aboutsummaryrefslogtreecommitdiffstats
path: root/src/fact-sales-order.py
diff options
context:
space:
mode:
authorT-Aji <tolujbd2@gmail.com>2024-08-22 10:09:22 +0100
committerT-Aji <tolujbd2@gmail.com>2024-08-22 10:09:22 +0100
commitd04f2474b9b6d3bc11441a1cecfb3cd9e3d67f69 (patch)
tree04cf2494f15e0f4bbb8b57705f133164d976abd0 /src/fact-sales-order.py
parent956bc9223a584c9cb687277f9000967f9b3ddc6b (diff)
parent5b2b4864eae129e112e70d093eb66498d7de401e (diff)
downloadde-project-bentley-d04f2474b9b6d3bc11441a1cecfb3cd9e3d67f69.tar.gz
de-project-bentley-d04f2474b9b6d3bc11441a1cecfb3cd9e3d67f69.zip
wip: creating dim dataframes
Diffstat (limited to 'src/fact-sales-order.py')
-rw-r--r--src/fact-sales-order.py29
1 files changed, 22 insertions, 7 deletions
diff --git a/src/fact-sales-order.py b/src/fact-sales-order.py
index ef18f02..870f660 100644
--- a/src/fact-sales-order.py
+++ b/src/fact-sales-order.py
@@ -1,7 +1,8 @@
import pandas as pd
from src.transform_lambda import get_dataframes
-dict_of_df = get_dataframes() # {"design": "design dataframe", "address": "address dataframe", ....}
+# {"design": "design dataframe", "address": "address dataframe", ....}
+dict_of_df = get_dataframes()
# iterates through each dataframe in the list of dataframes and assigns them to a variable
@@ -33,16 +34,30 @@ dim_currency["currency_name"] = dim_currency["currency_code"].map(mappings)
# creates the dim_location dataframe
-# need to change address id to location id
+# need to change address id to location id
"dim_location dataframe: (location_id, address_line_1, address_line_2, district, city, postal code, country, phone)"
df_address.rename(columns={"address_id": "location_id"})
dim_location = df_address.loc[:, "location_id", "address_line_1", "address_line_2", "district", "city", "postal_code" "country", "phone"]
# creates the dim_counterparty dataframe
-counterparty_address = pd.merge(df_counterparty, df_address, left_on="legal_address_id", right_on='address_id', how="outer")
-counterparty_address.rename(columns={"address_line_1": "counterparty_legal_address_line_1", "address_line_2": "counterparty_legal_address_line_2",
- "district": "counterparty_legal_district", "city": "counterparty_legal_city", "postal_code": "counterparty_postal_code",
- "country": "counterparty_legal_country", "phone": "counterparty_legal_phone_number"})
+counterparty_address = pd.merge(
+ df_counterparty,
+ df_address,
+ left_on="legal_address_id",
+ right_on="address_id",
+ how="outer"
+)
+counterparty_address.rename(
+ columns={
+ "address_line_1": "counterparty_legal_address_line_1",
+ "address_line_2": "counterparty_legal_address_line_2",
+ "district": "counterparty_legal_district",
+ "city": "counterparty_legal_city",
+ "postal_code": "counterparty_postal_code",
+ "country": "counterparty_legal_country",
+ "phone": "counterparty_legal_phone_number",
+ }
+)
dim_counterparty = df_counterparty.loc[:, "counterparty_id", "counterparty_legal_name", "counterparty_legal_address_line_1",
"counterparty_legal_address_line_2", "counterparty_legal_district", "counterpart_legal_city",
@@ -68,4 +83,4 @@ dim_date = ["date_id", "year", "month", "day", "day_of_week", "day_name", "month
# TO DO:
-# fact_sales_order \ No newline at end of file
+# fact_sales_order
git.ajschof.me — hosted by ajschofield — powered by cgit