.gitignore

@@ -3,5 +3,5 @@ _*
 !__init__.py
 *.pyc
 logs/
-*data/
+data/
 plots/*

Dockerfile

@@ -1,10 +0,0 @@
-FROM alpine:edge
-
-ADD ["requirements.txt", "/"]
-RUN echo "http://dl-cdn.alpinelinux.org/alpine/edge/testing/" >> /etc/apk/repositories && \
-	apk add --update --no-cache libpng freetype python3 libstdc++ libxml2 libxslt openblas geos libc-dev && \
-	apk add --update --no-cache --virtual .build-deps libpng-dev freetype-dev g++ python3-dev openblas-dev libxml2-dev libxslt-dev && \
-	pip3 --no-cache-dir install -r requirements.txt && \
-	apk del .build-deps && \
-	rm requirements.txt
-USER guest

Readme.md

@@ -1,20 +0,0 @@
-# Geogame Log Analyzer
-
-## Setup (webui)
-
-* First setup a reverse proxy (see *frontend/* for a reference with traefik)
-* Start the framework
-	* `docker-compose up -d`
-	* Default config expects a docker network connection to traefik
-		* name: 'traefik_net'
-		* created when using the traefik reference from *frontend/*
-		* `docker network inspect traefik_net`
-
-## log data
-
-### set mtime of gpx files to the first date:
-
-```
-for i in */*; do touch -m -d "$(head -n 15 $i|grep time | head -n 1 |cut -d">" -f 3|cut -d"<" -f1)" $i; done
-for i in */; do touch -m -d "$(head -n 15 $i/*.gpx|grep time | head -n 1 |cut -d">" -f 3|cut -d"<" -f1)" $i; done
-```

