├── .gitignore ├── Data ├── ContainsNull.csv ├── Moby-Dick.txt ├── appl_stock.csv ├── chinook.db ├── chinook.zip ├── people.json ├── sales_info.csv ├── sqlite_latest.jar └── users.parquet ├── DataFrame_operations_basics.ipynb ├── Dataframe_SQL_query.ipynb ├── Dataframe_introduction.ipynb ├── GroupBy_aggregrate.ipynb ├── Images ├── Components.png ├── RDD-1.png ├── RDD_dependency_graph.PNG ├── Readme.md ├── Spark ecosystem.png └── SparkSQL-1.png ├── Key-Value RDD basics.ipynb ├── LICENSE ├── Partioning and Gloming.ipynb ├── Python-and-Spark-for-Big-Data-master ├── Course_Notes.zip ├── Data Set Generator (remove me the future!) │ ├── Creating Fake Data.ipynb │ ├── DataSets │ │ ├── Facebook_metrics.txt │ │ ├── customer_churn.csv │ │ ├── dataset_Facebook.csv │ │ ├── dog_food.csv │ │ └── hack_data.csv │ ├── fake_customers.csv │ ├── hello.csv │ ├── new_customers.csv │ └── test.csv ├── Python-Crash-Course │ ├── Python Crash Course Exercises - Solutions.ipynb │ ├── Python Crash Course Exercises.ipynb │ └── Python Crash Course.ipynb ├── README.md ├── Spark Streaming │ ├── Introduction to Spark Streaming.ipynb │ └── TweetRead.py ├── Spark_DataFrame_Project_Exercise │ ├── Spark DataFrames Project Exercise - SOLUTIONS.ipynb │ ├── Spark DataFrames Project Exercise.ipynb │ └── walmart_stock.csv ├── Spark_DataFrames │ ├── ContainsNull.csv │ ├── DataFrame_Basic_Operations.ipynb │ ├── DataFrame_Basics.ipynb │ ├── Dates_and_Timestamps.ipynb │ ├── GroupBy_and_Aggregate_Functions.ipynb │ ├── Missing_Data.ipynb │ ├── appl_stock.csv │ ├── people.json │ └── sales_info.csv └── Spark_for_Machine_Learning │ ├── Clustering │ ├── Clustering Code Along.ipynb │ ├── Clustering_Code_Example.ipynb │ ├── Clustering_Consulting_Project.ipynb │ ├── Clustering_Consulting_Project_SOLUTIONS.ipynb │ ├── hack_data.csv │ ├── sample_kmeans_data.txt │ ├── seeds_dataset.csv │ └── seeds_dataset.txt │ ├── Linear_Regression │ ├── Data_Transformations.ipynb │ ├── Ecommerce_Customers.csv │ ├── Linear_Regression_Code_Along.ipynb │ ├── Linear_Regression_Consulting_Project.ipynb │ ├── Linear_Regression_Consulting_Project_SOLUTIONS.ipynb │ ├── Linear_Regression_Example.ipynb │ ├── cruise_ship_info.csv │ ├── fake_customers.csv │ └── sample_linear_regression_data.txt │ ├── Logistic_Regression │ ├── Logistic_Regression_Consulting_Project.ipynb │ ├── Logistic_Regression_Consulting_Project_SOLUTIONS.ipynb │ ├── Logistic_Regression_Example.ipynb │ ├── Titanic_Log_Regression_Code_Along.ipynb │ ├── customer_churn.csv │ ├── new_customers.csv │ ├── sample_libsvm_data.txt │ └── titanic.csv │ ├── Natural_Language_Processing │ ├── NLP_Code_Along.ipynb │ ├── Tools_for_NLP.ipynb │ └── smsspamcollection │ │ ├── SMSSpamCollection │ │ └── readme │ ├── Recommender_Systems │ ├── Consulting Project - Recommender Systems.ipynb │ ├── Meal_Info.csv │ ├── Recommender_Code_Along.ipynb │ └── movielens_ratings.csv │ └── Tree_Methods │ ├── College.csv │ ├── Tree Methods Code Along.ipynb │ ├── Tree_Methods_Consulting_Project.ipynb │ ├── Tree_Methods_Consulting_Project_SOLUTION.ipynb │ ├── Tree_Methods_Doc_Example.ipynb │ ├── dog_food.csv │ └── sample_libsvm_data.txt ├── RDD_Chaining_Execution.ipynb ├── README.md ├── Row_column_objects.ipynb ├── Spark-with-Python-writeup ├── Readme.md └── Spark-with-Python.md ├── SparkContext and RDD Basics.ipynb ├── SparkContext_Workers_Lazy_Evaluations.ipynb ├── Word_Count.ipynb ├── _config.yml └── notebook.tex /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/.gitignore -------------------------------------------------------------------------------- /Data/ContainsNull.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/ContainsNull.csv -------------------------------------------------------------------------------- /Data/Moby-Dick.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/Moby-Dick.txt -------------------------------------------------------------------------------- /Data/appl_stock.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/appl_stock.csv -------------------------------------------------------------------------------- /Data/chinook.db: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/chinook.db -------------------------------------------------------------------------------- /Data/chinook.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/chinook.zip -------------------------------------------------------------------------------- /Data/people.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/people.json -------------------------------------------------------------------------------- /Data/sales_info.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/sales_info.csv -------------------------------------------------------------------------------- /Data/sqlite_latest.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/sqlite_latest.jar -------------------------------------------------------------------------------- /Data/users.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Data/users.parquet -------------------------------------------------------------------------------- /DataFrame_operations_basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/DataFrame_operations_basics.ipynb -------------------------------------------------------------------------------- /Dataframe_SQL_query.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Dataframe_SQL_query.ipynb -------------------------------------------------------------------------------- /Dataframe_introduction.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Dataframe_introduction.ipynb -------------------------------------------------------------------------------- /GroupBy_aggregrate.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/GroupBy_aggregrate.ipynb -------------------------------------------------------------------------------- /Images/Components.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Images/Components.png -------------------------------------------------------------------------------- /Images/RDD-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Images/RDD-1.png -------------------------------------------------------------------------------- /Images/RDD_dependency_graph.PNG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Images/RDD_dependency_graph.PNG -------------------------------------------------------------------------------- /Images/Readme.md: -------------------------------------------------------------------------------- 1 | ## Images 2 | -------------------------------------------------------------------------------- /Images/Spark ecosystem.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Images/Spark ecosystem.png -------------------------------------------------------------------------------- /Images/SparkSQL-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Images/SparkSQL-1.png -------------------------------------------------------------------------------- /Key-Value RDD basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Key-Value RDD basics.ipynb -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/LICENSE -------------------------------------------------------------------------------- /Partioning and Gloming.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Partioning and Gloming.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Course_Notes.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Course_Notes.zip -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/Creating Fake Data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/Creating Fake Data.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/Facebook_metrics.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/Facebook_metrics.txt -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/customer_churn.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/customer_churn.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/dataset_Facebook.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/dataset_Facebook.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/dog_food.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/dog_food.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/hack_data.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/DataSets/hack_data.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/fake_customers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/fake_customers.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/hello.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/hello.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/new_customers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/new_customers.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Data Set Generator (remove me the future!)/test.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Python-Crash-Course/Python Crash Course Exercises - Solutions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Python-Crash-Course/Python Crash Course Exercises - Solutions.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Python-Crash-Course/Python Crash Course Exercises.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Python-Crash-Course/Python Crash Course Exercises.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Python-Crash-Course/Python Crash Course.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Python-Crash-Course/Python Crash Course.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/README.md -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark Streaming/Introduction to Spark Streaming.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark Streaming/Introduction to Spark Streaming.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark Streaming/TweetRead.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark Streaming/TweetRead.py -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrame_Project_Exercise/Spark DataFrames Project Exercise - SOLUTIONS.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrame_Project_Exercise/Spark DataFrames Project Exercise - SOLUTIONS.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrame_Project_Exercise/Spark DataFrames Project Exercise.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrame_Project_Exercise/Spark DataFrames Project Exercise.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrame_Project_Exercise/walmart_stock.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrame_Project_Exercise/walmart_stock.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/ContainsNull.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/ContainsNull.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/DataFrame_Basic_Operations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/DataFrame_Basic_Operations.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/DataFrame_Basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/DataFrame_Basics.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/Dates_and_Timestamps.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/Dates_and_Timestamps.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/GroupBy_and_Aggregate_Functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/GroupBy_and_Aggregate_Functions.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/Missing_Data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/Missing_Data.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/appl_stock.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/appl_stock.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/people.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/people.json -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_DataFrames/sales_info.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_DataFrames/sales_info.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering Code Along.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering Code Along.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering_Code_Example.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering_Code_Example.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering_Consulting_Project.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering_Consulting_Project.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering_Consulting_Project_SOLUTIONS.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/Clustering_Consulting_Project_SOLUTIONS.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/hack_data.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/hack_data.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/sample_kmeans_data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/sample_kmeans_data.txt -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/seeds_dataset.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/seeds_dataset.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/seeds_dataset.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Clustering/seeds_dataset.txt -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Data_Transformations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Data_Transformations.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Ecommerce_Customers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Ecommerce_Customers.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Code_Along.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Code_Along.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Consulting_Project.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Consulting_Project.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Consulting_Project_SOLUTIONS.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Consulting_Project_SOLUTIONS.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Example.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/Linear_Regression_Example.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/cruise_ship_info.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/cruise_ship_info.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/fake_customers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/fake_customers.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/sample_linear_regression_data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Linear_Regression/sample_linear_regression_data.txt -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Logistic_Regression_Consulting_Project.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Logistic_Regression_Consulting_Project.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Logistic_Regression_Consulting_Project_SOLUTIONS.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Logistic_Regression_Consulting_Project_SOLUTIONS.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Logistic_Regression_Example.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Logistic_Regression_Example.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Titanic_Log_Regression_Code_Along.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/Titanic_Log_Regression_Code_Along.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/customer_churn.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/customer_churn.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/new_customers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/new_customers.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/sample_libsvm_data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/sample_libsvm_data.txt -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/titanic.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Logistic_Regression/titanic.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/NLP_Code_Along.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/NLP_Code_Along.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/Tools_for_NLP.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/Tools_for_NLP.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/smsspamcollection/SMSSpamCollection: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/smsspamcollection/SMSSpamCollection -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/smsspamcollection/readme: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Natural_Language_Processing/smsspamcollection/readme -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/Consulting Project - Recommender Systems.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/Consulting Project - Recommender Systems.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/Meal_Info.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/Meal_Info.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/Recommender_Code_Along.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/Recommender_Code_Along.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/movielens_ratings.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Recommender_Systems/movielens_ratings.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/College.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/College.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree Methods Code Along.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree Methods Code Along.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree_Methods_Consulting_Project.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree_Methods_Consulting_Project.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree_Methods_Consulting_Project_SOLUTION.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree_Methods_Consulting_Project_SOLUTION.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree_Methods_Doc_Example.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/Tree_Methods_Doc_Example.ipynb -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/dog_food.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/dog_food.csv -------------------------------------------------------------------------------- /Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/sample_libsvm_data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Python-and-Spark-for-Big-Data-master/Spark_for_Machine_Learning/Tree_Methods/sample_libsvm_data.txt -------------------------------------------------------------------------------- /RDD_Chaining_Execution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/RDD_Chaining_Execution.ipynb -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/README.md -------------------------------------------------------------------------------- /Row_column_objects.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Row_column_objects.ipynb -------------------------------------------------------------------------------- /Spark-with-Python-writeup/Readme.md: -------------------------------------------------------------------------------- 1 | ## Spark with Python writeup 2 | -------------------------------------------------------------------------------- /Spark-with-Python-writeup/Spark-with-Python.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Spark-with-Python-writeup/Spark-with-Python.md -------------------------------------------------------------------------------- /SparkContext and RDD Basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/SparkContext and RDD Basics.ipynb -------------------------------------------------------------------------------- /SparkContext_Workers_Lazy_Evaluations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/SparkContext_Workers_Lazy_Evaluations.ipynb -------------------------------------------------------------------------------- /Word_Count.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/Word_Count.ipynb -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/_config.yml -------------------------------------------------------------------------------- /notebook.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tirthajyoti/Spark-with-Python/HEAD/notebook.tex --------------------------------------------------------------------------------