def best_ratio(yProba, yValidation, weightsValidation, pas = 0.01):
ratio_s = np.arange(0., 0.99, pas)
best_ams = 0.
for ratio in ratio_s:
yPredicted = get_yPredicted_ratio(yProba, ratio)
s, b = submission.get_s_b(yPredicted, yValidation, weightsValidation)
if b >= 0. and s >= 0.:
ams = hbc.AMS(s,b)
if ams >= best_ams:
best_ratio = ratio
best_ams = ams
else:
if b < 0.:
print ("WARNING: For a ratio of %f, b < 0 (b= %f).") %(ratio, b)
print ("This ratio has been ignored.")
else:
print ("WARNING: For a ratio of %f, s < 0 (s= %f).") %(ratio, s)
print ("This ratio has been ignored.")
ams = hbc.AMS(s,b)
if ams >= best_ams:
best_ratio = ratio
best_ams = ams
return best_ams, best_ratio
def best_treshold(yProba, yValidation, weightsValidation, pas = 0.01):
"""
Returns the treshold that maximises the AMS for the vectors of proba given
yProba : vectors of the probabilities computed with a classifier
yValid : vectors of the true label of the data
yWeights : vectors of the weights
pas : size of the interval between two probabilities tested
The weights must be balanced !
"""
treshold_s = np.arange(0., 1.0, pas)
best_ams = 0.
for treshold in treshold_s:
yPredicted_prov = get_yPredicted_treshold(yProba, treshold)
# if we work with multi-class:
if len(yPredicted_prov.shape) == 2:
if yPredicted_prov.shape[1] == 5:
# Reduce multiclass to binary
yPredicted = np.ones(yPredicted_prov.shape[0])
yPredicted[yPredicted_prov[:,4] == 0] = 0
else:
print "Error: in best_treshold() the shape of the input isn't correct"
else:
yPredicted = yPredicted_prov
s, b = submission.get_s_b(yPredicted, yValidation, weightsValidation)
ams = hbc.AMS(s,b)
if ams >= best_ams:
best_treshold = treshold
best_ams = ams
return best_ams, best_treshold
def evaluate_AMS(final_prediction, valid_s):
# Get s and b for each group (s_s, b_s) and the final final_s and
# final_b:
if type(final_prediction[2]) == list:
y_predicted_s = list(zip(*final_prediction)[2])
final_s, final_b, s_s, b_s = submission.get_s_b(y_predicted_s, valid_s[2],
valid_s[3])
else:
y_predicted_s = final_prediction[2]
final_s, final_b = submission.get_s_b(y_predicted_s, valid_s[2],
valid_s[3])
# Balance the s and b
final_s *= 250000/25000
final_b *= 250000/25000
# AMS final:
AMS = hbc.AMS(final_s , final_b)
print ("Expected AMS score for the 'on-top' classifier : %f") %AMS
#AMS by group
if type(y_predicted_s) == list:
AMS_s = []
for i, (s,b) in enumerate(zip(s_s, b_s)):
s *= 250000/y_predicted_s[i].shape[0]
b *= 250000/y_predicted_s[i].shape[0]
score = hbc.AMS(s,b)
AMS_s.append(score)
print("Expected AMS score for the 'on-top' classifer: group %i : %f" \
%(i, score))
print(" ")
else:
AMS_s = AMS
return final_s, final_b, AMS, AMS_s
def best_ratio_combinaison(yProba_s, yValidation_s, weightsValidation_s, ratio_s):
"""
returns the best ratio combinaison with the ratios specified in ratio_s for each
group
ratio_s : List of the list of the ratios to test for each group
the size of each list should not exceed 4 for computationnal time issues
"""
best_ratio_comb = [0.,0.,0.,0.,0.,0.,0.,0.]
AMS_max = 0.
"""
ratio_1_s = [0.06, 0.08,0.10,0.12]
ratio_2_s = [0.15,0.16,0.17,0.18]
ratio_3_s = [0.36,0.38,0.40,0.42]
ratio_4_s = [0.16,0.18,0.2,0.22]
ratio_5_s = [0.007,0.008,0.009,0.01]
ratio_6_s = [0.003,0.004,0.005,0.006]
ratio_7_s = [0.003,0.004,0.005,0.006]
ratio_8_s = [0.007,0.008,0.009,0.01]
"""
g_combinaisons = itertools.product(ratio_s[0], ratio_s[1],
ratio_s[2], ratio_s[3],
ratio_s[4], ratio_s[5],
ratio_s[6], ratio_s[7])
# if we work with multi-class:
if len(yProba_s[0].shape) == 2:
if yProba_s[0].shape[1] == 5:
for i,subset in enumerate(yProba_s):
yProba_s[i] = preTreatment.multiclass2binary(subset)
compteur = 0
for combinaison in g_combinaisons:
#if compteur%10000==0:
# print "number of iterations : %i" %compteur
compteur +=1
L = list(combinaison)
yPredicted_s, yPredicted_conca = get_yPredicted_ratio_8(yProba_s, L)
finals, finalb, s_s, b_s = submission.get_s_b(yPredicted_s,
yValidation_s,
weightsValidation_s)
AMS = hbc.AMS(finals, finalb)
if AMS > AMS_max:
AMS_max = AMS
best_ratio_comb = L
return AMS_max, best_ratio_comb
def main():
###############
### IMPORT ####
###############
# Importation parameters:
split= True
normalize = True
noise_var = 0.
ratio_train = 0.9
# Import the training data:
print("Extracting the data sets...")
start = time.clock()
train_s, valid_s, test_s = tokenizer.extract_data(split= split, \
normalize= normalize, \
noise_variance= noise_var, \
ratio_train= ratio_train)
yValid_conca = preTreatment.concatenate_vectors(valid_s[2])
weights_conca = preTreatment.concatenate_vectors(valid_s[3])
stop = time.clock()
print ("Extraction time: %i s") %(stop-start)
print(" ")
print(" ")
# Create the elected vectors for each group (best AMS score)
best_yPredicted_s = [np.zeros(valid_s[2][i].shape[0]) for i in range(8)]
best_yProba_s = [np.zeros(valid_s[2][i].shape[0]) for i in range(8)]
best_AMS_s = [0. for i in range(8)]
best_method_s = [0 for i in range(8)]
best_ratio_s = [0 for i in range(8)]
best_AMS_1_method = 0.
best_method = "methode"
best_ratio = "0."
