Merge pull request #12 from Zeutschler/dev

caching added

benchmarks/nano_vs_nano_cached.py

@@ -5,34 +5,32 @@
 from pathlib import Path
 import os
 
-
 # Create a DataFrame and NanoCube
 file_car_prices = Path(os.path.dirname(os.path.realpath(__file__))) / "files" / "car_prices.parquet"
 df = pd.read_parquet(file_car_prices)
-ns = NanoCube(df, dimensions=['make', 'model', 'trim', 'body'], measures=['mmr'], caching=False)
-
-# Create a DuckDB table
-duckdb.sql(f"CREATE TABLE car_prices AS SELECT * FROM '{file_car_prices}'")
+nc = NanoCube(df, dimensions=['make', 'model', 'trim', 'body'], measures=['mmr'], caching=False)
+nc_cached = NanoCube(df, dimensions=['make', 'model', 'trim', 'body'], measures=['mmr'], caching=True)
 
 
 def query_nanocube(loops=1000):
     value = 0
     for _ in range(loops):
-        value += ns.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')
+        value += nc.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')
     return value
 
-def query_duckdb(loops=1000):
+def query_nanocube_cached(loops=1000):
     value = 0
     for _ in range(loops):
-        value += duckdb.sql("SELECT SUM(mmr) FROM car_prices WHERE model='Optima' AND trim='LX' AND make='Kia' AND body='Sedan';").fetchall()[0][0]
+        value += nc_cached.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')
     return value
 
 
 if __name__ == '__main__':
-    pl_time = timeit(query_duckdb, number=1)
+    ncc_time = timeit(query_nanocube_cached, number=1)
     nc_time = timeit(query_nanocube, number=1)
-    print(f"DuckDB point query in {pl_time:.5f} sec.")
     print(f"NanoCube point query in {nc_time:.5f} sec.")
-    print(f"NanoCube is {pl_time/nc_time:.2f}x times faster than DuckDB on query with 4 filters on 1 measure:")
+    print(f"NanoCube(cached) point query in {ncc_time:.5f} sec.")
+    print(f"NanoCube cached is {nc_time/ncc_time:.2f}x times faster "
+          f"vs. uncached on recurring queries with {1000/ncc_time:,.0f} q/sec.")
     print(f"\tns.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')")
-    assert(query_nanocube() == query_duckdb())
+    assert(query_nanocube() == query_nanocube_cached())

benchmarks/nano_vs_polars.py

@@ -1,34 +1,37 @@
 from nanocube import NanoCube
 import pandas as pd
+import polars as pl
 from timeit import timeit
 from pathlib import Path
 import os
 
 # Create a DataFrame and NanoCube
 file_car_prices = Path(os.path.dirname(os.path.realpath(__file__))) / "files" / "car_prices.parquet"
 df = pd.read_parquet(file_car_prices)
-nc = NanoCube(df, dimensions=['make', 'model', 'trim', 'body'], measures=['mmr'], caching=False)
-nc_cached = NanoCube(df, dimensions=['make', 'model', 'trim', 'body'], measures=['mmr'], caching=True)
+ns = NanoCube(df, dimensions=['make', 'model', 'trim', 'body'], measures=['mmr'], caching=False)
+
+# Create a Polars table
+df = pl.read_parquet(file_car_prices)
 
 
 def query_nanocube(loops=1000):
     value = 0
     for _ in range(loops):
-        value += nc.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')
+        value += ns.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')
     return value
 
-def query_nanocube_cached(loops=1000):
+def query_polars(loops=1000):
     value = 0
     for _ in range(loops):
-        value += nc_cached.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')
+        value += df.filter(pl.col('make') == 'Kia', pl.col('model') == 'Optima', pl.col('trim') == 'LX', pl.col('body') == 'Sedan')['mmr'].sum()
     return value
 
 
 if __name__ == '__main__':
-    ncc_time = timeit(query_nanocube_cached, number=1)
+    pl_time = timeit(query_polars, number=1)
     nc_time = timeit(query_nanocube, number=1)
+    print(f"Polars point query in {pl_time:.5f} sec.")
     print(f"NanoCube point query in {nc_time:.5f} sec.")
-    print(f"NanoCube(cached) point query in {ncc_time:.5f} sec.")
-    print(f"NanoCube(cached) is {nc_time/ncc_time:.2f}x times faster than NanoCube(uncached) on 1000x executing the same query.")
+    print(f"NanoCube is {pl_time/nc_time:.2f}x times faster than Polars on query with 4 filters on 1 measure:")
     print(f"\tns.get('mmr', model='Optima', trim='LX', make='Kia', body='Sedan')")
-    assert(query_nanocube() == query_nanocube_cached())
+    assert(query_nanocube() == query_polars())