Split filters

pola-rs · Apr 11, 2024 · 78f0619 · 78f0619
1 parent 0bb7759
commit 78f0619
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 17 deletions.
diff --git a/queries/pandas/q3.py b/queries/pandas/q3.py
@@ -33,7 +33,8 @@ def query() -> pd.DataFrame:
         jn1 = fcustomer.merge(orders_ds, left_on="c_custkey", right_on="o_custkey")
         jn2 = jn1.merge(line_item_ds, left_on="o_orderkey", right_on="l_orderkey")
 
-        jn2 = jn2[(jn2["o_orderdate"] < var2) & (jn2["l_shipdate"] > var2)]
+        jn2 = jn2[jn2["o_orderdate"] < var2]
+        jn2 = jn2[jn2["l_shipdate"] > var2]
         jn2["revenue"] = jn2.l_extendedprice * (1 - jn2.l_discount)
 
         gb = jn2.groupby(

diff --git a/queries/pandas/q4.py b/queries/pandas/q4.py
@@ -26,11 +26,8 @@ def query() -> pd.DataFrame:
 
         jn = line_item_ds.merge(orders_ds, left_on="l_orderkey", right_on="o_orderkey")
 
-        jn = jn[
-            (jn["o_orderdate"] < var2)
-            & (jn["o_orderdate"] >= var1)
-            & (jn["l_commitdate"] < jn["l_receiptdate"])
-        ]
+        jn = jn[(jn["o_orderdate"] >= var1) & (jn["o_orderdate"] < var2)]
+        jn = jn[jn["l_commitdate"] < jn["l_receiptdate"]]
 
         jn = jn.drop_duplicates(subset=["o_orderpriority", "l_orderkey"])
 

diff --git a/queries/pandas/q5.py b/queries/pandas/q5.py
@@ -51,11 +51,8 @@ def query() -> pd.DataFrame:
             right_on=["s_suppkey", "s_nationkey"],
         )
 
-        jn5 = jn5[
-            (jn5["r_name"] == var1)
-            & (jn5["o_orderdate"] >= var2)
-            & (jn5["o_orderdate"] < var3)
-        ]
+        jn5 = jn5[jn5["r_name"] == var1]
+        jn5 = jn5[(jn5["o_orderdate"] >= var2) & (jn5["o_orderdate"] < var3)]
         jn5["revenue"] = jn5.l_extendedprice * (1.0 - jn5.l_discount)
 
         gb = jn5.groupby("n_name", as_index=False)["revenue"].sum()

diff --git a/queries/pandas/q6.py b/queries/pandas/q6.py
@@ -24,13 +24,12 @@ def query() -> pd.DataFrame:
         var5 = 24
 
         flineitem = line_item_ds[
-            (line_item_ds["l_shipdate"] >= var1)
-            & (line_item_ds["l_shipdate"] < var2)
-            & (line_item_ds["l_discount"] >= var3)
-            & (line_item_ds["l_discount"] <= var4)
-            & (line_item_ds["l_quantity"] < var5)
+            (line_item_ds["l_shipdate"] >= var1) & (line_item_ds["l_shipdate"] < var2)
         ]
-
+        flineitem = line_item_ds[
+            (line_item_ds["l_discount"] >= var3) & (line_item_ds["l_discount"] <= var4)
+        ]
+        flineitem = line_item_ds[line_item_ds["l_quantity"] < var5]
         result_value = (flineitem["l_extendedprice"] * flineitem["l_discount"]).sum()
         result_df = pd.DataFrame({"revenue": [result_value]})