Skip to content

Fix experiment assignment data alignment issues #7

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
whitehackr wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix experiment assignment data alignment issues #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cd68492
Fix experiment assignment generation to use correct date range
whitehackr Sep 4, 2025
f89fa30
Fix timestamp serialization in JSON upload method
whitehackr Sep 4, 2025
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
2 changes: 1 addition & 1 deletion scripts/experiment_effects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ def generate_free_shipping_threshold_overlay(
# Generate overlay data
overlay_data = generator.generate_experiment_overlay(
experiment_name='free_shipping_threshold_test_v1_1_1',
data_category='orders',WYC
data_category='orders',
granularity='order_id',
source_table_path='bigquery-public-data.thelook_ecommerce.orders',
assignments_df=assignments_df
Expand Down
25 changes: 17 additions & 8 deletions scripts/generate_synthetic_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,10 +93,9 @@ def generate_and_upload_all(self, sample_pct: float = 100.0):
orders_df = orders_df[orders_df['user_id'].isin(user_ids)]
logging.info(f"Sampled {sample_pct}% of data: {len(users_df)} users")

# Generate synthetic datasets (LEGACY - imports from archives)
# Generate experiment assignments using modern method (independent of sampling)
logging.info("Generating experiment assignments...")
from archives.experiment_assignments import generate_experiment_assignments
experiments_df = generate_experiment_assignments(users_df)
experiments_df = self._generate_free_shipping_threshold_assignments()
self._upload_dataframe(experiments_df, "experiment_assignments")

logging.info("Generating logistics data...")
Expand Down Expand Up @@ -232,15 +231,25 @@ def _upload_dataframe(self, df: pd.DataFrame, table_name: str):

table_ref = f"{self.project_id}.{self.dataset_id}.{table_name}"

# Configure load job
# Convert DataFrame to records for JSON upload (same method as experiment_effects.py)
# Convert timestamps to strings for JSON serialization
df_copy = df.copy()
for col in df_copy.columns:
if df_copy[col].dtype == 'datetime64[ns]':
df_copy[col] = df_copy[col].dt.strftime('%Y-%m-%d %H:%M:%S')

records = df_copy.to_dict('records')

# Configure load job for JSON format
job_config = bigquery.LoadJobConfig(
write_disposition="WRITE_TRUNCATE", # Replace existing data
autodetect=True # Auto-detect schema
autodetect=True, # Auto-detect schema
source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON
)

# Upload data
job = self.client.load_table_from_dataframe(
df, table_ref, job_config=job_config
# Upload data using JSON format
job = self.client.load_table_from_json(
records, table_ref, job_config=job_config
)
job.result() # Wait for completion

Expand Down