PCA

import pandas as pd
from sklearn.decomposition import PCA
import math


logicalLink = pd.read_csv('LogicalLink-2.csv')
# Just take these features of interest
df = logicalLink[['TT','UT','RP','CML','SP','LP']]

df.describe()
#print(df)


pca = PCA(n_components=2, svd_solver='full')
pca.fit(df)
T = pca.transform(df)
df.shape
df.head()
pca.explained_variance_ratio_
print(pca.components_)
components = pd.DataFrame(pca.components_, columns = df.columns, index=[1, 2])

print("component")
print(components)

def get_important_features(transformed_features, components_, columns):
    """
    This function will return the most "important"
    features so we can determine which have the most
    effect on multi-dimensional scaling
    """
    num_columns = len(columns)

    # Scale the principal components by the max value in
    # the transformed set belonging to that component
    xvector = components_[0] * max(transformed_features[:,0])
    yvector = components_[1] * max(transformed_features[:,1])

    # Sort each column by it's length. These are your *original*
    # columns, not the principal components.
    important_features = { columns[i] : math.sqrt(xvector[i]**2 + yvector[i]**2) for i in range(num_columns) }
    important_features = sorted(zip(important_features.values(), important_features.keys()), reverse=True)
    print("Features by importance:\n", important_features)

get_important_features(T, pca.components_, df.columns.values)