from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
import numpy as np

from load import load

def select_features(data):
    columns = list(filter(lambda column: 'UNITS' in column, data.columns))
    columns.remove('TOTAL_UNITS')
    array = data.as_matrix(columns)
    return np.nan_to_num(array)


if __name__ == "__main__":
    data = load()
    X = select_features(data)
    pca = PCA(n_components=2).fit(X)
    print(pca.explained_variance_ratio_)
    print(pca.explained_variance_)
    projection = pca.transform(X)
    np.savetxt("results.csv", projection, delimiter=",")
    exit()

'''
    kmeans = KMeans().fit(X)
    for label in kmeans.labels_:
        print(label)
'''