aboutsummaryrefslogtreecommitdiffstats
path: root/src
diff options
context:
space:
mode:
authorAng Bel <anzelikabelotelova@Anzelikas-MacBook-Air.local>2024-08-21 15:07:51 +0100
committerAng Bel <anzelikabelotelova@Anzelikas-MacBook-Air.local>2024-08-21 15:14:35 +0100
commit0c6e2f8486d1ec4d9b0bd4984e01baca3a159df0 (patch)
treea29c5dd0225d3ce377368886c44911fd97d89c01 /src
parent562fac411ce0bedf3dbf067390cacef89ef47981 (diff)
downloadde-project-bentley-0c6e2f8486d1ec4d9b0bd4984e01baca3a159df0.tar.gz
de-project-bentley-0c6e2f8486d1ec4d9b0bd4984e01baca3a159df0.zip
(tests) Read from s3 to df passes
Diffstat (limited to 'src')
-rw-r--r--src/transform_lambda.py26
1 files changed, 4 insertions, 22 deletions
diff --git a/src/transform_lambda.py b/src/transform_lambda.py
index 6f65728..ea4e16f 100644
--- a/src/transform_lambda.py
+++ b/src/transform_lambda.py
@@ -15,18 +15,6 @@ import pandas as pd
def lambda_handler(event, context):
s3_client = boto3.client('s3')
-
- tables = ['sales_order',
- 'transaction',
- 'payment',
- 'counterparty',
- 'address',
- 'staff',
- 'purchase_order',
- 'department',
- 'currency',
- 'design',
- 'payment_type']
try:
s3_bucket_name = event["Records"][0]["s3"]["bucket"]["name"]
s3_file_name = event["Records"][0]["s3"]["object"]["key"]
@@ -51,9 +39,8 @@ def lambda_handler(event, context):
'body': json.dumps('')
}
-## each csv file must be converted into a pandas df
-## done via read_csv, where stringIO creates an file-like-object from string - treats string like a file: as file is not physically stored in file
-## each file needs its own panda df (?) to be normalised
+## Started from fresh on Wed 21st Aug:
+
tables = ['sales_order',
'transaction',
'payment',
@@ -70,14 +57,9 @@ def read_from_s3_subfolder_to_df(tables, bucket, client=boto3.client('s3')):
table_dfs = {}
for table in tables:
response = client.list_objects_v2(Bucket=bucket, Prefix=table)
- list_of_keys = ['s3://'+object['Key'] for object in response['Contents']]
- print(list_of_keys)
+ list_of_keys = ['s3://'+bucket+'/'+object['Key'] for object in response['Contents']]
list_of_df = [pd.read_csv(key) for key in list_of_keys]
table_dfs[table] = pd.concat(list_of_df)
return table_dfs
- # exec("%s = %d" % (table,pd.concat(list_of_df)))
- # exec(f"{table} = {pd.concat(list_of_df)}")
- # table_dfs = [sales_order, transaction, payment, counterparty, address,
- # staff, purchase_order, department, currency, design, payment_type]
-
+
git.ajschof.me — hosted by ajschofield — powered by cgit