Faktoranalízis Python

##Faktoranalízis Python-ban
#!/usr/bin/env python
# coding: utf-8

import os
import pandas as pd
import numpy as np
from sklearn.decomposition import PCA
from sklearn import preprocessing
import matplotlib.pyplot as plt


ldir=os.chdir('C:\\Users\\36307\\Documents\\hdd\\Egyetem\\')
df=pd.read_csv('2017.csv')
df


countries = df['Country'].tolist()
df.drop(['Happiness.Score','Happiness.Rank','Whisker.high', 'Whisker.low'],axis=1,inplace=True)
df = df.set_index('Country')
df.head()



scaled_data = preprocessing.scale(df)
scaled_data


pca = PCA()
pca.fit(scaled_data)
pca_data = pca.transform(scaled_data)
pca_data



per_var = np.round(pca.explained_variance_ratio_* 100, decimals=1)
labels = ['FK' + str(x) for x in range(1, len(per_var)+1)]
plt.bar(x=range(1,len(per_var)+1), height=per_var, tick_label=labels)
plt.ylabel('Magyarázóerő (%)')
plt.xlabel('Főkomponens')
plt.title('Scree Plot')
plt.show()


loading_scores = pd.Series(pca.components_[0])
sorted_loading_scores = loading_scores.abs().sort_values(ascending=False)
print(sorted_loading_scores)


loadings = pd.Series(loading_scores)
factors = pd.Series(df.columns)
pd.concat([loadings, factors], axis=1)


from sklearn.metrics import euclidean_distances
from sklearn import manifold


seed = np.random.RandomState(seed=3)
similarities = euclidean_distances(df)
mds = manifold.MDS(n_components=3, max_iter=3000, eps=1e-9,
      random_state=seed, dissimilarity="precomputed", n_jobs=1)
pos = mds.fit(similarities).embedding_
pos


from matplotlib import pyplot
from mpl_toolkits.mplot3d import Axes3D
from numpy.random import rand
from pylab import figure

fig = figure()
ax = Axes3D(fig)

for i in range(len(pos)):
 ax.scatter(pos[i,0],pos[i,1],pos[i,2],color='b')
 ax.text(pos[i,0],pos[i,1],pos[i,2], countries[i], size=6, zorder=1, color='k')
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('z')
ax.set_title('MDS')
pyplot.show()