tool.py

import numpy as np
from sklearn.preprocessing import scale
import ctypes
import joblib
import statsmodels.tsa.api as smt
import random
import json

def label_one_left(labels):
    ret = []
    for lab in labels:
        if lab != 1:
            ret.append(0)
        else:
            ret.append(1)
    return ret

def print_label_sta(labels):
    sta = {}
    n = 0
    for lab in labels:
        if lab not in sta:
            sta[lab] = 1
        else:
            sta[lab] += 1
        n += 1
    for xkey in sta:
        print("lab:" + str(xkey) + ", n=" + str(sta[xkey]) + ", possession:" + str(sta[xkey]/n))

def load_model(modelfile):
    return joblib.load(modelfile)

def save_json(entity, path):
    f = open(path, 'w')
    json.dump(entity, f)
    f.close()

def load_json(path):
    f = open(path, 'r')
    ret = json.load(f)
    f.close()
    return ret

def save_joblib(entity, path):
    f = open(path, 'wb')
    joblib.dump(entity, f)
    f.close()

def load_joblib(path):
    f = open(path, 'rb')
    ret = joblib.load(f)
    f.close()
    return ret 

def quality_poor(seq, nrepeat=7):
    curNum = -1
    sameInRow = 1
    for x in seq:
        if x != curNum:
            sameInRow = 1
            curNum = x
        else:
            sameInRow = sameInRow + 1
        
        if sameInRow >= nrepeat:
            return True

    return False

def scale_by(featsets, scale_factors):
    std_feats = []
    npfeats = np.array(featsets)
    np_sf = np.array(scale_factors)
    for one in npfeats:
        featbuf = (one - np_sf[0]) / np_sf[1]
        std_feats.append(featbuf)
    return std_feats

def decrease100(rris):
    pnn100 = 0
    for i in range(1, len(rris)):
        if (rris[i] - rris[i - 1]) < 100:
            pnn100 += 1
    return pnn100 / (len(rris) - 1)

def serial_dscp(ser):
    ret = []
    #mean
    ret.append(np.mean(ser))#0,1
    #max
    smax = np.max(ser)
    ret.append(float(smax))#1,2
    #min
    smin = np.min(ser)
    ret.append(float(smin))#2,3
    #dist
    ret.append(float(smax - smin))#3,4
    #std
    ret.append(np.std(ser))#4,5
    #median
    ret.append(np.median(ser))#5,6

    return ret

def get_z_serial(ser, avg, std, maskval=None):
    ret = []
    for i in range(0, len(ser)):
        if ser[i] != maskval:
            ret.append((ser[i] - avg) / std)
        else:
            ret.append(maskval)

    return ret

def auto_corr_ser(dat, nlag, maskval=-999999):
    subsec = []
    begmasklen = 0
    for one in dat:
        if one != maskval:
            subsec.append(one)
        else:
            begmasklen += 1
            
    autoreg = smt.stattools.acf(subsec, nlags=nlag - begmasklen)
    ret = [maskval] * begmasklen
    ret.extend(autoreg)
    return ret

def adj_diff(dat):
    ret = []
    for i in range(1, len(dat)):
        ret.append(dat[i] - dat[i - 1])
    return ret

def diff_rms(dat):
    diff = []
    for i in range(1, len(dat)):
        diff.append((dat[i] - dat[i - 1])**2)
    dsum = 0
    for j in range(0, len(diff)):
        dsum += diff[j]
    dsum = dsum / len(dat)
    return (dsum ** 0.5)

def arrs_xtd_paras(arrs):
    long_arr = []
    for arr in arrs:
        long_arr.extend(arr)
    return np.mean(long_arr), np.std(long_arr)

def full_distance(rris):
    ret = 0
    for i in range(1, len(rris)):
        ret += np.abs(rris[i] - rris[i - 1])
    return ret

def scale(mat):
    avgs = []
    stds = []
    results = []
    ncase = len(mat)
    nfeat = len(mat[0])
    for j in range(0, nfeat):
        vals = []
        for i in range(0, ncase):
            vals.append(mat[i][j])
        avgs.append(np.mean(vals))
        xstd = np.std(vals)
        if xstd == 0:
            xstd = 1
        stds.append(xstd)
    
    for r in range(0, ncase):
        row = []
        for c in range(0, nfeat):
            row.append((mat[r][c] - avgs[c]) / stds[c])
        results.append(row)
    return results, avgs, stds

#tar high not included
def binarilize(tar_low, tar_high, dat):
    ret = []
    for one in dat:
        if tar_low <= one < tar_high:
            ret.append(1)
        else:
            ret.append(0)
    return ret

def multiple_split(feats, labs2d, test_size):
    xlen = len(feats)
    idx = list(range(0, xlen))
    ntest = int(xlen * test_size)
    test_idx = random.sample(idx, ntest)
    ny = len(labs2d)
    
    X = []
    Xt = []
    y = []
    yt = []
    
    for i in range(0, ny):
        y.append([])
        yt.append([])
    
    for i in range(0, xlen):
        if i in test_idx:
            Xt.append(feats[i])
            for j in range(0, ny):
                yt[j].append(labs2d[j][i])
        else:
            X.append(feats[i])
            for k in range(0, ny):
                y[k].append(labs2d[k][i])
                
    return X, Xt, y, yt

def linear_soomth(src, mask=-1):
    for i in range(0, len(src)):
        if src[i] == mask:
            begi=-1
            endi=-1
            
            #search backward
            for j in range(i-1, -1, -1):
                if src[j] != mask:
                    begi = j
                    break

            #search forward
            for k in range(i+1, len(src), 1):
                if src[k] != mask:
                    endi = k
                    break
            
            if begi != mask and endi != mask:
                full_stride = endi - begi
                loc_stride = i - begi
                stepval = (src[endi] - src[begi]) / full_stride
                src[i] = src[begi] + (stepval * loc_stride)
            elif begi == mask and endi != mask:
                src[i] = src[endi]
            elif begi != mask and endi == mask:
                src[i] = src[begi]
    return src
        

def gen_rrix211():
    x = [730,720,790,810,760,690,710,660,670,690,720,750,\
        750,800,820,760,710,730,780,750,760,790,1000,830,860,880,880,\
        820,850,850,880,830,860,880,840,830,890,910,860,880,890,810,\
        830,830,810,820,860,820,850,880,820,870,900,850,890,920,890,\
        910,920,870,940,950,880,920,930,900,940,950,930,950,980,970,\
        980,950,920,950,960,890,910,940,900,920,910,870,880,890,860,\
        860,860,830,820,860,830,880,910,910,870,930,940,900,940,970,\
        910,890,910,730,720,790,810,760,690,710,660,670,690,720,750,\
        750,800,820,760,710,730,780,750,760,790,860,830,860,880,880,\
        820,850,850,880,830,860,880,840,830,890,910,860,880,890,810,\
        830,830,810,820,860,820,850,880,820,870,900,850,890,920,890,\
        910,920,870,940,950,880,920,930,900,940,950,930,950,980,970,\
        980,950,920,950,960,890,910,940,900,920,910,870,880,890,860,\
        860,860,830,820,860,830,880,910,910,870,930,940,1200,940,970,\
        910,890,910,1000]

    return x

if __name__ == "__main__":
    # print(len(gen_rrix211()))
    x = [-1, 800, 900, -1, -1, 1200, -1, 1500, -1]
    xsmooth = linear_soomth(x)
    print(xsmooth)
    z = 0