Python scipy.maximum方法代碼示例

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def prior_log_loss(frac_pos, task = 'binary.classification'):
    ''' Baseline log loss. For multiplr classes ot labels return the volues for each column'''
    eps = 1e-15   
    frac_pos_ = sp.maximum (eps, frac_pos)
    if (task != 'multiclass.classification'): # binary case
        frac_neg = 1-frac_pos
        frac_neg_ = sp.maximum (eps, frac_neg)
        pos_class_log_loss_ = - frac_pos * np.log(frac_pos_)
        neg_class_log_loss_ = - frac_neg * np.log(frac_neg_)
        base_log_loss = pos_class_log_loss_ + neg_class_log_loss_
        # base_log_loss = mvmean(base_log_loss)
        # print('binary {}'.format(base_log_loss))
        # In the multilabel case, the right thing i to AVERAGE not sum
        # We return all the scores so we can normalize correctly later on
    else: # multiclass case
        fp = frac_pos_ / sum(frac_pos_) # Need to renormalize the lines in multiclass case
        # Only ONE label is 1 in the multiclass case active for each line
        pos_class_log_loss_ = - frac_pos * np.log(fp)
        base_log_loss = np.sum(pos_class_log_loss_) 
    return base_log_loss
        
# sklearn implementations for comparison 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def prep_optics(SetofObjects, epsilon):

    """
    Prep data set for main OPTICS loop
    
    SetofObjects: Instantiated instance of 'setOfObjects' class
    epsilon: Determines maximum object size that can be extracted. Smaller epsilons
        reduce run time.
    
    Returns modified setOfObjects tree structure
    
    """

    for j in SetofObjects._index:
        # Find smallest nonzero distance
        SetofObjects._core_dist[j] = np.sort(SetofObjects.data[j,:])[1] 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def expandClusterOrder(SetOfObjects, point, epsilon):

    """
    Expands OPTICS ordered list of clustering structure
    
    SetofObjects: Instantiated and prepped instance of 'setOfObjects' class
    epsilon: Determines maximum object size that can be extracted. Smaller epsilons
        reduce run time.

    """
    
    if SetOfObjects._core_dist[point] <= epsilon:
        while not SetOfObjects._processed[point]:
            SetOfObjects._processed[point] = True
            SetOfObjects._ordered_list.append(point)
            point = set_reach_dist(SetOfObjects, point, epsilon)
    else:
        SetOfObjects._processed[point] = True 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def log_loss(actual, predicted, epsilon=1e-15):
    """
    Calculates and returns the log loss (error) of a set of predicted probabilities
    (hint: see sklearn classifier's predict_proba methods).

    Source: https://www.kaggle.com/wiki/LogarithmicLoss
    
    In plain English, this error metric is typically used where you have to predict 
    that something is true or false with a probability (likelihood) ranging from 
    definitely true (1) to equally true (0.5) to definitely false(0).

    Note: also see (and use) scikitlearn: 
    http://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html#sklearn.metrics.log_loss
    """
    predicted = sp.maximum(epsilon, predicted)
    predicted = sp.minimum(1-epsilon, predicted)
    ll = sum(actual*sp.log(predicted) + sp.subtract(1,actual)*sp.log(sp.subtract(1,predicted)))
    ll = ll * -1.0/len(actual)
    return ll 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def bac_metric (solution, prediction, task='binary.classification'):
    ''' Compute the normalized balanced accuracy. The binarization and 
    the normalization differ for the multi-label and multi-class case. '''
    label_num = solution.shape[1]
    score = np.zeros(label_num)
    bin_prediction = binarize_predictions(prediction, task)
    [tn,fp,tp,fn] = acc_stat(solution, bin_prediction)
    # Bounding to avoid division by 0
    eps = 1e-15
    tp = sp.maximum (eps, tp)
    pos_num = sp.maximum (eps, tp+fn)
    tpr = tp / pos_num # true positive rate (sensitivity)
    if (task != 'multiclass.classification') or (label_num==1):
        tn = sp.maximum (eps, tn)
        neg_num = sp.maximum (eps, tn+fp)
        tnr = tn / neg_num # true negative rate (specificity)
        bac = 0.5*(tpr + tnr)
        base_bac = 0.5     # random predictions for binary case
    else: 
        bac = tpr
        base_bac = 1./label_num # random predictions for multiclass case
    bac = mvmean(bac)     # average over all classes
    # Normalize: 0 for random, 1 for perfect
    score = (bac - base_bac) / sp.maximum(eps, (1 - base_bac))
    return score 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def binary_logloss(p, y):
    epsilon = 1e-15
    p = sp.maximum(epsilon, p)
    p = sp.minimum(1-epsilon, p)
    res = sum(y * sp.log(p) + sp.subtract(1, y) * sp.log(sp.subtract(1, p)))
    res *= -1.0/len(y)
    return res 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def logloss(p, y):
    epsilon = 1e-15
    p = sp.maximum(epsilon, p)
    p = sp.minimum(1-epsilon, p)
    ll = sum(y*sp.log(p) + sp.subtract(1,y)*sp.log(sp.subtract(1,p)))
    ll = ll * -1.0/len(y)
    return ll

# B. Apply hash trick of the original csv row
# for simplicity, we treat both integer and categorical features as categorical
# INPUT:
#     csv_row: a csv dictionary, ex: {'Lable': '1', 'I1': '357', 'I2': '', ...}
#     D: the max index that we can hash to
# OUTPUT:
#     x: a list of indices that its value is 1 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def bac_metric (solution, prediction, task='binary.classification'):
    ''' Compute the normalized balanced accuracy. The binarization and 
    the normalization differ for the multi-label and multi-class case. '''
    # Convert to 2d if necessary
    solution = np.array(solution, ndmin=2)
    if solution.shape[1] == 1:
        solution = solution.T
    prediction = np.array(prediction, ndmin=2)
    if prediction.shape[1] == 1:
        prediction = prediction.T
    # Carry on
    label_num = solution.shape[1]
    score = np.zeros(label_num)
    bin_prediction = binarize_predictions(prediction, task)
    [tn,fp,tp,fn] = acc_stat(solution, bin_prediction)
    # Bounding to avoid division by 0
    eps = 1e-15
    tp = sp.maximum (eps, tp)
    pos_num = sp.maximum (eps, tp+fn)
    tpr = tp / pos_num # true positive rate (sensitivity)
    if (task != 'multiclass.classification') or (label_num==1):
        tn = sp.maximum (eps, tn)
        neg_num = sp.maximum (eps, tn+fp)
        tnr = tn / neg_num # true negative rate (specificity)
        bac = 0.5*(tpr + tnr)
        base_bac = 0.5     # random predictions for binary case
    else: 
        bac = tpr
        base_bac = 1./label_num # random predictions for multiclass case
    bac = mvmean(bac)     # average over all classes
    # Normalize: 0 for random, 1 for perfect
    score = (bac - base_bac) / sp.maximum(eps, (1 - base_bac))
    return score 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def pac_metric (solution, prediction, task='binary.classification'):
    ''' Probabilistic Accuracy based on log_loss metric. 
    We assume the solution is in {0, 1} and prediction in [0, 1].
    Otherwise, run normalize_array.''' 
    debug_flag=False
    [sample_num, label_num] = solution.shape
    if label_num==1: task='binary.classification'
    eps = 1e-15
    the_log_loss = log_loss(solution, prediction, task)
    # Compute the base log loss (using the prior probabilities)    
    pos_num = 1.* sum(solution) # float conversion!
    frac_pos = pos_num / sample_num # prior proba of positive class
    the_base_log_loss = prior_log_loss(frac_pos, task)
    # Alternative computation of the same thing (slower)    
    # Should always return the same thing except in the multi-label case
    # For which the analytic solution makes more sense
    if debug_flag:
        base_prediction = np.empty(prediction.shape)
        for k in range(sample_num): base_prediction[k,:] = frac_pos
        base_log_loss = log_loss(solution, base_prediction, task)  
        diff = np.array(abs(the_base_log_loss-base_log_loss))
        if len(diff.shape)>0: diff=max(diff)
        if(diff)>1e-10: 
            print('Arrggh {} != {}'.format(the_base_log_loss,base_log_loss))
    # Exponentiate to turn into an accuracy-like score.
    # In the multi-label case, we need to average AFTER taking the exp 
    # because it is an NL operation
    pac = mvmean(np.exp(-the_log_loss)) 
    base_pac = mvmean(np.exp(-the_base_log_loss))
    # Normalize: 0 for random, 1 for perfect    
    score = (pac - base_pac) / sp.maximum(eps, (1 - base_pac))
    return score 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def log_loss(solution, prediction, task = 'binary.classification'):
    ''' Log loss for binary and multiclass. '''
    [sample_num, label_num] = solution.shape
    eps = 1e-15
    
    pred = np.copy(prediction) # beware: changes in prediction occur through this
    sol = np.copy(solution)
    if (task == 'multiclass.classification') and (label_num>1):
        # Make sure the lines add up to one for multi-class classification
        norma = np.sum(prediction, axis=1)
        for k in range(sample_num):
            pred[k,:] /= sp.maximum (norma[k], eps) 
        # Make sure there is a single label active per line for multi-class classification
        sol = binarize_predictions(solution, task='multiclass.classification')
        # For the base prediction, this solution is ridiculous in the multi-label case
    
    # Bounding of predictions to avoid log(0),1/0,...
    pred = sp.minimum (1-eps, sp.maximum (eps, pred))
    # Compute the log loss    
    pos_class_log_loss = - mvmean(sol*np.log(pred), axis=0)
    if (task != 'multiclass.classification') or (label_num==1):
        # The multi-label case is a bunch of binary problems.
        # The second class is the negative class for each column.
        neg_class_log_loss = - mvmean((1-sol)*np.log(1-pred), axis=0)
        log_loss = pos_class_log_loss + neg_class_log_loss
        # Each column is an independent problem, so we average.
        # The probabilities in one line do not add up to one.
        # log_loss = mvmean(log_loss) 
        # print('binary {}'.format(log_loss))
        # In the multilabel case, the right thing i to AVERAGE not sum
        # We return all the scores so we can normalize correctly later on
    else:
        # For the multiclass case the probabilities in one line add up one.
        log_loss = pos_class_log_loss
        # We sum the contributions of the columns.
        log_loss = np.sum(log_loss) 
        #print('multiclass {}'.format(log_loss))
    return log_loss 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def predict(self, X):
        prediction = self.predict_method(X)
        # Calibrate proba
        if self.task != 'regression' and self.postprocessor!=None:
            prediction = self.postprocessor.predict_proba(prediction)
        # Keep only 2nd column because the second one is 1-first
        if self.target_num==1 and len(prediction.shape)>1 and prediction.shape[1]>1:
            prediction = prediction[:,1]
        # Make sure the normalization is correct
        if self.task=='multiclass.classification':
            eps = 1e-15
            norma = np.sum(prediction, axis=1)
            for k in range(prediction.shape[0]):
                prediction[k,:] /= sp.maximum(norma[k], eps)
        return prediction 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def logloss(y_true, y_predicted):
    epsilon = 1e-6
    y_predicted = sp.maximum(epsilon, y_predicted)
    y_predicted = sp.minimum(1 - epsilon, y_predicted)
    ll = log_loss(y_true, y_predicted)
    return ll 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def build_optics(SetOfObjects, epsilon):

    """
    Builds OPTICS ordered list of clustering structure
    
    SetofObjects: Instantiated and prepped instance of 'setOfObjects' class
    epsilon: Determines maximum object size that can be extracted. Smaller epsilons
        reduce run time.

    """

    for point in SetOfObjects._index:
        if not SetOfObjects._processed[point]:
            expandClusterOrder(SetOfObjects, point, epsilon) 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def set_reach_dist(SetOfObjects, point_index, epsilon):

    """
    Sets reachability distance and ordering. This function is the primary workhorse of
    the OPTICS algorithm.
    
    SetofObjects: Instantiated and prepped instance of 'setOfObjects' class
    epsilon: Determines maximum object size that can be extracted. Smaller epsilons
        reduce run time. (float)

    """
    
    row = [SetOfObjects.data[point_index,:]]
    indices = np.argsort(row)
    distances = np.sort(row)

    if scipy.iterable(distances):

        unprocessed = indices[(SetOfObjects._processed[indices] < 1)[0].T]
        rdistances = scipy.maximum(distances[(SetOfObjects._processed[indices] < 1)[0].T],
            SetOfObjects._core_dist[point_index])
        SetOfObjects._reachability[unprocessed] = scipy.minimum(
            SetOfObjects._reachability[unprocessed], rdistances)

        if unprocessed.size > 0:
            return unprocessed[np.argsort(np.array(SetOfObjects._reachability[
                unprocessed]))[0]]
        else:
            return point_index
    else:
        return point_index 

# 需要導入模塊: import scipy [as 別名]
# 或者: from scipy import maximum [as 別名]
def my_logloss(act, pred):
    epsilon = 1e-15
    pred = K.maximum(epsilon, pred)
    pred = K.minimum(1 - epsilon, pred)
    ll = K.sum(act * K.log(pred) + (1 - act) * K.log(1 - pred))
    ll = ll * -1.0 / K.shape(act)[0]

    return ll