From 1ba7230de96092e9f401067317d0dfaf881b971b Mon Sep 17 00:00:00 2001 From: T-Aji Date: Fri, 23 Aug 2024 09:55:33 +0100 Subject: dataframes combined into one file --- src/dataframes.py | 238 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 238 insertions(+) create mode 100644 src/dataframes.py (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py new file mode 100644 index 0000000..9ce3be0 --- /dev/null +++ b/src/dataframes.py @@ -0,0 +1,238 @@ +import pandas as pd +from bs4 import BeautifulSoup +from src.transform_lambda import read_from_s3_subfolder_to_df, tables +from src.extract_lambda import extract_bucket +import json +import boto3 +import re +from datetime import datetime as dt +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 + +def create_dim_transaction(dict_of_df): + pass + +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"] = pd.to_datetime(df_sales["created_at"]).dt.date + df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time + pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") + # df_sales.rename(columns={"staff_id": "sales_staff_id"}) + fact_sales_order = df_sales.loc[:,[ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id" + ]] + return fact_sales_order + +## fact_purchase_order from purchase_order +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'].date() + df_po['created_time'] = df_po['created_at'].dt.time + df_po['last_updated_date'] = df_po['last_updated_at'].date() + df_po['last_updated_time'] = df_po['last_updated_at'].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.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + return df_po + + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + fact_payment = df_payment.loc[:,[ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date" + ]] + return fact_payment + +## dim_location from address --> drops 2 columns +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'}).set_index('location_id') + return df_loc + +## dim_counterparty from address and counterparty +def create_dim_counterparty(dict_of_df): + df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) + df_cp = pd.merge(dict_of_df['counterparty'], + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer").set_index('counterparty_id') + return df_cp + + +## dim_date from purchase_order +def create_dim_date(dict_of_df): + sr_date = pd.concat([dict_of_df['created_date'],dict_of_df['last_updated_date'],dict_of_df['agreed_delivery_date'],dict_of_df['agreed_payment_date']]).sort() + df_date = pd.DataFrame(sr_date,columns='date_id') + 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 + df_date.set_index('date_id') + +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 + +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').set_index('currency_id') + return dim_cur + + + + + + + +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 + +def create_fact_payment(dict_of_df): + df_payment = dict_of_df["payment"] + df_payment.index.name = "payment_record_id" + df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + fact_payment = df_payment.loc[:,[ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date" + ]] + return fact_payment + +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 + +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 + +def create_dim_currency(dict_of_df): + df_currency = dict_of_df["currency"] + dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] + mappings = { + "GBP": "Pound", + "USD": "US Dollar", + "EUR": "Euro" + } + dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) + return dim_currency + + +def create_dim_date(dict_of_df): + df_sales = dict_of_df["sales"] + df_sales = df_sales.loc[:, ["agreed_delivery_date"]] + df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] + df_sales["year"] = df_sales["agreed_delivery_date"].dt.year + df_sales["month"] = df_sales["agreed_delivery_date"].dt.month + df_sales["day"] = df_sales["agreed_delivery_date"].dt.day + df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek + df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() + df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() + df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + return dim_date + + +# TO DO: +# complete dim_date from merged fact table +# merge dataframes into one dataframe +# remove duplicates +# test dim_date and fact_sales_order + +def create_sales_star_schema(dict_of_df): + dim_design = create_dim_design(dict_of_df) + dim_staff = create_dim_staff(dict_of_df) + dim_currency = create_dim_currency(dict_of_df) + dim_date = create_dim_date(dict_of_df) + + fact_sales_order = create_fact_sales_order(dict_of_df) + + fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') + fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') + + return fact_sales_order + + + +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 + + + + + -- cgit v1.2.3 From 2231ea89329bd500f7371b7395f5208f7a86c20e Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 10:11:40 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 8e20c5c according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/93 --- src/dataframes.py | 293 +++++++++++++++++++++++++---------------- src/transform_lambda.py | 100 +++++++------- tests/test_fact_sales_order.py | 90 ++++++++++--- tests/test_transform_lambda.py | 16 ++- 4 files changed, 319 insertions(+), 180 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 9ce3be0..684f102 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -8,7 +8,7 @@ import re from datetime import datetime as dt import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -21,9 +21,11 @@ import requests # dim_currency # dim_counterparty + def create_dim_transaction(dict_of_df): pass + def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" @@ -33,36 +35,46 @@ def create_fact_sales_order(dict_of_df): df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") # df_sales.rename(columns={"staff_id": "sales_staff_id"}) - fact_sales_order = df_sales.loc[:,[ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id" - ]] + fact_sales_order = df_sales.loc[ + :, + [ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id", + ], + ] return fact_sales_order -## fact_purchase_order from purchase_order + +# fact_purchase_order from purchase_order + + 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'].date() - df_po['created_time'] = df_po['created_at'].dt.time - df_po['last_updated_date'] = df_po['last_updated_at'].date() - df_po['last_updated_time'] = df_po['last_updated_at'].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.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].date() + df_po["created_time"] = df_po["created_at"].dt.time + df_po["last_updated_date"] = df_po["last_updated_at"].date() + df_po["last_updated_time"] = df_po["last_updated_at"].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.