├── .gitattributes ├── .gitignore ├── Chapter01 ├── hello_world.java └── hello_world.py ├── Chapter02 └── hello_world.py ├── Chapter03 ├── data │ ├── scf_data.json │ └── scf_output_data.json ├── process_data.py ├── process_data_2.py └── sys_test.py ├── Chapter04 ├── code │ ├── csv_intro.py │ ├── json_to_csv.py │ ├── pandas_intro.py │ └── xml_to_json.py └── notes │ ├── roads_by_country_notes.txt │ └── wikipedia_notes.txt ├── Chapter05 ├── explore_addresses.py ├── extract_street_names.py └── regex_intro.py ├── Chapter06 └── r_intro.R ├── Chapter07 ├── data │ ├── artificial_roads_by_region.csv │ ├── gas_prices.csv │ └── vehicles.csv ├── dplyr_tidyr_intro.R └── roads_2011.R ├── Chapter08 ├── get_recent_issues.py ├── get_scf_date_range.py └── output_data │ └── .~lock.scf_date_range_issues.csv# ├── Chapter09 ├── dont_do_this.py ├── mongodb.txt └── process_large_data.py ├── LICENSE └── README.md /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/.gitignore -------------------------------------------------------------------------------- /Chapter01/hello_world.java: -------------------------------------------------------------------------------- 1 | System.out.println("Hello World!"); 2 | -------------------------------------------------------------------------------- /Chapter01/hello_world.py: -------------------------------------------------------------------------------- 1 | print("Hello World!") 2 | -------------------------------------------------------------------------------- /Chapter02/hello_world.py: -------------------------------------------------------------------------------- 1 | print("Hello World!") 2 | -------------------------------------------------------------------------------- /Chapter03/data/scf_data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter03/data/scf_data.json -------------------------------------------------------------------------------- /Chapter03/data/scf_output_data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter03/data/scf_output_data.json -------------------------------------------------------------------------------- /Chapter03/process_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter03/process_data.py -------------------------------------------------------------------------------- /Chapter03/process_data_2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter03/process_data_2.py -------------------------------------------------------------------------------- /Chapter03/sys_test.py: -------------------------------------------------------------------------------- 1 | import sys 2 | print(sys.argv) 3 | -------------------------------------------------------------------------------- /Chapter04/code/csv_intro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter04/code/csv_intro.py -------------------------------------------------------------------------------- /Chapter04/code/json_to_csv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter04/code/json_to_csv.py -------------------------------------------------------------------------------- /Chapter04/code/pandas_intro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter04/code/pandas_intro.py -------------------------------------------------------------------------------- /Chapter04/code/xml_to_json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter04/code/xml_to_json.py -------------------------------------------------------------------------------- /Chapter04/notes/roads_by_country_notes.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter04/notes/roads_by_country_notes.txt -------------------------------------------------------------------------------- /Chapter04/notes/wikipedia_notes.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter04/notes/wikipedia_notes.txt -------------------------------------------------------------------------------- /Chapter05/explore_addresses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter05/explore_addresses.py -------------------------------------------------------------------------------- /Chapter05/extract_street_names.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter05/extract_street_names.py -------------------------------------------------------------------------------- /Chapter05/regex_intro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter05/regex_intro.py -------------------------------------------------------------------------------- /Chapter06/r_intro.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter06/r_intro.R -------------------------------------------------------------------------------- /Chapter07/data/artificial_roads_by_region.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter07/data/artificial_roads_by_region.csv -------------------------------------------------------------------------------- /Chapter07/data/gas_prices.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter07/data/gas_prices.csv -------------------------------------------------------------------------------- /Chapter07/data/vehicles.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter07/data/vehicles.csv -------------------------------------------------------------------------------- /Chapter07/dplyr_tidyr_intro.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter07/dplyr_tidyr_intro.R -------------------------------------------------------------------------------- /Chapter07/roads_2011.R: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter08/get_recent_issues.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter08/get_recent_issues.py -------------------------------------------------------------------------------- /Chapter08/get_scf_date_range.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter08/get_scf_date_range.py -------------------------------------------------------------------------------- /Chapter08/output_data/.~lock.scf_date_range_issues.csv#: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter08/output_data/.~lock.scf_date_range_issues.csv# -------------------------------------------------------------------------------- /Chapter09/dont_do_this.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter09/dont_do_this.py -------------------------------------------------------------------------------- /Chapter09/mongodb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter09/mongodb.txt -------------------------------------------------------------------------------- /Chapter09/process_large_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/Chapter09/process_large_data.py -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Practical-Data-Wrangling/HEAD/README.md --------------------------------------------------------------------------------