Skip to content

Instantly share code, notes, and snippets.

Avatar
🎯
makin' the codes.

Tony Poerio adpoe

🎯
makin' the codes.
  • Pittsburgh
View GitHub Profile
@adpoe
adpoe / treeTraversals.hs
Created Jun 16, 2016
Haskell Binary Tree Traversals
View treeTraversals.hs
-- Do Tree Traversals and Built a Visitation List for each
preorder :: BinaryTree a -> [a]
preorder Leaf = []
preorder (Node left root right) = root : preorder left ++ preorder right
-- NOTE: Need to use the ++ so each list gets built separately and then concatenated
-- after it hits bottom
inorder :: BinaryTree a -> [a]
inorder Leaf = []
@adpoe
adpoe / svm_and_sift.ipynb
Last active Dec 24, 2016
SVM and SIFT Nature Conservatory Kaggle Entry
View svm_and_sift.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@adpoe
adpoe / keras_for_nature_conservatory_kaggle.ipynb
Last active Dec 24, 2016
A Quick Start Guide for Using Keras in the Nature Conservatory Kaggle
View keras_for_nature_conservatory_kaggle.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@adpoe
adpoe / mv_grad_desc.py
Created Dec 16, 2016
Multivariate Gradient Descent in Python
View mv_grad_desc.py
def multivariate_gradient_descent(training_examples, alpha=0.01):
"""
Apply gradient descent on the training examples to learn a line that fits through the examples
:param examples: set of all examples in (x,y) format
:param alpha = learning rate
:return:
"""
# initialize the weight and x_vectors
W = [0 for index in range(0, len(training_examples[0][0]))]
@adpoe
adpoe / uni_gd.py
Created Dec 16, 2016
Univariate Gradient Descent, in Python
View uni_gd.py
def gradient_descent(training_examples, alpha=0.01):
"""
Apply gradient descent on the training examples to learn a line that fits through the examples
:param examples: set of all examples in (x,y) format
:param alpha = learning rate
:return:
"""
# initialize w0 and w1 to some small value, here just using 0 for simplicity
w0 = 0
w1 = 0
@adpoe
adpoe / flappy_states.py
Created Dec 15, 2016
State Representations for a Flappy Bird AI
View flappy_states.py
# first value in state tuple
height_category = 0
dist_to_pipe_bottom = pipe_bottom - bird.y
if dist_to_pipe_bottom < 8: # very close
height_category = 0
elif dist_to_pipe_bottom < 20: # close
height_category = 1
elif dist_to_pipe_bottom < 125: #mid
height_category = 2
elif dist_to_pipe_bottom < 250: # far
@adpoe
adpoe / energy.m
Created Sep 27, 2016
Energy Function - Matlab
View energy.m
function [ energy_matrix ] = energy_image( image_matrix_input )
%ENERGY_IMAGE Computes the energy at each pixel in a matrix nxmx3 matrix
% Outputs a 2D-matrix containing energy equation outputs, of datatype DBL
% convert image to grayscale first
G = rgb2gray(image_matrix_input);
% convert to double
G2 = im2double(G);
@adpoe
adpoe / binaryTree.hs
Created Jun 16, 2016
Binary Tree in Haskell
View binaryTree.hs
data BinaryTree a =
Leaf
| Node (BinaryTree a) a (BinaryTree a)
deriving (Eq, Ord, Show)
@adpoe
adpoe / quicksort.hs
Created Jun 16, 2016
Very simple Quicksort Implementation from "Learn You a Haskell For Great Good!"
View quicksort.hs
quicksort :: (Ord a) => [a] -> [a]
quicksort [] = []
quicksort (x:xs) =
let smallerSorted = quicksort [a | a <- xs, a <= x]
biggerSorted = quicksort [a | a <- xs, a > x]
in smallerSorted ++ [x] ++ biggerSorted
@adpoe
adpoe / std_normal.py
Created Mar 25, 2016
standard normal random variates
View std_normal.py
# PROCEDURE, From ROSS: Simulation (5th Edition) Page 78
# Step 1: Generate Y1, an exponential random variable with rate 1
Y1 = gen_exponential_distro_rand_variable()
# Step 2: Generate Y2, an exponential random variable with rate 2
Y2 = gen_exponential_distro_rand_variable()
# Step 3: If Y2 - (Y1 - 1)^2/2 > 0, set Y = Y2 - (Y1 - 1)^2/2, and go to Step 4 (accept)
#         Otherwise, go to Step 1 (reject)
subtraction_value = ( math.pow( ( Y1 - 1 ), 2 ) ) / 2
critical_value = Y2 - subtraction_value
if critical_value > 0: