menu

Kaggler

Kaggler

One-Hot, Label, Target, Frequency, and Embedding Encoders for Categorical Features import pandas as pd from kaggler.preprocessing import OneHotEncoder, LabelEncoder, TargetEncoder, FrequencyEncoder, EmbeddingEncoder

trn = pd.read_csv('train.csv')
target_col = trn.columns[-1]
cat_cols = [col for col in trn.columns if trn[col].dtype == 'object']

ohe = OneHotEncoder(min_obs=100) # grouping all categories with less than 100 occurences
lbe = LabelEncoder(min_obs=100)  # grouping all categories with less than 100 occurences
te = TargetEncoder()			 # replacing each category with the average target value of the category
fe = FrequencyEncoder()	         # replacing each category with the frequency value of the category
ee = EmbeddingEncoder()          # mapping each category to a vector of real numbers

X_ohe = ohe.fit_transform(trn[cat_cols])	    # X_ohe is a scipy sparse matrix
trn[cat_cols] = lbe.fit_transform(trn[cat_cols])
trn[cat_cols] = te.fit_transform(trn[cat_cols])
trn[cat_cols] = fe.fit_transform(trn[cat_cols])
X_ee = ee.fit_transform(trn[cat_cols], trn[target_col])          # X_ee is a numpy matrix

tst = pd.read_csv('test.csv')
X_ohe = ohe.transform(tst[cat_cols])
tst[cat_cols] = lbe.transform(tst[cat_cols])
tst[cat_cols] = te.transform(tst[cat_cols])
tst[cat_cols] = fe.transform(tst[cat_cols])
X_ee = ee.transform(tst[cat_cols])



编辑