Update all tpch examples to use select instead of select_columns

timsaucer · timsaucer · commit 90e1597ecfc5 · 2024-10-21T13:18:53.000-04:00
diff --git a/examples/tpch/convert_data_to_parquet.py b/examples/tpch/convert_data_to_parquet.py
@@ -138,6 +138,6 @@
 
     df = ctx.read_csv(source_file, schema=schema, has_header=False, delimiter="|")
 
-    df = df.select_columns(*output_cols)
+    df = df.select(*output_cols)
 
     df.write_parquet(dest_file, compression="snappy")
diff --git a/examples/tpch/q02_minimum_cost_supplier.py b/examples/tpch/q02_minimum_cost_supplier.py
@@ -43,10 +43,10 @@
 
 ctx = SessionContext()
 
-df_part = ctx.read_parquet(get_data_path("part.parquet")).select_columns(
+df_part = ctx.read_parquet(get_data_path("part.parquet")).select(
     "p_partkey", "p_mfgr", "p_type", "p_size"
 )
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_acctbal",
     "s_name",
     "s_address",
@@ -55,13 +55,13 @@
     "s_nationkey",
     "s_suppkey",
 )
-df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select_columns(
+df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select(
     "ps_partkey", "ps_suppkey", "ps_supplycost"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_regionkey", "n_name"
 )
-df_region = ctx.read_parquet(get_data_path("region.parquet")).select_columns(
+df_region = ctx.read_parquet(get_data_path("region.parquet")).select(
     "r_regionkey", "r_name"
 )
 
@@ -115,7 +115,7 @@
 
 # From the problem statement, these are the values we wish to output
 
-df = df.select_columns(
+df = df.select(
     "s_acctbal",
     "s_name",
     "n_name",
diff --git a/examples/tpch/q03_shipping_priority.py b/examples/tpch/q03_shipping_priority.py
@@ -37,13 +37,13 @@
 
 ctx = SessionContext()
 
-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(
+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(
     "c_mktsegment", "c_custkey"
 )
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderdate", "o_shippriority", "o_custkey", "o_orderkey"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_orderkey", "l_extendedprice", "l_discount", "l_shipdate"
 )
 
@@ -80,7 +80,7 @@
 
 # Change the order that the columns are reported in just to match the spec
 
-df = df.select_columns("l_orderkey", "revenue", "o_orderdate", "o_shippriority")
+df = df.select("l_orderkey", "revenue", "o_orderdate", "o_shippriority")
 
 # Show result
 
diff --git a/examples/tpch/q04_order_priority_checking.py b/examples/tpch/q04_order_priority_checking.py
@@ -39,10 +39,10 @@
 
 ctx = SessionContext()
 
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderdate", "o_orderpriority", "o_orderkey"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_orderkey", "l_commitdate", "l_receiptdate"
 )
 
@@ -54,7 +54,7 @@
 # Limit results to cases where commitment date before receipt date
 # Aggregate the results so we only get one row to join with the order table.
 # Alternately, and likely more idiomatic is instead of `.aggregate` you could
-# do `.select_columns("l_orderkey").distinct()`. The goal here is to show
+# do `.select("l_orderkey").distinct()`. The goal here is to show
 # multiple examples of how to use Data Fusion.
 df_lineitem = df_lineitem.filter(col("l_commitdate") < col("l_receiptdate")).aggregate(
     [col("l_orderkey")], []
diff --git a/examples/tpch/q05_local_supplier_volume.py b/examples/tpch/q05_local_supplier_volume.py
@@ -47,22 +47,22 @@
 
 ctx = SessionContext()
 
-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(
+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(
     "c_custkey", "c_nationkey"
 )
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_custkey", "o_orderkey", "o_orderdate"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_orderkey", "l_suppkey", "l_extendedprice", "l_discount"
 )
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey", "s_nationkey"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_regionkey", "n_name"
 )
-df_region = ctx.read_parquet(get_data_path("region.parquet")).select_columns(
+df_region = ctx.read_parquet(get_data_path("region.parquet")).select(
     "r_regionkey", "r_name"
 )
 
diff --git a/examples/tpch/q06_forecasting_revenue_change.py b/examples/tpch/q06_forecasting_revenue_change.py
@@ -51,7 +51,7 @@
 
 ctx = SessionContext()
 
