walterreade

Walter Reade Publications

Peer Reviewed

• Patton, P. T., et al., (2023). A deep learning approach to photo–identification demonstrates high performance on two dozen cetacean species. Methods in Ecology and Evolution, 00, 1– 15. [Open Access]
• Wayment-Steele, H.K., Kladwang, W., Watkins, A.M. et al. "Deep learning models for predicting RNA degradation via dual crowdsourcing" Nat Mach Intell 4, 1174–1184 (2022). [Abstract] [pre-print]
• Cheeseman, T., Southerland, K., Park, J. et al., "Advanced image recognition: a fully automated, high-accuracy photo-identification matching system for humpback whales", Mammalian Biology (2021) [Abstract]
• Bratholm, L.A, et al., "A community-powered search of machine learning strategy space to find NMR property prediction models," PLOS ONE, July 20, 2021,

walterreade

### for brand-new only
  sudo apt-get update
  sudo apt-get install htop
  sudo apt-get install build-essential

  wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
  bash Miniconda3-latest-Linux-x86_64.sh 
  rm Miniconda3-latest-Linux-x86_64.sh

walterreade

# http://www.dataiku.com/blog/2015/08/24/xgboost_and_dss.html

import dataiku
import pandas as pd, numpy as np
from dataiku import pandasutils as pdu
from sklearn.metrics import roc_auc_score
import xgboost as xgb
from hyperopt import hp, fmin, tpe, STATUS_OK, Trials 

train = dataiku.Dataset("train").get_dataframe()

walterreade

sudo apt-get install make
sudo apt-get update
sudo apt-get install gcc
sudo apt-get install g++
sudo apt-get install git
sudo git clone https://github.com/dmlc/xgboost
cd xgboost
./build.sh
cd python-package
python setup.py install

walterreade

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
import warnings
import numpy as np
import pandas as pd
import sys

__author__ = "Mohsen Mesgarpour"
__copyright__ = "Copyright 2016, https://github.com/mesgarpour"
__credits__ = ["Mohsen Mesgarpour"]

walterreade

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

walterreade

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.

It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data

In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/

walterreade

walterreade

# -*- coding: utf-8 -*-
"""
Regularized Tree Ensemble

@author: gert.jacobusse@rogatio.nl
@license: FreeBSD

Originally posted:
https://www.kaggle.com/c/bnp-paribas-cardif-claims-management/forums/t/20207/why-every-good-script-is-using-extratreeclassifier-one-way-or-the-other/115621

walterreade

def removeLink(content):
    urls = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', content)
    for i in range(0, len(urls)):
        content = content.replace(urls[i], '')
    return content