pca_feature_transformation.py

import numpy as np
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, StandardScaler


def read_data(file_name):
    return pd.read_csv(file_name)


def remove_unwanted_features(dataset):
    X = dataset.iloc[:, 3:13].values
    y = dataset.iloc[:, 13].values
    return X, y


def label_encoder(X):
    label_encoder_X = LabelEncoder()
    X[:, 1] = label_encoder_X.fit_transform(X[:, 1])
    X[:, 2] = label_encoder_X.fit_transform(X[:, 2])
    return X


def hot_encoder(X):
    one_hot_encoder = OneHotEncoder(categorical_features=[1])
    X = one_hot_encoder.fit_transform(X).toarray()
    return X


def feature_scaling(dataset):
    scaler = StandardScaler()
    cols = ["CreditScore", "Age", "Tenure", "Balance", "EstimatedSalary"]
    dataset[cols] = scaler.fit_transform(dataset[cols])
    return dataset


def feature_transform(X):
    pca = PCA(n_components=8)
    X = pca.fit_transform(X)
    eigen_values = pca.explained_variance_
    return X


if __name__ == '__main__':
    np.set_printoptions(threshold=np.inf)
    dataset = read_data("Churn_Modelling.csv")
    dataset = feature_scaling(dataset)
    X, y = remove_unwanted_features(dataset)
    X = label_encoder(X)
    X = hot_encoder(X)
    X = feature_transform(X)