In [1]:
%matplotlib inline
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [2]:
df = pd.read_excel('data_july.xlsx','core1+FAC+MRI.m6')
In [3]:
df = df.dropna()
In [4]:
df.shape
Out[4]:
In [5]:
predictor_keys = [u'Alpha1MicroglobulinA1Microugml.bl', u'Alpha2MacroglobulinA2MacromgmL.bl', u'Alpha1AntichymotrypsinAACTugml.bl', u'Alpha1AntitrypsinAATmgmL.bl', u'AngiotensinConvertingEnzymeACEngml.bl', u'AdiponectinugmL.bl', u'AlphaFetoproteinAFPngmL.bl', u'AgoutiRelatedProteinAGRPpgmL.bl', u'Angiopoietin2ANG2ngmL.bl', u'AngiotensinogenngmL.bl', u'ApolipoproteinAIApoAImgmL.bl', u'ApolipoproteinAIIApoAIIngml.bl', u'ApolipoproteinAIVApoAIVugml.bl', u'ApolipoproteinBApoBugml.bl', u'ApolipoproteinCIApoCIngml.bl', u'ApolipoproteinCIIIApoCIIIugmL.bl', u'ApolipoproteinDApoDugml.bl', u'ApolipoproteinEApoEugml.bl', u'ApolipoproteinHApoHugmL.bl', u'AXLReceptorTyrosineKinaseAXLngmL.bl', u'Beta2MicroglobulinB2MugmL.bl', u'BrainDerivedNeurotrophicFactorBDNFngmL.bl', u'BLymphocyteChemoattractantBLCpgml.bl', u'BoneMorphogeneticProtein6BMP6ngmL.bl', u'BrainNatriureticPeptideBNPpgml.bl', u'BetacellulinBTCpgmL.bl', u'ComplementC3C3mgmL.bl', u'CancerAntigen199CA199UmL.bl', u'CalcitoninpgmL.bl', u'CD40antigenCD40ngmL.bl', u'CD40LigandCD40LngmL.bl', u'CD5CD5Lngml.bl', u'CarcinoembryonicAntigenCEAngmL.bl', u'ChromograninACgAngmL.bl', u'CreatineKinaseMBCKMBngmL.bl', u'ClusterinCLUugml.bl', u'CiliaryNeurotrophicFactorCNTFpgmL.bl', u'ComplementFactorHugml.bl', u'CortisolCortisolngml.bl', u'Cpeptidengml.bl', u'CReactiveProteinCRPugmL.bl', u'CystatinCngml.bl', u'EpidermalGrowthFactorEGFpgmL.bl', u'EpidermalGrowthFactorReceptorEGFRngmL.bl', u'EpithelialDerivedNeutrophilActivatingngmL.bl', u'Eotaxin1pgmL.bl', u'Eotaxin3pgmL.bl', u'ESelectinngmL.bl', u'FattyAcidBindingProteinheartFABPngmL.bl', u'FactorVIIngmL.bl', u'FASLGReceptorFASngmL.bl', u'FasLigandFasLpgmL.bl', u'FetuinAugml.bl', u'FibroblastGrowthFactor4FGF4pgmL.bl', u'FibrinogenmgmL.bl', u'FerritinFRTNngmL.bl', u'FollicleStimulatingHormoneFSHmIUmL.bl', u'GrowthHormoneGHngmL.bl', u'GrowthRegulatedalphaproteinGROalphpgmL.bl', u'GlutathioneSTransferasealphaGSTalpngml.bl', u'HaptoglobinmgmL.bl', u'HeparinBindingEGFLikeGrowthFactorpgmL.bl', u'ChemokineCC4HCC4ngmL.bl', u'HepatocyteGrowthFactorHGFngmL.bl', u'TLymphocyteSecretedProteinI309I3pgmL.bl', u'IntercellularAdhesionMolecule1ICAMngmL.bl', u'ImmunoglobulinAIgAmgmL.bl', u'ImmunoglobulinEIgEngmL.bl', u'InsulinlikeGrowthFactorBindingProtengmL.bl', u'ImmunoglobulinMIGMmgmL.bl', u'Interleukin13IL13pgmL.bl', u'Interleukin16IL16pgmL.bl', u'Interleukin18IL18pgmL.bl', u'Interleukin3IL3ngmL.bl', u'Interleukin6receptorIL6rngmL.bl', u'Interleukin8IL8pgmL.bl', u'InsulinuIUmL.bl', u'InterferongammaInducedProtein10IPpgml.bl', u'KidneyInjuryMolecule1KIM1ngml.bl', u'LeptinngmL.bl', u'LuteinizingHormoneLHmIUmL.bl', u'ApolipoproteinaLpaugmL.bl', u'MonocyteChemotacticProtein1MCP1pgmL.bl', u'MonocyteChemotacticProtein2MCP2pgml.bl', u'MonocyteChemotacticProtein3MCP3pgmL.bl', u'MonocyteChemotacticProtein4MCP4pgml.bl', u'MacrophageColonyStimulatingFactor1ngmL.bl', u'MacrophageDerivedChemokineMDCpgmL.bl', u'MacrophageMigrationInhibitoryFactorngmL.bl', u'MonokineInducedbyGammaInterferonMIpgml.bl', u'MacrophageInflammatoryProtein1alphapgmL.bl', u'MacrophageInflammatoryProtein1betapgmL.bl', u'MacrophageInflammatoryProtein3alphapgml.bl', u'MatrixMetalloproteinase1MMP1ngml.bl', u'MatrixMetalloproteinase10MMP10ngml.bl', u'MatrixMetalloproteinase2MMP2ngmL.bl', u'MatrixMetalloproteinase7MMP7ngml.bl', u'MatrixMetalloproteinase9MMP9ngmL.bl', u'MatrixMetalloproteinase9totalMMP9ngml.bl', u'MyeloidProgenitorInhibitoryFactor1ngmL.bl', u'MyeloperoxidaseMPOngmL.bl', u'MyoglobinngmL.bl', u'NeutrophilGelatinaseAssociatedLipocalngml.bl', u'NeuronalCellAdhesionMoleculeNrCAMngmL.bl', u'Osteopontinngml.bl', u'PlasminogenActivatorInhibitor1PAI1ngmL.bl', u'ProstaticAcidPhosphatasePAPngmL.bl', u'PregnancyAssociatedPlasmaProteinAPmIUmL.bl', u'PulmonaryandActivationRegulatedChemongmL.bl', u'PlateletDerivedGrowthFactorBBPDGFpgml.bl', u'PlacentaGrowthFactorPLGFpgml.bl', u'PancreaticPolypeptidePPPpgml.bl', u'ProlactinPRLngml.bl', u'ProinsulinIntactpM.bl', u'ProinsulinTotalpM.bl', u'PeptideYYPYYpgmL.bl', u'ReceptorforadvancedglycosylationendngmL.bl', u'TCellSpecificProteinRANTESRANTESngmL.bl', u'Resistinngml.bl', u'SerumAmyloidPComponentSAPugmL.bl', u'StemCellFactorSCFpgmL.bl', u'SerumGlutamicOxaloaceticTransaminaseugmL.bl', u'SexHormoneBindingGlobulinSHBGnmolL.bl', u'SuperoxideDismutase1SolubleSOD1ngmL.bl', u'SortilinngmL.bl', u'ThyroxineBindingGlobulinTBGugmL.bl', u'ThymusExpressedChemokineTECKngmL.bl', u'TestosteroneTotalngml.bl', u'TrefoilFactor3TFF3ugml.bl', u'TammHorsfallUrinaryGlycoproteinTHPugml.bl', u'Thrombospondin1ngmL.bl', u'TissueInhibitorofMetalloproteinases1ngmL.bl', u'ThrombomodulinTMngml.bl', u'TenascinCTNCngmL.bl', u'TumorNecrosisFactoralphaTNFalphapgmL.bl', u'TumorNecrosisFactorReceptorLike2TngmL.bl', u'ThrombopoietinngmL.bl', u'TNFRelatedApoptosisInducingLigandRengmL.bl', u'SerotransferrinTransferrinmgdl.bl', u'ThyroidStimulatingHormoneTSHuIUmL.bl', u'TransthyretinTTRmgdl.bl', u'VascularCellAdhesionMolecule1VCAMngmL.bl', u'VascularEndothelialGrowthFactorVEGFpgmL.bl', u'Vitronectinugml.bl', u'VitaminKDependentProteinSVKDPSugml.bl', u'vonWillebrandFactorvWFugmL.bl', u'BMI', u'Gender_num', u'WHITMATHYP_450', u'ADNI_MEM450.bl', u'ADNI_EF450.bl', u'VSBPSYS', u'ApoE_gene_risk', u'age_123', u'New_IL6_ord_450', u'FAC1_10', u'FAC2_10', u'FAC3_10', u'FAC4_10', u'FAC5_10', u'L_Hip_pcntICV.bsc', u'R_Hip_pcntICV.bsc', u'L_amygdala_pcntICV.bsc', u'R_amygdala_pcntICV.bsc', u'L_InfLatVentr_pcntICV.bsc', u'R_InfLatVentr_pcntICV.bsc', u'L_Accumbens_pcntICV.bsc', u'R_Accumbens_pcntICV.bsc', u'L_CerebCtx_pcntICV.bsc', u'R_CerebCtx_pcntICV.bsc', u'L_CerebCtx_WM_pcntICV.bsc', u'R_CerebCtx_WM_pcntICV.bsc', u'L_VentDorsCol_pcntICV.bsc', u'R_VentDorsCol_pcntICV.bsc', u'L_LatVentr_pcntICV.bsc', u'R_LatVentr_pcntICV.bsc', u'L_SupParietal_pcntICV.bsc', u'R_SupParietal_pcntICV.bsc', u'L_Hip_pcntICV.m06', u'R_Hip_pcntICV.m06', u'L_amygdala_pcntICV.m06', u'R_amygdala_pcntICV.m06', u'L_InfLatVentr_pcntICV.m06', u'R_InfLatVentr_pcntICV.m06', u'L_Accumbens_pcntICV.m06', u'R_Accumbens_pcntICV.m06', u'L_CerebCtx_pcntICV.m06', u'R_CerebCtx_pcntICV.m06', u'L_CerebCtx_WM_pcntICV.m06', u'R_CerebCtx_WM_pcntICV.m06', u'L_VentDorsCol_pcntICV.m06', u'R_VentDorsCol_pcntICV.m06', u'L_LatVentr_pcntICV.m06', u'R_LatVentr_pcntICV.m06', u'L_SupParietal_pcntICV.m06', u'R_SupParietal_pcntICV.m06', u'FAC1_11', u'FAC2_11', u'FAC3_11', u'FAC4_11', u'FAC5_11', u'ST29SV_apc_L.Hip', u'ST88SV_apc_R.Hip', u'ST83TA_apc_R.ERC', u'ST52TA_apc_L.Prec', u'ST111TA_apc_R.Prec', u'ST50TA_apc_L.PostCing', u'ST109TA_apc_R.PostCing', u'ST37SV_apc_L.LatVent', u'ST96SV_apc_R.LatVent', u'ST20SV_apc_L.WM_Ctx', u'ST24TA_apc_L.ERC', u'ST19SV_apc_L.GM_Ctx', u'ST79SV_apc_R.WM_Ctx', u'ST78SV_apc_R.GM_Ctx', u'ST40TA_apc_L.MidTemp', u'ST99TA_apc_R.MidTemp', u'ST12SV_apc_L.Amyg', u'ST71SV_apc_R.Amyg', u'ST71SV_apc_R.Amyg.1', u'temp_comp_apc']
In [6]:
df['target_vs8'] = map(lambda x: 0 if x in [1,2,3,4,5,6,7] else 1 if x in [8] else np.nan, df['target'])
df['target_vs68'] = map(lambda x: 0 if x in [1,2,3,4,5] else 1 if x in [6, 8] else np.nan, df['target'])
df['target_vs468'] = map(lambda x: 0 if x in [1,2,3] else 1 if x in [4, 6, 8] else np.nan, df['target'])
In [7]:
from sklearn.cross_validation import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.cross_validation import StratifiedKFold, permutation_test_score
In [8]:
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.metrics import confusion_matrix, classification_report, roc_curve, auc
In [10]:
for target in ["target_vs8", "target_vs68", "target_vs468"]:
rf = RandomForestClassifier(bootstrap=True, class_weight=None, criterion='entropy',
max_depth=None, max_features='auto', max_leaf_nodes=None,
min_samples_leaf=2, min_samples_split=10, n_estimators=10, n_jobs=1,
oob_score=False,
warm_start=False)
ab = AdaBoostClassifier(algorithm='SAMME.R', base_estimator=None,
learning_rate=1.0, n_estimators=20)
relevant_frame = df[predictor_keys + [target]].dropna()
X, y = relevant_frame[predictor_keys], relevant_frame[target]
X_train, X_test, y_train, y_test = train_test_split(X, y)
for clf in [rf, ab]:
clf.fit(X_train, y_train)
predict_on_training = [score[1] for score in clf.predict_proba(X_train)]
fpr, tpr, thresholds = roc_curve(y_train, predict_on_training)
optfpr, opttpr, optimal = min(zip(fpr, tpr, thresholds), key=lambda a: abs(a[1] - (1 - a[0])))
y_score = [score[1] for score in clf.predict_proba(X_test)]
y_pred = [int(s>=optimal) for s in y_score]
# print ['{0:.2f}'.format(val) for val in y_score]
cm = confusion_matrix(y_test, y_pred)
# fpr, tpr, thresholds = roc_curve(y_test, y_score)
plt.figure()
plt.plot(fpr, tpr)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC {0} {1}'.format(str(clf)[:str(clf).find('(')], target))
plt.legend(loc="lower right")
plt.show()
fig, axes = plt.subplots(2,1, figsize=(10,4), sharex=True)
axes[0].scatter(predict_on_training, y_train, c='purple')
axes[1].scatter(y_score, y_test, c=y_pred, cmap='bwr')
axes[0].yaxis.set_ticks([0, 1])
axes[1].yaxis.set_ticks([0, 1])
axes[0].set_title('TRAINING SET PREDICTIONS VS VALIDATION SET PREDICTIONS')
axes[1].set_xlabel('Score')
axes[0].set_ylabel('True Label')
axes[1].set_ylabel('True Label')
axes[0].plot([optimal,optimal],[-1,2],'r--')
axes[1].plot([optimal,optimal],[-1,2],'r--')
fig.show()
print "Optimal Split At fpr:{0:.2f} tpr:{1:.2f} using thredhold: {2:.2f}".format(optfpr, opttpr, optimal)
plt.style.use('ggplot')
plt.matshow(cm, cmap=plt.get_cmap('YlGnBu'))
plt.colorbar()
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.show()
print classification_report(y_test, y_pred)
if hasattr(clf, 'feature_importances_'):
print 'TOP 10 FEATURES (IMPORTANCE):\n'
for k,i in sorted(zip(predictor_keys,clf.feature_importances_), key=lambda x: x[1], reverse=True)[:10]:
print "{1:40.3f} {0:40}".format(k,i)
print '\n'+'='*100
In [ ]:
In [ ]: