sadimanna

def prcurve(y,pred):
    P = []
    R = []
    thresholds = np.arange(0.0,1.0+0.01,0.01)
    for th in thresholds:
        P.append(precision(y,pred,th))
        R.append(recall(y,pred,th))
    plt.figure(figsize=(10,10))
    plt.plot(R,P,linewidth=2)
    plt.xlim(0.0, 1.0)

sadimanna

def bootstrap_metric(y, pred, classes, metric='auc',bootstraps = 100, fold_size = 1000):
    statistics = np.zeros((len(classes), bootstraps))
    if metric=='AUC':
        metric_func = roc_auc_score
    if metric=='Sensitivity':
        metric_func = sensitivity
    if metric=='Specificity':
        metric_func = specificity
    if metric=='Accuracy':
        metric_func = get_accuracy

sadimanna

# class_labels should contain names of both the classes
def plot_confusion_matrix(y_true,y_pred,class_labels):
    cm = np.zeros((2,2))
    cm[0,0] = np.sum((y_true==1) & (y_pred>0.5)) #TP
    cm[0,1] = np.sum((y_true==0) & (y_pred>0.5)) #FP
    cm[1,0] = np.sum((y_true==1) & (y_pred<0.5)) #FN
    cm[1,1] = np.sum((y_true==0) & (y_pred<0.5)) #TN
    cm_sum = np.sum(cm, axis=1, keepdims=True)
    cm_perc = cm / cm_sum.astype(float) * 100
    annot = np.empty_like(cm).astype(str)

sadimanna

def plot_perf_metrics_errbars(y,pred,class_labels):
    metric_dfs = get_confidence_intervals(y,pred,class_labels)
    metrics = list(metric_dfs.keys())
    fig,axs = plt.subplots(len(metrics),1,sharey=True)
    for i in range(len(metrics)):
        ci = metric_dfs[metrics[i]][['Mean '+metrics[i]+' (CI 5%-95%)']].values[0]
        ci_mean,ci_ints = ci[0].split(' ')
        ci_mean = float(ci_mean)
        ci_min,ci_max = list(map(float,ci_ints.strip('()').split('-')))
        ci_err = (ci_max-ci_min)/2

sadimanna

def get_performance_metrics(y, pred, class_labels, tp=TP, tn=TN, fp=FP,fn=FN,
                            acc=accuracy, spec=specificity, sens=sensitivity, 
                            ppv=ppv, npv=npv, auc=auc_score, f1=fscore, 
                            prevalence=prevalence, thresholds=[]):
    if len(thresholds) != len(class_labels):
        thresholds = [.5] * len(class_labels)
		
    func_dict = locals()
    func_keys = list(func_dict.keys())
    columns = [""]

sadimanna

y = np.array([]).reshape((0,NUM_CLASSES))
pred = np.array([]).reshape((0,NUM_CLASSES))

for i in range(NUM_ITERS):
    X,y_true = DATAGEN.__getitem__(i)
    if y_true.shape[1]!=NUM_CLASSES:
        y = np.append(y,to_categorical(y_true,num_classes=NUM_CLASSES),axis=0)
    
    y_pred = model(X)
    pred = np.append(pred,y_pred,axis=0)

sadimanna

def get_roc_curve(gt, pred, target_names):
    for i in range(len(target_names)):
        curve_function = plot_roc_curve
        auc_roc = auc_score(gt[:, i], pred[:, i])
        label = str(target_names[i]) + " AUC: %.3f " % auc_roc
        xlabel = "False positive rate"
        ylabel = "True positive rate"
        a, b, _ = curve_function(gt[:, i], pred[:, i])
        plt.figure(1, figsize=(7, 7))
        plt.plot([0, 1], [0, 1], 'k--')

sadimanna

int i, j; 
char filename[] = "Input_Image.bmp"; 
int data = 0, offset, bpp = 0, width, height; 
long bmpsize = 0, bmpdataoff = 0; 
int** image; 
int temp = 0; 

// Reading the BMP File 
FILE* image_file; 
image_file = fopen(filename, "rb"); 

sadimanna

// Creating the Histogram 
int hist[256]; 

for (i = 0; i < 256; i++) 
	hist[i] = 0; 

for (i = 0; i < height; i++) 
	for (j = 0; j < width; j++) 
		hist[image[i][j]] += 1; 

sadimanna

// Finding number of 
// non-zero occurrences 
int nodes = 0; 
for (i = 0; i < 256; i++) 
{ 
	if (hist[i] != 0) 
		nodes += 1; 
}