######################
### PRE-TREATMENT ####
######################
print("------------------------- Pre-treatment --------------------------")
### Average number of signal per subset:
print("Train subsets signal average:")
train_s_average = preTreatment.ratio_sig_per_dataset(train_s[2])
print(" ")
print("Valid subsets signal average:")
valid_s_average = preTreatment.ratio_sig_per_dataset(valid_s[2])
print(" ")
print(" ")
############
# ANALYSES #
############
# Dictionnary that will contain all the data for each methods. In the end
# we'll have a dict of dict
# Keys of the methods : {naiveBayes, svm, kNeighbors, lda, qda, adaBoost,
# randomForest, gradientBoosting}
dMethods ={}
# NAIVE BAYES:
kwargs_bayes = {}
dMethods['naiveBayes'] = analyse.analyse(train_s, valid_s, 'naiveBayes',
kwargs_bayes)
kwargs_bayes = {}
dMethods['naiveBayes'] = analyse.analyse(train_s, valid_s, 'naiveBayes',
kwargs_bayes)
# SVM
kwargs_svm ={}
dMethods['svm'] = analyse.analyse(train_s, valid_s,'svm', kwargs_svm)
# K NEIGHBORS
kwargs_tuning_kn = {'n_neighbors': [20,50]}
dTuning = tuningModel.parameters_grid_search(train_s, valid_s, 'kNeighbors',
kwargs_tuning_kn)
dMethods['kNeighbors'] = combineClassifiers.select_best_classifiers(dTuning, valid_s)
# LDA
kwargs_lda = {}
dMethods['lda'] = analyse.analyse(train_s, valid_s, 'lda', kwargs_lda)
# QDA
kwargs_qda= {}
dMethods['qda'] = analyse.analyse(train_s, valid_s, 'qda', kwargs_qda)
# ADABOOST
kwargs_ada= { 'n_estimators': 50,
'learning_rate': 1.,
'algorithm': 'SAMME.R',
'random_state':None}
dMethods['adaBoost'] = analyse.analyse(train_s, valid_s, 'adaBoost',
kwargs_ada)
# RANDOM FOREST:
kwargs_tuning_rdf = {'n_estimators': [10,50,100]}
dTuning = tuningModel.parameters_grid_search(train_s, valid_s, 'randomForest',
kwargs_tuning_rdf)
dMethods['randomForest'] = combineClassifiers.select_best_classifiers(dTuning,
valid_s)
# GRADIENT BOOSTING
kwargs_gradB = {}
dMethods['gradientBoosting'] = analyse.analyse(train_s, valid_s, 'gradientBoosting', kwargs_gradB)
kwargs_tuning_gradB = {'loss': ['deviance'], 'learning_rate': [0.1],
'n_estimators': [100], 'subsample': [1.0],
'min_samples_split': [2], 'min_samples_leaf': [1],
'max_depth': [10], 'init': [None], 'random_state': [None],
'max_features': [None], 'verbose': [0]}
dTuning = tuningModel.parameters_grid_search(train_s, valid_s,
'gradientBoosting',
kwargs_tuning_gradB)
dMethods['gradientBoosting'] = combineClassifiers.select_best_classifiers(
dTuning,
valid_s)
print(" ")
##################
# POST-TREATMENT #
##################
print("-------------------- Best overall combination --------------------")
dCombine = combineClassifiers.select_best_classifiers(dMethods, valid_s)
print("-------------------------- Thresholding --------------------------")
# COMBINED CLASSIFIERS:
f = open("Tests/test_treshold_combined.txt","w")
yProba_s = dCombine['yProba_s']
yPredicted_s = dCombine['yPredicted_s']
#Let's concatenate the vectors
yProba_conca = preTreatment.concatenate_vectors(yProba_s)
yPredicted_conca = preTreatment.concatenate_vectors(yPredicted_s)
# Best treshold global
best_treshold = tresholding.best_treshold(yProba_conca, yValid_conca, weights_conca)
yPredicted_treshold = tresholding.get_yPredicted_treshold(yProba_conca, best_treshold)
s, b = submission.get_s_b(yPredicted_treshold, yValid_conca, weights_conca)
s *= 10
b *= 10
ams = hbc.AMS(s,b)
if ams > best_AMS_1_method:
best_AMS_1_method = ams
best_method = dCombine['method'][i]
best_ratio = best_treshold
# Best treshold group by group
for i in range(8):
best_treshold = tresholding.best_treshold(yProba_s[i], valid_s[2][i], valid_s[3][i])
yPredicted_s[i] = tresholding.get_yPredicted_treshold(yProba_s[i], best_treshold)
s, b = submission.get_s_b(yPredicted_s[i], valid_s[2][i], valid_s[3][i])
s *= 250000/yPredicted_s[i].shape[0]
b *= 250000/yPredicted_s[i].shape[0]
ams = hbc.AMS(s,b)
if ams > best_AMS_s[i]:
best_yPredicted_s[i] = yPredicted_s[i]
best_yProba_s[i] = yProba_s[i]
best_AMS_s[i] = ams
best_method_s[i] = dCombine['method'][i]
best_ratio_s[i] = best_treshold
# FOR EACH METHOD:
for method in dMethods:
yProba_s = dMethods[method]['yProba_s']
