Shuaiyi Zhang understar

## preproc.py
# (C) Kyle Kastner, June 2014
# License: BSD 3 clause

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.utils import array2d, as_float_array
from scipy.linalg import eigh
import numpy as np

class ZCA(BaseEstimator, TransformerMixin):
    def __init__(self, n_components=None, bias=.1, copy=True):

## gist:d28554d0d05ce7beac7c
import numpy as np

def makeGaussian(size, fwhm = 3, center=None):
    """ Make a square gaussian kernel.

    size is the length of a side of the square
    fwhm is full-width-half-maximum, which
    can be thought of as an effective radius.
    """

## sides
# -*- coding: utf-8 -*-
"""
Created on Wed Jan 08 18:02:10 2014

@author: understar
"""
from __future__ import division
from collections import Counter
import sys
from random import randint

## PicConverText.py
#!/usr/bin/env python
# coding=utf8
# author=evi1m0
# website=linux.im

'''
    12306 Captcha Picture:
    author: Evi1m0@20150316
        1. Download Captcha
        2. Pic Conver Text

## gist:2c879afc911d9152e49ca6ded0ac8cfa
# code from http://danieljlewis.org/files/2010/06/Jenks.pdf
# described at http://danieljlewis.org/2010/06/07/jenks-natural-breaks-algorithm-in-python/

def getJenksBreaks( dataList, numClass ):
  dataList.sort()
  mat1 = []
  for i in range(0,len(dataList)+1):
    temp = []
    for j in range(0,numClass+1):
      temp.append(0)

## landsat_notes.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                understar
                / landsat_notes.md
            
            
              Created
              April 27, 2017 05:21
                — forked from oeon/landsat_notes.md
            
              
                notes from processing Harmony Landsat post
              
          
    ##This workflow is only for the pansharpened images
####red-green-blue

gdalbuildvrt -separate -q -srcnodata "0 0 0" -vrtnodata "0 0 0" rgb.vrt LC80430352013339LGN00_B4.tif LC80430352013339LGN00_B3.tif LC80430352013339LGN00_B2.tif
####NIR, SWIR, and visible red

gdalbuildvrt -separate -q -srcnodata "0 0 0" -vrtnodata "0 0 0" false.vrt LC80430352013339LGN00_B5.tif LC80430352013339LGN00_B6.tif LC80430352013339LGN00_B4.tif
####color infrared

gdalbuildvrt -separate -q -srcnodata "0 0 0" -vrtnodata "0 0 0" cir.vrt LC80430352013339LGN00_B5.tif LC80430352013339LGN00_B3.tif LC80430352013339LGN00_B4.tif

  
## img2wav.py
"""
Demonstrates playing the generated samples directly using PyAudio
Tested on PyAudio 0.2.7 http://people.csail.mit.edu/hubert/pyaudio/
"""

from __future__ import division
from pysstv.sstv import SSTV
from time import sleep
from itertools import islice
import struct, pyaudio

## plot_rbm_logistic_classification.py
"""
==============================================================
Restricted Boltzmann Machine features for digit classification
==============================================================

For greyscale image data where pixel values can be interpreted as degrees of
blackness on a white background, like handwritten digit recognition, the
Bernoulli Restricted Boltzmann machine model (:class:`BernoulliRBM
<sklearn.neural_network.BernoulliRBM>`) can perform effective non-linear
feature extraction.
	# (C) Kyle Kastner, June 2014
	# License: BSD 3 clause

	from sklearn.base import BaseEstimator, TransformerMixin
	from sklearn.utils import array2d, as_float_array
	from scipy.linalg import eigh
	import numpy as np

	class ZCA(BaseEstimator, TransformerMixin):
	def __init__(self, n_components=None, bias=.1, copy=True):
	import numpy as np

	def makeGaussian(size, fwhm = 3, center=None):
	""" Make a square gaussian kernel.

	size is the length of a side of the square
	fwhm is full-width-half-maximum, which
	can be thought of as an effective radius.
	"""
	# -- coding: utf-8 --
	"""
	Created on Wed Jan 08 18:02:10 2014

	@author: understar
	"""
	from __future__ import division
	from collections import Counter
	import sys
	from random import randint
	#!/usr/bin/env python
	# coding=utf8
	# author=evi1m0
	# website=linux.im

	'''
	12306 Captcha Picture:
	author: Evi1m0@20150316
	1. Download Captcha
	2. Pic Conver Text
	# code from http://danieljlewis.org/files/2010/06/Jenks.pdf
	# described at http://danieljlewis.org/2010/06/07/jenks-natural-breaks-algorithm-in-python/

	def getJenksBreaks( dataList, numClass ):
	dataList.sort()
	mat1 = []
	for i in range(0,len(dataList)+1):
	temp = []
	for j in range(0,numClass+1):
	temp.append(0)
	"""
	Demonstrates playing the generated samples directly using PyAudio
	Tested on PyAudio 0.2.7 http://people.csail.mit.edu/hubert/pyaudio/
	"""

	from __future__ import division
	from pysstv.sstv import SSTV
	from time import sleep
	from itertools import islice
	import struct, pyaudio
	"""
	==============================================================
	Restricted Boltzmann Machine features for digit classification
	==============================================================

	For greyscale image data where pixel values can be interpreted as degrees of
	blackness on a white background, like handwritten digit recognition, the
	Bernoulli Restricted Boltzmann machine model (:class:`BernoulliRBM
	<sklearn.neural_network.BernoulliRBM>`) can perform effective non-linear
	feature extraction.