import os

rtdir = '/srv/ftp/hummingbird/2021/07/21'
#rtdir = os.getcwd()


files_read = list()
for cdir, _,  files in os.walk(rtdir):
    for f in files:
        if f.endswith('.json'):
            files_read.append(os.path.join(cdir, f))



import json

fcontents = dict()

for f in files_read:
    with open(f) as ff:
        fcontents[f] = json.load(ff)

def compute_2d_scores(cbbs):
    locs = list()
    scores = list()
    n_scores = 0
    for cbb in cbbs:
        if len(cbb['scores']) > 0:
            n_scores+=1
            first_box = cbb['boxes'][0]
            first_score = cbb['scores'][0]

            x_cent = np.mean(first_box[0::2])
            y_cent = np.mean(first_box[1::2])
            locs.append([x_cent, y_cent])
            scores.append(first_score)

    center = np.average(locs, weights=scores, axis=0)
    stddev = np.average(np.linalg.norm(center - locs,axis=1),weights=scores)

    return stddev, scores





data = {'file':list(), 'stddev':list(),'weights':list()}
for fname, contents in fcontents.items():
    if len(contents) > 0:
        data['file'].append(fname)
        sdev, sc = compute_2d_scores(contents)
        data['stddev'].append(sdev)
        data['weights'].append(np.average(sc))


import pandas as pd


df = pd.DataFrame(data)
fil = df.loc[(df['weights'] > 0.4) & (df['stddev'] > 400) ]