Created
April 20, 2014 00:57
-
-
Save ghl3/11102044 to your computer and use it in GitHub Desktop.
Convert nominal (string, object) features in a pandas dataframe to integers
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
def get_nominal_integer_dict(nominal_vals): | |
d = {} | |
for val in nominal_vals: | |
if val not in d: | |
current_max = max(d.values()) if len(d) > 0 else -1 | |
d[val] = current_max+1 | |
return d | |
def convert_to_integer(srs): | |
d = get_nominal_integer_dict(srs) | |
return srs.map(lambda x: d[x]) | |
def convert_strings_to_integer(df): | |
ret = pd.DataFrame() | |
for column_name in df: | |
column = df[column_name] | |
if column.dtype=='string' or column.dtype=='object': | |
ret[column_name] = convert_to_integer(column) | |
else: | |
ret[column_name] = column | |
return ret |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment