Additional Exploratory Analysis - Albert

In [1]:

    

import os
PATH="/Users/albertlee/claritycontrol/code/scripts" # use your own path
os.chdir(PATH)


import clarity as cl  # I wrote this module for easier operations on data

import matplotlib.pyplot as plt
import jgraph as ig

import clarity.resources as rs
import csv,gc  # garbage memory collection :)

import matplotlib
#import matplotlib.pyplot as plt
import numpy as np

from skimage import data, img_as_float
from skimage import exposure

from numpy import genfromtxt

BINS=32 # histogram bins
RANGE=(10.0,300.0)

matplotlib.rcParams['font.size'] = 8

my_data = genfromtxt('../data/hist/Fear199.csv', delimiter=',')
print my_data


    

    




/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.
  warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')






    




[  4.90000000e+01   5.80000000e+01   1.35000000e+02   2.99000000e+02
   7.36000000e+02   2.50000000e+03   7.66600000e+03   4.64490000e+04
   1.51772000e+06   1.16437106e+08   1.97147778e+08   5.00216770e+07
   3.75322990e+07   2.74382340e+07   1.78604610e+07   1.09035570e+07
   7.49919200e+06   4.36949700e+06   3.13623000e+06   2.34876700e+06
   1.79951900e+06   1.42698700e+06   1.15425800e+06   9.54144000e+05
   8.01040000e+05   6.74604000e+05   5.75535000e+05   4.91377000e+05
   4.22580000e+05   3.63628000e+05   3.17308000e+05   3.02971000e+05]

In [7]:

    

for token in rs.TOKENS:
    c = cl.Clarity(token)
    fname = rs.HIST_DATA_PATH+"4bin"+token+".csv"
    hist, bin_edges = c.loadImg().getHistogram(bins=BINS,range=RANGE,density=False)
    np.savetxt(fname,hist,delimiter=',')
    print fname,"saved."
    del c
    my_data = genfromtxt(fname, delimiter=',')
    print my_data
    gc.collect()


    

    




Image Loaded: ../data/raw/Cocaine174.img
../data/hist/4binCocaine174.csv saved.
Image Loaded: ../data/raw/Cocaine175.img
../data/hist/4binCocaine175.csv saved.
Image Loaded: ../data/raw/Cocaine178.img
../data/hist/4binCocaine178.csv saved.
Image Loaded: ../data/raw/Control181.img
../data/hist/4binControl181.csv saved.
Image Loaded: ../data/raw/Control182.img
../data/hist/4binControl182.csv saved.
Image Loaded: ../data/raw/Control189.img
../data/hist/4binControl189.csv saved.
Image Loaded: ../data/raw/Control239.img
../data/hist/4binControl239.csv saved.
Image Loaded: ../data/raw/Control258.img
../data/hist/4binControl258.csv saved.
Image Loaded: ../data/raw/Fear187.img
../data/hist/4binFear187.csv saved.
Image Loaded: ../data/raw/Fear197.img
../data/hist/4binFear197.csv saved.
Image Loaded: ../data/raw/Fear199.img
../data/hist/4binFear199.csv saved.
Image Loaded: ../data/raw/Fear200.img
../data/hist/4binFear200.csv saved.
[  2.53130000e+04   1.96457382e+08   4.00785140e+07   9.07274100e+06]

In [8]:

    

import numpy as np
import clarity.resources as rs
features = np.empty(shape=(1,BINS))
for token in rs.TOKENS:
    fname = rs.HIST_DATA_PATH+"4bin"+token+".csv"
    data = np.loadtxt(fname,delimiter=',')
    features = np.vstack([features,data])
features = features[1:,]
minc = np.min(features)
maxc = np.max(features)
features = (features-minc)/(maxc-minc)
print features
np.savetxt(rs.HIST_DATA_PATH+"4binfeatures.csv",features,delimiter=',')


    

    




[[  5.90824742e-05   1.00000000e+00   1.22120148e-01   3.20605118e-02]
 [  4.02513940e-05   7.51001373e-01   7.80913612e-02   1.58931904e-02]
 [  5.33573911e-05   6.79104808e-01   1.37626229e-01   3.64573693e-02]
 [  2.78582353e-05   4.21585477e-01   9.71577021e-02   3.32082903e-02]
 [  5.92327137e-06   4.24638954e-01   8.67806085e-02   1.53308807e-02]
 [  5.73946775e-05   6.93202617e-01   4.52744512e-02   9.53192775e-03]
 [  6.05608946e-05   7.68823440e-01   8.30486167e-02   1.90907356e-02]
 [  7.38027465e-05   7.55535379e-01   1.10174701e-01   2.62104007e-02]
 [  4.78017270e-05   6.07689571e-01   8.28482612e-02   2.16572894e-02]
 [  3.81464430e-05   6.13776330e-01   1.01223540e-01   2.66232891e-02]
 [  5.20707658e-05   7.33350093e-01   3.62225482e-02   6.27126756e-03]
 [  0.00000000e+00   3.13955869e-01   6.40167239e-02   1.44604348e-02]]

In [9]:

    

from sklearn import cross_validation
from sklearn.cross_validation import LeaveOneOut
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis

%matplotlib inline

np.random.seed(12345678)  # for reproducibility, set random seed

# Cocaine = ["Cocaine174","Cocaine175","Cocaine178"]
# Control = ["Control181","Control182","Control189","Control239","Control258"]
# Fear = ["Fear187","Fear197","Fear199","Fear200"]

features = np.loadtxt(rs.HIST_DATA_PATH+"4binfeatures.csv",delimiter=',')
temp_mu = np.mean(features,axis=1)
temp_std = np.std(features,axis=1)

mu = [np.mean(temp_mu[0:3]),np.mean(temp_mu[3:8]),np.mean(temp_mu[8:12])]
std = [np.mean(temp_std[0:3]),np.mean(temp_std[3:8]),np.mean(temp_std[8:12])]
print mu
print std
std=[1,1,1]

# define number of subjects per class
S = np.array((9, 21, 30, 39, 45, 63, 81, 96, 108, 210, 333))

names = ["Nearest Neighbors", "Linear SVM", "Random Forest",
         "Linear Discriminant Analysis", "Quadratic Discriminant Analysis"]

classifiers = [
    KNeighborsClassifier(3),
    SVC(kernel="linear", C=0.5),
    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
    LinearDiscriminantAnalysis()]


    

    




[0.23770897349869147, 0.17949098607239755, 0.16388957730669243]
[0.33325814318994945, 0.25244003850017155, 0.2346371954529729]

In [10]:

    

accuracy = np.zeros((len(S), len(classifiers), 2), dtype=np.dtype('float64'))
for idx1, s in enumerate(S):
    s0=s/3
    s1=s/3
    s2=s/3
    
    x0 = np.random.normal(mu[0],std[0],(s0,BINS))
    x1 = np.random.normal(mu[1],std[1],(s1,BINS))
    x2 = np.random.normal(mu[2],std[2],(s2,BINS))
    X = x0
    X = np.vstack([X,x1])
    X = np.vstack([X,x2])
    y = np.append(np.append(np.zeros(s0), np.ones(s1)),np.ones(s2)*2)
    for idx2, cla in enumerate(classifiers):
        X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.4, random_state=0)
        clf = cla.fit(X_train, y_train)
        loo = LeaveOneOut(len(X))
        scores = cross_validation.cross_val_score(clf, X, y, cv=loo)
        accuracy[idx1, idx2,] = [scores.mean(), scores.std()]
        print("Accuracy of %s: %0.2f (+/- %0.2f)" % (names[idx2], scores.mean(), scores.std() * 2))
    
print accuracy


    

    




Accuracy of Nearest Neighbors: 0.22 (+/- 0.83)
Accuracy of Linear SVM: 0.11 (+/- 0.63)
Accuracy of Random Forest: 0.22 (+/- 0.83)
Accuracy of Linear Discriminant Analysis: 0.33 (+/- 0.94)
Accuracy of Nearest Neighbors: 0.33 (+/- 0.94)
Accuracy of Linear SVM: 0.24 (+/- 0.85)






    




/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/discriminant_analysis.py:387: UserWarning: Variables are collinear.
  warnings.warn("Variables are collinear.")






    




Accuracy of Random Forest: 0.29 (+/- 0.90)
Accuracy of Linear Discriminant Analysis: 0.33 (+/- 0.94)
Accuracy of Nearest Neighbors: 0.20 (+/- 0.80)
Accuracy of Linear SVM: 0.23 (+/- 0.85)






    




/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/discriminant_analysis.py:453: UserWarning: The priors do not sum to 1. Renormalizing
  UserWarning)






    




Accuracy of Random Forest: 0.30 (+/- 0.92)
Accuracy of Linear Discriminant Analysis: 0.33 (+/- 0.94)
Accuracy of Nearest Neighbors: 0.33 (+/- 0.94)
Accuracy of Linear SVM: 0.10 (+/- 0.61)
Accuracy of Random Forest: 0.26 (+/- 0.87)
Accuracy of Linear Discriminant Analysis: 0.13 (+/- 0.67)
Accuracy of Nearest Neighbors: 0.31 (+/- 0.93)
Accuracy of Linear SVM: 0.04 (+/- 0.41)
Accuracy of Random Forest: 0.31 (+/- 0.93)
Accuracy of Linear Discriminant Analysis: 0.16 (+/- 0.72)
Accuracy of Nearest Neighbors: 0.40 (+/- 0.98)
Accuracy of Linear SVM: 0.57 (+/- 0.99)
Accuracy of Random Forest: 0.40 (+/- 0.98)
Accuracy of Linear Discriminant Analysis: 0.49 (+/- 1.00)
Accuracy of Nearest Neighbors: 0.40 (+/- 0.98)
Accuracy of Linear SVM: 0.28 (+/- 0.90)
Accuracy of Random Forest: 0.23 (+/- 0.85)
Accuracy of Linear Discriminant Analysis: 0.28 (+/- 0.90)
Accuracy of Nearest Neighbors: 0.30 (+/- 0.92)
Accuracy of Linear SVM: 0.29 (+/- 0.91)
Accuracy of Random Forest: 0.29 (+/- 0.91)
Accuracy of Linear Discriminant Analysis: 0.25 (+/- 0.87)
Accuracy of Nearest Neighbors: 0.32 (+/- 0.94)
Accuracy of Linear SVM: 0.46 (+/- 1.00)
Accuracy of Random Forest: 0.31 (+/- 0.92)
Accuracy of Linear Discriminant Analysis: 0.44 (+/- 0.99)
Accuracy of Nearest Neighbors: 0.32 (+/- 0.94)
Accuracy of Linear SVM: 0.37 (+/- 0.96)
Accuracy of Random Forest: 0.35 (+/- 0.96)
Accuracy of Linear Discriminant Analysis: 0.37 (+/- 0.97)
Accuracy of Nearest Neighbors: 0.36 (+/- 0.96)
Accuracy of Linear SVM: 0.40 (+/- 0.98)
Accuracy of Random Forest: 0.30 (+/- 0.92)
Accuracy of Linear Discriminant Analysis: 0.38 (+/- 0.97)
[[[ 0.22222222  0.41573971]
  [ 0.11111111  0.31426968]
  [ 0.22222222  0.41573971]
  [ 0.33333333  0.47140452]]

 [[ 0.33333333  0.47140452]
  [ 0.23809524  0.42591771]
  [ 0.28571429  0.45175395]
  [ 0.33333333  0.47140452]]

 [[ 0.2         0.4       ]
  [ 0.23333333  0.42295258]
  [ 0.3         0.45825757]
  [ 0.33333333  0.47140452]]

