def main(): maxFeature, featureChoices = getMFCCs() cls = getClassifiersWithoutFS() X_train, y_train, X_dev, y_dev, y_bin_train, y_bin_dev = preLoadData() X_train_default, X_dev_default, chosenFeatures, numOfFeatures = selectFeatures(maxFeature, featureChoices, X_train, X_dev) X_train_normalized, X_dev_normalized, chosenFeatures, numOfFeatures = selectFeaturesWithFeatureStandardization(maxFeature, featureChoices, X_train, X_dev) plotMFCCsFirst2Bin(X_train_default, X_train_normalized)
def main():
maxFeature, featureChoices = getAllFeatures()
#get only mean
#maxFeature, featureChoices = getMeanFeatures()
#use small feature sets to test
#maxFeature, featureChoices = getTestFeatures()
X_train, y_train, X_dev, y_dev, y_bin_train, y_bin_dev = preLoadData()
chosenFeatureAndModels = automaticChooseFeatures(True, maxFeature,
featureChoices, 0,
X_train, X_dev,
y_bin_train, y_bin_dev)
saveAsTable('classifierWithFeature.csv', chosenFeatureAndModels)
# Author: Noel Dawe <*****@*****.**>
# Edited b
# License: BSD 3 clause
from sklearn.externals.six.moves import zip
import matplotlib.pyplot as plt
from sklearn.datasets import make_gaussian_quantiles
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
from classifierWithFS import preLoadData, getBestMeanFeatures, selectFeatures
X_train, y_train_phq8, X_test, y_dev, y_train, y_test = preLoadData()
maxFeature, featureChoices = getBestMeanFeatures()
X_train, X_test, chosenFeatures, numOfFeatures = selectFeatures(
maxFeature, featureChoices, X_train, X_test)
bdt_real = AdaBoostClassifier(random_state=13370)
bdt_real.fit(X_train, y_train)
real_test_errors = []
for real_test_predict in bdt_real.staged_predict(X_test):
real_test_errors.append(1. - accuracy_score(real_test_predict, y_test))
n_trees_real = len(bdt_real)
# add a paragraph 'Processed Data'
#1) generate the dataset with 526 features
#2) the predictive variance and predictive mean (best and worst) of some vectors from the dot product.
# 3-th leading minor not positive definite
# ("GP exp sine squared", gp.GaussianProcessRegressor(kernel=gp.kernels.ExpSineSquared())),
#("GP rational quadratic", None, gp.GaussianProcessRegressor(kernel=gp.kernels.RationalQuadratic())),
#("GP white kernel", None, gp.GaussianProcessRegressor(kernel=gp.kernels.WhiteKernel())),
#("GP abs_exp", None, gp.GaussianProcess(corr='absolute_exponential')),
#("GP squared_exp", ["All"], gp.GaussianProcess(corr='squared_exponential')),
#("GP cubic", None, gp.GaussianProcess(corr='cubic')),
#("GP linear", None, gp.GaussianProcess(corr='linear')),
#("GP RBF ARD", ["All"], RBF_ARD_WRAPPER(kern.RBF(input_dim=n_feats, variance=1., lengthscale=np.array([1]*n_feats), ARD=True)))]
]
X_train, y_train, X_dev, y_dev, y_bin_train, y_bin_dev = preLoadData()
#maxFeature, featureChoices = getBestMeanFeatures()
#maxFeature, featureChoices = getBestMeanStdFeatures()
#maxFeature, featureChoices = getBestNormalizedMeanStdFeatures()
maxFeature, featureChoices = getBestNormalizedMeanFeatures()
#X_train, X_dev, chosenFeatures, numOfFeatures = selectFeatures(maxFeature, featureChoices, X_train, X_dev)
X_train, X_dev, chosenFeatures, numOfFeatures = selectFeaturesWithFeatureStandardization(maxFeature, featureChoices, X_train, X_dev)
modeString = 'All'
models_rmse = []
for name, featSelectionMode, model in regressors:
model.fit(X_train, y_train)
predictTrain = model.predict(X_train)
predictDev = model.predict(X_dev)