def runRandomForest(trainDataParam, testDataParam):
res_combo_dict ={}
#n_estimators_list=[500]
n_estimators_list = [75, 80, 85]
criterion_list = ['gini', 'entropy']
#max_features_list = ['auto', 'sqrt', 'log2', None]
max_depth_list = [5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, None]
max_leaf_nodes_list = [5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, None]
bootstrap_list = [True, False]
#min_samples_split_list = [5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100]
#oob_score_list = [True, False]
min_weight_fraction_leaf_list = [0.1, 0.2, 0.3, 0.4, 0.5] # cannot be more than 0.50
### setting the aprameters : test purpose
# n_estimators_list=[50, 50000]
# criterion_list = ['gini', 'entropy']
# max_features_list=['auto', None]
# max_depth_list = [1, 1000 ]
# max_leaf_nodes_list = [None, 5, 1000] # in our datset only 549 legit samples so should eb limited to 549
# bootstrap_list=[True, False]
# min_samples_split_list = [1, 1000] # in our datset only 549 legit samples so should eb limited to 549
# oob_score_list=[True, False]
# min_weight_fraction_leaf_list=[0.0, 0.5] # must be between 0.0 and 0.50
# warm_start_list=[True, False]
###
for eti in n_estimators_list:
for crit in criterion_list:
for max_depth_ in max_depth_list:
for max_leaf in max_leaf_nodes_list:
for bootstrap_ in bootstrap_list:
for mwfratleaf in min_weight_fraction_leaf_list:
## display params:
# n_jobs has been set to -1 to use all the cores avialable , not part fo an experiemnt
print "##########"
print "n_estimators={}, criterion={}, max_dept={}, max_leaf_nodes={}".format(eti, crit, max_depth_, max_leaf )
print "bootstrap={}, min-wt-frac={}".format(bootstrap_, mwfratleaf )
key_str_1 = str(eti) + "_" + crit + "_" + str(max_depth_) + "_" + str(max_leaf) + "_"
key_str_2 = str(bootstrap_) + "_" + str(mwfratleaf) + "_"
key_for_dict = key_str_1 + key_str_2
## fire up the model
with IO_.duration():
theRndForestModel = RandomForestClassifier(
n_estimators=eti, criterion=crit,
max_depth=max_depth_,
min_weight_fraction_leaf=mwfratleaf,
max_leaf_nodes=max_leaf, bootstrap=bootstrap_
)
res_tuple = perform_cross_validation(theRndForestModel, trainDataParam, testDataParam, 10)
res_combo_dict[key_for_dict] = res_tuple
print "##########"
return res_combo_dict
max_leaf_nodes=10000)
mae_for_param_combo_2 = perform_cross_validation(
the_Model_2, trainingData, testData, cv_param)[1]
t2 = time.time()
time_for_param_comb_2 = t2 - t1
mae_list_2.append(mae_for_param_combo_2)
time_list_2.append(time_for_param_comb_2)
mae_a12_ = a12_utility.doSlowA12(mae_list_1, mae_list_2)
time_a12_ = a12_utility.doSlowA12(time_list_2, time_list_1)
print "MAE comaprison: is default worse than 'best combo' ?", mae_a12_
print "time comaprison: is 'best' combo slower than default ?", time_a12_
datasetFileName = "13_NonZeroDataset_Aggolo.csv"
iterations = 10000
cv_param = 5
print "========== Random Forest =========="
with IO_.duration():
runRFTest(datasetFileName, iterations, cv_param)
print "========== KNN =========="
with IO_.duration():
runknnTest(datasetFileName, iterations, cv_param)
print "========== SVM =========="
with IO_.duration():
runsvmTest(datasetFileName, iterations, cv_param)
print "========== CART =========="
with IO_.duration():
runCARTTest(datasetFileName, iterations, cv_param)
mae_for_param_combo_2 = perform_cross_validation(the_Model_2, trainingData, testData, cv_param)[1]
t2 = time.time()
time_for_param_comb_2 = t2 - t1
mae_list_2.append(mae_for_param_combo_2)
time_list_2.append(time_for_param_comb_2)
mae_a12_ = a12_utility.doSlowA12(mae_list_1, mae_list_2)
time_a12_ = a12_utility.doSlowA12(time_list_2, time_list_1)
print "MAE comaprison: is default worse than 'best combo' ?", mae_a12_
print "time comaprison: is 'best' combo slower than default ?", time_a12_
datasetFileName="13_NonZeroDataset_Aggolo.csv"
iterations=10000
cv_param = 5
print "========== Random Forest =========="
with IO_.duration():
runRFTest(datasetFileName, iterations, cv_param)
print "========== KNN =========="
with IO_.duration():
runknnTest(datasetFileName, iterations, cv_param)
print "========== SVM =========="
with IO_.duration():
runsvmTest(datasetFileName, iterations, cv_param)
print "========== CART =========="
with IO_.duration():
runCARTTest(datasetFileName, iterations, cv_param)
def runRandomForest(trainDataParam, testDataParam):
res_combo_dict ={}
# ### setting the aprameters
n_estimators_list=[500]
#n_estimators_list=[10, 50, 100, 500]
criterion_list = ['gini', 'entropy']
max_features_list=['auto', 'sqrt', 'log2', None]
max_depth_list = [5, 15, 50, None ]
max_leaf_nodes_list = [None, 25, 50, 75] # in our datset only 549 legit samples so should eb limited to 549
bootstrap_list=[True, False]
min_samples_split_list = [1, 25, 50, 100] # in our datset only 549 legit samples so should eb limited to 549
oob_score_list=[True, False]
min_weight_fraction_leaf_list=[0.0, 0.2, 0.3, 0.4] # must be between 0.0 and 0.50
warm_start_list=[True, False]
# ###
### setting the aprameters : test purpose
# n_estimators_list=[50, 50000]
# criterion_list = ['gini', 'entropy']
# max_features_list=['auto', None]
# max_depth_list = [1, 1000 ]
# max_leaf_nodes_list = [None, 5, 1000] # in our datset only 549 legit samples so should eb limited to 549
# bootstrap_list=[True, False]
# min_samples_split_list = [1, 1000] # in our datset only 549 legit samples so should eb limited to 549
# oob_score_list=[True, False]
# min_weight_fraction_leaf_list=[0.0, 0.5] # must be between 0.0 and 0.50
# warm_start_list=[True, False]
###
for eti in n_estimators_list:
for crit in criterion_list:
for maxfeat in max_features_list:
for max_depth_ in max_depth_list:
for max_leaf in max_leaf_nodes_list:
for bootstrap_ in bootstrap_list:
for min_sample in min_samples_split_list:
if bootstrap_==False:
oob_score_list=[False, False]
for oob_ in oob_score_list:
for mwfratleaf in min_weight_fraction_leaf_list:
for warm_start_ in warm_start_list:
## display params:
# n_jobs has been set to -1 to use all the cores avialable , not part fo an experiemnt
print "##########"
print "n_estimators={}, criterion={}, max_features={}, max_dept={}, max_leaf_nodes={}".format(eti, crit, maxfeat, max_depth_, max_leaf )
print "bootstrap={}, min-sample-split={}, oob_score={}, min-wt-frac={}, warm-start={}".format(bootstrap_, min_sample, oob_, mwfratleaf, warm_start_ )
key_str_1 = str(eti) + "_" + crit + "_" + str(maxfeat) + "_" + str(max_depth_) + "_" + str(max_leaf) + "_"
key_str_2 = str(bootstrap_) + "_" + str(min_sample) + "_" + str(oob_) + "_" + str(mwfratleaf) + "_" +str(warm_start_)
key_for_dict = key_str_1 + key_str_2
## fire up the model
with IO_.duration():
theRndForestModel = RandomForestClassifier(
n_estimators=eti, criterion=crit,
max_depth=max_depth_, min_samples_split=min_sample,
max_features=maxfeat, min_weight_fraction_leaf=mwfratleaf,
max_leaf_nodes=max_leaf, bootstrap=bootstrap_,
oob_score=oob_, n_jobs=-1 , warm_start=warm_start_
)
res_tuple = perform_cross_validation(theRndForestModel, trainDataParam, testDataParam, 2)
res_combo_dict[key_for_dict] = res_tuple
print "##########"
return res_combo_dict
