├── .gitignore ├── 01_getting_started ├── 01_getting_started.ipynb ├── 02_overview_of_spark_documentation.ipynb ├── 03_overview_of_spark_sql_cli.ipynb ├── 04_overview_of_spark_sql_properties.ipynb ├── 05_running_os_commands.ipynb ├── 06_understanding_warehouse_directory.ipynb ├── 07_managing_spark_metastore_databases.ipynb ├── 08_managing_spark_metastore_tables.ipynb ├── 09_retrieve_metadata_of_tables.ipynb ├── 10_role_of_spark_or_hive_metastore.ipynb └── 11_exercise_getting_started.ipynb ├── 02_overview_of_hdfs ├── 01_Overview of HDFS.ipynb ├── 02_using_hdfs_cli.ipynb ├── 03_getting_help_or_usage.ipynb ├── 04_listing_hdfs_files.ipynb ├── 05_managing_hdfs_directories.ipynb ├── 06_copying_files_from_local_to_hdfs.ipynb ├── 07_copying_files_from_hdfs_to_local.ipynb ├── 08_copying_files_from_hdfs_to_hdfs.ipynb ├── 09_previewing_data_in_hdfs_files.ipynb ├── 10_getting_file_metadata.ipynb ├── 11_hdfs_blocksize.ipynb ├── 12_hdfs_replication_factor.ipynb ├── 13_getting_hdfs_storage_usage.ipynb ├── 14_using_hdfs_stat_command.ipynb ├── 15_hdfs_file_permissions.ipynb ├── 16_overriding_properties.ipynb └── understanding_linux_file_system_240.ipynb ├── 03_basic_transformations ├── 01_basic_transformations.ipynb ├── 02_spark_sql_overview.ipynb ├── 03_define_problem_statement.ipynb ├── 04_preparing_tables.ipynb ├── 05_projecting_data.ipynb ├── 06_filtering_data.ipynb ├── 07_joining_tables_inner.ipynb ├── 08_joining_tables_outer.ipynb ├── 09_aggregating_data.ipynb ├── 10_sorting_data.ipynb ├── 11_conclusion_final_solution.ipynb └── 12_exercises_basic_sql_queries.ipynb ├── 04_basic_ddl_and_dml ├── 01_basic_ddl_and_dml.ipynb ├── 02_create_spark_metastore_tables.ipynb ├── 03_overview_of_data_types.ipynb ├── 04_adding_comments.ipynb ├── 05_loading_data_into_tables_local.ipynb ├── 06_loading_data_into_tables_hdfs.ipynb ├── 07_loading_data_append_and_overwrite.ipynb ├── 08_creating_external_tables.ipynb ├── 09_managed_vs_external_tables.ipynb ├── 10_overview_of_file_formats.ipynb ├── 11_dropping_tables_and_databases.ipynb ├── 12_truncating_tables.ipynb └── 13_exercises_managing_tables.ipynb ├── 05_dml_and_partitioning ├── 01_dml_and_partitioning.ipynb ├── 02_introduction_to_partitioning.ipynb ├── 03_creating_tables_using_parquet.ipynb ├── 04_load_vs_insert.ipynb ├── 05_inserting_data_using_stage_table.ipynb ├── 06_creating_partitioned_tables.ipynb ├── 07_adding_partitions_to_tables.ipynb ├── 08_loading_data_into_partitions.ipynb ├── 09_inserting_data_into_partitions.ipynb ├── 10_using_dynamic_partition_mode.ipynb └── 11_exercises_partitioned_tables.ipynb ├── 06_predefined_functions ├── 01_predefined_functions.ipynb ├── 02_overview_of_functions.ipynb ├── 03_validating_functions.ipynb ├── 04_string_manipulation_functions.ipynb ├── 05_date_manipulation_functions.ipynb ├── 06_overview_of_numeric_functions.ipynb ├── 07_data_type_conversion.ipynb ├── 08_handling_null_values.ipynb ├── 09_using_case_and_when.ipynb ├── 10_query_example_word_count.ipynb └── 11_exercises_pre_defined_functions.ipynb ├── 07_windowing_functions ├── 01_windowing_functions.ipynb ├── 02_prepare_database.ipynb ├── 03_overview_of_windowing_functions.ipynb ├── 04_aggregations_using_windowing_functions.ipynb ├── 05_using_lead_or_lag.ipynb ├── 06_getting_first_and_last_values.ipynb ├── 07_ranking_using_windowing_functions.ipynb ├── 08_order_of_execution_of_sql.ipynb ├── 09_overview_of_sub_queries.ipynb ├── 10_filtering_window_function_results.ipynb ├── 11_cumulative_or_moving_aggregations.ipynb └── 12_exercises_windowing_functions.ipynb ├── 08_analyze_github_activity └── 02_download_data.ipynb ├── LICENSE ├── README.md ├── Spark Data Frames to Temp Views.ipynb ├── _config.yml ├── _toc.yml └── spark-sql.ipynb /.gitignore: -------------------------------------------------------------------------------- 1 | .ipynb_checkpoints 2 | -------------------------------------------------------------------------------- /01_getting_started/01_getting_started.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/01_getting_started.ipynb -------------------------------------------------------------------------------- /01_getting_started/02_overview_of_spark_documentation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/02_overview_of_spark_documentation.ipynb -------------------------------------------------------------------------------- /01_getting_started/03_overview_of_spark_sql_cli.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/03_overview_of_spark_sql_cli.ipynb -------------------------------------------------------------------------------- /01_getting_started/04_overview_of_spark_sql_properties.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/04_overview_of_spark_sql_properties.ipynb -------------------------------------------------------------------------------- /01_getting_started/05_running_os_commands.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/05_running_os_commands.ipynb -------------------------------------------------------------------------------- /01_getting_started/06_understanding_warehouse_directory.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/06_understanding_warehouse_directory.ipynb -------------------------------------------------------------------------------- /01_getting_started/07_managing_spark_metastore_databases.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/07_managing_spark_metastore_databases.ipynb -------------------------------------------------------------------------------- /01_getting_started/08_managing_spark_metastore_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/08_managing_spark_metastore_tables.ipynb -------------------------------------------------------------------------------- /01_getting_started/09_retrieve_metadata_of_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/09_retrieve_metadata_of_tables.ipynb -------------------------------------------------------------------------------- /01_getting_started/10_role_of_spark_or_hive_metastore.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/10_role_of_spark_or_hive_metastore.ipynb -------------------------------------------------------------------------------- /01_getting_started/11_exercise_getting_started.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/01_getting_started/11_exercise_getting_started.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/01_Overview of HDFS.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/01_Overview of HDFS.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/02_using_hdfs_cli.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/02_using_hdfs_cli.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/03_getting_help_or_usage.