from sklearn.decomposition import PCA
from scipy.spatial import distance
import generate_data
import settings
import logging
import numpy as np
logging.basicConfig(level=logging.INFO)
X_mnist_raw = generate_data.load_x_mnist_raw()
num_pca_dimensions = settings.parameters.get(
"num_pca_dimensions", settings.parameters["num_pca_dimensions"])
pca_random_seed = settings.parameters.get(
"pca_random_seed", settings.parameters["pca_random_seed"])
X_mnist_old = np.zeros((X_mnist_raw.shape[0], num_pca_dimensions))
for i in range(1000):
mnist_pca = PCA(n_components=num_pca_dimensions,
svd_solver='full',
random_state=i)
X_mnist = mnist_pca.fit_transform(X_mnist_raw)
D = distance.pdist(X_mnist)
min_dist = np.min(D)
logging.info(
"After PCA - minimum distance between samples is %f, dist to old %f",
min_dist, np.max(np.abs(X_mnist_old - X_mnist)))
X_mnist_old = X_mnist
import generate_data
import settings
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import settings
parameters = settings.parameters
X_mnist_raw = generate_data.load_x_mnist_raw(parameters=parameters)
letters_A, letters_A_raw = generate_data.load_A_letters(parameters=parameters)
print(letters_A_raw.shape, np.max(letters_A_raw[0, :]),
np.min(letters_A_raw[0, :]))
width = 10 #total number to show in one row
start_index = 0
height = 10 # Number of rows /2 to show. half will go to labels, half to pictures.
f, ax = plt.subplots(height, width)
f.set_size_inches(16, 16)
f.subplots_adjust()
for i in range(int(height)):
for j in range(width):
ax[i][j].imshow(letters_A_raw[start_index + width * i + j, :].reshape(
28, 28),
cmap='gray_r')
#ax[2*i+1][j].text(text=str(letters_A_labels[start_index + width*i + j])
#str(chr(