Skip to content

Fix format_timestamp.py bug #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix format_timestamp.py bug #19

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 14 additions & 4 deletions ...data_preprocessing_examples/oci_data_flow_based_examples/example_code/format_timestamp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from pyspark.sql import functions as F
import argparse

ISO_TIMESTAMP_FORMAT = "yyyy-MM-dd'T'HH:mm:ss'Z'"

def __create_spark_session(session_name):
"""
Expand All @@ -16,20 +17,23 @@ def __create_spark_session(session_name):


# The empty **kwargs is for generalization of the function interface
def format_timestamp(df, **kwargs):
def format_timestamp(df,
columnName="timestamp",
timestampFormat=ISO_TIMESTAMP_FORMAT, **kwargs):
"""
Reformat timestamps to ISO 8601
Args:
df: input dataframe
columnName: timestamp column name
timestampFormat: timestamp format used

Return:
input dataframe with timestamps formatted as ISO 8601
"""
return df.withColumn(
"timestamp",
columnName,
F.date_format(
F.to_timestamp("timestamp"), "yyyy-MM-dd'T'HH:mm:ss'Z'").cast(
"string"
F.to_timestamp(columnName, timestampFormat), ISO_TIMESTAMP_FORMAT
),
)

Expand All @@ -38,6 +42,12 @@ def format_timestamp(df, **kwargs):
parser = argparse.ArgumentParser()
parser.add_argument("--input", required=True)
parser.add_argument("--output", required=True)
parser.add_argument(
"--columnName", required=False, default="timestamp"
)
parser.add_argument(
"--timestampFormat", required=False, default=ISO_TIMESTAMP_FORMAT
)
parser.add_argument("--coalesce", required=False, action="store_true")
args = parser.parse_args()

Expand Down