yPredicted_s = dMethods[method]['yPredicted_s']
#Let's concatenate the vectors
yProba_conca = preTreatment.concatenate_vectors(yProba_s)
yPredicted_conca = preTreatment.concatenate_vectors(yPredicted_s)
# Best treshold global
best_treshold = tresholding.best_treshold(yProba_conca, yValid_conca, weights_conca)
yPredicted_treshold = tresholding.get_yPredicted_treshold(yProba_conca, best_treshold)
s, b = submission.get_s_b(yPredicted_treshold, yValid_conca, weights_conca)
s *= 10
b *= 10
ams = hbc.AMS(s,b)
if ams > best_AMS_1_method:
best_AMS_1_method = ams
best_method = str(method)
best_ratio = best_treshold
# Best treshold group by group
for i in range(8):
best_treshold = tresholding.best_treshold(yProba_s[i], valid_s[2][i],
valid_s[3][i])
yPredicted_s[i] = tresholding.get_yPredicted_treshold(yProba_s[i],
best_treshold)
s, b = submission.get_s_b(yPredicted_s[i], valid_s[2][i],
valid_s[3][i])
s *= 250000/yPredicted_s[i].shape[0]
b *= 250000/yPredicted_s[i].shape[0]
ams = hbc.AMS(s,b)
if ams > best_AMS_s[i]:
best_yPredicted_s[i] = yPredicted_s[i]
best_yProba_s[i] = yProba_s[i]
best_AMS_s[i] = ams
best_method_s[i] = str(method)
best_ratio_s[i] = best_treshold
# Let's concatenate the 8 vectors which performs the best on each on
# each of the sub group and tresholding it
best_yPredicted_conca = preTreatment.concatenate_vectors(best_yPredicted_s)
best_treshold_conca = tresholding.best_treshold(best_yPredicted_conca, yValid_conca, weights_conca)
best_yPredicted_conca_treshold = tresholding.get_yPredicted_treshold(best_yPredicted_conca, best_treshold_conca)
best_final_s, best_final_b, best_s_s, best_b_s = submission.get_s_b_8(best_yPredicted_s, valid_s[2], valid_s[3])
best_s_treshold, best_b_treshold = submission.get_s_b(best_yPredicted_conca_treshold, yValid_conca, weights_conca)
best_final_s *= 10
best_final_b *= 10
best_s_treshold *= 10
best_b_treshold *= 10
best_AMS = hbc.AMS(best_final_s, best_final_b)
best_AMS_treshold = hbc.AMS(best_s_treshold, best_b_treshold)
print "Best AMS using one of the methods : %f" %best_AMS_1_method
print " method : %s" %(str(method))
print " ratio : %f" %(best_ratio)
print " "
print "Best AMS final : %f" %best_AMS
print "Best AMS final after final tresholding : %f" %best_AMS_treshold
print "best ratio on the concatenated vector : %f" %best_treshold_conca
print " "
for n in range(8):
print "Best AMS group %i: %f - method %s - ratio %f" \
%(n, best_AMS_s[n], best_method_s[n], best_ratio_s[n])
return best_yPredicted_s, valid_s
predProba_Valid2_s = xgBoost.predict_proba(predictor_s, valid_RM_s_2[1])
# Thresholding the predictions:
predProba_Valid2 = preTreatment.concatenate_vectors(predProba_Valid2_s)
predLabel5_Valid2 = tresholding.get_yPredicted_ratio(predProba_Valid2,
best_ratio)
# Binarize the prediction:
predLabel_Valid2 = preTreatment.multiclass2binary(predLabel5_Valid2)
# Concatenate data:
yValid2 = preTreatment.concatenate_vectors(valid_RM_s_2[2])
weightsValidation = preTreatment.concatenate_vectors(valid_RM_s_2[3])
# Estimation the AMS:
s, b = submission.get_s_b(predLabel_Valid2, yValid2, weightsValidation)
s *= 250000/predLabel_Valid2.shape[0]
b *= 250000/predLabel_Valid2.shape[0]
ams = hbc.AMS(s,b)
print "Valid_RM_2 - ratio : %f - best ams : %f" %(best_ratio, ams)
print(" ")
# Saving the model if it's better:
if ams > best_ams:
best_ams = ams
best_imp_lim = importance_lim
best_best_ratio = best_ratio
best_n_removeFeatures = n_removeFeatures
best_predictor_s = predictor_s
def train(max_depth, n_rounds):
###############
### IMPORT ####
###############
# Importation parameters:
split= True
normalize = True
noise_var = 0.
train_size = 200000
train_size2 = 25000
valid_size = 25000
remove_999 = False
# Import the training data:
print("Extracting the data sets...")
start = time.clock()
train_s, train2_s, valid_s, test_s = tokenizer.extract_data(split= split, \
normalize= normalize, \
remove_999 = remove_999, \
noise_variance= noise_var, \
n_classes = "multiclass", \
train_size = train_size, \
train_size2 = train_size2, \
valid_size = valid_size)
#RANDOM FOREST:
#kwargs_grad = {}
#kwargs_rdf = {'n_estimators': 100}
print "Training on the train set ..."
