Mehdi Cherti mehdidc

## README.md

      
              3 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                mehdidc
                / README.md
            
            
              Created
              March 20, 2016 17:33
                — forked from EderSantana/CATCH_Keras_RL.md
            
              
                Keras plays catch - a single file Reinforcement Learning example
              
          
    Code for Keras plays catch blog post
Train

python qlearn.py
Test


Generate figures


## pyearth_multicolumn_benchmark.py
import numpy as np
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
from pyearth import Earth
import time
from itertools import product

np.random.seed(2)

## pyearth_missing_benchmark.py
import numpy as np
import os
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
from pyearth import Earth
import time

np.random.seed(2)

## elastic_transform.py
import numpy
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter

def elastic_transform(image, alpha, sigma, random_state=None):
    """Elastic deformation of images as described in [Simard2003]_.


    .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
       Convolutional Neural Networks applied to Visual Document Analysis", in

## pyearth_benchmark_old_vs_new.py
import numpy as np
import time

from joblib import Memory

import pandas as pd

from bokeh.charts import show, Bar
from bokeh.io import output_file, vplot

## min-char-rnn.py
"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

## gam.py
from sklearn.ensemble import RandomForestRegressor
from sklearn.base import clone
import numpy as np

class GAM(object):
    """
    Simple generalized additive model which fits each feature w.r.t
    the output independently using a model specified by
    base_estimator. the final predictions can be done by regressing linearly
    the predictions of the model of each features by using a pipeline.

## imgstovideo.py
from tempfile import mkdtemp
import shutil
import os
import sys
import subprocess

from skimage.io import imsave

cmd_tpl = 'ffmpeg -y -framerate {framerate} -i {pattern} -c:v libx264 -r {rate} -pix_fmt yuv420p {out}'

## parametric_tsne.py
# Code adapted from https://github.com/kylemcdonald/Parametric-t-SNE
import numpy as np
import theano.tensor as T

def Hbeta(D, beta):
    P = np.exp(-D * beta)
    sumP = np.sum(P)
    H = np.log(sumP) + beta * np.sum(np.multiply(D, P)) / sumP
    P = P / sumP
    return H, P

## ranking.py
"""
Implementation of pairwise ranking using scikit-learn LinearSVC

Reference: "Large Margin Rank Boundaries for Ordinal Regression", R. Herbrich,
    T. Graepel, K. Obermayer.

Authors: Fabian Pedregosa <fabian@fseoane.net>
         Alexandre Gramfort <alexandre.gramfort@inria.fr>
"""
	import numpy as np
	import matplotlib as mpl
	mpl.use('Agg')
	import matplotlib.pyplot as plt
	from pyearth import Earth
	import time
	from itertools import product

	np.random.seed(2)
	import numpy as np
	import os
	import matplotlib as mpl
	mpl.use('Agg')
	import matplotlib.pyplot as plt
	from pyearth import Earth
	import time

	np.random.seed(2)
	import numpy
	from scipy.ndimage.interpolation import map_coordinates
	from scipy.ndimage.filters import gaussian_filter

	def elastic_transform(image, alpha, sigma, random_state=None):
	"""Elastic deformation of images as described in [Simard2003]_.


	.. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
	Convolutional Neural Networks applied to Visual Document Analysis", in
	import numpy as np
	import time

	from joblib import Memory

	import pandas as pd

	from bokeh.charts import show, Bar
	from bokeh.io import output_file, vplot
	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)
	from sklearn.ensemble import RandomForestRegressor
	from sklearn.base import clone
	import numpy as np

	class GAM(object):
	"""
	Simple generalized additive model which fits each feature w.r.t
	the output independently using a model specified by
	base_estimator. the final predictions can be done by regressing linearly
	the predictions of the model of each features by using a pipeline.
	from tempfile import mkdtemp
	import shutil
	import os
	import sys
	import subprocess

	from skimage.io import imsave

	cmd_tpl = 'ffmpeg -y -framerate {framerate} -i {pattern} -c:v libx264 -r {rate} -pix_fmt yuv420p {out}'
	# Code adapted from https://github.com/kylemcdonald/Parametric-t-SNE
	import numpy as np
	import theano.tensor as T

	def Hbeta(D, beta):
	P = np.exp(-D * beta)
	sumP = np.sum(P)
	H = np.log(sumP) + beta * np.sum(np.multiply(D, P)) / sumP
	P = P / sumP
	return H, P
	"""
	Implementation of pairwise ranking using scikit-learn LinearSVC

	Reference: "Large Margin Rank Boundaries for Ordinal Regression", R. Herbrich,
	T. Graepel, K. Obermayer.

	Authors: Fabian Pedregosa <fabian@fseoane.net>
	Alexandre Gramfort <alexandre.gramfort@inria.fr>
	"""