From 9874906db46a9b6c4b2c82f19e3a05e85551e5df Mon Sep 17 00:00:00 2001 From: klee2024 <88099550+klee2024@users.noreply.github.com> Date: Tue, 19 Mar 2024 19:29:33 -0500 Subject: [PATCH 1/4] Update README.md w/ name --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 75106f7..55cd13d 100644 --- a/README.md +++ b/README.md @@ -83,3 +83,6 @@ Student Email: adilk@uchicago.edu Student Name: Nayna Pashilkar Student Email: npashilkar@uchicago.edu + +Student Name: Kaya Lee +Student Email: klee2024@uchicago.edu From a73712f73a72629b546f957ed3f046e16b991dad Mon Sep 17 00:00:00 2001 From: bhavyapan <112483284+bhavyapan@users.noreply.github.com> Date: Thu, 21 Mar 2024 14:19:22 -0500 Subject: [PATCH 2/4] added name to README.md --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 75106f7..1db5753 100644 --- a/README.md +++ b/README.md @@ -83,3 +83,6 @@ Student Email: adilk@uchicago.edu Student Name: Nayna Pashilkar Student Email: npashilkar@uchicago.edu + +Student Name: Bhavya Pandey +Student Email: bhavyapandey@uchicago.edu From f60fecbfd5ea24453a3fbb4162c56093e63fd214 Mon Sep 17 00:00:00 2001 From: ygxu01 <103914540+ygxu01@users.noreply.github.com> Date: Thu, 21 Mar 2024 16:34:47 -0500 Subject: [PATCH 3/4] update Readme.md with my name --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 75106f7..00e7ca1 100644 --- a/README.md +++ b/README.md @@ -83,3 +83,6 @@ Student Email: adilk@uchicago.edu Student Name: Nayna Pashilkar Student Email: npashilkar@uchicago.edu + +Student Name: Yangge Xu +Student Email: yanggexu@uchicago.edu From 1841b83f39d7052647f7945ac1740fbb0e31f426 Mon Sep 17 00:00:00 2001 From: Trevor Spreadbury Date: Thu, 28 Mar 2024 14:12:00 +0000 Subject: [PATCH 4/4] added check to see if 'deduplicated_UUIDs.csv' exists before reading --- src/utils/linkage_and_network_pipeline.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/src/utils/linkage_and_network_pipeline.py b/src/utils/linkage_and_network_pipeline.py index 0855d23..c67cbe4 100644 --- a/src/utils/linkage_and_network_pipeline.py +++ b/src/utils/linkage_and_network_pipeline.py @@ -150,10 +150,12 @@ def preprocess_transactions(transactions: pd.DataFrame) -> pd.DataFrame: transactions["purpose"] = transactions["purpose"].str.upper() - deduped = pd.read_csv(BASE_FILEPATH / "output" / "deduplicated_UUIDs.csv") - transactions[["donor_id", "recipient_id"]] = transactions[ - ["donor_id", "recipient_id"] - ].replace(deduped) + deduplicated_uuid_path = BASE_FILEPATH / "output" / "deduplicated_UUIDs.csv" + if deduplicated_uuid_path.exists(): + deduped = pd.read_csv(BASE_FILEPATH / "output" / "deduplicated_UUIDs.csv") + transactions[["donor_id", "recipient_id"]] = transactions[ + ["donor_id", "recipient_id"] + ].replace(deduped) return transactions