commit c67fca4f253af03f510ed071930965bc33db0182
Author: Mihit <me@mihitmittal.com>
Date:   Sun Mar 16 21:32:53 2025 +1100

    init

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..e28517f
--- /dev/null
+++ b/main.py
@@ -0,0 +1,29 @@
+from pyspark.sql import SparkSession
+from pyspark.sql.functions import col
+import argparse
+
+def transform_data(data_source: str, output_uri: str) -> None:
+    with SparkSession.builder.appName("Big Basket Analysis").getOrCreate() as spark:
+        df = spark.read.option("header", "true").csv(data_source)
+
+        df.createOrReplaceTempView("bigbasket_products")
+
+        SQL_QUERY = """
+            select product, count(*) 
+            from bigbasket_products
+            group by product
+        """
+
+        transformed_df = spark.sql(SQL_QUERY)
+
+        print(f"Number of rows: {transformed_df.count()}")
+
+        transform_df.write.mode("overwrite").parquet(output_uri)
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data_source')
+    parser.add_argument('--output_uri')
+    args = parser.parse_args()
+
+    transform_data(args.data_source, args.output_uri)
\ No newline at end of file