#predictor_s = randomForest.train_classifier(train_s[1], train_s[2], kwargs_rdf)
#XGBOOST
kwargs_xgb = {'bst_parameters': \
{'booster_type': 0, \
#'objective': 'binary:logitraw',
'objective': 'multi:softprob', 'num_class': 5,
'bst:eta': 0.1, # the bigger the more conservative
'bst:subsample': 1, # prevent over fitting if <1
'bst:max_depth': max_depth, 'eval_metric': 'auc', 'silent': 1,
'nthread': 8 }, \
'n_rounds': n_rounds}
predictor_s = xgBoost.train_classifier(train_s[1], train_s[2], train_s[3], 550000, kwargs_xgb)
#TEST / SUBMISSION
"""
yProbaTest_s = []
yProbaTestBinary_s = []
print "Classifying the test set..."
for i in range(8):
yProbaTest = xgBoost.predict_proba(predictor_s[i], test_s[1][i])
yProbaTest_s.append(yProbaTest)
print "Making the binary proba vector..."
for i in range(8):
yProbaTestBinary_s.append(np.zeros(yProbaTest_s[i].shape[0]))
for i in range(8):
for j in range(yProbaTest_s[i].shape[0]):
yProbaTestBinary_s[i][j] = 1 - yProbaTest_s[i][j][0]
print "Concatenating the vectors..."
yProbaTestBinary = preTreatment.concatenate_vectors(yProbaTestBinary_s)
IDs = preTreatment.concatenate_vectors(test_s[0])
yProbaTestBinaryRanked = submission.rank_signals(yProbaTestBinary)
yPredictedTest = tresholding.get_yPredicted_ratio(yProbaTestBinary, 0.15)
s = submission.print_submission(IDs, yProbaTestBinaryRanked, yPredictedTest, "newAMSmesure")
"""
# TRAIN AND VALID
yPredictedTrain2_s = []
yProbaTrain2_s = []
yProbaTrain2Binary_s = []
yPredictedValid_s = []
yProbaValid_s = []
yProbaValidBinary_s = []
print "Classifying the train2 set..."
for i in range(8):
yProbaTrain2 = xgBoost.predict_proba(predictor_s[i], train2_s[1][i])
yProbaTrain2_s.append(yProbaTrain2)
print "Classifying the valid set..."
for i in range(8):
yProbaValid = xgBoost.predict_proba(predictor_s[i], valid_s[1][i])
yProbaValid_s.append(yProbaValid)
print "Making the binary proba vector..."
for i in range(8):
yProbaTrain2Binary_s.append(np.zeros(yProbaTrain2_s[i].shape[0]))
yProbaValidBinary_s.append(np.zeros(yProbaValid_s[i].shape[0]))
for i in range(8):
for j in range(yProbaTrain2_s[i].shape[0]):
yProbaTrain2Binary_s[i][j] = 1 - yProbaTrain2_s[i][j][0]
for j in range(yProbaValid_s[i].shape[0]):
yProbaValidBinary_s[i][j] = 1 - yProbaValid_s[i][j][0]
print "Concatenating the vectors..."
yProbaTrain2Binary = preTreatment.concatenate_vectors(yProbaTrain2Binary_s)
yProbaValidBinary = preTreatment.concatenate_vectors(yProbaValidBinary_s)
yTrain2 = preTreatment.concatenate_vectors(train2_s[2])
yValid = preTreatment.concatenate_vectors(valid_s[2])
weightsTrain2 = preTreatment.concatenate_vectors(train2_s[3])
weightsValid = preTreatment.concatenate_vectors(valid_s[3])
print "Putting all the real labels to 1"
yTrain2 = preTreatment.multiclass2binary(yTrain2)
yValid = preTreatment.multiclass2binary(yValid)
print "Getting the best ratios..."
best_ams_train2_global, best_ratio_global = tresholding.best_ratio(yProbaTrain2Binary, yTrain2, weightsTrain2)
#best_ams_train2_combinaison, best_ratio_combinaison = tresholding.best_ratio_combinaison_global(yProbaTrain2Binary_s, train2_s[2], train2_s[3], 1)
yPredictedValid = tresholding.get_yPredicted_ratio(yProbaValidBinary, 0.15)
yPredictedValid_best_ratio_global = tresholding.get_yPredicted_ratio(yProbaValidBinary, best_ratio_global)
#yPredictedValid_best_ratio_combinaison_s, yPredictedValid_best_ratio_combinaison = tresholding.get_yPredicted_ratio_8(yProbaTrain2Binary_s, best_ratio_combinaison)
#Let's compute the predicted AMS
s, b = submission.get_s_b(yPredictedValid, yValid, weightsValid)
AMS = hbc.AMS(s,b)
#s_best_ratio_combinaison, b_best_ratio_combinaison = submission.get_s_b(yPredictedValid_best_ratio_combinaison, yValid, weightsValid)
#AMS_best_ratio_combinaison = hbc.AMS(s_best_ratio_combinaison, b_best_ratio_combinaison)
s_best_ratio_global, b_best_ratio_global = submission.get_s_b(yPredictedValid_best_ratio_global, yValid, weightsValid)
AMS_best_ratio_global = hbc.AMS(s_best_ratio_global, b_best_ratio_global)
print "AMS 0.15 = %f" %AMS
print " "
#print "AMS best ratio combi= %f" %AMS_best_ratio_combinaison
#print "best AMS train2 ratio combinaison= %f" %best_ams_train2_combinaison
#print "best ratio combinaison train 2 = %s" %str(best_ratio_combinaison)
print " "
print "best AMS valid ratio global= %f" %AMS_best_ratio_global
print "best AMS train2 ratio global= %f" %best_ams_train2_global
print "best ratio global train2 = %f" %best_ratio_global
return AMS
def analyse(train_s, train2_s, valid_s, method_name, kwargs={}):
"""
methode name = string, name of the method (eg :"naiveBayes")
kwargs = dictionnary of the paraters of the method
train_s = training set for the classifier(s)
train2_s = training set for the meta parameters (eg : the best treshold)
valid_s : validation set
None of the set must be empty !