 [[ 0.33333333  0.47140452]
  [ 0.1025641   0.30338871]
  [ 0.25641026  0.43665093]
  [ 0.12820513  0.33431807]]

 [[ 0.31111111  0.46294815]
  [ 0.04444444  0.20608041]
  [ 0.31111111  0.46294815]
  [ 0.15555556  0.36243348]]

 [[ 0.3968254   0.48923921]
  [ 0.57142857  0.49487166]
  [ 0.3968254   0.48923921]
  [ 0.49206349  0.49993701]]

 [[ 0.39506173  0.48886395]
  [ 0.28395062  0.45091314]
  [ 0.2345679   0.42372845]
  [ 0.28395062  0.45091314]]

 [[ 0.30208333  0.45916118]
  [ 0.29166667  0.45452967]
  [ 0.29166667  0.45452967]
  [ 0.25        0.4330127 ]]

 [[ 0.32407407  0.46802785]
  [ 0.46296296  0.49862637]
  [ 0.30555556  0.46064233]
  [ 0.43518519  0.49578124]]

 [[ 0.32380952  0.46792832]
  [ 0.36666667  0.48189441]
  [ 0.35238095  0.47771186]
  [ 0.37142857  0.4831867 ]]

 [[ 0.36036036  0.48010496]
  [ 0.3993994   0.48977497]
  [ 0.3033033   0.45968512]
  [ 0.38438438  0.48644941]]]

In [11]:

    

plt.errorbar(S, accuracy[:,0,0], yerr = accuracy[:,0,1], hold=True, label=names[0])
plt.errorbar(S, accuracy[:,1,0], yerr = accuracy[:,1,1], color='green', hold=True, label=names[1])
plt.errorbar(S, accuracy[:,2,0], yerr = accuracy[:,2,1], color='red', hold=True, label=names[2])
plt.errorbar(S, accuracy[:,3,0], yerr = accuracy[:,3,1], color='black', hold=True, label=names[3])
# plt.errorbar(S, accuracy[:,4,0], yerr = accuracy[:,4,1], color='brown', hold=True, label=names[4])
plt.xscale('log')
plt.xlabel('number of samples')
plt.ylabel('accuracy')
plt.title('Accuracy of classification under simulated data')
plt.axhline(1, color='red', linestyle='--')
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plt.show()


    

In [12]:

    

y=np.array([0,0,0,1,1,1,1,1,2,2,2,2])
features = np.loadtxt(rs.HIST_DATA_PATH+"4binfeatures.csv",delimiter=',')


    

In [13]:

    

accuracy=np.zeros((len(classifiers),2))
for idx, cla in enumerate(classifiers):
    X_train, X_test, y_train, y_test = cross_validation.train_test_split(features, y, test_size=0.4, random_state=0)
    clf = cla.fit(X_train, y_train)
    loo = LeaveOneOut(len(features))
    scores = cross_validation.cross_val_score(clf, features, y, cv=loo)
    accuracy[idx,] = [scores.mean(), scores.std()]
    print("Accuracy of %s: %0.2f (+/- %0.2f)" % (names[idx], scores.mean(), scores.std() * 2))


    

    




Accuracy of Nearest Neighbors: 0.00 (+/- 0.00)
Accuracy of Linear SVM: 0.25 (+/- 0.87)
Accuracy of Random Forest: 0.33 (+/- 0.94)
Accuracy of Linear Discriminant Analysis: 0.25 (+/- 0.87)

In [ ]:

    

for token in rs.TOKENS:
    c = cl.Clarity(token)
    fname = rs.HIST_DATA_PATH+"1bin"+token+".csv"
    hist, bin_edges = c.loadImg().getHistogram(bins=BINS,range=RANGE,density=False)
    np.savetxt(fname,hist,delimiter=',')
    print fname,"saved."
    del c
    my_data = genfromtxt(fname, delimiter=',')
    print my_data
    gc.collect()


    

    




Image Loaded: ../data/raw/Cocaine174.img

In [ ]: