aboutsummaryrefslogtreecommitdiffstats
path: root/csit.infra.etl
diff options
context:
space:
mode:
authorpmikus <peter.mikus@protonmail.ch>2023-08-17 12:26:28 +0000
committerPeter Mikus <peter.mikus@protonmail.ch>2023-08-21 04:49:19 +0000
commitb0b7f8dfdd37d45de0f3fcf758798e3bfbb9381d (patch)
tree7c7f41c4529cfe42e3bc11114a3b1ac49660ffdd /csit.infra.etl
parente9c8b39d0b6c8b7e72f26ace8233df078811b3a1 (diff)
feat(terraform): ETL for 2310
Signed-off-by: pmikus <peter.mikus@protonmail.ch> Change-Id: I3013b8be6a7f06d2f1f3b8320e7cb6f057a47491
Diffstat (limited to 'csit.infra.etl')
-rw-r--r--csit.infra.etl/coverage_device_rls2310.py (renamed from csit.infra.etl/coverage_device_rls2306.py)4
-rw-r--r--csit.infra.etl/coverage_hoststack_rls2310.py (renamed from csit.infra.etl/coverage_hoststack_rls2306.py)4
-rw-r--r--csit.infra.etl/coverage_mrr_rls2310.py (renamed from csit.infra.etl/coverage_mrr_rls2306.py)4
-rw-r--r--csit.infra.etl/coverage_ndrpdr_rls2310.py (renamed from csit.infra.etl/coverage_ndrpdr_rls2306.py)4
-rw-r--r--csit.infra.etl/coverage_reconf_rls2310.py (renamed from csit.infra.etl/coverage_reconf_rls2306.py)4
-rw-r--r--csit.infra.etl/coverage_soak_rls2310.py (renamed from csit.infra.etl/coverage_soak_rls2306.py)4
-rw-r--r--csit.infra.etl/iterative_hoststack_rls2310.py (renamed from csit.infra.etl/iterative_hoststack_rls2306.py)4
-rw-r--r--csit.infra.etl/iterative_mrr_rls2310.py (renamed from csit.infra.etl/iterative_mrr_rls2306.py)4
-rw-r--r--csit.infra.etl/iterative_ndrpdr_rls2310.py (renamed from csit.infra.etl/iterative_ndrpdr_rls2306.py)4
-rw-r--r--csit.infra.etl/iterative_reconf_rls2310.py (renamed from csit.infra.etl/iterative_reconf_rls2306.py)4
-rw-r--r--csit.infra.etl/iterative_soak_rls2310.py (renamed from csit.infra.etl/iterative_soak_rls2306.py)4
11 files changed, 22 insertions, 22 deletions
diff --git a/csit.infra.etl/coverage_device_rls2306.py b/csit.infra.etl/coverage_device_rls2310.py
index 2d4f59b29c..509a73f0de 100644
--- a/csit.infra.etl/coverage_device_rls2306.py
+++ b/csit.infra.etl/coverage_device_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-coverage-2306" in path]
+filtered_paths = [path for path in paths if "report-coverage-2310" in path]
out_sdf = process_json_to_dataframe("device", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/coverage_hoststack_rls2306.py b/csit.infra.etl/coverage_hoststack_rls2310.py
index 9a5f7a5bc9..7c9e950bf7 100644
--- a/csit.infra.etl/coverage_hoststack_rls2306.py
+++ b/csit.infra.etl/coverage_hoststack_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-coverage-2306" in path]
+filtered_paths = [path for path in paths if "report-coverage-2310" in path]
out_sdf = process_json_to_dataframe("hoststack", filtered_paths)
out_sdf.show(truncate=False)
@@ -155,7 +155,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/coverage_mrr_rls2306.py b/csit.infra.etl/coverage_mrr_rls2310.py
index 02ea40ef2b..4f8b5c8799 100644
--- a/csit.infra.etl/coverage_mrr_rls2306.py
+++ b/csit.infra.etl/coverage_mrr_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-coverage-2306" in path]
+filtered_paths = [path for path in paths if "report-coverage-2310" in path]
out_sdf = process_json_to_dataframe("mrr", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/coverage_ndrpdr_rls2306.py b/csit.infra.etl/coverage_ndrpdr_rls2310.py
index 5987e3eaa1..f2b30ed4fa 100644
--- a/csit.infra.etl/coverage_ndrpdr_rls2306.py
+++ b/csit.infra.etl/coverage_ndrpdr_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-coverage-2306" in path]
+filtered_paths = [path for path in paths if "report-coverage-2310" in path]
out_sdf = process_json_to_dataframe("ndrpdr", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/coverage_reconf_rls2306.py b/csit.infra.etl/coverage_reconf_rls2310.py
index 32885744d7..aff458c30a 100644
--- a/csit.infra.etl/coverage_reconf_rls2306.py
+++ b/csit.infra.etl/coverage_reconf_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-coverage-2306" in path]
+filtered_paths = [path for path in paths if "report-coverage-2310" in path]
out_sdf = process_json_to_dataframe("reconf", filtered_paths)
out_sdf.show(truncate=False)
@@ -155,7 +155,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/coverage_soak_rls2306.py b/csit.infra.etl/coverage_soak_rls2310.py
index fd4b9fed35..2e1a739d74 100644
--- a/csit.infra.etl/coverage_soak_rls2306.py
+++ b/csit.infra.etl/coverage_soak_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-coverage-2306" in path]
+filtered_paths = [path for path in paths if "report-coverage-2310" in path]
out_sdf = process_json_to_dataframe("soak", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/coverage_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/iterative_hoststack_rls2306.py b/csit.infra.etl/iterative_hoststack_rls2310.py
index 0b179dea88..7b2984694a 100644
--- a/csit.infra.etl/iterative_hoststack_rls2306.py
+++ b/csit.infra.etl/iterative_hoststack_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-iterative-2306" in path]
+filtered_paths = [path for path in paths if "report-iterative-2310" in path]
out_sdf = process_json_to_dataframe("hoststack", filtered_paths)
out_sdf.show(truncate=False)
@@ -155,7 +155,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/iterative_mrr_rls2306.py b/csit.infra.etl/iterative_mrr_rls2310.py
index 33ffff7ce4..12a4c26fb6 100644
--- a/csit.infra.etl/iterative_mrr_rls2306.py
+++ b/csit.infra.etl/iterative_mrr_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-iterative-2306" in path]
+filtered_paths = [path for path in paths if "report-iterative-2310" in path]
out_sdf = process_json_to_dataframe("mrr", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/iterative_ndrpdr_rls2306.py b/csit.infra.etl/iterative_ndrpdr_rls2310.py
index 9b3a36be18..d368c4a8fc 100644
--- a/csit.infra.etl/iterative_ndrpdr_rls2306.py
+++ b/csit.infra.etl/iterative_ndrpdr_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-iterative-2306" in path]
+filtered_paths = [path for path in paths if "report-iterative-2310" in path]
out_sdf = process_json_to_dataframe("ndrpdr", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/iterative_reconf_rls2306.py b/csit.infra.etl/iterative_reconf_rls2310.py
index a45ac66a83..ef5e604af3 100644
--- a/csit.infra.etl/iterative_reconf_rls2306.py
+++ b/csit.infra.etl/iterative_reconf_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-iterative-2306" in path]
+filtered_paths = [path for path in paths if "report-iterative-2310" in path]
out_sdf = process_json_to_dataframe("reconf", filtered_paths)
out_sdf.show(truncate=False)
@@ -155,7 +155,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",
diff --git a/csit.infra.etl/iterative_soak_rls2306.py b/csit.infra.etl/iterative_soak_rls2310.py
index ccc5012199..cfe733ba9a 100644
--- a/csit.infra.etl/iterative_soak_rls2306.py
+++ b/csit.infra.etl/iterative_soak_rls2310.py
@@ -141,7 +141,7 @@ paths = wr.s3.list_objects(
ignore_empty=True
)
-filtered_paths = [path for path in paths if "report-iterative-2306" in path]
+filtered_paths = [path for path in paths if "report-iterative-2310" in path]
out_sdf = process_json_to_dataframe("soak", filtered_paths)
out_sdf.printSchema()
@@ -154,7 +154,7 @@ out_sdf = out_sdf \
try:
wr.s3.to_parquet(
df=out_sdf.toPandas(),
- path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2306",
+ path=f"s3://{S3_DOCS_BUCKET}/csit/parquet/iterative_rls2310",
dataset=True,
partition_cols=["test_type", "year", "month", "day"],
compression="snappy",