"""
# Prediction on the validation set:
print("------------------- Analyse: %s -----------------------") \
%(method_name)
classifier_s = eval(method_name).train_classifier(train_s[1], train_s[2],
kwargs)
yProbaTrain2_s = eval(method_name).predict_proba(classifier_s, train2_s[1])
yProbaValid_s = eval(method_name).predict_proba(classifier_s, valid_s[1])
# Convert the validations vectors four 's' classes into one single s
# classe
if type(valid_s[2]) == list:
for i in range(len(valid_s[2])):
for j in range(valid_s[2][i].shape[0]):
if valid_s[2][i][j] >=1:
valid_s[2][i][j] = 1
# Convert the train2 vectors four 's' classes into one single s
# classe
if type(train2_s[2]) == list:
for i in range(len(train2_s[2])):
for j in range(train2_s[2][i].shape[0]):
if train2_s[2][i][j] >=1:
train2_s[2][i][j] = 1
# Let's define the vectors of probabilities of being 's'
# Train2 set
if type(yProbaTrain2_s) == list:
yProbaTrain2Binary_s = []
for i in range(8):
yProbaTrain2Binary_s.append(np.zeros(len(yProbaTrain2_s[i][:,1])))
for i in range(8):
for j in range(len(yProbaTrain2_s[i][:,1])):
yProbaTrain2Binary_s[i][j] = 1 - yProbaTrain2_s[i][j][0]
else:
yProbaTrain2Binary_s = np.zeros(len(yProbaTrain2_s[i][:,1]))
for j in range(len(yProbaTrain2_s[i][:,1])):
yProbaTrain2Binary_s[j] = 1 - yProbaTrain2_s[j][0]
# Validation set
if type(yProbaValid_s) == list:
yProbaValidBinary_s = []
for i in range(8):
yProbaValidBinary_s.append(np.zeros(len(yProbaValid_s[i][:,1])))
for i in range(8):
for j in range(len(yProbaValid_s[i][:,1])):
yProbaValidBinary_s[i][j] = 1 - yProbaValid_s[i][j][0]
else:
yProbaValidBinary_s = np.zeros(len(yProbaValid_s[i][:,1]))
for j in range(len(yProbaValid_s[i][:,1])):
yProbaValidBinary_s[j] = 1 - yProbaValid_s[j][0]
# If we work with lists, let's get the concatenated vectors:
# TRAIN SET
if type(train_s[3]) ==list:
weightsTrain_conca = preTreatment.concatenate_vectors(train_s[3])
else:
weightsTrain_conca = train_s[3]
# VALID SET
# Validation Vectors
if type(valid_s[2]) == list:
yValid_conca = preTreatment.concatenate_vectors(valid_s[2])
else:
yValid_conca = valid_s[2]
# Weights Vectors
if type(valid_s[3]) == list:
weightsValid_conca = preTreatment.concatenate_vectors(valid_s[3])
else:
weightsValid_conca = valid_s[3]
# Binary Proba Vectors
if type(yProbaValidBinary_s) == list:
yProbaValidBinary_conca = preTreatment.concatenate_vectors(
yProbaValidBinary_s)
else:
yProbaValidBinary_conca = yProbaValidBinary_s
# All Proba Vectors
if type(yProbaValid_s) == list:
yProbaValid_conca = preTreatment.concatenate_vectors(yProbaValid_s)
else:
yProbaValid_conca = yProbaValid_s
#TRAIN2 SET
# Validation Vectors
if type(train2_s[2]) == list:
yTrain2_conca = preTreatment.concatenate_vectors(train2_s[2])
else:
yTrain2_conca = train2_s[2]
# Weights Vectors
if type(train2_s[3]) == list:
weightsTrain2_conca = preTreatment.concatenate_vectors(train2_s[3])
else:
weightsTrain2_conca = train2_s[3]
# Binary Proba Vectors
if type(yProbaTrain2Binary_s) == list:
yProbaTrain2Binary_conca = preTreatment.concatenate_vectors(
yProbaTrain2Binary_s)
else:
yProbaTrain2Binary_conca = yProbaTrain2Binary_s
# All Proba Vectors
if type(yProbaTrain2_s) == list:
yProbaTrain2_conca = preTreatment.concatenate_vectors(yProbaTrain2_s)
else:
yProbaTrain2_conca = yProbaTrain2_s
# Let's rebalance the weight so their sum is equal to the total sum
# of the train set
sumWeightsTotal = sum(weightsTrain_conca)+sum(weightsTrain2_conca)+sum(weightsValid_conca)
weightsTrain2_conca *= sumWeightsTotal/sum(weightsTrain2_conca)
weightsValid_conca *= sumWeightsTotal/sum(weightsValid_conca)
for i in range(8):
train2_s[3][i] *= sumWeightsTotal/sum(weightsTrain2_conca)
valid_s[3][i] *= sumWeightsTotal/sum(weightsValid_conca)
# Let's get the best global treshold on the train2 set
AMS_treshold_train2, best_treshold_global = tresholding.\
best_treshold(yProbaTrain2Binary_conca,
yTrain2_conca,
weightsTrain2_conca)
yPredictedValid_conca_treshold = tresholding.get_yPredicted_treshold(
yProbaValidBinary_conca,
best_treshold_global)
# Let's get the best ratio treshold on the train2 set
AMS_ratio_global_train2, best_ratio_global = tresholding.\
best_ratio(yProbaTrain2Binary_conca,
yTrain2_conca,
weightsTrain2_conca)
yPredictedValid_conca_ratio_global = tresholding.get_yPredicted_ratio(
yProbaValidBinary_conca,
best_ratio_global)