analysis/analyzers/analyzer/default.py

@@ -1,233 +0,0 @@
-import logging
-from collections import defaultdict, OrderedDict
-
-from analysis.util import json_path
-from . import Result, LogSettings, Analyzer, ResultStore
-
-
-class WhitelistAnalyzer(Analyzer): #TODO
-	__name__ = "WhiteList"
-
-	def __init__(self, settings: LogSettings) -> None:
-		super().__init__(settings)
-		self.key = settings.custom["whitelist"]["key"]
-		self.filter_objs = settings.custom["whitelist"]["objs"]
-		self.valid_entries = settings.custom["whitelist"]["valid"]
-		self.blocked = False
-
-	def result(self, store: ResultStore, name=None) -> None:
-		store.add(Result(type(self), {"blocked": self.blocked}, name=name))
-
-	def process(self, entry: dict) -> bool:
-		if entry[self.settings.type_field] in self.filter_objs:
-			if not json_path(entry, self.key) in self.valid_entries:
-				self.blocked = True
-		return self.blocked
-
-
-class LocationAnalyzer(Analyzer):
-	"""
-	store spatial log entries
-	"""
-	__name__ = "Location"
-	log = logging.getLogger(__name__)
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-		self.entries = []
-
-	def result(self, store: ResultStore, **kwargs) -> None:
-		#self.log.debug(len(self.entries))
-		store.add(Result(type(self), list(self.entries), name=kwargs['name']))
-
-	def process(self, entry: dict) -> bool:
-		if entry[self.settings.type_field] in self.settings.spatials:
-			self.entries.append(entry)
-		# self.log.debug(len(self.entries))
-		return False
-
-
-class LogEntryCountAnalyzer(Analyzer):
-	#TODO: flexibler: z.b. min/max lat/long
-	"""
-	count occurrences of log entry types
-	"""
-	__name__ = "LogEntryCount"
-
-	def result(self, store: ResultStore) -> None:
-		store.add(Result(type(self), dict(self.store)))
-
-	def process(self, entry: dict) -> bool:
-		self.store[entry[self.settings.type_field]] += 1
-		return False
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-		self.store = defaultdict(lambda: 0)
-
-
-class LogEntrySequenceAnalyzer(Analyzer):
-	"""
-	store sequence of all log entry types
-	"""
-	__name__ = "LogEntrySequence"
-
-	def result(self, store: ResultStore) -> None:
-		store.add(Result(type(self), list(self.store)))
-
-	def process(self, entry: dict) -> bool:
-		entry_type = entry[self.settings.type_field]
-		self.store.append(entry_type)
-		return False
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-		self.store = []
-
-
-class ActionSequenceAnalyzer(LogEntrySequenceAnalyzer):
-	"""
-	find sequence of non-spatial log entry types
-	"""
-	__name__ = "ActionSequenceAnalyzer"
-
-	def process(self, entry: dict) -> bool:
-		entry_type = entry[self.settings.type_field]
-		if entry_type in self.settings.spatials:
-			return False
-		self.store.append(entry_type)
-		return False
-
-
-class CategorizerStub(Analyzer):
-	"""
-	generate a new Category in a ResultStore
-	"""
-
-	def process(self, entry: dict) -> bool:
-		raise NotImplementedError()
-
-	__name__ = "Categorizer"
-
-	def result(self, store: ResultStore, name=None) -> None:
-		print(name if name else self.key)
-		store.new_category((name, self.key) if name else self.key)
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-		self.key = "default"
-
-class SimpleCategorizer(CategorizerStub):
-	def process(self, entry):
-		return False
-
-
-class Store(Analyzer):
-	"""
-	Store the entire log
-	"""
-	__name__ = "Store"
-
-	def result(self, store: ResultStore) -> None:
-		store.add(Result(type(self), list(self.store)))
-
-	def process(self, entry: dict) -> bool:
-		self.store.append(entry)
-		return False
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-		self.store: list = []
-
-
-class ProgressAnalyzer(Analyzer):
-	"""track spatial and ingame progress"""
-	__name__ = "ProgressAnalyzer"
-
-	def __init__(self, settings: LogSettings) -> None:
-		super().__init__(settings)
-		self.spatial = OrderedDict()
-		self.board = OrderedDict()
-
-	def result(self, store: ResultStore) -> None:
-		store.add(Result(type(self), {"spatials": self.spatial, "boards": self.board}))
-
-	def process(self, entry: dict) -> bool:
-		if entry[self.settings.type_field] in self.settings.spatials:
-			self.spatial[entry["timestamp"]] = 				{
-					'timestamp': entry['timestamp'],
-					'coordinates': json_path(entry, "location.coordinates"),
-					'accuracy': entry['accuracy']
-				}
-		if entry[self.settings.type_field] in self.settings.boards:
-			self.board[entry["timestamp"]] = entry
-		return False
-
-
-class MetaDataAnalyzer(Analyzer):
-	"""collect metadata"""
-	__name__ = "MetaDataAnalyzer"
-
-	def result(self, store: ResultStore, name=None) -> None:
-		store.add(Result(type(self), dict(self.store)))
-
-	def process(self, entry: dict) -> bool:
-		if not "metadata" in self.settings.custom:
-			return False
-		for mdata in self.settings.custom["metadata"]:
-			key = self.settings.custom["metadata"]
-			if key in entry:
-				self.store[mdata] = json_path(entry, key)
-
-	def __init__(self, settings: LogSettings) -> None:
-		super().__init__(settings)
-		self.store = {}
-
-
-def write_logentry_count_csv(LogEntryCountCSV, store, render, analyzers):
-	global cat, data, lines, csvfile
-	LogEntryCountCSV.summary = None
-	for cat in store.get_categories():
-		data = store.get_category(cat)
-		render(analyzers.LogEntryCountAnalyzer, data, name=cat)
-	if LogEntryCountCSV.summary:
-		headers = []
-		lines = []
-		for name in LogEntryCountCSV.summary:
-			data = LogEntryCountCSV.summary[name]
-			for head in data:
-				if not head in headers:
-					headers.append(head)
-			line = [name]
-			for head in headers:
-				line.append(data[head]) if head in data else line.append(0)
-			lines.append(line)
-		import csv
-
-		with open('logentrycount.csv', 'w', newline='') as csvfile:
-			writer = csv.writer(csvfile, quoting=csv.QUOTE_NONE)
-			writer.writerow(["name"] + [h.split(".")[-1] for h in headers])
-			for line in lines:
-				writer.writerow(line)
-
-
-def write_simulation_flag_csv(store):
-	global csvfile, result, i
-	from datetime import datetime
-	import json
-	json.dump(store.serializable(), open("simus.json", "w"), indent=2)
-	with open("simus.csv", "w") as csvfile:
-		csvfile.write("instanceconfig,log,simu,answered,universe_state,selected_actions,timestamp,time\n")
-		for key in store.get_store():
-			csvfile.write("{}\n".format(key))
-			for result in store.store[key]:
-				csvfile.write(",{}\n".format(result.name))
-				for i in result.get():
-					csvfile.write(",,{},{},{},{},{},{}\n".format(
-						i['answers']['@id'],
-						i['answers']['answered'],
-						len(i['answers']['universe_state']) if i['answers']['universe_state'] else 0,
-						len(i['selected_actions']) if i['selected_actions'] else 0,
-						i['timestamp'],
-						str(datetime.fromtimestamp(i['timestamp'] / 1000))
-					))

