-
-
Save jurand71/46d7e641193a562bdbd6143f6b0dba19 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 libraries | |
import numpy as np | |
import pandas as pd | |
# Display all columns | |
pd.set_option('display.max_columns', None) | |
# Import Houseprice data from GitHub | |
df = pd.read_csv('https://github.com/jurand71/datasets/raw/master/HouseSalePriceCompetition/houseprice.csv') | |
# Determine categorical variables in the dataset | |
categorical_variables = [var for var in df.columns if df[var].dtype == 'O'] | |
# Let's explore the cardinality in variables | |
categories = {} | |
for cat_variable in categorical_variables: | |
categories[df[cat_variable].name] = list(df[cat_variable].unique()) | |
# Three variables were chosen from categorical variables for OneHotEncoder | |
usecols = ['HeatingQC','KitchenQual','CentralAir'] | |
df = df[usecols] | |
# Import OneHotEncoder class | |
from sklearn.preprocessing import OneHotEncoder | |
enc = OneHotEncoder(categories='auto', | |
drop='first', # to return k-1, drop=false to return k dummies | |
sparse=False, | |
handle_unknown='error') # helps deal with rare labels) | |
enc.fit(df.fillna('Missing')) | |
# Learned categories in dataset | |
enc.categories_ | |
# Transform encoding for dataset | |
enc_data = enc.transform(df.fillna('Missing')) | |
# Convert array to dataframe | |
pd.DataFrame(enc_data).head() | |
# Retrieve the feature names | |
enc.get_feature_names_out() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment