Exemplo n.º 1
0
    def __init__(self, per_data, per_lens=None, n_states=None):
        if per_lens is None:
            per_lens = list(map(len, per_data))

        if len(per_data.shape) > 2:
            per_data = per_data.reshape(-1, per_data.shape[-1])

        if n_states is None:
            components = [2, 4, 6, 8, 10]

            hmms = [GaussianHMM(n_components=c) for c in components]

            map(lambda g: g.fit(per_data, per_lens), hmms)
            scores = map(lambda g: aic(g, per_data, per_lens), hmms)

            max_score, self.hmm = sorted(zip(scores, hmms))[0]
        else:
            self.hmm = GaussianHMM(n_components=n_states)
            self.hmm.fit(per_data, per_lens)

        ll = self.hmm.score(per_data, per_lens)
        print "Goal HMM n_components", self.hmm.n_components, "Log likelihood", ll

        upper_idxs = [per_lens[0] - 1]
        start_idxs = [0]
        for i in range(1, len(per_lens)):
            upper_idxs.append(upper_idxs[i - 1] + per_lens[i])
            start_idxs.append(start_idxs[i - 1] + per_lens[i - 1])

        self.final_states = np.array(self.hmm.predict(per_data,
                                                      per_lens))[upper_idxs]
        print self.final_states
        self.T = int(np.mean(per_lens))
        self.n_components = self.hmm.n_components
def aic(em_fit_result_dict):
  '''
        Compute Akaike Information Criterion.
    '''
  # Number of parameters:
  # - mixt_target: 1
  # - mixt_random: 1
  # - mixt_nontarget: K
  K = em_fit_result_dict['mixt_nontargets'].size + 2

  return utils.aic(K, em_fit_result_dict['train_LL'])
Exemplo n.º 3
0
def aic(em_fit_result_dict):
    '''
        Compute Akaike Information Criterion.
    '''
    # Number of parameters:
    # - mixt_target: 1
    # - mixt_random: 1
    # - mixt_nontarget: K
    # - kappa: 1
    K = 3 + em_fit_result_dict['K']

    return utils.aic(K, em_fit_result_dict['train_LL'])
Exemplo n.º 4
0
def rf_func(k, combo):
    regr = RandomForestClassifier(random_state=0, n_estimators=10)  ##########
    data = matrices[k, :, 1:][:, combo]
    response = binary_labels[k]
    reg_f = regr.fit(data, response)
    #features = reg_f.feature_importances_
    loglik = utils.loglik_logistic(reg_f, data, response)
    aic = utils.aic(loglik, data.shape[0], data.shape[1])
    locations = np.where(combo)[0]
    model_coefs = np.array(combo).astype(float)
    np.put(model_coefs, locations, reg_f.feature_importances_)
    return [aic, model_coefs]
def aic(em_fit_result_dict):
  '''
        Compute Akaike Information Criterion.
    '''
  # Number of parameters:
  # - mixt_target: Tnum
  # - mixt_random: Tnum
  # - mixt_nontargets: Tnum - 1
  # - alpha: 1
  # - beta: 1
  K = em_fit_result_dict['mixt_target'].size + em_fit_result_dict['mixt_random'].size + em_fit_result_dict['mixt_nontargets'].size + 1

  return utils.aic(K, em_fit_result_dict['train_LL'])
Exemplo n.º 6
0
def aic(em_fit_result_dict):
    '''
        Compute Akaike Information Criterion.
    '''
    # Number of parameters:
    # - mixt_target_tr: Tnum
    # - mixt_random_tr: Tnum
    # - mixt_nontarget: sum(T_space - 1)
    # - alpha: 1
    # - beta: 1
    K = em_fit_result_dict['mixt_target_tr'].size + em_fit_result_dict['mixt_random_tr'].size + em_fit_result_dict['mixt_nontargets_tr'].size + 2

    return utils.aic(K, em_fit_result_dict['train_LL'])