5) calculatemedian_latlong.py

__author__ = 'Shweta'

import csv
import glob
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from datetime import date, timedelta, datetime
from pylab import scatter, show, title, xlabel, ylabel, plot, contour
import re
import os, time
import datetime
from collections import defaultdict
import itertools
import math
import numpy
from math import radians, cos, sin, asin, sqrt

############## This script calculates the median values for all the latitude and longitude for each unique BSSID and writes to a file.
def median(lst):
    return numpy.mean(numpy.array(lst))


def haversine(lon1, lat1, lon2, lat2):
    """
    Calculate the great circle distance between two points
    on the earth (specified in decimal degrees)
    """
    # convert decimal degrees to radians
    lon1, lat1, lon2, lat2 = map(radians, [lon1, lat1, lon2, lat2])
    # haversine formula
    dlon = lon2 - lon1
    dlat = lat2 - lat1
    a = sin(dlat / 2) ** 2 + cos(lat1) * cos(lat2) * sin(dlon / 2) ** 2
    c = 2 * asin(sqrt(a))
    metr = 6367 * c * 1000
    return metr


fz1 = open("bssidmappingfile.csv", "w", encoding="utf8")
cz1 = csv.writer(fz1)
cz1.writerow(["BSSID","Longitude", "Latitude"])

################### euclidean
subbud = pd.read_csv("mergedbssid_final.csv")

bs = subbud.BSSID.unique()
elat1 = subbud.Latitude.tolist()
elong1 = subbud.Longitude.tolist()

minpts = 3

for i, v in enumerate(bs):
    # t=eud[eud['BSSID']==v]
    t = subbud[subbud['BSSID'] == v]  # find all matches for BSSID.
    vlat = t.Latitude
    vlong = t.Longitude
    clat1 = vlat.astype(float)
    clat11 = clat1.tolist()

    clong1 = vlong.astype(float)
    clong11 = clong1.tolist()

    ##############trying median

    if (len(clat11) > minpts and len(clong11) > minpts):
        clat = median((clat11))
        clong = median((clong11))
        cz1.writerow([bs[i], clong, clat])  # appending not found.
fz1.close()