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) return df_po @@ -73,69 +85,97 @@ def create_fact_payment(dict_of_df): df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] + fact_payment = df_payment.loc[ + :, + [ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] return fact_payment -## dim_location from address --> drops 2 columns + +# dim_location from address --> drops 2 columns + + 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'}).set_index('location_id') + df_loc = ( + dict_of_df["address"] + .drop(labels=["created_at", "last_updated"], axis=1) + .rename(columns={"address_id": "location_id"}) + .set_index("location_id") + ) return df_loc -## dim_counterparty from address and counterparty + +# dim_counterparty from address and counterparty + + def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) - df_cp = pd.merge(dict_of_df['counterparty'], - df_prefixed_address, - left_on="legal_address_id", - right_on="address_id", - how="outer").set_index('counterparty_id') + df_prefixed_address = dict_of_df["address"].add_prefix( + "counterparty_legal_", axis=1 + ) + df_cp = pd.merge( + dict_of_df["counterparty"], + df_prefixed_address, + left_on="legal_address_id", + right_on="address_id", + how="outer", + ).set_index("counterparty_id") return df_cp -## dim_date from purchase_order +# dim_date from purchase_order def create_dim_date(dict_of_df): - sr_date = pd.concat([dict_of_df['created_date'],dict_of_df['last_updated_date'],dict_of_df['agreed_delivery_date'],dict_of_df['agreed_payment_date']]).sort() - df_date = pd.DataFrame(sr_date,columns='date_id') - 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 - df_date.set_index('date_id') + sr_date = pd.concat( + [ + dict_of_df["created_date"], + dict_of_df["last_updated_date"], + dict_of_df["agreed_delivery_date"], + dict_of_df["agreed_payment_date"], + ] + ).sort() + df_date = pd.DataFrame(sr_date, columns="date_id") + 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 + df_date.set_index("date_id") + 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"})] + 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) + df_cur = sr.str.split(pat=" - ", expand=True).rename( + {0: "currency_code", 1: "currency_name"}, axis=1 + ) return df_cur -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').set_index('currency_id') - return dim_cur - - - - +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" + ).set_index("currency_id") + return dim_cur def create_dim_payment_type(dict_of_df): @@ -143,6 +183,7 @@ def create_dim_payment_type(dict_of_df): dim_payment_type = df_payment_type.loc[:, ["payment_type_id", "payment_type_name"]] return dim_payment_type + def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" @@ -150,41 +191,57 @@ def create_fact_payment(dict_of_df): df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] + fact_payment = df_payment.loc[ + :, + [ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] return fact_payment + 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"]] + dim_design = df_design.loc[ + :, ["design_id", "design_name", "file_name", "file_location"] + ] return dim_design + 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']] + 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 + def create_dim_currency(dict_of_df): df_currency = dict_of_df["currency"] dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] - mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" - } + mappings = {"GBP": "Pound", "USD": "US Dollar", "EUR": "Euro"} dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) return dim_currency @@ -200,39 +257,49 @@ def create_dim_date(dict_of_df): df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + dim_date = [ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ] # series.dt.quarter() return dim_date -# TO DO: +# TO DO: # complete dim_date from merged fact table # merge dataframes into one dataframe # remove duplicates # test dim_date and fact_sales_order + def create_sales_star_schema(dict_of_df): dim_design = create_dim_design(dict_of_df) dim_staff = create_dim_staff(dict_of_df) dim_currency = create_dim_currency(dict_of_df) dim_date = create_dim_date(dict_of_df) - + fact_sales_order = create_fact_sales_order(dict_of_df) - - fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') - - return fact_sales_order + fact_sales_order = fact_sales_order.merge(dim_design, on="design_id", how="left") + fact_sales_order = fact_sales_order.merge( + dim_staff, left_on="sales_staff_id", right_on="staff_id", how="left" + ) + fact_sales_order = fact_sales_order.merge( + dim_currency, on="currency_id", how="left" + ) + fact_sales_order = fact_sales_order.merge( + dim_date, left_on="agreed_delivery_date", right_on="date_id", how="left" + ) + + return fact_sales_order 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 - - - - - diff --git a/src/transform_lambda.py b/src/transform_lambda.py index d30d91d..3e74ee0 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -6,12 +6,14 @@ import pandas as pd import pyarrow as pa import pyarrow.parquet as pq from src.dataframes import * + # from src.extract_lambda import extract_bucket, DBConnectionException import boto3 from botocore.exceptions import ClientError from pg8000.native import Connection, InterfaceError from datetime import datetime + class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -20,6 +22,7 @@ class DBConnectionException(Exception): self.message = str(e) super().__init__(self.message) + logger = logging.getLogger(__name__) logging.basicConfig( @@ -45,44 +48,45 @@ tables = [ "payment_type", ] + def lambda_handler(event, context): db = None - - try: + + try: db = connect_to_database() - bucket = bucket_name('transform') + bucket = bucket_name("transform") existing_s3_files = list_existing_s3_files(bucket) - dict_of_df = read_from_s3_subfolder_to_df(tables, extract_bucket(), client=boto3.client("s3")) + dict_of_df = read_from_s3_subfolder_to_df( + tables, extract_bucket(), 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)} - + "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)} - + "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 + existing_s3_files, immutable_df_dict, mutable_df_dict, bucket ) - - if not status['uploaded']: + + if not status["uploaded"]: logger.info("No dataframes written to the bucket.") return { - 'statusCode': 204, - "body": json.dumps("No files where uploaded."), + "statusCode": 204, + "body": json.dumps("No files where uploaded."), } - + return { "statusCode": 200, "body": json.dumps( @@ -90,7 +94,7 @@ def lambda_handler(event, context): '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.")} @@ -99,34 +103,38 @@ def lambda_handler(event, context): 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': []} +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) + status["not_uploaded"].append(table_name) else: - parquet_file = df.to_parquet(f'{table_name}.parquet', engine='pyarrow') #or fastparquet - client.upload_file(parquet_file, bucket, f'{table_name}.parquet') - status['uploaded'].append(table_name) + parquet_file = df.to_parquet( + f"{table_name}.parquet", engine="pyarrow" + ) # or fastparquet + client.upload_file(parquet_file, 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 + 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(parquet_file, bucket, s3_key) - status['uploaded'].append(table_name) - + status["uploaded"].append(table_name) return status - def retrieve_secrets(): secret_name = "bentley-secrets" region_name = "eu-west-2" @@ -175,19 +183,23 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client("s3")): 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"] + 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) + response = client.list_objects_v2(Bucket=bucket_name) if "Contents" in response: existing_files = [obj["Key"] for obj in response["Contents"]] @@ -198,4 +210,4 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): except ClientError as e: logger.error(f"Error listing S3 objects: {e}") - return existing_files \ No newline at end of file + return existing_files diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 82845d7..87e3ade 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,57 +1,109 @@ -from src.fact_sales_order import create_dim_design, create_dim_staff, create_dim_currency +from src.fact_sales_order import ( + create_dim_design, + create_dim_staff, + create_dim_currency, +) import pandas as pd + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreateDimCurrency: def test_dim_currency_returns_dataframe(self): d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} test_df = {"currency": pd.DataFrame(data=d)} result = create_dim_currency(test_df) - assert isinstance(result, pd.DataFrame) - + assert isinstance(result, pd.DataFrame) + def test_dim_currency_returns_columns_and_values(self): d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} test_df = {"currency": pd.DataFrame(data=d)} result = create_dim_currency(test_df) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() assert result.equals(expected_result) - - \ No newline at end of file diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 516f83b..a91da92 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -39,7 +39,12 @@ class TestReadFromS3: ) print(result) expected_df = pd.DataFrame( - np.array([["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"]]), + np.array( + [ + ["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], + ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"], + ] + ), columns=["Food_type", "Flavour", "Colour", "last_updated"], ) assert isinstance(result, dict) @@ -56,7 +61,12 @@ class TestReadFromS3: tables, bucket="dummy_buc", client=s3_client ) expected_foods_df = pd.DataFrame( - np.array([["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"]]), + np.array( + [ + ["Vegetable", "Sour", "Green", "2022-11-03 14:20:49.962"], + ["Berry", "Sweet", "Red", "2022-11-03 14:20:49.962"], + ] + ), columns=["Food_type", "Flavour", "Colour", "last_updated"], ) expected_cars_df = pd.DataFrame( @@ -72,5 +82,3 @@ class TestReadFromS3: assert list(result.keys()) == tables assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) - - -- cgit v1.2.3 From eb0449447af38b8e162421b92cd0d8a8744540c6 Mon Sep 17 00:00:00 2001 From: T-Aji Date: Fri, 23 Aug 2024 11:42:34 +0100 Subject: removed duplicate functions --- src/dataframes.py | 117 +++++++++++++----------------------------------------- 1 file changed, 28 insertions(+), 89 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 9ce3be0..380e4c5 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -1,11 +1,5 @@ import pandas as pd from bs4 import BeautifulSoup -from src.transform_lambda import read_from_s3_subfolder_to_df, tables -from src.extract_lambda import extract_bucket -import json -import boto3 -import re -from datetime import datetime as dt import requests #Table names: @@ -21,8 +15,7 @@ import requests # dim_currency # dim_counterparty -def create_dim_transaction(dict_of_df): - pass + def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] @@ -31,8 +24,6 @@ def create_fact_sales_order(dict_of_df): df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - pd.merge(dict_of_df["staff"], df_sales["sales_staff_id"], on="staff_id", how="left") - # df_sales.rename(columns={"staff_id": "sales_staff_id"}) fact_sales_order = df_sales.loc[:,[ "sales_record_id", "sales_order_id", @@ -90,6 +81,11 @@ def create_fact_payment(dict_of_df): ]] return fact_payment +def create_dim_transaction(dict_of_df): + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1).set_index('transaction_id') + dim_transaction = df_transaction.loc[:, ["payment_type_id", "payment_type_name"]] + return dim_transaction + ## dim_location from address --> drops 2 columns 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'}).set_index('location_id') @@ -119,6 +115,20 @@ def create_dim_date(dict_of_df): df_date['quarter'] = df_date['date_id'].dt.quarter df_date.set_index('date_id') +def create_dim_date(dict_of_df): + df_sales = dict_of_df["sales"] + df_sales = df_sales.loc[:, ["agreed_delivery_date"]] + df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] + df_sales["year"] = df_sales["agreed_delivery_date"].dt.year + df_sales["month"] = df_sales["agreed_delivery_date"].dt.month + df_sales["day"] = df_sales["agreed_delivery_date"].dt.day + df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek + df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() + df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() + df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() + dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() + return dim_date + def scrape_currency_names(): response = requests.get('https://www.xe.com/currency/').content soup = BeautifulSoup(response,'html.parser') @@ -130,107 +140,36 @@ def scrape_currency_names(): 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').set_index('currency_id') + print(dim_cur) 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 -def create_fact_payment(dict_of_df): - df_payment = dict_of_df["payment"] - df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] - return fact_payment - +#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 -def create_dim_currency(dict_of_df): - df_currency = dict_of_df["currency"] - dim_currency = df_currency.loc[:, ["currency_id", "currency_code"]] - mappings = { - "GBP": "Pound", - "USD": "US Dollar", - "EUR": "Euro" - } - dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings) - return dim_currency -def create_dim_date(dict_of_df): - df_sales = dict_of_df["sales"] - df_sales = df_sales.loc[:, ["agreed_delivery_date"]] - df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] - df_sales["year"] = df_sales["agreed_delivery_date"].dt.year - df_sales["month"] = df_sales["agreed_delivery_date"].dt.month - df_sales["day"] = df_sales["agreed_delivery_date"].dt.day - df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek - df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() - df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() - df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() - return dim_date -# TO DO: -# complete dim_date from merged fact table -# merge dataframes into one dataframe -# remove duplicates -# test dim_date and fact_sales_order - -def create_sales_star_schema(dict_of_df): - dim_design = create_dim_design(dict_of_df) - dim_staff = create_dim_staff(dict_of_df) - dim_currency = create_dim_currency(dict_of_df) - dim_date = create_dim_date(dict_of_df) - - fact_sales_order = create_fact_sales_order(dict_of_df) - - fact_sales_order = fact_sales_order.merge(dim_design, on='design_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_staff, left_on='sales_staff_id', right_on='staff_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_currency, on='currency_id', how='left') - fact_sales_order = fact_sales_order.merge(dim_date, left_on='agreed_delivery_date', right_on='date_id', how='left') - - return fact_sales_order -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 + + + + -- cgit v1.2.3 From eeaaeb471f3410e5c655836253484a41e54ef71b Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Fri, 23 Aug 2024 13:13:41 +0100 Subject: fix: refactoring for create_dim_date to include all date columns from all fact dfs, tested on dummy data. Tests are not written --- src/dataframes.py | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 380e4c5..042c8aa 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -104,30 +104,23 @@ def create_dim_counterparty(dict_of_df): ## dim_date from purchase_order def create_dim_date(dict_of_df): - sr_date = pd.concat([dict_of_df['created_date'],dict_of_df['last_updated_date'],dict_of_df['agreed_delivery_date'],dict_of_df['agreed_payment_date']]).sort() - df_date = pd.DataFrame(sr_date,columns='date_id') + fact_dfs = [create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df)] + date_col_names = [col_name for col_name in list(fact_dfs[0].columns) if 'date' in col_name] + list_of_date_columns = [] + for df in fact_dfs: + 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 - df_date.set_index('date_id') - -def create_dim_date(dict_of_df): - df_sales = dict_of_df["sales"] - df_sales = df_sales.loc[:, ["agreed_delivery_date"]] - df_sales["agreed_delivery_date"] = pd.to_datetime["agreed_delivery_date"] - df_sales["year"] = df_sales["agreed_delivery_date"].dt.year - df_sales["month"] = df_sales["agreed_delivery_date"].dt.month - df_sales["day"] = df_sales["agreed_delivery_date"].dt.day - df_sales["day_of_week"] = df_sales["agreed_delivery_date"].dt.dayofweek - df_sales["day_name"] = df_sales["agreed_delivery_date"].dt.day_name() - df_sales["month_name"] = df_sales["agreed_delivery_date"].dt.month_name() - df_sales["quarter"] = df_sales["agreed_delivery_date"].dt.quarter() - dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month_name", "quarter"] #series.dt.quarter() - return dim_date + 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 #By default, the DataFrame index is not included when uploading to RDS. We are not setting indexes to retain the column information + return def scrape_currency_names(): response = requests.get('https://www.xe.com/currency/').content -- cgit v1.2.3 From a69fe58b47bcc5ad02986bcf404f060774aec9a7 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Fri, 23 Aug 2024 16:22:52 +0100 Subject: wip: pushing again --- src/dataframes.py | 12 ++++++------ src/transform_lambda.py | 1 + tests/test_transform_lambda.py | 43 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 47 insertions(+), 9 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 684f102..18e1fac 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -1,11 +1,11 @@ import pandas as pd from bs4 import BeautifulSoup -from src.transform_lambda import read_from_s3_subfolder_to_df, tables -from src.extract_lambda import extract_bucket -import json -import boto3 -import re -from datetime import datetime as dt +# from src.transform_lambda import read_from_s3_subfolder_to_df, tables +# from src.extract_lambda import extract_bucket +# import json +# import boto3 +# import re +# from datetime import datetime as dt import requests # Table names: diff --git a/src/transform_lambda.py b/src/transform_lambda.py index defa15d..7677f66 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -207,5 +207,6 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): except ClientError as e: logger.error(f"Error listing S3 objects: {e}") + raise e return existing_files diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 37ca08f..06235f7 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,12 +1,19 @@ -from src.transform_lambda import read_from_s3_subfolder_to_df +from src.transform_lambda import read_from_s3_subfolder_to_df, list_existing_s3_files from moto import mock_aws import pytest import pandas as pd import os import boto3 +from botocore.exceptions import ClientError import numpy as np +# import caplog +import logging + +logger = logging.getLogger() +logger.setLevel(logging.INFO) + @pytest.fixture(scope="class") def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" @@ -23,7 +30,7 @@ def s3_client(aws_credentials): class TestReadFromS3: - @pytest.mark.skip(reason="The test is broken!") + # @pytest.mark.skip(reason="The test is broken!") def test_returns_dictionary_with_correct_value_pair(self, s3_client): s3_client.create_bucket( Bucket="dummy_buc", @@ -53,7 +60,7 @@ class TestReadFromS3: assert isinstance(result["Foods"], pd.DataFrame) assert result["Foods"].eq(expected_df, axis="columns").all(axis=None) - @pytest.mark.skip(reason="The test is broken!") + # @pytest.mark.skip(reason="The test is broken!") def test_returns_dictionary_of_dataframes_for_multiple_tables(self, s3_client): s3_client.upload_file( "tests/dummy_2.csv", "dummy_buc", "Cars/2024/08/21/Cars_14:03:56.csv" @@ -84,3 +91,33 @@ class TestReadFromS3: assert list(result.keys()) == tables assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) + +class TestListExistingFiles: + def test_functions_receives_error_if_no_bucket(self, s3_client, caplog): + caplog.set_level(logging.INFO) + + with pytest.raises(ClientError): + list_existing_s3_files('rando_bucket', client=s3_client) + + assert "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist" in caplog.text + + def test_recieves_logger_error_if_no_files_listed(self, s3_client, caplog): + caplog.set_level(logging.INFO) + + s3_client.create_bucket( + Bucket='mock_bucket', + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + ) + response = list_existing_s3_files('mock_bucket', client=s3_client) + assert 'The bucket is empty' in caplog.text + + def test_retrieves_existing_files(self, s3_client, caplog): + caplog.set_level(logging.INFO) + + s3_client.upload_file( + "tests/dummy.txt", 'mock_bucket', "dummy.txt" + ) + result = list_existing_s3_files('mock_bucket', client=s3_client) + assert result == ["dummy.txt"] + + \ No newline at end of file -- cgit v1.2.3 From 821e241c925e682845e02e9609ba3a2c758966d8 Mon Sep 17 00:00:00 2001 From: Ang Bel Date: Fri, 23 Aug 2024 17:09:27 +0100 Subject: tests: additional tests written (pass) for dim tables transformation. Fact transformation functions not yet tested --- src/dataframes.py | 30 ++++++----- tests/test_fact_sales_order.py | 113 ++++++++++++++++++++++++----------------- 2 files changed, 82 insertions(+), 61 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 042c8aa..7d10aa7 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -81,28 +81,28 @@ def create_fact_payment(dict_of_df): ]] return fact_payment +#test passed def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1).set_index('transaction_id') - dim_transaction = df_transaction.loc[:, ["payment_type_id", "payment_type_name"]] - return dim_transaction + df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + return df_transaction -## dim_location from address --> drops 2 columns +#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'}).set_index('location_id') + df_loc = dict_of_df['address'].drop(labels=['created_at', 'last_updated'], axis=1).rename(columns={'address_id': 'location_id'}) return df_loc -## dim_counterparty from address and counterparty + def create_dim_counterparty(dict_of_df): df_prefixed_address = dict_of_df['address'].add_prefix('counterparty_legal_', axis=1) df_cp = pd.merge(dict_of_df['counterparty'], df_prefixed_address, left_on="legal_address_id", - right_on="address_id", - how="outer").set_index('counterparty_id') + right_on="counterparty_legal_address_id", + how="outer") + df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) return df_cp - -## dim_date from purchase_order +#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)] date_col_names = [col_name for col_name in list(fact_dfs[0].columns) if 'date' in col_name] @@ -119,9 +119,10 @@ def create_dim_date(dict_of_df): 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 #By default, the DataFrame index is not included when uploading to RDS. We are not setting indexes to retain the column information - return + 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') @@ -130,11 +131,12 @@ def scrape_currency_names(): 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').set_index('currency_id') - print(dim_cur) + 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"] diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index ca53faa..f0796eb 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -1,6 +1,7 @@ -from src.dataframes import create_dim_design, create_dim_staff, create_dim_payment_type, create_dim_counterparty, create_dim_currency +from src.dataframes import * import pandas as pd from unittest.mock import patch +from datetime import datetime as dt class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): @@ -52,59 +53,77 @@ class TestCreatePaymentType: assert result.equals(expected_df) class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_values(self): - data_d = {"counterparty_id": ["Hello", "Bye"], + + def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): + data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], "counterparty_legal_name": ["Hello", "Bye"], - "counterparty_legal_address_line_1": ["Hello", "Bye"], - } - data_a = {"address_id": - "address", - } - test_df = {"address": pd.DataFrame(data=data_a)} - test_df = {} + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"]}) + data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], + "postcode":[98365,93753]}) + test_df = {"address": data_a,"counterparty":data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", - "counterparty_legal_name", - "counterparty_legal_address_line_1", - "counterparty_legal_address_line_2", - "counterparty_legal_district", - "counterparty_legal_city", - "counterparty_legal_postal_code", - "counterparty_legal_postal_code", - "counterparty_legal_phone_number"] - expected_d = {"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "counterparty_legal_address_line_1": ["Hello", "Bye"], - "counterparty_legal_address_line_2": ["Hello", "Bye"], - "counterparty_legal_district": ["Hello", "Bye"], - "counterparty_legal_city": ["Hello", "Bye"], - "counterparty_legal_postal_code": ["Hello", "Bye"], - "counterparty_legal_postal_code": ["Hello", "Bye"], - "counterparty_legal_phone_number": ["Hello", "Bye"]} - expected_df = pd.DataFrame(data=expected_d) + expected_columns = ["counterparty_id", "counterparty_legal_name", + "commercial_contact", "counterparty_legal_postcode"] + print(data_l) + print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns - assert result.equals(expected_df) -# # figuring out how to mock currency scraper functiom -# class TestCreateDimCurrency: -# @patch("src.dataframes.scrape_currency_names") -# def test_dim_currency_returns_columns_and_values(self): -# d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} -# test_df = {"currency": pd.DataFrame(data=d)} -# result = create_dim_currency(test_df) -# expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} -# expected_df = pd.DataFrame(data=expected_d) -# expected_result = expected_df.copy() -# assert result.equals(expected_result) +class TestCreateDimCurrency: + + def test_dim_currency_returns_columns_and_values(self): + nones = [None,None,None] + d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + test_df = {"currency": pd.DataFrame(data=d)} + scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) + result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) + expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} + expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) -# def test_dim_currency_returns_dataframe(self): -# d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"]} -# test_df = {"currency": pd.DataFrame(data=d)} -# result = create_dim_currency(test_df) -# assert isinstance(result, pd.DataFrame) + def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): + result = scrape_currency_names() + assert isinstance(result,pd.DataFrame) + assert list(result.columns) == ['currency_code', 'currency_name'] + +class TestCreateDimDate: + + def test_returns_required_columns(self): + df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) + df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) + df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) + expected_df = pd.DataFrame(data= + [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], + [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], + [dt(2021,9,13),2021,9,13,0,'Monday','September',3], + [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], + [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], + columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + with patch("src.dataframes.create_fact_payment") as mock_fp: + with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: + with patch("src.dataframes.create_fact_sales_order") as mock_fso: + mock_fp.return_value = df_one + mock_fpo.return_value = df_two + mock_fso.return_value = df_three + result = create_dim_date({'dum':0}) + result.reset_index(inplace=True,drop=True) + assert result.eq(expected_df, axis="columns").all(axis=None) - +class TestCreateDimLocation: + def test_returns_correct_columns_lo(self): + dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','address_id','postal_code'])} + result = create_dim_location(dict_df) + assert list(result.columns) == ['location_id','postal_code'] + +class TestCreateDimTransaction: + def test_returns_correct_columns_tr(self): + dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], + columns=['created_at','last_updated','transaction_id','some_other_id'])} + result = create_dim_transaction(dict_df) + assert list(result.columns) == ['transaction_id','some_other_id'] \ No newline at end of file -- cgit v1.2.3 From 30525f27ba1d20c65216cbe58a62953b8f1fe947 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:11:04 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 821e241 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/96 --- src/dataframes.py | 250 +++++++++++++++++++++++++---------------- tests/test_fact_sales_order.py | 235 ++++++++++++++++++++++++++++---------- 2 files changed, 330 insertions(+), 155 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 7d10aa7..737ee2a 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -2,7 +2,7 @@ import pandas as pd from bs4 import BeautifulSoup import requests -#Table names: +# Table names: # fact_sales_order # fact_purchase_orders # fact_payment @@ -16,7 +16,6 @@ import requests # dim_counterparty - def create_fact_sales_order(dict_of_df): df_sales = dict_of_df["sales_order"] df_sales.index.name = "sales_record_id" @@ -24,36 +23,46 @@ def create_fact_sales_order(dict_of_df): df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time - fact_sales_order = df_sales.loc[:,[ - "sales_record_id", - "sales_order_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "sales_staff_id", - "counterparty_id", - "units_sold", - "unit_price", - "currency_id", - "design_id", - "agreed_payment_date", - "agreed_delivery_date", - "agreed_delivery_location_id" - ]] + fact_sales_order = df_sales.loc[ + :, + [ + "sales_record_id", + "sales_order_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "sales_staff_id", + "counterparty_id", + "units_sold", + "unit_price", + "currency_id", + "design_id", + "agreed_payment_date", + "agreed_delivery_date", + "agreed_delivery_location_id", + ], + ] return fact_sales_order -## fact_purchase_order from purchase_order + +# fact_purchase_order from purchase_order + + 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'].date() - df_po['created_time'] = df_po['created_at'].dt.time - df_po['last_updated_date'] = df_po['last_updated_at'].date() - df_po['last_updated_time'] = df_po['last_updated_at'].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.drop(labels=['created_at','last_updated_at'],axis=1,inplace=True) + df_po = dict_of_df["purchase_order"] + df_po.index.name = "purchase_record_id" + df_po["created_date"] = df_po["created_at"].date() + df_po["created_time"] = df_po["created_at"].dt.time + df_po["last_updated_date"] = df_po["last_updated_at"].date() + df_po["last_updated_time"] = df_po["last_updated_at"].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.drop(labels=["created_at", "last_updated_at"], axis=1, inplace=True) return df_po @@ -64,109 +73,158 @@ def create_fact_payment(dict_of_df): df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time - fact_payment = df_payment.loc[:,[ - "payment_record_id", - "payment_id", - "created_date", - "created_time", - "last_updated_date", - "last_updated_time", - "transaction_id", - "counterparty_id", - "payment_amount", - "currency_id", - "payment_type_id", - "paid", - "payment_date" - ]] + fact_payment = df_payment.loc[ + :, + [ + "payment_record_id", + "payment_id", + "created_date", + "created_time", + "last_updated_date", + "last_updated_time", + "transaction_id", + "counterparty_id", + "payment_amount", + "currency_id", + "payment_type_id", + "paid", + "payment_date", + ], + ] return fact_payment -#test passed + +# test passed + + def create_dim_transaction(dict_of_df): - df_transaction = dict_of_df["transaction"].drop(labels=['created_at', 'last_updated'], axis=1) + df_transaction = dict_of_df["transaction"].drop( + labels=["created_at", "last_updated"], axis=1 + ) return df_transaction -#test passed + +# 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'}) + 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'].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="outer") - df_cp.drop(columns=["legal_address_id","counterparty_legal_address_id"],inplace=True) + df_prefixed_address = dict_of_df["address"].