walterreade

thisField.setValue(0)

walterreade

import pandas as pd
pd.set_option('display.mpl_style', 'default')
pd.set_option('display.width', 200)
pd.set_option('display.max_columns', 20)
pd.set_option('display.max_rows', 50)
pd.set_option('precision', 5)


import matplotlib.pyplot as plt
import seaborn as sns

walterreade

fscore = [ (v,k) for k,v in clf.get_fscore().iteritems() ]
fscore.sort(reverse=True)

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

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()

scores = pd.read_csv('liberty-mutual-group-property-inspection-prediction_public_leaderboard.csv')

scores['SubmissionDate'] = [time.date() for time in scores['SubmissionDate'].astype('datetime64[ns]')]
scores['SubmissionDate'] = [time for time in scores['SubmissionDate'].astype(str)]

walterreade

plt.style.use('bmh')
colors = ['#348ABD', '#A60628', '#7A68A6', '#467821', '#D55E00', 
          '#CC79A7', '#56B4E9', '#009E73', '#F0E442', '#0072B2']



https://github.com/rasbt/matplotlib-gallery

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

# http://www.dataiku.com/blog/2015/08/24/xgboost_and_dss.html
from pandas.core.categorical import Categorical
from scipy.sparse import csr_matrix
import numpy as np

def sparse_dummies(categorical_values):
    categories = Categorical.from_array(categorical_values)
    N = len(categorical_values)
    row_numbers = np.arange(N, dtype=np.int)
    ones = np.ones((N,))

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

from scipy import exp, log
from scipy.special import gammaln

def prob_unique(N, r):
  """ If you have a set of N things to choose from, and take r samples, 
  the probability that all r samples are unique.
  http://www.johndcook.com/blog/2016/01/30/general-birthday-problem 
  """
    return exp( gammaln(N+1) - gammaln(N-r+1) - r*log(N) )