egutierrez
63a9cb5273
Datascience: aggregate_by_group, deduplicate_entities/relations, detect_drift, diff_entities/relations, extract_entities/relations_llm, hotness_score, melt, merge_graphs, pivot, build_entity/relation_schema_prompt. Finance: avellaneda_stoikov_quotes, generate_gbm_prices, generate_taker_order, hawkes_intensity + módulo finance.py. Cybersecurity: envelope_encrypt/decrypt + módulo cybersecurity.py. Pipelines: extraction_pipeline, monte_carlo_market, run_market_sim. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
79 lines
2.7 KiB
Python
79 lines
2.7 KiB
Python
"""Tests para pivot."""
|
|
|
|
import sys
|
|
import os
|
|
sys.path.insert(0, os.path.dirname(__file__))
|
|
|
|
from pivot import pivot
|
|
|
|
|
|
def test_pivot_basico_con_sum():
|
|
"""Pivot basico con sum."""
|
|
rows = [
|
|
{"region": "US", "product": "A", "sales": 10},
|
|
{"region": "US", "product": "B", "sales": 20},
|
|
{"region": "EU", "product": "A", "sales": 15},
|
|
]
|
|
result = pivot(rows, index="region", columns="product", values="sales")
|
|
assert len(result) == 2
|
|
us = next(r for r in result if r["region"] == "US")
|
|
eu = next(r for r in result if r["region"] == "EU")
|
|
assert us["A"] == 10
|
|
assert us["B"] == 20
|
|
assert eu["A"] == 15
|
|
assert eu["B"] == 0
|
|
|
|
|
|
def test_pivot_con_count_y_mean():
|
|
"""Pivot con count y mean."""
|
|
rows = [
|
|
{"region": "US", "product": "A", "sales": 10},
|
|
{"region": "US", "product": "A", "sales": 20},
|
|
{"region": "EU", "product": "A", "sales": 15},
|
|
]
|
|
result_count = pivot(rows, index="region", columns="product", values="sales", agg="count")
|
|
us_count = next(r for r in result_count if r["region"] == "US")
|
|
assert us_count["A"] == 2
|
|
|
|
result_mean = pivot(rows, index="region", columns="product", values="sales", agg="mean")
|
|
us_mean = next(r for r in result_mean if r["region"] == "US")
|
|
assert us_mean["A"] == 15.0
|
|
|
|
|
|
def test_pivot_valores_faltantes_rellenados_con_0():
|
|
"""Valores faltantes rellenados con 0."""
|
|
rows = [
|
|
{"region": "US", "product": "A", "sales": 5},
|
|
{"region": "EU", "product": "B", "sales": 8},
|
|
]
|
|
result = pivot(rows, index="region", columns="product", values="sales")
|
|
us = next(r for r in result if r["region"] == "US")
|
|
eu = next(r for r in result if r["region"] == "EU")
|
|
assert us["B"] == 0
|
|
assert eu["A"] == 0
|
|
|
|
|
|
def test_pivot_una_sola_fila():
|
|
"""Una sola fila."""
|
|
rows = [{"region": "US", "product": "A", "sales": 42}]
|
|
result = pivot(rows, index="region", columns="product", values="sales")
|
|
assert len(result) == 1
|
|
assert result[0]["region"] == "US"
|
|
assert result[0]["A"] == 42
|
|
|
|
|
|
def test_pivot_multiples_valores_por_celda_requieren_agregacion():
|
|
"""Multiples valores por celda requieren agregacion."""
|
|
rows = [
|
|
{"region": "US", "product": "A", "sales": 10},
|
|
{"region": "US", "product": "A", "sales": 30},
|
|
]
|
|
result_sum = pivot(rows, index="region", columns="product", values="sales", agg="sum")
|
|
assert result_sum[0]["A"] == 40
|
|
|
|
result_min = pivot(rows, index="region", columns="product", values="sales", agg="min")
|
|
assert result_min[0]["A"] == 10
|
|
|
|
result_max = pivot(rows, index="region", columns="product", values="sales", agg="max")
|
|
assert result_max[0]["A"] == 30
|