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_shipdate", "l_quantity", "l_extendedprice", "l_discount"
 )
 
diff --git a/examples/tpch/q07_volume_shipping.py b/examples/tpch/q07_volume_shipping.py
@@ -49,19 +49,19 @@
 
 ctx = SessionContext()
 
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey", "s_nationkey"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_shipdate", "l_extendedprice", "l_discount", "l_suppkey", "l_orderkey"
 )
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderkey", "o_custkey"
 )
-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(
+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(
     "c_custkey", "c_nationkey"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_name"
 )
 
diff --git a/examples/tpch/q08_market_share.py b/examples/tpch/q08_market_share.py
@@ -47,25 +47,23 @@
 
 ctx = SessionContext()
 
-df_part = ctx.read_parquet(get_data_path("part.parquet")).select_columns(
-    "p_partkey", "p_type"
-)
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_part = ctx.read_parquet(get_data_path("part.parquet")).select("p_partkey", "p_type")
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey", "s_nationkey"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_partkey", "l_extendedprice", "l_discount", "l_suppkey", "l_orderkey"
 )
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderkey", "o_custkey", "o_orderdate"
 )
-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(
+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(
     "c_custkey", "c_nationkey"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_name", "n_regionkey"
 )
-df_region = ctx.read_parquet(get_data_path("region.parquet")).select_columns(
+df_region = ctx.read_parquet(get_data_path("region.parquet")).select(
     "r_regionkey", "r_name"
 )
 
@@ -133,7 +131,7 @@
 
 # When we join to the customer dataframe, we don't want to confuse other columns, so only
 # select the supplier key that we need
-df_national_suppliers = df_national_suppliers.select_columns("s_suppkey")
+df_national_suppliers = df_national_suppliers.select("s_suppkey")
 
 
 # Part 3: Combine suppliers and customers and compute the market share
diff --git a/examples/tpch/q09_product_type_profit_measure.py b/examples/tpch/q09_product_type_profit_measure.py
@@ -39,27 +39,25 @@
 
 ctx = SessionContext()
 
-df_part = ctx.read_parquet(get_data_path("part.parquet")).select_columns(
-    "p_partkey", "p_name"
-)
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_part = ctx.read_parquet(get_data_path("part.parquet")).select("p_partkey", "p_name")
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey", "s_nationkey"
 )
-df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select_columns(
+df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select(
     "ps_suppkey", "ps_partkey", "ps_supplycost"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_partkey",
     "l_extendedprice",
     "l_discount",
     "l_suppkey",
     "l_orderkey",
     "l_quantity",
 )
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderkey", "o_custkey", "o_orderdate"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_name", "n_regionkey"
 )
 
diff --git a/examples/tpch/q10_returned_item_reporting.py b/examples/tpch/q10_returned_item_reporting.py
@@ -44,7 +44,7 @@
 
 ctx = SessionContext()
 
-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(
+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(
     "c_custkey",
     "c_nationkey",
     "c_name",
@@ -53,13 +53,13 @@
     "c_phone",
     "c_comment",
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_extendedprice", "l_discount", "l_orderkey", "l_returnflag"
 )
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderkey", "o_custkey", "o_orderdate"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_name", "n_regionkey"
 )
 
@@ -87,7 +87,7 @@
 df = df.join(df_nation, (["c_nationkey"], ["n_nationkey"]), how="inner")
 
 # These are the columns the problem statement requires
-df = df.select_columns(
+df = df.select(
     "c_custkey",
     "c_name",
     "revenue",
diff --git a/examples/tpch/q11_important_stock_identification.py b/examples/tpch/q11_important_stock_identification.py
@@ -37,13 +37,13 @@
 
 ctx = SessionContext()
 
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey", "s_nationkey"
 )
-df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select_columns(
+df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select(
     "ps_supplycost", "ps_availqty", "ps_suppkey", "ps_partkey"
 )
-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(
+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(
     "n_nationkey", "n_name"
 )
 
@@ -75,7 +75,7 @@
 df = df.filter(col("value") / col("total_value") >= lit(FRACTION))
 
 # We only need to report on these two columns
-df = df.select_columns("ps_partkey", "value")
+df = df.select("ps_partkey", "value")
 
 # Sort in descending order of value
 df = df.sort(col("value").sort(ascending=False))
diff --git a/examples/tpch/q12_ship_mode_order_priority.py b/examples/tpch/q12_ship_mode_order_priority.py
@@ -42,10 +42,10 @@
 
 ctx = SessionContext()
 