analysis/analyzers/render/__init__.py

@@ -1,26 +0,0 @@
-import logging
-from typing import List
-
-from analysis.analyzers.analyzer import ResultStore
-from .. import Result
-
-logger = logging.getLogger(__name__)
-
-class Render:
-	result_types = []
-
-	def render(self, results: List[Result], name=None) -> [str]:
-		raise NotImplementedError()
-
-	def render_store(self, store: ResultStore, name=None) -> str:
-		logging.getLogger(__name__).warning("using default implementation!")
-		for category in store.get_categories():
-			self.render(store.get_category(category), name=name)
-
-	def filter(self, results: List[Result]):
-		if len(self.result_types) == 0:
-			return results
-		return filter(self.__filter__, results)
-
-	def __filter__(self, obj: Result):
-		return obj.analysis() in self.result_types

analysis/analyzers/render/default.py

@@ -1,165 +0,0 @@
-import copy
-import json
-import logging
-from typing import List
-
-import datetime
-import matplotlib.pyplot as plt
-
-from analysis.analyzers import LogEntryCountAnalyzer
-from analysis.util.meta_temp import GEOJSON_COORDINATES, GEOJSON_PATTERN, KML_PATTERN
-from . import Render, Result
-from analysis.analyzers import LocationAnalyzer
-
-log = logging.getLogger(__name__)
-
-
-class PrintRender(Render):
-	def render(self, results: List[Result], name=None):
-		print("\t" + "\n\t".join([str(r) for r in results]))
-
-
-class JSONRender(Render):
-	def render(self, results: List[Result], name=None):
-		print(json.dumps([r.get() for r in self.filter(results)], indent=1))
-
-
-class SpatialRender:
-	result_types = [LocationAnalyzer]
-
-
-class TrackRender(SpatialRender, Render):
-
-	def render(self, results: List[Result], name=None):
-		data = []
-		log.debug(results)
-		for result in self.filter(results):
-			if len(result.get()) > 0:
-				data.append(
-					[[entry['location']['coordinates'][1], entry['location']['coordinates'][0]] for entry in
-					 # TODO: configurable
-					 result.get()])
-		dumps = json.dumps(data)
-		with open("track_data.js", "w") as out:
-			out.write("tracks=" + dumps + ";")
-		return dumps
-
-
-def format_time(ts):
-	return datetime.datetime.fromtimestamp(ts / 1000).strftime("%Y-%m-%dT%H:%M:%S.%f")
-
-
-class KMLRender(SpatialRender, Render):
-
-	def render(self, results: List[Result], name=None):
-		files = []
-		for result in self.filter(results):
-			times = ["<when>{time}</when>".format(time=format_time(entry["timestamp"])) for entry in result.get()]
-			coords = [
-				"<gx:coord>{long} {lat} 0.0</gx:coord>"
-					.format(
-					lat=entry['location']['coordinates'][1],
-					long=entry['location']['coordinates'][0])
-				for entry in result.get()
-			]
-			if name:
-				filename = str(name) + ".kml"
-			else:
-				filename = str(result.name) + ".kml"
-			print(filename)
-			with open(filename, "w") as out:
-				out.write(
-					KML_PATTERN.format(name=str(result.name), coordinates="\n".join(coords), when="\n".join(times)))
-			#with open(filename + ".json", "w") as out: #FIXME: why am I here??
-			#	json.dump(result.get(), out, indent=1)
-			files.append(filename)
-		return files
-
-
-class GeoJSON(SpatialRender, Render):
-	template = {
-	"type": "FeatureCollection",
-	"features": [
-		{
-			"type": "Feature",
-			"properties": {},
-			"geometry": {
-				"type": "LineString",
-				"coordinates": []
-			}
-		}
-	]
-}
-
-	def make_geojson(self, src):
-		coordinates = []
-		times = []
-		for location in src:
-			#print(location)
-			coordinates.append(location["location"]["coordinates"])
-			times.append(location["timestamp"])
-		template = copy.deepcopy(self.template)
-		template["features"][0]["properties"] = {"times": times}
-		template["features"][0]["geometry"]["coordinates"] = coordinates
-		return template
-
-	def render(self, results: List[Result], name=None) -> [str]:
-		files = []
-		for result in self.filter(results):
-			if name:
-				filename = str(name) + ".geojson"
-			else:
-				filename = str(result.name) + ".geojson"
-			json = self.make_geojson(result.get())
-			with open(filename, "w") as out:
-				json.dump(self.template, out, indent=1)
-			files.append(filename)
-		return files
-
-
-class HeatMapRender(TrackRender):
-	weight = 0.01
-
-	def render(self, results: List[Result], name=None):
-		raw = super(HeatMapRender, self).render(results)
-		data = []
-		for session in json.loads(raw):
-			data += [(entry[0], entry[1], self.weight) for entry in session]
-		dumps = json.dumps(data)
-		with open('heat_data.js', 'w') as out:
-			out.write("coords = " + dumps + ";")
-		return dumps
-
-
-class LogEntryCountAnalyzerPlot(Render):
-	result_types = [LogEntryCountAnalyzer]
-
-	def render(self, results: List[Result], name=None):
-		raw_data = list(self.filter(results))[0].get()
-		print(raw_data)
-		labels = []
-		data = []
-		for x in sorted(raw_data.items()):
-			labels.append(str(x[0]).split(".")[-1])
-			data.append(x[1])
-		plt.bar(range(len(data)), list(data))
-		plt.xticks(range(len(data)), labels, rotation="vertical")
-		plt.tight_layout()
-
-		name = "plots/{}.png".format(name)
-		plt.savefig(name)
-		plt.cla()
-		plt.clf()
-		plt.close()
-
-
-class LogEntryCountCSV(Render):
-	result_types = [LogEntryCountAnalyzer]
-	summary = None
-
-	def render(self, results: List[Result], name=None):
-		if self.summary is None:
-			return
-		for result in self.filter(results):
-			raw_data = result.get()
-			self.summary[name] = raw_data

