hive> CREATE TABLE taxi_data
    > (
    > vendor_id INT,
    > tpep_pickup_datetime TIMESTAMP,
    > tpep_dropoff_datetime TIMESTAMP,
    > passenger_count INT,
    > trip_distance DOUBLE,
    > pulocation_id INT,
    > dolocation_id INT,
    > ratecode_id INT,
    > store_and_fwd_flag string,
    > payment_type INT,
    > fare_amount DOUBLE,
    > extra DOUBLE,
    > mta_tax DOUBLE,
    > improvement_surcharge DOUBLE,
    > tip_amount DOUBLE,
    > tolls_amount DOUBLE,
    > total_amount DOUBLE
    > )
    > ROW format delimited
    > FIELDS TERMINATED BY ','
    > LINES TERMINATED BY '\n'
    > stored AS parquet
    > location 'hdfs:///user/root/2020'
    > TBLPROPERTIES ("skip.header.line.count"="1");
OK
TIME taken: 0.08 seconds
hive> SHOW TABLES;
OK
dim_vendor
taxi_data
TIME taken: 0.026 seconds, Fetched: 2 ROW(s)
hive> SELECT 8 FROM taxi_data LIMIT 5;
OK
Failed WITH exception java.io.IOException:java.lang.RuntimeException: hdfs://rc1b-dataproc-m-st8trv5rgtmo8iwo.mdb.yandexcloud.net/USER/root/2020/yellow_tripdata_2020-01.csv IS NOT a Parquet file. expected magic NUMBER at tail [80, 65, 82, 49] but found [44, 48, 13, 10]
TIME taken: 0.218 seconds