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_orderkey", "o_orderpriority"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_orderkey", "l_shipmode", "l_commitdate", "l_shipdate", "l_receiptdate"
 )
 
diff --git a/examples/tpch/q13_customer_distribution.py b/examples/tpch/q13_customer_distribution.py
@@ -38,12 +38,10 @@
 
 ctx = SessionContext()
 
-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(
     "o_custkey", "o_comment"
 )
-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(
-    "c_custkey"
-)
+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select("c_custkey")
 
 # Use a regex to remove special cases
 df_orders = df_orders.filter(
diff --git a/examples/tpch/q14_promotion_effect.py b/examples/tpch/q14_promotion_effect.py
@@ -41,12 +41,10 @@
 
 ctx = SessionContext()
 
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_partkey", "l_shipdate", "l_extendedprice", "l_discount"
 )
-df_part = ctx.read_parquet(get_data_path("part.parquet")).select_columns(
-    "p_partkey", "p_type"
-)
+df_part = ctx.read_parquet(get_data_path("part.parquet")).select("p_partkey", "p_type")
 
 
 # Check part type begins with PROMO
diff --git a/examples/tpch/q15_top_supplier.py b/examples/tpch/q15_top_supplier.py
@@ -41,10 +41,10 @@
 
 ctx = SessionContext()
 
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_suppkey", "l_shipdate", "l_extendedprice", "l_discount"
 )
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey",
     "s_name",
     "s_address",
@@ -79,7 +79,7 @@
 df = df.join(df_supplier, (["l_suppkey"], ["s_suppkey"]), "inner")
 
 # Return only the columns requested
-df = df.select_columns("s_suppkey", "s_name", "s_address", "s_phone", "total_revenue")
+df = df.select("s_suppkey", "s_name", "s_address", "s_phone", "total_revenue")
 
 # If we have more than one, sort by supplier number (suppkey)
 df = df.sort(col("s_suppkey").sort())
diff --git a/examples/tpch/q16_part_supplier_relationship.py b/examples/tpch/q16_part_supplier_relationship.py
@@ -40,13 +40,13 @@
 
 ctx = SessionContext()
 
-df_part = ctx.read_parquet(get_data_path("part.parquet")).select_columns(
+df_part = ctx.read_parquet(get_data_path("part.parquet")).select(
     "p_partkey", "p_brand", "p_type", "p_size"
 )
-df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select_columns(
+df_partsupp = ctx.read_parquet(get_data_path("partsupp.parquet")).select(
     "ps_suppkey", "ps_partkey"
 )
-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(
+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(
     "s_suppkey", "s_comment"
 )
 
@@ -75,7 +75,7 @@
 
 df = df_part.join(df_partsupp, (["p_partkey"], ["ps_partkey"]), "inner")
 
-df = df.select_columns("p_brand", "p_type", "p_size", "ps_suppkey").distinct()
+df = df.select("p_brand", "p_type", "p_size", "ps_suppkey").distinct()
 
 df = df.aggregate(
     [col("p_brand"), col("p_type"), col("p_size")],
diff --git a/examples/tpch/q17_small_quantity_order.py b/examples/tpch/q17_small_quantity_order.py
@@ -38,10 +38,10 @@
 
 ctx = SessionContext()
 
-df_part = ctx.read_parquet(get_data_path("part.parquet")).select_columns(
+df_part = ctx.read_parquet(get_data_path("part.parquet")).select(
     "p_partkey", "p_brand", "p_container"
 )
-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(
+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(
     "l_partkey", "l_quantity", "l_extendedprice"
 )
 
diff --git a/examples/tpch/q18_large_volume_customer.py b/examples/tpch/q18_large_volume_customer.py
diff --git a/examples/tpch/q19_discounted_revenue.py b/examples/tpch/q19_discounted_revenue.py
diff --git a/examples/tpch/q20_potential_part_promotion.py b/examples/tpch/q20_potential_part_promotion.py
diff --git a/examples/tpch/q21_suppliers_kept_orders_waiting.py b/examples/tpch/q21_suppliers_kept_orders_waiting.py
diff --git a/examples/tpch/q22_global_sales_opportunity.py b/examples/tpch/q22_global_sales_opportunity.py