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="outer", + ) + df_cp.drop( + columns=["legal_address_id", "counterparty_legal_address_id"], inplace=True + ) return df_cp -#test passed + +# 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)] - date_col_names = [col_name for col_name in list(fact_dfs[0].columns) if 'date' in col_name] + fact_dfs = [ + create_fact_payment(dict_of_df), + create_fact_purchase_orders(dict_of_df), + create_fact_sales_order(dict_of_df), + ] + date_col_names = [ + col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name + ] list_of_date_columns = [] for df in fact_dfs: 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']) + 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 + 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 -#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 +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/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index f0796eb..a245379 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -3,42 +3,88 @@ import pandas as pd from unittest.mock import patch from datetime import datetime as dt + class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) assert isinstance(result, pd.DataFrame) def test_dim_design_returns_correct_columns_and_values(self): - d = {"test": ["Hello", "Bye"], "design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], - "file_name": ["Hello", "Bye"], "file_location": ["Hello", "Bye"], "Hello": ["Hello", "Bye"]} + d = { + "test": ["Hello", "Bye"], + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + "Hello": ["Hello", "Bye"], + } test_df = {"design": pd.DataFrame(data=d)} result = create_dim_design(test_df) - d2 = {"design_id": ["Hello", "Bye"], "design_name": ["Hello", "Bye"], "file_name": ["Hello", "Bye"], - "file_location": ["Hello", "Bye"]} + d2 = { + "design_id": ["Hello", "Bye"], + "design_name": ["Hello", "Bye"], + "file_name": ["Hello", "Bye"], + "file_location": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=d2) expected_result = expected_df.copy() assert result.equals(expected_result) + class TestCreateDimStaff: def test_dim_staff_returns_dataframe(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - assert isinstance(result, pd.DataFrame) + assert isinstance(result, pd.DataFrame) def test_dim_staff_returns_correct_columns_and_values(self): - d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} - d2 = {"department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"], "department_id": ["Hello", "Bye"]} + d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } + d2 = { + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + "department_id": ["Hello", "Bye"], + } test_df = {"staff": pd.DataFrame(data=d), "department": pd.DataFrame(data=d2)} result = create_dim_staff(test_df) - expected_d = {"staff_id": ["Hello", "Bye"], "first_name": ["Hello", "Bye"], "last_name": ["Hello", "Bye"], "department_name": ["Hello", "Bye"], "location": ["Hello", "Bye"], "email_address": ["Hello", "Bye"]} + expected_d = { + "staff_id": ["Hello", "Bye"], + "first_name": ["Hello", "Bye"], + "last_name": ["Hello", "Bye"], + "department_name": ["Hello", "Bye"], + "location": ["Hello", "Bye"], + "email_address": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) expected_result = expected_df.copy() - assert result.equals(expected_result) + assert result.equals(expected_result) + class TestCreatePaymentType: def test_create_dim_payment_type_returns_correct_columns_and_values(self): @@ -46,84 +92,155 @@ class TestCreatePaymentType: test_df = {"payment_type": pd.DataFrame(data=d)} result = create_dim_payment_type(test_df) expected_columns = ["payment_type_id", "payment_type_name"] - expected_d = {"payment_type_id": ["Hello", "Bye"], "payment_type_name": ["Hello", "Bye"]} + expected_d = { + "payment_type_id": ["Hello", "Bye"], + "payment_type_name": ["Hello", "Bye"], + } expected_df = pd.DataFrame(data=expected_d) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns assert result.equals(expected_df) + class TestCreateDimCounterparty: - def test_create_dim_counterparty_type_returns_correct_columns_and_object(self): - data_l = pd.DataFrame(data={"counterparty_id": ["Hello", "Bye"], - "counterparty_legal_name": ["Hello", "Bye"], - "commercial_contact": ["Hello", "Bye"], - "legal_address_id": ["bond street", "regent street"]}) - data_a = pd.DataFrame(data={"address_id":["bond street", "regent street"], - "postcode":[98365,93753]}) - test_df = {"address": data_a,"counterparty":data_l} + data_l = pd.DataFrame( + data={ + "counterparty_id": ["Hello", "Bye"], + "counterparty_legal_name": ["Hello", "Bye"], + "commercial_contact": ["Hello", "Bye"], + "legal_address_id": ["bond street", "regent street"], + } + ) + data_a = pd.DataFrame( + data={ + "address_id": ["bond street", "regent street"], + "postcode": [98365, 93753], + } + ) + test_df = {"address": data_a, "counterparty": data_l} result = create_dim_counterparty(test_df) - expected_columns = ["counterparty_id", "counterparty_legal_name", - "commercial_contact", "counterparty_legal_postcode"] + expected_columns = [ + "counterparty_id", + "counterparty_legal_name", + "commercial_contact", + "counterparty_legal_postcode", + ] print(data_l) print(data_a) assert isinstance(result, pd.DataFrame) assert list(result.columns) == expected_columns + class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): - nones = [None,None,None] - d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"],"created_at":nones,"last_updated":nones} + nones = [None, None, None] + d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "created_at": nones, + "last_updated": nones, + } test_df = {"currency": pd.DataFrame(data=d)} - scraper_output = pd.DataFrame({"currency_code":["RUS","USD","PHP","GBP","EUR"],"currency_name":["Rubble","US Dollar","Peso","Pound","Euro"]}) - result = create_dim_currency(test_df,names=scraper_output).sort_values(by="currency_code",axis=0) - expected_d = {"currency_id": [1, 2, 3], "currency_code": ["USD", "EUR", "GBP"], "currency_name": ["US Dollar", "Euro", "Pound"]} - expected_df = pd.DataFrame(data=expected_d).sort_values(by="currency_code",axis=0) - assert isinstance(result, pd.DataFrame) - assert result.equals(expected_df) + scraper_output = pd.DataFrame( + { + "currency_code": ["RUS", "USD", "PHP", "GBP", "EUR"], + "currency_name": ["Rubble", "US Dollar", "Peso", "Pound", "Euro"], + } + ) + result = create_dim_currency(test_df, names=scraper_output).sort_values( + by="currency_code", axis=0 + ) + expected_d = { + "currency_id": [1, 2, 3], + "currency_code": ["USD", "EUR", "GBP"], + "currency_name": ["US Dollar", "Euro", "Pound"], + } + expected_df = pd.DataFrame(data=expected_d).sort_values( + by="currency_code", axis=0 + ) + assert isinstance(result, pd.DataFrame) + assert result.equals(expected_df) def test_scrape_currency_names_returns_dataframe_with_correct_collumns(self): result = scrape_currency_names() - assert isinstance(result,pd.DataFrame) - assert list(result.columns) == ['currency_code', 'currency_name'] + assert isinstance(result, pd.DataFrame) + assert list(result.columns) == ["currency_code", "currency_name"] -class TestCreateDimDate: +class TestCreateDimDate: def test_returns_required_columns(self): - df_one = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 5, 13),'not_dat':None},index=[0]) - df_two = pd.DataFrame(data={'updated_date':dt(2020, 5, 17),'created_date':dt(2021, 9, 13)},index=[0]) - df_three = pd.DataFrame(data={'updated_date':dt(2022, 5, 17),'created_date':dt(2023, 5, 13)},index=[0]) - expected_df = pd.DataFrame(data= - [[dt(2020,5,17),2020,5,17,6,'Sunday','May',2], - [dt(2021,5,13),2021,5,13,3,'Thursday','May',2], - [dt(2021,9,13),2021,9,13,0,'Monday','September',3], - [dt(2022,5,17),2022,5,17,1,'Tuesday','May',2], - [dt(2023,5,13),2023,5,13,5,'Saturday','May',2]], - columns=['date_id','year','month','day','day_of_week','day_name','month_name','quarter']) + df_one = pd.DataFrame( + data={ + "updated_date": dt(2020, 5, 17), + "created_date": dt(2021, 5, 13), + "not_dat": None, + }, + index=[0], + ) + df_two = pd.DataFrame( + data={"updated_date": dt(2020, 5, 17), "created_date": dt(2021, 9, 13)}, + index=[0], + ) + df_three = pd.DataFrame( + data={"updated_date": dt(2022, 5, 17), "created_date": dt(2023, 5, 13)}, + index=[0], + ) + expected_df = pd.DataFrame( + data=[ + [dt(2020, 5, 17), 2020, 5, 17, 6, "Sunday", "May", 