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/03_getting_help_or_usage.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/04_listing_hdfs_files.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/04_listing_hdfs_files.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/05_managing_hdfs_directories.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/05_managing_hdfs_directories.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/06_copying_files_from_local_to_hdfs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/06_copying_files_from_local_to_hdfs.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/07_copying_files_from_hdfs_to_local.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/07_copying_files_from_hdfs_to_local.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/08_copying_files_from_hdfs_to_hdfs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/08_copying_files_from_hdfs_to_hdfs.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/09_previewing_data_in_hdfs_files.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/09_previewing_data_in_hdfs_files.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/10_getting_file_metadata.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/10_getting_file_metadata.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/11_hdfs_blocksize.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/11_hdfs_blocksize.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/12_hdfs_replication_factor.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/12_hdfs_replication_factor.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/13_getting_hdfs_storage_usage.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/13_getting_hdfs_storage_usage.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/14_using_hdfs_stat_command.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/14_using_hdfs_stat_command.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/15_hdfs_file_permissions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/15_hdfs_file_permissions.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/16_overriding_properties.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/16_overriding_properties.ipynb -------------------------------------------------------------------------------- /02_overview_of_hdfs/understanding_linux_file_system_240.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/02_overview_of_hdfs/understanding_linux_file_system_240.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/01_basic_transformations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/01_basic_transformations.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/02_spark_sql_overview.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/02_spark_sql_overview.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/03_define_problem_statement.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/03_define_problem_statement.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/04_preparing_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/04_preparing_tables.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/05_projecting_data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/05_projecting_data.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/06_filtering_data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/06_filtering_data.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/07_joining_tables_inner.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/07_joining_tables_inner.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/08_joining_tables_outer.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/08_joining_tables_outer.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/09_aggregating_data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/09_aggregating_data.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/10_sorting_data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/10_sorting_data.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/11_conclusion_final_solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/11_conclusion_final_solution.ipynb -------------------------------------------------------------------------------- /03_basic_transformations/12_exercises_basic_sql_queries.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/03_basic_transformations/12_exercises_basic_sql_queries.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/01_basic_ddl_and_dml.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/01_basic_ddl_and_dml.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/02_create_spark_metastore_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/02_create_spark_metastore_tables.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/03_overview_of_data_types.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/03_overview_of_data_types.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/04_adding_comments.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/04_adding_comments.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/05_loading_data_into_tables_local.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/05_loading_data_into_tables_local.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/06_loading_data_into_tables_hdfs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/06_loading_data_into_tables_hdfs.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/07_loading_data_append_and_overwrite.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/07_loading_data_append_and_overwrite.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/08_creating_external_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/08_creating_external_tables.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/09_managed_vs_external_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/09_managed_vs_external_tables.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/10_overview_of_file_formats.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/10_overview_of_file_formats.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/11_dropping_tables_and_databases.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/11_dropping_tables_and_databases.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/12_truncating_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/12_truncating_tables.ipynb -------------------------------------------------------------------------------- /04_basic_ddl_and_dml/13_exercises_managing_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/04_basic_ddl_and_dml/13_exercises_managing_tables.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/01_dml_and_partitioning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/01_dml_and_partitioning.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/02_introduction_to_partitioning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/02_introduction_to_partitioning.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/03_creating_tables_using_parquet.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/03_creating_tables_using_parquet.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/04_load_vs_insert.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/04_load_vs_insert.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/05_inserting_data_using_stage_table.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/05_inserting_data_using_stage_table.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/06_creating_partitioned_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/06_creating_partitioned_tables.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/07_adding_partitions_to_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/07_adding_partitions_to_tables.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/08_loading_data_into_partitions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/08_loading_data_into_partitions.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/09_inserting_data_into_partitions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/09_inserting_data_into_partitions.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/10_using_dynamic_partition_mode.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/10_using_dynamic_partition_mode.ipynb -------------------------------------------------------------------------------- /05_dml_and_partitioning/11_exercises_partitioned_tables.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/05_dml_and_partitioning/11_exercises_partitioned_tables.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/01_predefined_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/01_predefined_functions.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/02_overview_of_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/02_overview_of_functions.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/03_validating_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/03_validating_functions.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/04_string_manipulation_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/04_string_manipulation_functions.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/05_date_manipulation_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/05_date_manipulation_functions.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/06_overview_of_numeric_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/06_overview_of_numeric_functions.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/07_data_type_conversion.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/07_data_type_conversion.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/08_handling_null_values.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/08_handling_null_values.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/09_using_case_and_when.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/09_using_case_and_when.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/10_query_example_word_count.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/10_query_example_word_count.ipynb -------------------------------------------------------------------------------- /06_predefined_functions/11_exercises_pre_defined_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/06_predefined_functions/11_exercises_pre_defined_functions.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/01_windowing_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/01_windowing_functions.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/02_prepare_database.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/02_prepare_database.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/03_overview_of_windowing_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/03_overview_of_windowing_functions.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/04_aggregations_using_windowing_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/04_aggregations_using_windowing_functions.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/05_using_lead_or_lag.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/05_using_lead_or_lag.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/06_getting_first_and_last_values.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/06_getting_first_and_last_values.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/07_ranking_using_windowing_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/07_ranking_using_windowing_functions.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/08_order_of_execution_of_sql.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/08_order_of_execution_of_sql.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/09_overview_of_sub_queries.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/09_overview_of_sub_queries.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/10_filtering_window_function_results.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/10_filtering_window_function_results.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/11_cumulative_or_moving_aggregations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/11_cumulative_or_moving_aggregations.ipynb -------------------------------------------------------------------------------- /07_windowing_functions/12_exercises_windowing_functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/07_windowing_functions/12_exercises_windowing_functions.ipynb -------------------------------------------------------------------------------- /08_analyze_github_activity/02_download_data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/08_analyze_github_activity/02_download_data.ipynb -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # CCA 175 Spark and Hadoop Developer 2 | -------------------------------------------------------------------------------- /Spark Data Frames to Temp Views.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/Spark Data Frames to Temp Views.ipynb -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/_config.yml -------------------------------------------------------------------------------- /_toc.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/_toc.yml -------------------------------------------------------------------------------- /spark-sql.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/itversity/spark-sql/HEAD/spark-sql.ipynb --------------------------------------------------------------------------------