Original file line number	Diff line number	Diff line change
`@@ -37,13 +37,13 @@`
`37`	`37`
`38`	`38`	`ctx = SessionContext()`
`39`	`39`
`40`		`-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(`
	`40`	`+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(`
`41`	`41`	`"c_mktsegment", "c_custkey"`
`42`	`42`	`)`
`43`		`-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(`
	`43`	`+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(`
`44`	`44`	`"o_orderdate", "o_shippriority", "o_custkey", "o_orderkey"`
`45`	`45`	`)`
`46`		`-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(`
	`46`	`+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(`
`47`	`47`	`"l_orderkey", "l_extendedprice", "l_discount", "l_shipdate"`
`48`	`48`	`)`
`49`	`49`
`@@ -80,7 +80,7 @@`
`80`	`80`
`81`	`81`	`# Change the order that the columns are reported in just to match the spec`
`82`	`82`
`83`		`-df = df.select_columns("l_orderkey", "revenue", "o_orderdate", "o_shippriority")`
	`83`	`+df = df.select("l_orderkey", "revenue", "o_orderdate", "o_shippriority")`
`84`	`84`
`85`	`85`	`# Show result`
`86`	`86`
Original file line number	Diff line number	Diff line change
`@@ -47,22 +47,22 @@`
`47`	`47`
`48`	`48`	`ctx = SessionContext()`
`49`	`49`
`50`		`-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(`
	`50`	`+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(`
`51`	`51`	`"c_custkey", "c_nationkey"`
`52`	`52`	`)`
`53`		`-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(`
	`53`	`+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(`
`54`	`54`	`"o_custkey", "o_orderkey", "o_orderdate"`
`55`	`55`	`)`
`56`		`-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(`
	`56`	`+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(`
`57`	`57`	`"l_orderkey", "l_suppkey", "l_extendedprice", "l_discount"`
`58`	`58`	`)`
`59`		`-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(`
	`59`	`+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(`
`60`	`60`	`"s_suppkey", "s_nationkey"`
`61`	`61`	`)`
`62`		`-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(`
	`62`	`+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(`
`63`	`63`	`"n_nationkey", "n_regionkey", "n_name"`
`64`	`64`	`)`
`65`		`-df_region = ctx.read_parquet(get_data_path("region.parquet")).select_columns(`
	`65`	`+df_region = ctx.read_parquet(get_data_path("region.parquet")).select(`
`66`	`66`	`"r_regionkey", "r_name"`
`67`	`67`	`)`
`68`	`68`
Original file line number	Diff line number	Diff line change
`@@ -51,7 +51,7 @@`
`51`	`51`
`52`	`52`	`ctx = SessionContext()`
`53`	`53`
`54`		`-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(`
	`54`	`+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(`
`55`	`55`	`"l_shipdate", "l_quantity", "l_extendedprice", "l_discount"`
`56`	`56`	`)`
`57`	`57`
Original file line number	Diff line number	Diff line change
`@@ -49,19 +49,19 @@`
`49`	`49`
`50`	`50`	`ctx = SessionContext()`
`51`	`51`
`52`		`-df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select_columns(`
	`52`	`+df_supplier = ctx.read_parquet(get_data_path("supplier.parquet")).select(`
`53`	`53`	`"s_suppkey", "s_nationkey"`
`54`	`54`	`)`
`55`		`-df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select_columns(`
	`55`	`+df_lineitem = ctx.read_parquet(get_data_path("lineitem.parquet")).select(`
`56`	`56`	`"l_shipdate", "l_extendedprice", "l_discount", "l_suppkey", "l_orderkey"`
`57`	`57`	`)`
`58`		`-df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select_columns(`
	`58`	`+df_orders = ctx.read_parquet(get_data_path("orders.parquet")).select(`
`59`	`59`	`"o_orderkey", "o_custkey"`
`60`	`60`	`)`
`61`		`-df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select_columns(`
	`61`	`+df_customer = ctx.read_parquet(get_data_path("customer.parquet")).select(`
`62`	`62`	`"c_custkey", "c_nationkey"`
`63`	`63`	`)`
`64`		`-df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select_columns(`
	`64`	`+df_nation = ctx.read_parquet(get_data_path("nation.parquet")).select(`
`65`	`65`	`"n_nationkey", "n_name"`
`66`	`66`	`)`
`67`	`67`