fit_transform() takes 2 positional arguments but 3 were given with LabelBinarizer

Question

I am totally new to Machine Learning and I have been working with unsupervised learning technique.

Image shows my sample Data(After all Cleaning) Screenshot : Sample

Answer 1

To perform one-hot encoding for multiple categorical features, we can create a new class which customizes our own multiple categorical features binarizer and plug it into categorical pipeline as follows.

Suppose CAT_FEATURES = ['cat_feature1', 'cat_feature2'] is a list of categorical features. The following scripts shall resolve the issue and produce what we want.

import pandas as pd
from sklearn.pipeline import Pipeline
from sklearn.base import BaseEstimator, TransformerMixin

class CustomLabelBinarizer(BaseEstimator, TransformerMixin):
    """Perform one-hot encoding to categorical features."""
    def __init__(self, cat_features):
        self.cat_features = cat_features

    def fit(self, X_cat, y=None):
        return self

    def transform(self, X_cat):
        X_cat_df = pd.DataFrame(X_cat, columns=self.cat_features)
        X_onehot_df = pd.get_dummies(X_cat_df, columns=self.cat_features)
        return X_onehot_df.values

# Pipeline for categorical features.
cat_pipeline = Pipeline([
    ('selector', DataFrameSelector(CAT_FEATURES)),
    ('onehot_encoder', CustomLabelBinarizer(CAT_FEATURES))
])