PCA Diploma

print(__doc__)

import matplotlib.pyplot as plt

import csv
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

def pca_ol(filename):

  X = []
  y = [0, 1, 2]

  with open(filename) as csvfile:
      readCSV = csv.reader(csvfile, delimiter=',')
      for row in readCSV:
          row = [float(i.replace(",",".")) for i in row]
          X.append(row)

  target_names = ["G1", "G2", "G3"]

  pca = PCA(n_components=2)
  X_r = pca.fit(X).transform(X)

  # Percentage of variance explained for each components
  print('explained variance ratio (first two components): %s'
        % str(pca.explained_variance_ratio_))

  plt.figure()
  colors = ['navy', 'turquoise', 'darkorange']
  lw = 2

  print(X_r)


  for color, i, target_name in zip(colors, [0, 1, 2], target_names):
      plt.scatter(X_r[i, 0], X_r[i, 1], color=color, alpha=.8, lw=lw,
                  label=target_name)

  plt.legend(loc='best', shadow=False, scatterpoints=1)

  plt.show()



# pca_ol('tdgma1.csv')
# pca_ol('tdgma2.csv')
# pca_ol('tdgma3.csv')
# pca_ol('tdgma4.csv')
pca_ol('tdgma5.csv')
print(__doc__)

import matplotlib.pyplot as plt

import csv
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

def pca_ol(filename):

  X = []
  y = [0, 1, 2]

  with open(filename) as csvfile:
      readCSV = csv.reader(csvfile, delimiter=',')
      for row in readCSV:
          row = [float(i.replace(",",".")) for i in row]
          X.append(row)

  target_names = ["G1", "G2", "G3"]

  pca = PCA(n_components=2)
  X_r = pca.fit(X).transform(X)

  # Percentage of variance explained for each components
  print('explained variance ratio (first two components): %s'
        % str(pca.explained_variance_ratio_))

  plt.figure()
  colors = ['navy', 'turquoise', 'darkorange']
  lw = 2

  print(X_r)


  for color, i, target_name in zip(colors, [0, 1, 2], target_names):
      plt.scatter(X_r[i, 0], X_r[i, 1], color=color, alpha=.8, lw=lw,
                  label=target_name)

  plt.legend(loc='best', shadow=False, scatterpoints=1)

  plt.show()



# pca_ol('tdgma1.csv')
# pca_ol('tdgma2.csv')
# pca_ol('tdgma3.csv')
# pca_ol('tdgma4.csv')
pca_ol('tdgma5.csv')