
+
+logging.getLogger("botocore").setLevel(logging.WARNING)
+
+TABLES = [
+    "sales_order",
+    "transaction",
+    "payment",
+    "counterparty",
+    "address",
+    "staff",
+    "purchase_order",
+    "department",
+    "currency",
+    "design",
+    "payment_type",
+]
+
+
+def lambda_handler(event, context):
+    db = None
+
+    try:
+        db = connect_to_database()
+        bucket = bucket_name("transform")
+
+        existing_s3_files = list_existing_s3_files(bucket)
+
+        dict_of_df = read_from_s3_subfolder_to_df(
+            TABLES, bucket_name("extract"), client=boto3.client("s3")
+        )
+
+        immutable_df_dict = {
+            "dim_counterparty": create_dim_counterparty(dict_of_df),
+            "dim_date": create_dim_date(dict_of_df),
+            "dim_location": create_dim_location(dict_of_df),
+            "dim_staff": create_dim_staff(dict_of_df),
+            "dim_design": create_dim_design(dict_of_df),
+        }
+
+        mutable_df_dict = {
+            "fact_sales_order": create_fact_sales_order(dict_of_df),
+            "fact_purchase_order": create_fact_purchase_orders(dict_of_df),
+            "fact_payment": create_fact_payment(dict_of_df),
+            "dim_currency": create_dim_currency(dict_of_df),
+        }
+
+        status = process_to_parquet_and_upload_to_s3(
+            existing_s3_files, immutable_df_dict, mutable_df_dict, bucket
+        )
+
+        if not status["uploaded"]:
+            logger.info("No dataframes written to the bucket.")
+            return {
+                "statusCode": 204,
+                "body": json.dumps("No files where uploaded."),
+            }
+
+        return {
+            "statusCode": 200,
+            "body": json.dumps(
+                f"""Parquet files processed for {', '.join(status['uploaded'])} and uploaded successfully.{
+                'The following tables were not uploaded: '+', '.join([status['not_uploaded']]) if status['not_uploaded'] else ''}"""
+            ),
+        }
+
+    except Exception as e:
+        logger.error(f"Error: {e}", exc_info=True)
+        return {"statusCode": 500, "body": json.dumps("Internal server error.")}
+    finally:
+        if db:
+            db.close()
+
+
+def process_to_parquet_and_upload_to_s3(
+    existing_s3_files,
+    immutable_df_dict,
+    mutable_df_dict,
+    bucket,
+    client=boto3.client("s3"),
+):
+    status = {"uploaded": [], "not_uploaded": []}
+
+    for table_name, df in immutable_df_dict.items():
+        if table_name in existing_s3_files:
+            status["not_uploaded"].append(table_name)
+        else:
+            parquet_file = df.to_parquet(
+                f"{table_name}.parquet", engine="pyarrow"
+            )  # or fastparquet
+            # changed parquet_file variable to the file name
+            client.upload_file(f"{table_name}.parquet", bucket, f"{table_name}.parquet")
+            status["uploaded"].append(table_name)
+
+    for table_name, df in mutable_df_dict.items():
+        s3_key = datetime.strftime(
+            datetime.today(), f"{table_name}/%Y/%m/%d/{table_name}_%H:%M:%S.parquet"
+        )
+        parquet_file = df.to_parquet(
+            f"{table_name}.parquet", engine="pyarrow"
+        )  # or fastparquet
+        client.upload_file(f"{table_name}.parquet", bucket, s3_key)
+        status["uploaded"].append(table_name)
+
+    return status
+
+
+def retrieve_secrets():
+    secret_name = "bentley-secrets"
+    region_name = "eu-west-2"
+
+    # Create a Secrets Manager client
+    session = boto3.session.Session()
+    client = session.client(service_name="secretsmanager", region_name=region_name)
+
+    try:
+        get_secret_value_response = client.get_secret_value(SecretId=secret_name)
+    except ClientError as e:
+        logger.error(f"Failed to retrieve secret {secret_name}: {str(e)}")
+        raise e
+    except KeyError:
+        logger.error(f"Secret {secret_name} does not contain a SecretString")
+        raise ValueError(f"Secret {secret_name} does not contain a SecretString")
+
+    return get_secret_value_response["SecretString"]
+
+
+def connect_to_database() -> Connection:
+    try:
+        secrets = json.loads(retrieve_secrets())
+        host = secrets["host"]
+        port = secrets["port"]
+        user = secrets["user"]
+        password = secrets["password"]
+        database = secrets["database"]
+
+        return Connection(
+            database=database, user=user, password=password, host=host, port=port
+        )
+    except InterfaceError as i:
+        logger.error(f"Interface error: {i}")
+        raise DBConnectionException("Failed to connect to database")
+
+
+def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")):
+    table_dfs = {}
+    for table in tables:
+        response = client.list_objects_v2(Bucket=bucket, Prefix=table)
+        list_of_keys = [
+            "s3://" + bucket + "/" + object["Key"] for object in response["Contents"]
+        ]
+        list_of_df = [pd.read_csv(key) for key in list_of_keys]
+        table_dfs[table] = pd.concat(list_of_df)
+    return table_dfs
+
+
+def bucket_name(bucket_prefix, client=boto3.client("s3")):
+    response = client.list_buckets()
+    bucket_filter = [
+        bucket["Name"]
+        for bucket in response["Buckets"]
+        if bucket_prefix in bucket["Name"]
+    ]
+
+    return bucket_filter[0]
+
+
+def list_existing_s3_files(bucket_name, client=boto3.client("s3")):
+    logging.info("Listing existing S3 files")
+
+    try:
+        response = client.list_objects_v2(Bucket=bucket_name)
+
+        if "Contents" in response:
+            existing_files = [obj["Key"] for obj in response["Contents"]]
+        else:
+            logger.error("The bucket is empty")
+            return []  # changed from None to [] so it is an iterable
+
+    except ClientError as e:
+        logger.error(f"Error listing S3 objects: {e}")
+        raise e
+
+    return existing_files
+
+
+if __name__ == "__main__":
+    lambda_handler({}, "")