mirror of
https://github.com/velocitatem/PHANTOM.git
synced 2026-05-31 08:33:36 +00:00
ad9423bf59
* introducing airflow to run pipeline * chore: updating dag with upload to registry * introducing complete provider (non refactored and noisy) * chore: removing old shit * generic pricing baselines * feature: super simple model registry (to be updated maybe third party OS software) * chore: refactoring the providers docker config and requirements * chore: refactored and broke down components (braking * exporting all * local pipeline excution working * fix: fixing import structures from nonrelativistic * chore: enables cross comm pickling with fully e2e pipeline compilation * docs: what the pipeline is like now * pipelines local running and pipeline high level definition * cleaning old pipeline and vectorization * leaked but fixing, not so important * test: started with pipeline step testing * chore: cleaning up provider of prices * test: extra tests wit hsemantic meaning checks * migrating pricers * feature: introducing pricing predictors (pricers) * chore: e2e is done with new pipeline * extra session feature extraction * feature: experiemntal sessin pricer and metrics(vibe) * chore: redefined and connected pricers (#29)
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
import pytest
|
|
import random
|
|
import pandas as pd
|
|
from procesing.steps import (
|
|
CreatePriceBucketsStep,
|
|
AugmentEventNamesStep
|
|
)
|
|
|
|
def test_bucketing(pipeline_context):
|
|
step = CreatePriceBucketsStep(context=pipeline_context)
|
|
|
|
# Test with normal price data
|
|
df = pd.DataFrame({
|
|
'metadata_price': random.sample(range(10, 1000), 100)
|
|
})
|
|
result = step.transform(df)
|
|
assert 'price_bucket' in result.columns
|
|
# test if is categorical
|
|
assert isinstance(result['price_bucket'].dtype, pd.CategoricalDtype)
|
|
assert result['price_bucket'].nunique() == 3 # as per context config
|
|
# distribution check
|
|
counts = result['price_bucket'].value_counts()
|
|
assert all(counts > 0)
|
|
assert counts.max() - counts.min() <= 10 # roughly equal distribution for 100 samples
|
|
# Test with empty DataFrame
|
|
df = pd.DataFrame()
|
|
result = step.transform(df)
|
|
assert 'price_bucket' in result.columns
|
|
assert result.empty
|
|
|
|
|
|
def test_augment_names(pipeline_context):
|
|
df = pd.DataFrame({
|
|
'eventName': ['click', 'view', 'purchase'],
|
|
'productId': ['prod_1', 'prod_2', None],
|
|
'price_bucket': ['PB_1', None, 'PB_3']
|
|
})
|
|
step = AugmentEventNamesStep(context=pipeline_context)
|
|
result = step.transform(df)
|
|
expected_event_names = [
|
|
'click_prod_1@PB_1',
|
|
'view',
|
|
'purchase'
|
|
]
|
|
assert result['eventName'].tolist() == expected_event_names
|