added tv2news strategy

server/nightr/app.py

@@ -21,6 +21,7 @@ strategies = {
     "steam": (1.0, steam.probability),
     "australia": (1.0, miloStrats.australiaStrat),
     "camera": (1.0, miloStrats.camImgStrat),
+    "tv2news": (1.0, miloStrats.tv2newsStrat)
 }
 
 

server/nightr/strategies/miloStrats.py

@@ -1,9 +1,11 @@
 from datetime import datetime
+import requests
 
 import cv2
 from pytz import timezone
 
 from ..util import Context, Prediction
+#from server.nightr.util import Context, Prediction
 
 
 def camImgStrat(context : Context) -> Prediction:
@@ -25,16 +27,37 @@ def camImgStrat(context : Context) -> Prediction:
 
 def australiaStrat(context : Context) -> Prediction:
     """
-    Time in Australia
+    Using time in Australia
     """
     australia = timezone('Australia/Melbourne')
     t = datetime.now().astimezone(australia)
     hour = t.hour
     p = Prediction()
     if hour > 22 or hour < 6:
-        p.probability = 1.0
-        p.reasons.append('It\'s day-time in Australia')
-    else:
         p.probability = 0.0
         p.reasons.append('It\'s night-time in Australia')
+    else:
+        p.probability = 1.0
+        p.reasons.append('It\'s day-time in Australia')
     return p
+
+def tv2newsStrat(context : Context) -> Prediction:
+    r = requests.get('http://mpx.services.tv2.dk/api/latest')
+    data = r.json()
+    publish_dates = [(x['pubDate'])//1000 for x in data][:10]
+    delta_times = []
+    for i in range(len(publish_dates)):
+        if i == 0 : continue
+        delta_times.append(publish_dates[i-1] - publish_dates[i])
+
+    avg_delta = 0
+    for d in delta_times:
+        avg_delta += d
+    avg_timestamp = avg_delta // len(delta_times) // 60
+    p = Prediction()
+    print('average time between articles on tv2:', avg_timestamp, 'minutes')
+    p.probability = 1.0 if avg_timestamp > 50 else 0.0
+    p.reasons.append('There were ' + ('few' if avg_timestamp > 50 else 'many') + ' recent articles on TV2 News')
+    print(p.reasons[0])
+    return p
+

server/nightr/strategies/parking_aarhus_1430.json

@@ -0,0 +1 @@
+{"help": "https://portal.opendata.dk/api/3/action/help_show?name=datastore_search", "success": true, "result": {"include_total": true, "resource_id": "2a82a145-0195-4081-a13c-b0e587e9b89c", "fields": [{"type": "int", "id": "_id"}, {"type": "text", "id": "date"}, {"type": "text", "id": "garageCode"}, {"type": "int4", "id": "totalSpaces"}, {"type": "int4", "id": "vehicleCount"}], "records_format": "objects", "records": [{"_id": 1, "date": "2019/04/06 14:30:01", "garageCode": "NORREPORT", "totalSpaces": 80, "vehicleCount": 61}, {"_id": 2, "date": "2019/04/06 14:30:01", "garageCode": "SCANDCENTER", "totalSpaces": 1240, "vehicleCount": 1033}, {"_id": 6, "date": "2019/04/06 14:30:01", "garageCode": "SALLING", "totalSpaces": 700, "vehicleCount": 575}, {"_id": 7, "date": "2019/04/06 14:30:01", "garageCode": "DOKK1", "totalSpaces": 1000, "vehicleCount": 0}, {"_id": 8, "date": "2019/04/06 14:30:01", "garageCode": "Navitas", "totalSpaces": 449, "vehicleCount": 208}, {"_id": 9, "date": "2019/04/06 14:30:01", "garageCode": "NewBusgadehuset", "totalSpaces": 105, "vehicleCount": 101}, {"_id": 3, "date": "2019/04/06 14:30:01", "garageCode": "BRUUNS", "totalSpaces": 953, "vehicleCount": 598}, {"_id": 4, "date": "2019/04/06 14:30:01", "garageCode": "MAGASIN", "totalSpaces": 378, "vehicleCount": 361}, {"_id": 5, "date": "2019/04/06 14:30:01", "garageCode": "KALKVAERKSVEJ", "totalSpaces": 210, "vehicleCount": 278}, {"_id": 10, "date": "2019/04/06 14:30:01", "garageCode": "Urban Level 1", "totalSpaces": 319, "vehicleCount": 99}, {"_id": 11, "date": "2019/04/06 14:30:01", "garageCode": "Urban Level 2+3", "totalSpaces": 654, "vehicleCount": 170}], "_links": {"start": "/api/3/action/datastore_search?resource_id=2a82a145-0195-4081-a13c-b0e587e9b89c", "next": "/api/3/action/datastore_search?offset=100&resource_id=2a82a145-0195-4081-a13c-b0e587e9b89c"}, "total": 11}}

server/nightr/strategies/strat_utils.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import urllib.request
-
+import json
+import requests
 
 def determine_month():
     ds = pd.read_excel(urllib.request.urlopen('https://sundogbaelt.dk/wp-content/uploads/2019/04/trafiktal-maaned.xls'))
@@ -12,3 +13,10 @@ def determine_month():
     last_year_total = sum(ds['Total'][amount_of_cur_year+1:amount_of_cur_year+13])
 
     return ((12/(last_year_total//cur_year_total))+1), cur_year_total, last_year_total
+
+
+
+def write_json(url, data_name, time):
+    r = requests.get(url)
+    with open(f"{data_name}_{time}.json", 'w') as f:
+        json.dump(r.json(), f)

server/nightr/strategies/svm_strat.py

@@ -0,0 +1,44 @@
+from sklearn import svm
+from sklearn.externals import joblib
+import requests
+import glob
+import json
+import numpy as np
+
+
+from server.nightr.strategies.strat_utils import write_json
+
+
+def find_data(time):
+    write_json("https://portal.opendata.dk/api/3/action/datastore_search?resource_id=2a82a145-0195-4081-a13c-b0e587e9b89c", "parking_aarhus", time)
+
+def load_data():
+
+    X = []
+    Y = []
+
+    for filename in glob.glob("parking_aarhus*"):
+        p_class = '2330' in filename
+
+        with open(filename) as file:
+            data = json.load(file)
+
+        records = data['result']['records']
+        frequencies = [house['vehicleCount'] / house['totalSpaces'] for house in records]
+        X.append(frequencies)
+        Y.append(int(p_class))
+
+    return np.array(X), np.array(Y)
+
+def train():
+    X, Y = load_data()
+    classifier = svm.SVC(C=10, gamma=0.01, probability=True)
+    classifier.fit(X, Y)
+    joblib.dump(classifier, "nightness_classifier.pkl")
+
+def predict(X):
+    classifier = joblib.load("nightness_classifier.pkl")
+    prob = classifier.predict_proba(X)
+    return prob[0, 1]
+
+train()