2], + [dt(2021, 5, 13), 2021, 5, 13, 3, "Thursday", "May", 2], + [dt(2021, 9, 13), 2021, 9, 13, 0, "Monday", "September", 3], + [dt(2022, 5, 17), 2022, 5, 17, 1, "Tuesday", "May", 2], + [dt(2023, 5, 13), 2023, 5, 13, 5, "Saturday", "May", 2], + ], + columns=[ + "date_id", + "year", + "month", + "day", + "day_of_week", + "day_name", + "month_name", + "quarter", + ], + ) with patch("src.dataframes.create_fact_payment") as mock_fp: with patch("src.dataframes.create_fact_purchase_orders") as mock_fpo: with patch("src.dataframes.create_fact_sales_order") as mock_fso: mock_fp.return_value = df_one mock_fpo.return_value = df_two mock_fso.return_value = df_three - result = create_dim_date({'dum':0}) - result.reset_index(inplace=True,drop=True) + result = create_dim_date({"dum": 0}) + result.reset_index(inplace=True, drop=True) assert result.eq(expected_df, axis="columns").all(axis=None) - -class TestCreateDimLocation: + +class TestCreateDimLocation: def test_returns_correct_columns_lo(self): - dict_df = {'address':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','address_id','postal_code'])} + dict_df = { + "address": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=["created_at", "last_updated", "address_id", "postal_code"], + ) + } result = create_dim_location(dict_df) - assert list(result.columns) == ['location_id','postal_code'] - + assert list(result.columns) == ["location_id", "postal_code"] + + class TestCreateDimTransaction: - def test_returns_correct_columns_tr(self): - dict_df = {'transaction':pd.DataFrame(data=[['some_time','some_other_time',1,'SE18 9QO']], - columns=['created_at','last_updated','transaction_id','some_other_id'])} + def test_returns_correct_columns_tr(self): + dict_df = { + "transaction": pd.DataFrame( + data=[["some_time", "some_other_time", 1, "SE18 9QO"]], + columns=[ + "created_at", + "last_updated", + "transaction_id", + "some_other_id", + ], + ) + } result = create_dim_transaction(dict_df) - assert list(result.columns) == ['transaction_id','some_other_id'] - \ No newline at end of file + assert list(result.columns) == ["transaction_id", "some_other_id"] -- cgit v1.2.3 From 843471508b150f505c2b8921d175c8f9b781bf48 Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Fri, 23 Aug 2024 16:25:59 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in 8f75a47 according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/96 --- src/dataframes.py | 76 +++++++++++++++++++++++------------------- tests/test_fact_sales_order.py | 3 -- 2 files changed, 41 insertions(+), 38 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index fc84f48..f2cae5d 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -16,14 +16,15 @@ import requests # dim_counterparty - 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"] = pd.to_datetime(df_sales["created_at"]).dt.date df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime( + df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime( + df_sales["last_updated"]).dt.time fact_sales_order = df_sales.loc[ :, [ @@ -70,10 +71,14 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime(df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime(df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime(df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime(df_payment["last_updated"]).dt.time + df_payment["created_date"] = pd.to_datetime( + df_payment["created_at"]).dt.date + df_payment["created_time"] = pd.to_datetime( + df_payment["created_at"]).dt.time + df_payment["last_updated_date"] = pd.to_datetime( + df_payment["last_updated"]).dt.date + df_payment["last_updated_time"] = pd.to_datetime( + df_payment["last_updated"]).dt.time fact_payment = df_payment.loc[ :, [ @@ -95,7 +100,6 @@ def create_fact_payment(dict_of_df): return fact_payment - # test passed @@ -117,10 +121,10 @@ def create_dim_location(dict_of_df): def create_dim_counterparty(dict_of_df): - df_prefixed_address = dict_of_df["address"].add_prefix( + df_prefixed_address=dict_of_df["address"].add_prefix( "counterparty_legal_", axis=1 ) - df_cp = pd.merge( + df_cp=pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -137,40 +141,40 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs = [ + fact_dfs=[ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), ] - date_col_names = [ + date_col_names=[ col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name ] - list_of_date_columns = [] + list_of_date_columns=[] for df in fact_dfs: 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"]) + 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 + 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 = [ + 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( + sr=pd.Series(currency) + df_cur=sr.str.split(pat=" - ", expand=True).rename( {0: "currency_code", 1: "currency_name"}, axis=1 ) return df_cur @@ -179,8 +183,9 @@ def scrape_currency_names(): 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=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 @@ -189,8 +194,9 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): # 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"]] + 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 @@ -199,8 +205,8 @@ def create_dim_payment_type(dict_of_df): def create_dim_design(dict_of_df): - df_design = dict_of_df["design"] - dim_design = df_design.loc[ + df_design=dict_of_df["design"] + dim_design=df_design.loc[ :, ["design_id", "design_name", "file_name", "file_location"] ] return dim_design @@ -210,10 +216,10 @@ def create_dim_design(dict_of_df): # tests passed def create_dim_staff(dict_of_df): - staff_department = pd.merge( + staff_department=pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff = staff_department.loc[ + dim_staff=staff_department.loc[ :, [ "staff_id", diff --git a/tests/test_fact_sales_order.py b/tests/test_fact_sales_order.py index 77395a1..a245379 100644 --- a/tests/test_fact_sales_order.py +++ b/tests/test_fact_sales_order.py @@ -4,7 +4,6 @@ from unittest.mock import patch from datetime import datetime as dt - class TestCreateDimDesign: def test_dim_design_returns_dataframe(self): d = { @@ -135,7 +134,6 @@ class TestCreateDimCounterparty: class TestCreateDimCurrency: - def test_dim_currency_returns_columns_and_values(self): nones = [None, None, None] d = { @@ -246,4 +244,3 @@ class TestCreateDimTransaction: } result = create_dim_transaction(dict_df) assert list(result.columns) == ["transaction_id", "some_other_id"] - -- cgit v1.2.3 From 72ebda950c84d7b519db9a236b35a7fafcbb1899 Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Tue, 27 Aug 2024 09:30:34 +0100 Subject: wip: added a bracket in dataframes --- src/dataframes.py | 4 ++-- src/transform_lambda.py | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index f2cae5d..d0479f1 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -115,9 +115,9 @@ 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"}) + .rename(columns={"address_id": "location_id"})) return df_loc - + def create_dim_counterparty(dict_of_df): diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 7677f66..57e9042 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -5,12 +5,13 @@ import logging import pandas as pd import pyarrow as pa import pyarrow.parquet as pq -from src.dataframes import * +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.""" -- cgit v1.2.3 From c68f63fa3aebcf9b77c24d6e2aec91a4ff4950bb Mon Sep 17 00:00:00 2001 From: lian-manonog Date: Tue, 27 Aug 2024 10:46:03 +0100 Subject: wip: refactored fact payment function --- src/dataframes.py | 14 ++++++-------- src/transform_lambda.py | 3 +++ 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index d0479f1..94eb509 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -71,14 +71,12 @@ def create_fact_purchase_orders(dict_of_df): def create_fact_payment(dict_of_df): df_payment = dict_of_df["payment"] df_payment.index.name = "payment_record_id" - df_payment["created_date"] = pd.to_datetime( - df_payment["created_at"]).dt.date - df_payment["created_time"] = pd.to_datetime( - df_payment["created_at"]).dt.time - df_payment["last_updated_date"] = pd.to_datetime( - df_payment["last_updated"]).dt.date - df_payment["last_updated_time"] = pd.to_datetime( - df_payment["last_updated"]).dt.time + df_payment["created_date"] = df_payment["created_at"].date() + df_payment["created_time"] = df_payment["created_at"].time + df_payment["last_updated_date"] = df_payment["last_updated"].date() + df_payment["last_updated_time"] = df_payment["last_updated"].time + df_payment["payment_date"] = pd.to_datetime( + df_payment["payment_date"], format="%Y-%m-%d") fact_payment = df_payment.loc[ :, [ diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 57e9042..565b4ee 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -211,3 +211,6 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): raise e return existing_files + +if __name__ == '__main__': + lambda_handler({}, '') \ No newline at end of file -- cgit v1.2.3 From e51e9fc3c7fa886fe5e753bd123d45c8871673bc Mon Sep 17 00:00:00 2001 From: "deepsource-autofix[bot]" <62050782+deepsource-autofix[bot]@users.noreply.github.com> Date: Tue, 27 Aug 2024 09:46:39 +0000 Subject: style: format code with Autopep8, Black and Ruff Formatter This commit fixes the style issues introduced in c68f63f according to the output from Autopep8, Black and Ruff Formatter. Details: https://github.com/ajschofield/de-project-bentley/pull/97 --- src/dataframes.py | 74 ++++++++++++++++++++---------------------- src/transform_lambda.py | 6 ++-- tests/test_transform_lambda.py | 44 +++++++++++++++---------- 3 files changed, 65 insertions(+), 59 deletions(-) (limited to 'src/dataframes.py') diff --git a/src/dataframes.py b/src/dataframes.py index 94eb509..ab53063 100644 --- a/src/dataframes.py +++ b/src/dataframes.py @@ -21,10 +21,8 @@ def create_fact_sales_order(dict_of_df): df_sales.index.name = "sales_record_id" df_sales["created_date"] = pd.to_datetime(df_sales["created_at"]).dt.date df_sales["created_time"] = pd.to_datetime(df_sales["created_at"]).dt.time - df_sales["last_updated_date"] = pd.to_datetime( - df_sales["last_updated"]).dt.date - df_sales["last_updated_time"] = pd.to_datetime( - df_sales["last_updated"]).dt.time + df_sales["last_updated_date"] = pd.to_datetime(df_sales["last_updated"]).dt.date + df_sales["last_updated_time"] = pd.to_datetime(df_sales["last_updated"]).dt.time fact_sales_order = df_sales.loc[ :, [ @@ -76,7 +74,8 @@ def create_fact_payment(dict_of_df): df_payment["last_updated_date"] = df_payment["last_updated"].date() df_payment["last_updated_time"] = df_payment["last_updated"].time df_payment["payment_date"] = pd.to_datetime( - df_payment["payment_date"], format="%Y-%m-%d") + df_payment["payment_date"], format="%Y-%m-%d" + ) fact_payment = df_payment.loc[ :, [ @@ -113,16 +112,16 @@ 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"})) + .rename(columns={"address_id": "location_id"}) + ) return df_loc - def create_dim_counterparty(dict_of_df): - df_prefixed_address=dict_of_df["address"].add_prefix( + df_prefixed_address = dict_of_df["address"].add_prefix( "counterparty_legal_", axis=1 ) - df_cp=pd.merge( + df_cp = pd.merge( dict_of_df["counterparty"], df_prefixed_address, left_on="legal_address_id", @@ -139,51 +138,51 @@ def create_dim_counterparty(dict_of_df): def create_dim_date(dict_of_df): - fact_dfs=[ + fact_dfs = [ create_fact_payment(dict_of_df), create_fact_purchase_orders(dict_of_df), create_fact_sales_order(dict_of_df), ] - date_col_names=[ + date_col_names = [ col_name for col_name in list(fact_dfs[0].columns) if "date" in col_name ] - list_of_date_columns=[] + list_of_date_columns = [] for df in fact_dfs: 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"]) + 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 + 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=[ + 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( + 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 = 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 @@ -191,33 +190,32 @@ def create_dim_currency(dict_of_df, names=scrape_currency_names()): # 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"]] + 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[ + 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( + staff_department = pd.merge( dict_of_df["staff"], dict_of_df["department"], on="department_id", how="left" ) - dim_staff=staff_department.loc[ + dim_staff = staff_department.loc[ :, [ "staff_id", diff --git a/src/transform_lambda.py b/src/transform_lambda.py index 565b4ee..2cd9272 100644 --- a/src/transform_lambda.py +++ b/src/transform_lambda.py @@ -11,7 +11,6 @@ from pg8000.native import Connection, InterfaceError from datetime import datetime - class DBConnectionException(Exception): """Wraps pg8000.native Error or DatabaseError.""" @@ -212,5 +211,6 @@ def list_existing_s3_files(bucket_name, client=boto3.client("s3")): return existing_files -if __name__ == '__main__': - lambda_handler({}, '') \ No newline at end of file + +if __name__ == "__main__": + lambda_handler({}, "") diff --git a/tests/test_transform_lambda.py b/tests/test_transform_lambda.py index 00f3d83..5ed743e 100644 --- a/tests/test_transform_lambda.py +++ b/tests/test_transform_lambda.py @@ -1,4 +1,8 @@ -from src.transform_lambda import read_from_s3_subfolder_to_df, list_existing_s3_files, bucket_name +from src.transform_lambda import ( + read_from_s3_subfolder_to_df, + list_existing_s3_files, + bucket_name, +) from moto import mock_aws import pytest import pandas as pd @@ -6,14 +10,15 @@ import os import boto3 from botocore.exceptions import ClientError import numpy as np + # import caplog import logging - logger = logging.getLogger() logger.setLevel(logging.INFO) + @pytest.fixture(scope="class") def aws_credentials(): os.environ["AWS_ACCESS_KEY_ID"] = "testing" @@ -92,42 +97,45 @@ class TestReadFromS3: assert result["Foods"].eq(expected_foods_df, axis="columns").all(axis=None) assert result["Cars"].eq(expected_cars_df, axis="columns").all(axis=None) + class TestListExistingFiles: def test_functions_receives_error_if_no_bucket(self, s3_client, caplog): caplog.set_level(logging.INFO) with pytest.raises(ClientError): - list_existing_s3_files('rando_bucket', client=s3_client) + list_existing_s3_files("rando_bucket", client=s3_client) - assert "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist" in caplog.text + assert ( + "Error listing S3 objects: An error occurred (NoSuchBucket) when calling the ListObjectsV2 operation: The specified bucket does not exist" + in caplog.text + ) def test_recieves_logger_error_if_no_files_listed(self, s3_client, caplog): caplog.set_level(logging.INFO) s3_client.create_bucket( - Bucket='mock_bucket', - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + Bucket="mock_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) - response = list_existing_s3_files('mock_bucket', client=s3_client) - assert 'The bucket is empty' in caplog.text + response = list_existing_s3_files("mock_bucket", client=s3_client) + assert "The bucket is empty" in caplog.text def test_retrieves_existing_files(self, s3_client, caplog): caplog.set_level(logging.INFO) - s3_client.upload_file( - "tests/dummy.txt", 'mock_bucket', "dummy.txt" - ) - result = list_existing_s3_files('mock_bucket', client=s3_client) + s3_client.upload_file("tests/dummy.txt", "mock_bucket", "dummy.txt") + result = list_existing_s3_files("mock_bucket", client=s3_client) assert result == ["dummy.txt"] + class TestBucketName: def test_functions_retrieves_bucket(self, s3_client): s3_client.create_bucket( - Bucket='mock_bucket', - CreateBucketConfiguration={"LocationConstraint": "eu-west-2"} + Bucket="mock_bucket", + CreateBucketConfiguration={"LocationConstraint": "eu-west-2"}, ) - - bucket = bucket_name('mock_bucket', s3_client) - assert bucket == 'mock_bucket' - # def test_ \ No newline at end of file + bucket = bucket_name("mock_bucket", s3_client) + assert bucket == "mock_bucket" + + # def test_ -- cgit v1.2.3