chribsen

from __future__ import division
import numpy as np
from sklearn.cluster import DBSCAN, KMeans
import psycopg2

from collections import defaultdict
import folium

EARTH_CIRCUMFERENCE = 6378137     # earth circumference in meters
colors = ['green', 'red', 'yellow', 'blue', 'black', 'white', 'gray', 'pink', 'cloud']

chribsen

import psycopg2
import psycopg2.extras
from collections import defaultdict


conn_dtu = psycopg2.connect(<connstring>)
cur_dtu = conn_dtu.cursor(cursor_factory=psycopg2.extras.DictCursor)

cur_dtu.execute("""SELECT user_a, user_b FROM derived_friend_list""")

chribsen

from sklearn.cross_validation import cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import MultinomialNB
import psycopg2
import psycopg2.extras
from collections import Counter
from sklearn.feature_selection import VarianceThreshold
from sklearn.feature_selection import RFECV
from sklearn import metrics
from sklearn.cross_validation import KFold, StratifiedKFold

chribsen

import psycopg2

conn_dtu = psycopg2.connect('connstring')
cur_dtu = conn_dtu.cursor()

cur_dtu.execute("select user_id, array_agg(country_id) FROM derived_countries_visited where country_id != 53 group by user_id")

lookup = {}

for each in cur_dtu.fetchall():

chribsen

# (latitude, longitude)
# This is a newer polygon, that bounds DK
dk_polygon = [
(58.44773280389084, 10.3271484375),
(56.51101750495214, 6.591796875),
(55.02802211299252, 7.6904296875),
(54.470037612805754, 12.12890625),
(55.23528803992295, 12.7496337890625),
(55.912272930063615, 12.7001953125),
(56.07510136019262, 12.6068115234375)]

chribsen

from __future__ import division
import numpy as np
from sklearn.cluster import DBSCAN, KMeans
from sklearn.preprocessing import StandardScaler
from data import points
import psycopg2
import matplotlib.pyplot as plt
import sys
from collections import defaultdict
import math, json

chribsen

import requests, json
import time


# Places token
token = '<my_token>'
params = {'access_token': token,
          'center': ','.join([str(55.622534), str(12.080729)]),
          'distance': 10000,
          'type': 'place',

chribsen

import requests, json
import time

# Places token
token = '<my_token>'

params = {'key': token,
	'location': ','.join([str(55.622534),str(12.080729)]),
	'radius': 10000}

chribsen

import psycopg2
from itertools import groupby

conn_dtu = psycopg2.connect("<connstring>")
cur_dtu = conn_dtu.cursor()

cur_dtu.execute("select user_a, user_b, meeting_array from temp_friend_meetings where met_consecutive_days is null")

for idx, each in enumerate(cur_dtu.fetchall()):
    meeting_vector = each[2]

chribsen

-- This SELECT statement counts how many days a pair of users have had at least 1 co-occurence and then bins them by day.
-- Used for visualization.

select s, sum(t.cou) from generate_series(0,10) as s left join
  (select user_a, user_b, count(*) as cou from derived_friend_list_days where nr_of_occurences > 0 group by user_a, user_b) as t
  on t.cou = s
  group by s;