Merge pull request #157 from best-practice-and-impact/synthetic-data-branch

Synthetic data branch

Author: donadviser

.gitignore

@@ -6,4 +6,5 @@ __pycache__
 !.gitignore
 .ipynb_checkpoints*
 _build/
-test_update_links/*
+test_update_links/*
+.venv/*

Rplots.pdf

@@ -10,3 +10,5 @@ rescue_with_pop_path_csv: "file:////home/cdsw/ons-spark/ons-spark/data/rescue_wi
 rescue_with_pop_path_parquet: "file:////home/cdsw/ons-spark/ons-spark/data/rescue_with_pop.parquet"
 staging_table_example: "staging_example_"
 database: "train_tmp"
+census_2011_teaching_data_path_csv: "file:////home/cdsw/ons-spark/ons-spark/data/census_2011_microdata_teaching_file.csv"
+census_relationship_file_path_csv: "file:////home/cdsw/ons-spark/ons-spark/data/census_relationship_file.csv"

config.yaml

@@ -71,5 +71,5 @@ parts:
   - file: ancillary-topics/pandas-udfs
   - file: ancillary-topics/r-udfs
   - file: ancillary-topics/hive-partitions
-
-  
+  - file: ancillary-topics/synthpop_with_r
+  - file: ancillary-topics/synthetic_data_python