# Let's get the best ratios combinaison
if type(train_s[2]) == list:
AMS_ratio_combinaison_train2, best_ratio_combinaison = tresholding.\
best_ratio_combinaison_global(
yProbaTrain2Binary_s,
train2_s[2],
train2_s[3],
30)
yPredictedValid_ratio_comb_s, yPredictedValid_conca_ratio_combinaison =\
tresholding.get_yPredicted_ratio_8(
yProbaValidBinary_s,
best_ratio_combinaison)
# Let's compute the final s and b for each method
s_treshold, b_treshold = submission.get_s_b(
yPredictedValid_conca_treshold,
yValid_conca,
weightsValid_conca)
s_ratio_global, b_ratio_global = submission.get_s_b(
yPredictedValid_conca_ratio_global,
yValid_conca,
weightsValid_conca)
if type(train_s[2]) == list:
s_ratio_combinaison, b_ratio_combinaison = submission.get_s_b(
yPredictedValid_conca_ratio_combinaison,
yValid_conca,
weightsValid_conca)
# AMS final:
AMS_treshold_valid = hbc.AMS(s_treshold, b_treshold)
AMS_ratio_global_valid = hbc.AMS(s_ratio_global, b_ratio_global)
if type(train_s[2]) == list:
AMS_ratio_combinaison_valid = hbc.AMS(s_ratio_combinaison,
b_ratio_combinaison)
"""
#AMS by group:
if type(train_s[2]) == list:
AMS_s = []
for i, (s,b) in enumerate(zip(s_s, b_s)):
s *= 250000/yPredictedValid_s[i].shape[0]
b *= 250000/yPredictedValid_s[i].shape[0]
score = hbc.AMS(s,b)
AMS_s.append(score)
"""
# Classification error:
classif_succ_treshold = eval(method_name).get_classification_error(
yPredictedValid_conca_treshold,
yValid_conca,
normalize= True)
classif_succ_ratio_global = eval(method_name).get_classification_error(
yPredictedValid_conca_ratio_global,
yValid_conca,
normalize= True)
classif_succ_ratio_combinaison = eval(method_name).get_classification_error(
yPredictedValid_conca_ratio_combinaison,
yValid_conca,
normalize= True)
# Numerical score:
"""
if type(yProbaValid_s) == list:
sum_s_treshold_s = []
sum_b_treshold_s = []
sum_s_ratio_global_s = []
sum_b_ratio_global_s = []
sum_s_ratio_combinaison_s = []
sum_b_ratio_combinaison_s = []
for i in range(len(yPredictedValid_s)):
# treshold
sum_s_treshold, sum_b_treshold = submission.get_numerical_score(yPredictedValid_conca_treshold_s[i],
valid_s[2][i])
sum_s_treshold_s.append(sum_s)
sum_b_treshold_s.append(sum_b)
# ratio global
sum_s_ratio_global, sum_b_ratio_global = submission.get_numerical_score(yPredictedValid_conca_ratio_global_s[i],
valid_s[2][i])
sum_s_ratio_global_s.append(sum_s_ratio_global)
sum_b_ratio_global_s.append(sum_b_ratio_global)
# ratio combinaison
sum_s_ratio_combinaison, sum_b_ratio_combinaison = submission.get_numerical_score(yPredictedValid_conca_ratio_combinaison_s[i],
valid_s[2][i])
sum_s_ratio_combinaison_s.append(sum_s_ratio_combinaison)
sum_b_ratio_combinaison_s.append(sum_b_ratio_combinaison)
else:
sum_s, sum_b = submission.get_numerical_score(yPredictedValid_s,
valid_s[2])
"""
d = {'classifier_s':classifier_s,
'yPredictedValid_conca_treshold': yPredictedValid_conca_treshold,
'yPredictedValid_conca_ratio_global' : \
yPredictedValid_conca_ratio_global,
'yProbaTrain2_s': yProbaTrain2_s,
'yProbaTrain2Binary_s': yProbaTrain2Binary_s,
'yProbaTrain2_conca': yProbaTrain2_conca,
'yProbaTrain2Binary_conca': yProbaTrain2Binary_conca,
'yProbaValid_s':yProbaValid_s,
'yProbaValidBinary_s':yProbaValidBinary_s,
'yProbaValid_conca':yProbaValid_conca,
'yProbaValidBinary_conca': yProbaValidBinary_conca,
'AMS_treshold_train2':AMS_treshold_train2,
'AMS_ratio_global_train2':AMS_ratio_global_train2,
'AMS_treshold_valid':AMS_treshold_valid,
'AMS_ratio_global_valid':AMS_ratio_global_valid,
'best_treshold_global' : best_treshold_global,
'best_ratio_global':best_ratio_global,
'classif_succ_treshold': classif_succ_treshold,
'classif_succ_ratio_global': classif_succ_ratio_global,
'method': method_name,
'parameters': kwargs}
if type(train_s[2])==list:
d['yPredictedValid_conca_ratio_combinaison'] = yPredictedValid_conca_ratio_combinaison
d['AMS_ratio_combinaison_train2'] = AMS_ratio_combinaison_train2
d['AMS_ratio_combinaison_valid'] = AMS_ratio_combinaison_valid,
d['best_ratio_combinaison'] = best_ratio_combinaison,
d['classif_succ_ratio_combinaison'] = classif_succ_ratio_combinaison
return d
def main():
###############
### IMPORT ####
###############
# Importation parameters:
split= True
normalize = True
noise_var = 0.
n_classes = "binary"
train_size = 200000
train_size2 = 25000
valid_size = 25000
# Import the training data:
print("Extracting the data sets...")
