"""
Description: Contains feature processing pipelines used for preprocessing
                raw data into a format that can be used.

"""
import pandas as pd
import numpy as np
# utils etc
import re
import json

# tensorflow imports
import tensorflow as tf

# scikitlearn
from sklearn.preprocessing import (
    # Scalers
    StandardScaler,
    # Encoders
    OneHotEncoder
)

from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.feature_selection import (
    SelectPercentile
)


"""
Feature Processing Pipeline Factory v1
"""


def feature_preprocessing_basic_features(categorical_cols,
                                        numerical_float_cols,
                                        bool_cols):
    """
        Feature processing basic features (v1)
        params:
            - categorical_cols (list[str]) - list of categorical features
            - numerical_float_cols (list[str]) - list of float cols,.
            - bool_cols (list[str]) - list of boolean feature

        returns:
            - pipeline (sklearn.Pipeline)
    """
    # categorical feature
    categorical_features_pipeline = [
        ("categorical_features",
            OneHotEncoder(handle_unknown='infrequent_if_exist'),
            categorical_cols)
    ]

    # numerical features
    numerical_floats_features_pipeline = [
        ("float_features", StandardScaler(),  numerical_float_cols)
    ]

    # bool features
    bool_features_pipeline = [
        ("boolean_features", OneHotEncoder(), bool_cols),
    ]

    final_pipeline = categorical_features_pipeline + \
                    numerical_floats_features_pipeline +\
                    bool_features_pipeline

    # column transformers
    column_transform_fns = ColumnTransformer(transformers=final_pipeline,
                                             remainder='drop')

    return Pipeline(steps=[("feature_processor", column_transform_fns)])