mirror-github-bspeice/betterwithdata_cleaning_4
1
0
Fork 0
mirror of https://github.com/bspeice/betterwithdata_cleaning_4 synced 2024-12-04 21:28:09 -05:00
Code Issues Releases Wiki Activity

mv

Browse Source
This commit is contained in:
Ivan Ivanov 2015-11-07 17:04:11 -05:00
parent 318f990a30
commit 63c1ff7386
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
scripts/enrich_dataset.py
View File

@ -38,7 +38,12 @@ def get_labels(PUFId, varName):
def load_dictionary(dictfile): def load_dictionary(dictfile):
df = pd.read_csv(dictfile) df = pd.read_csv(dictfile)
return dict(zip(df.NAME, df.DESCRIPTION))
dictionary = dict(zip(df.NAME, df.DESCRIPTION))
srcs = dictionary.keys()
for k in srcs:
dictionary[k + '_label'] = dictionary[k] + '_label'
return dictionary
# hardcoded config of which file corresponds to which year. # hardcoded config of which file corresponds to which year.
@ -49,11 +54,15 @@ YEAR_FILES = dict([('h{}e.csv'.format(idx), 2013-i) for i, idx in enumerate([160
if __name__ == '__main__': if __name__ == '__main__':
# Usage:
# $0 --input-file data/emergency\ visits/h94e.csv \
# --output-dir data/emergency\ visits/ \
# --column-dictionary FYCCodebook_2013.csv
#
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument('--input-file') parser.add_argument('--input-file')
parser.add_argument('--output-dir') parser.add_argument('--output-dir')
parser.add_argument('--column-dictionary') parser.add_argument('--column-dictionary')
parser.add_argument('--category')
args = parser.parse_args() args = parser.parse_args()
infile = os.path.basename(args.input_file) infile = os.path.basename(args.input_file)
@ -73,9 +82,6 @@ if __name__ == '__main__':
if args.column_dictionary: if args.column_dictionary:
dictionary = load_dictionary(args.column_dictionary) dictionary = load_dictionary(args.column_dictionary)
srcs = dictionary.keys()
for k in srcs:
dictionary[k + '_label'] = dictionary[k] + '_label'
raw_data.columns = [dictionary.get(col, col) for col in raw_data.columns] raw_data.columns = [dictionary.get(col, col) for col in raw_data.columns]