start = time.clock()
train_s, train2_s, valid_s, test_s = tokenizer.extract_data(split= split,
normalize= normalize,
noise_variance= noise_var,
n_classes = n_classes,
train_size = train_size,
train_size2 = train_size2,
valid_size = valid_size)
# Remerging the y and weights of the validation if necessary:
if type(valid_s[2]) == list:
yValid_conca = preTreatment.concatenate_vectors(valid_s[2])
weights_conca = preTreatment.concatenate_vectors(valid_s[3])
stop = time.clock()
print ("Extraction time: %i s") %(stop-start)
print(" ")
print(" ")
######################
### PRE-TREATMENT ####
######################
print("------------------------- Pre-treatment --------------------------")
### Average number of signal per subset:
print("Train subsets signal average:")
train_s_average = preTreatment.ratio_sig_per_dataset(train_s[2])
print(" ")
print("Valid subsets signal average:")
valid_s_average = preTreatment.ratio_sig_per_dataset(valid_s[2])
print(" ")
print(" ")
############
# ANALYSES #
############
# Dictionnary that will contain all the data for each methods. In the end
# we'll have a dict of dict
# Keys of the methods : {naiveBayes, svm, kNeighbors, lda, qda, adaBoost,
# randomForest}
dMethods ={}
# NAIVE BAYES:
kwargs_bayes = {}
dMethods['naiveBayes'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'naiveBayes',
kwargs = kwargs_bayes)
# SVM
"""
kwargs_svm ={}
dMethods['svm'] = analyse.analyse(train_s, valid_s,'svm', kwargs_svm)
"""
"""
# K NEIGHBORS
kwargs_kn = {'n_neighbors':50}
dMethods['kNeighbors'] = analyse.analyse(train_s, valid_s, 'kNeighbors',
kwargs_kn)
"""
# LDA
kwargs_lda = {}
dMethods['lda'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'lda',
kwargs = kwargs_lda)
# QDA
kwargs_qda= {}
dMethods['qda'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'qda',
kwargs = kwargs_qda)
"""
# ADABOOST
kwargs_ada= { 'n_estimators': 50,
'learning_rate': 1.,
'algorithm': 'SAMME.R',
'random_state':None}
dMethods['adaBoost'] = analyse.analyse(train_s, valid_s, 'adaBoost',
kwargs_ada)
"""
# RANDOM FOREST:
kwargs_randomForest= {'n_estimators': 10}
dMethods['randomForest'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'randomForest',
kwargs = kwargs_randomForest)
# RANDOM FOREST 2:
kwargs_randomForest= {'n_estimators': 100}
dMethods['randomForest2'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'randomForest',
kwargs = kwargs_randomForest)
"""
# ADABOOST2
kwargs_ada= { 'n_estimators': 100,
'learning_rate': .5,
'algorithm': 'SAMME.R',
'random_state':None}
dMethods['adaBoost2'] = analyse.analyse(train_s, valid_s, 'adaBoost',
kwargs_ada)
# RANDOM FOREST 3:
kwargs_randomForest= {'n_estimators': 100}
dMethods['randomForest3'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'randomForest',
kwargs = kwargs_randomForest)
# RANDOM FOREST 4:
kwargs_randomForest= {'n_estimators': 100}
dMethods['randomForest4'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'randomForest',
kwargs = kwargs_randomForest)
# RANDOM FOREST 5:
kwargs_randomForest= {'n_estimators': 100}
dMethods['randomForest5'] = analyse.analyse(train_s= train_s, train2_s= train2_s,
valid_s= valid_s,
method_name = 'randomForest',
kwargs = kwargs_randomForest)
# GRADIENT BOOSTING:
kwargs_gradB = {'loss': 'deviance', 'learning_rate': 0.1,
'n_estimators': 100, 'subsample': 1.0,
'min_samples_split': 2, 'min_samples_leaf': 200,
'max_depth': 10, 'init': None, 'random_state': None,
'max_features': None, 'verbose': 0}
dMethods['gradientBoosting'] = analyse.analyse(train_s, valid_s,
'gradientBoosting', kwargs_gradB)
"""
print(" ")
##################
# POST-TREATMENT #
##################
print("------------------------ Feaure importance: -----------------------")
if type(dMethods['randomForest2']['predictor_s']) == list:
for i,predictor_s in enumerate(dMethods['randomForest2']['predictor_s']):
print "Subset %i:" %i
print predictor_s.feature_importances_
else:
print "Dataset: "
print dMethods['randomForest2']['predictor_s'].feature_importances_
print("------------------------ On-top predictor -----------------------")
# Classifiers to be ignored:
#ignore = ['randomForest2', 'randomForest']
ignore = []
clf_onTop = 'randomForest'
parameters = {}#{'C': 0.5, 'kernel': 'rbf', 'degree': 3, 'gamma': 0.0,
# 'coef0': 0.0, 'shrinking':True, 'probability':True,
# 'tol': 0.001, 'cache_size': 200, 'class_weight': None}
print ("We will use an 'on-top' predictor on %i classifiers using a %s.") \
%(len(dMethods.keys())-len(ignore), clf_onTop)
final_prediction_s, dOnTop = onTopClassifier.SL_classification(dMethods,
valid_s, train_s,
ignore = ignore,
method= clf_onTop, parameters= parameters)
print("-------------------------- Tresholding -------------------------")
### ON THE 'ON-TOP' CLASSIFIER:
# Create the elected vectors for each group (best AMS score)
OT_best_yPredicted_s = [np.zeros(valid_s[2][i].shape[0]) for i in range(8)]
OT_best_yProba_s = [np.zeros(valid_s[2][i].shape[0]) for i in range(8)]
OT_best_AMS_s = [0. for i in range(8)]
OT_best_method_s = [0 for i in range(8)]
OT_best_ratio_s = [0 for i in range(8)]
OT_best_sum_s_s = [0 for i in range(8)]
OT_best_sum_b_s = [0 for i in range(8)]
OT_best_method = "On-top"
OT_yProba_s = dOnTop['yProba_s']
OT_yPredicted_s = dOnTop['yPredicted_s']
#Let's concatenate the vectors
OT_yProba_conca = preTreatment.concatenate_vectors(OT_yProba_s)
OT_yPredicted_conca = preTreatment.concatenate_vectors(OT_yPredicted_s)
# Best treshold global
OT_best_ratio = tresholding.best_treshold(OT_yProba_conca, yValid_conca,
weights_conca)
OT_yPredicted_treshold = tresholding.get_yPredicted_treshold(OT_yProba_conca,
OT_best_ratio)
OT_s, OT_b = submission.get_s_b(OT_yPredicted_treshold, yValid_conca,
weights_conca)
OT_s *= 10
OT_b *= 10
OT_best_AMS = hbc.AMS(OT_s,OT_b)
# COMPARISON BEST TRESHOLD IN DMETHOD
# FOR EACH METHOD:
best_yPredicted_s = [np.zeros(valid_s[2][i].shape[0]) for i in range(8)]
best_yProba_s = [np.zeros(valid_s[2][i].shape[0]) for i in range(8)]
best_AMS_s = [0. for i in range(8)]
best_method_s = [0 for i in range(8)]
best_ratio_s = [0 for i in range(8)]
best_AMS_1_method = 0.
best_method = "methode"
best_ratio = "0."
for method in dMethods:
yProba_s = dMethods[method]['yProba_s']
yPredicted_s = dMethods[method]['yPredicted_s']
#Let's concatenate the vectors
yProba_conca = preTreatment.concatenate_vectors(yProba_s)
yPredicted_conca = preTreatment.concatenate_vectors(yPredicted_s)
# Best treshold global
best_treshold = tresholding.best_treshold(yProba_conca, yValid_conca, weights_conca)
yPredicted_treshold = tresholding.get_yPredicted_treshold(yProba_conca, best_treshold)
s, b = submission.get_s_b(yPredicted_treshold, yValid_conca, weights_conca)
s *= 10
b *= 10
ams = hbc.AMS(s,b)
if ams > best_AMS_1_method:
best_AMS_1_method = ams
best_method = str(method)
best_ratio = best_treshold
# Let's concatenate the 8 vectors which performs the best on each on
# each of the sub group and tresholding it
best_yPredicted_conca = preTreatment.concatenate_vectors(best_yPredicted_s)
best_treshold_conca = tresholding.best_treshold(best_yPredicted_conca, yValid_conca, weights_conca)
best_yPredicted_conca_treshold = tresholding.get_yPredicted_treshold(best_yPredicted_conca, best_treshold_conca)
best_final_s, best_final_b, best_s_s, best_b_s = submission.get_s_b_8(best_yPredicted_s, valid_s[2], valid_s[3])
best_s_treshold, best_b_treshold = submission.get_s_b(best_yPredicted_conca_treshold, yValid_conca, weights_conca)
best_final_s *= 10
best_final_b *= 10
best_s_treshold *= 10
best_b_treshold *= 10
best_AMS = hbc.AMS(best_final_s, best_final_b)
best_AMS_treshold = hbc.AMS(best_s_treshold, best_b_treshold)
print "Best AMS using one of the methods : %f" %best_AMS_1_method
print " method : %s" %(str(method))
print " ratio : %f" %(best_ratio)
print " "
print "Best AMS concatenate: %f" %best_AMS
print "Best AMS concatenate after final tresholding : %f" %best_AMS_treshold
print "best ratio on the concatenated vector : %f" %best_treshold_conca
print " "
print "Best AMS on-top : %f" %OT_best_AMS
print "Best ratio on the concatenated vector : %f" %OT_best_ratio
print " "
"""
# Best treshold group by group
for i in range(8):
OT_best_treshold_s = tresholding.best_treshold(OT_yProba_s[i],
valid_s[2][i],
valid_s[3][i])
OT_yPredicted_s[i] = tresholding.get_yPredicted_treshold(OT_yProba_s[i],
OT_best_treshold_s)
s, b = submission.get_s_b(OT_yPredicted_s[i], valid_s[2][i],
valid_s[3][i])
s *= 250000/yPredicted_s[i].shape[0]
b *= 250000/yPredicted_s[i].shape[0]
ams = hbc.AMS(s,b)
if ams > best_AMS_s[i]:
best_yPredicted_s[i] = yPredicted_s[i]
best_yProba_s[i] = yProba_s[i]
best_AMS_s[i] = ams
best_method_s[i] = dOnTop['method']
best_ratio_s[i] = best_treshold
best_sum_s_s[i] = s
best_sum_b_s[i] = b
for n in range(8):
print "Best AMS group %i: %f - method %s - ratio %f" \
%(n, best_AMS_s[n], best_method_s[n], best_ratio_s[n])
print "Best AMS : %f" %best_AMS_1_method
print " ratio : %f" %(best_ratio)
print " "
"""
"""
##############
# SUBMISSION #
##############
print("-------------------------- Submission ---------------------------")
# Prediction on the test set:
# method used for the submission
# TODO : Verifier que le nom de la method a bien la bonne forme(
# creer une liste de noms de methodes)
#method = "randomForest"
#test_prediction_s, test_proba_s = eval(method).get_test_prediction(
# dMethods[method]['predictor_s'],
# test_s[1])
test_prediction_s, test_proba_s = onTopClassifier.get_SL_test_prediction(
dMethods, dOnTop, test_s[1])
print("Test subsets signal average:")
test_s_average = preTreatment.ratio_sig_per_dataset(test_prediction_s)
print(" ")
#RankOrder = np.arange(1,550001)
if type(test_prediction_s) == list:
test_prediction_s = np.concatenate(test_prediction_s)
test_proba_s = np.concatenate(test_proba_s)
RankOrder = onTopClassifier.rank_signals(test_proba_s)
ID = np.concatenate(test_s[0])
else:
ID = test_s[0]
# Create a submission file:
sub = submission.print_submission(ID, RankOrder , test_prediction_s)
return sub
"""
return 0
