Created
October 24, 2015 16:05
-
-
Save saihttam/cad6d3d223fc8d769227 to your computer and use it in GitHub Desktop.
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 | |
from sklearn.feature_extraction import DictVectorizer | |
def one_hot_dataframe(data, cols, replace=False): | |
""" Takes a dataframe and a list of columns that need to be encoded. | |
Returns a 3-tuple comprising the data, the vectorized data, | |
and the fitted vectorizor.""" | |
vec = DictVectorizer(sparse=False) | |
vecData = pd.DataFrame(vec.fit_transform(data[cols].T.to_dict().values())) | |
vecData.columns = vec.get_feature_names() | |
vecData.index = data.index | |
if replace is True: | |
data = data.drop(cols, axis=1) | |
data = data.join(vecData) | |
return (data, vecData, vec) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment