In [1]:

    

%pylab
%matplotlib inline


    

    




Using matplotlib backend: TkAgg
Populating the interactive namespace from numpy and matplotlib

In [2]:

    

cd ..


    

    




/afs/inf.ed.ac.uk/user/s11/s1145806/Documents/git/neukrill-net-work

In [3]:

    

import sys
import numpy as np
import skimage
import cv2
import sklearn
import imp


    

In [4]:

    

from holoviews import *


    

    




:0: FutureWarning: IPython widgets are experimental and may change in the future.

In [5]:

    

import neukrill_net.utils
import neukrill_net.highlevelfeatures


    

In [6]:

    

import time


    

In [7]:

    

settings = neukrill_net.utils.Settings('settings.json')


    

In [8]:

    

X,y = settings.flattened_train_paths(settings.classes)


    

In [9]:

    

hlf = neukrill_net.highlevelfeatures.ThresholdAdjacency()


    

In [10]:

    

t0 = time.time()
XF = hlf.transform(X)
print("Computing features took {}".format(time.time()-t0))


    

    




Computing features took 85.849462986

In [20]:

    

XF.shape


    

    
Out[20]:





(1, 30336, 54)

In [24]:

    

sklearn.externals.joblib.dump((hlf,XF,y),'cache/pftas.pkl')


    

    
Out[24]:





['cache/pftas.pkl', 'cache/pftas.pkl_01.npy']

In [11]:

    

import sklearn.naive_bayes


    

In [12]:

    

clf = sklearn.naive_bayes.GaussianNB()


    

In [13]:

    

t0 = time.time()
X_train, X_test, y_train, y_test = sklearn.cross_validation.train_test_split(
    sklearn.preprocessing.StandardScaler().fit_transform(XF.squeeze(0)), y, test_size=0.5, random_state=42)
clf.fit(X_train, y_train)

t1 = time.time()
total = t1-t0
print("Time={}".format(total))

print("Accuracy={}".format(clf.score(X_test, y_test)))
print("Logloss={}".format(sklearn.metrics.log_loss(y_test, clf.predict_proba(X_test))))


    

    




Time=0.0756931304932
Accuracy=0.191455696203
Logloss=14.5961701725

In [14]:

    

clf = sklearn.linear_model.LogisticRegression(random_state=42)


    

In [15]:

    

t0 = time.time()
X_train, X_test, y_train, y_test = sklearn.cross_validation.train_test_split(
    sklearn.preprocessing.StandardScaler().fit_transform(XF.squeeze(0)), y, test_size=0.5, random_state=42)
clf.fit(X_train, y_train)

t1 = time.time()
total = t1-t0
print("Time={}".format(total))

print("Accuracy={}".format(clf.score(X_test, y_test)))
print("Logloss={}".format(sklearn.metrics.log_loss(y_test, clf.predict_proba(X_test))))


    

    




Time=97.2654531002
Accuracy=0.32865242616
Logloss=2.76713927682

In [16]:

    

import sklearn.ensemble


    

In [17]:

    

clf = sklearn.ensemble.RandomForestClassifier(n_estimators=1000, max_depth=20, min_samples_leaf=5)

t0 = time.time()
X_train, X_test, y_train, y_test = sklearn.cross_validation.train_test_split(
    sklearn.preprocessing.StandardScaler().fit_transform(XF.squeeze(0)), y, test_size=0.5, random_state=42)
clf.fit(X_train, y_train)

t1 = time.time()
total = t1-t0
print("Time={}".format(total))

print("Accuracy={}".format(clf.score(X_test, y_test)))
print("Logloss={}".format(sklearn.metrics.log_loss(y_test, clf.predict_proba(X_test))))


    

    




Time=310.334695101
Accuracy=0.404535864979
Logloss=2.40882472837

In [18]:

    

clf = sklearn.svm.SVC(kernel='linear', probability=True, random_state=42)

t0 = time.time()
X_train, X_test, y_train, y_test = sklearn.cross_validation.train_test_split(
    sklearn.preprocessing.StandardScaler().fit_transform(XF.squeeze(0)), y, test_size=0.5, random_state=42)
clf.fit(X_train, y_train)

t1 = time.time()
total = t1-t0
print("Time={}".format(total))

print("Accuracy={}".format(clf.score(X_test, y_test)))
print("Logloss={}".format(sklearn.metrics.log_loss(y_test, clf.predict_proba(X_test))))


    

    




Time=106.997659206
Accuracy=0.380472046414
Logloss=2.49029657269

In [19]:

    

clf = sklearn.svm.SVC(probability=True, random_state=42)

t0 = time.time()
X_train, X_test, y_train, y_test = sklearn.cross_validation.train_test_split(
    sklearn.preprocessing.StandardScaler().fit_transform(XF.squeeze(0)), y, test_size=0.5, random_state=42)
clf.fit(X_train, y_train)

t1 = time.time()
total = t1-t0
print("Time={}".format(total))

print("Accuracy={}".format(clf.score(X_test, y_test)))
print("Logloss={}".format(sklearn.metrics.log_loss(y_test, clf.predict_proba(X_test))))


    

    




Time=113.672945023
Accuracy=0.382977320675
Logloss=2.36932021533