analysis/analyzers/render/wip.py

@@ -1,395 +0,0 @@
-import json
-
-import numpy as np
-
-import analysis.analyzers
-from analysis import analyzers
-from analysis.util.geo import calc_distance
-
-
-def time_distribution(store):
-	# json.dump(store.serializable(), open("new.json", "w"), indent=1)
-
-	keys = [
-		"simu",
-		"question",
-		"image",
-		"audio",
-		"video",
-		"other",
-		"map"
-	]
-	import matplotlib.pyplot as plt
-
-	# results = []
-
-	places = defaultdict(list)
-
-	for log in store.get_all():
-		result = defaultdict(lambda: 0)
-		for i in log.get()['track']:
-			duration = i['properties']['end_timestamp'] - i['properties']['start_timestamp']
-			result[i['properties']['activity_type']] += duration
-		print(json.dumps(result, indent=4))
-		total = sum(result.values())
-		print(total)
-		percentage = defaultdict(lambda: 0)
-		minutes = defaultdict(lambda: 0)
-		for i in result:
-			percentage[i] = result[i] / total
-			minutes[i] = result[i] / 60_000
-		print(json.dumps(percentage, indent=4))
-		if not 'error' in result:
-			# places[log.get()['instance']].append(percentage)
-			places[log.get()['instance']].append(minutes)
-
-	for place in places:
-		places[place] = sorted(places[place], key=lambda item: item['map'])
-
-	dummy = [0] * len(keys)
-	results = []
-	sites = []
-	from util.meta_temp import CONFIG_NAMES
-
-	for i in places:
-		for j in places[i]:
-			ordered = []
-			for k in keys:
-				ordered.append(j[k])
-			results.append(ordered)
-		results.append(dummy)
-		sites.append(CONFIG_NAMES[i] if i in CONFIG_NAMES else "---")
-
-	size = len(results)
-	ind = np.arange(size)
-	width = 0.9
-	print(results)
-	data = list(zip(*results))
-	print(data)
-	lines = []
-	bottom = [0] * len(results)
-	for i in range(0, len(data)):
-		lines.append(plt.bar(ind, data[i], bottom=bottom, width=width)[0])
-		for k, x in enumerate(data[i]):
-			bottom[k] += x
-	plt.legend(lines, keys)
-	plt.title(", ".join(sites))
-	plt.show()
-
-
-# size = len(results)
-# ind = np.arange(size)
-# width = 0.9
-# print(results)
-# data = list(zip(*results))
-# print(data)
-# lines = []
-# bottom = [0] * len(results)
-# for i in range(0, len(data)):
-#	lines.append(plt.bar(ind, data[i], bottom=bottom, width=width)[0])
-#	for k, x in enumerate(data[i]):
-#		bottom[k] += x
-# plt.legend(lines, keys)
-# plt.title("Zwei Spiele in Filderstadt (t1=237min; t2=67min)")
-# plt.show()
-
-# json.dump(store.serializable(), open("new.json", "w"), indent=1)
-
-
-from collections import defaultdict
-import matplotlib.pyplot as plt
-from analysis.util.meta_temp import CONFIG_NAMES
-
-keys = [
-	"simu",
-	"question",
-	"image",
-	"audio",
-	"video",
-	"other",
-	"map",
-	# "error"
-]
-
-loc_keys = [
-	"question",
-	"image",
-	"audio",
-	"video"
-]
-
-
-def get_data(store, relative_values=True, sort=True, show_errors=False):
-	places = defaultdict(list)
-
-	for log in store.get_all():
-		if not log.analysis() == analyzers.ActivityMapper:
-			continue
-		result = defaultdict(lambda: 0)
-		for i in log.get()['track']:
-			duration = i['properties']['end_timestamp'] - i['properties']['start_timestamp']
-			result[i['properties']['activity_type']] += duration
-		print(json.dumps(result, indent=4))
-		total = sum(result.values())
-		print(total)
-		percentage = defaultdict(lambda: 0)
-		minutes = defaultdict(lambda: 0)
-		for i in result:
-			percentage[i] = result[i] / total
-			minutes[i] = result[i] / 60_000
-		print(json.dumps(percentage, indent=4))
-		if not 'error' in result or show_errors:
-			if relative_values:
-				places[log.get()['instance']].append(percentage)
-			else:
-				places[log.get()['instance']].append(minutes)
-	if sort:
-		for place in places:
-			places[place] = sorted(places[place], key=lambda item: item['map'])
-	return places
-
-
-whitelist = ['16fc3117-61db-4f50-b84f-81de6310206f', '5e64ce07-1c16-4d50-ac4e-b3117847ea43',
-			 '90278021-4c57-464e-90b1-d603799d07eb', 'ff8f1e8f-6cf5-4a7b-835b-5e2226c1e771']
-
-
-def get_data_distance(store, relative_values=True, sort=True, show_errors=False):
-	places = defaultdict(list)
-
-	for log in store.get_all():
-		if not log.analysis() == analyzers.ActivityMapper:
-			continue
-		result = defaultdict(lambda: 0)
-		for i in log.get()['track']:
-			coords = i['coordinates']
-			if len(coords) > 1:
-				distance = calc_distance(coords)
-				result[i['properties']['activity_type']] += distance
-		total = sum(result.values())
-		percentage = defaultdict(lambda: 0)
-		for i in result:
-			if not total == 0:
-				percentage[i] = result[i] / total
-		if not 'error' in result or show_errors:
-			if relative_values:
-				places[log.get()['instance']].append(percentage)
-			else:
-				places[log.get()['instance']].append(result)
-	if sort:
-		for place in places:
-			places[place] = sorted(places[place], key=lambda item: item['map'])
-	return places
-
-
-def get_all_data(store, sort=False, relative=True):
-	places = defaultdict(list)
-	simu_distribution = defaultdict(lambda: 0)
-	# divisiors = {"time":60_000, "space":1000000}
-	for log in store.get_all():
-		if not log.analysis() == analyzers.ActivityMapper:
-			continue
-		result = defaultdict(lambda: defaultdict(lambda: 0))
-		for i in log.get()['features']:
-			coords = i["geometry"]['coordinates']
-			print(coords)
-			if len(coords) > 1:
-				distance = calc_distance(json.dumps(i["geometry"]))
-			else:
-				distance = 0.0
-			result["space"][i['properties']['activity_type']] += distance
-			duration = i['properties']['end_timestamp'] - i['properties']['start_timestamp']
-			result["time"][i['properties']['activity_type']] += duration
-		total_space = sum(result["space"].values())
-		total_time = sum(result["time"].values())
-		percentage = defaultdict(lambda: defaultdict(lambda: 0))
-		total = defaultdict(lambda: defaultdict(lambda: 0))
-		for i in result["space"]:
-			if not total_space == 0:
-				percentage[i]["space"] = result["space"][i] / total_space
-			else:
-				percentage[i]["space"] = 0
-			if not total_time == 0:
-				percentage[i]["time"] = result["time"][i] / total_time
-			else:
-				percentage[i]["time"] = 0
-			for t in ("space", "time"):
-				# total[i][t] += (result[t][i] / divisiors[t])
-				total[i][t] += result[t][i]
-		print(percentage)
-		if not 'error' in result:
-			if relative:
-				value = percentage
-			else:
-				value = total
-			places[log.get()["properties"]['instance']].append(value)
-			simus = defaultdict(lambda: 0)
-			for item in log.get()["properties"]['boards']:
-				if item["extra_data"]["activity_type"] == "simu":
-					simus[item["board_id"]] += 1
-			simu_distribution[len(simus)] += 1
-
-	if sort:
-		for place in places:
-			places[place] = sorted(places[place], key=lambda item: item['map']['time'])
-	print(simu_distribution)
-	return places
-
-
-def stack_data(keys, places, type="space"):
-	divisiors = {"time": 60_000, "space": 1000}
-	# divisiors = {"time": 1, "space": 1}
-	dummy = [0] * len(keys)
-	results = []
-	sites = []
-	for i in sorted(places):
-		if not i in whitelist:
-			continue
-		place = sorted(places[i], key=lambda item: item['map'][type])
-		for j in place:
-			ordered = []
-			for k in keys:
-				if k in j:
-					ordered.append(j[k][type] / divisiors[type])
-				else:
-					ordered.append(0)
-			print(sum(ordered))
-			# if sum(ordered) > 0.9 and sum(ordered) < 4000 and sum(ordered)>10:
-			if sum(ordered) > 0.9 and sum(ordered) < 100:
-				# print(sum(ordered), 1-sum(ordered))
-				# if sum(ordered)<1:
-				#	ordered[-2] = 1-sum(ordered[:-2], ordered[-1])
-				results.append(ordered)
-		results.append(dummy)
-		sites.append(CONFIG_NAMES[i] if i in CONFIG_NAMES else "---")
-	return results, sites
-
-
-def plot_data(places, keys):
-	results, sites = stack_data(keys, places)
-	dpi = 86.1
-	plt.figure(figsize=(1280 / dpi, 720 / dpi))
-	size = len(results)
-	print("{} elements total".format(size))
-	ind = np.arange(size)
-	width = 1
-	# print(results)
-	data = list(zip(*results))
-	# print(data)
-	lines = []
-	bottom = [0] * size
-	plt.ticklabel_format(useMathText=False)
-	for i in range(0, len(data)):
-		lines.append(plt.bar(ind, data[i], bottom=bottom, width=width)[0])
-		for k, x in enumerate(data[i]):
-			bottom[k] += x
-	plt.legend(lines, keys)
-	plt.title(", ".join(sites))
-	# plt.show()
-	dpi = 86
-	plt.savefig("space_abs_{}.png".format(size), dpi=dpi, bbox_inches="tight")
-
-
-colors = {
-	"simu": "blue",
-	"question": "orange",
-	"image": "green",
-	"audio": "red",
-	"video": "purple",
-	"other": "brown",
-	"map": "violet",
-	# "error":"grey",
-	"tasks": "olive",
-}
-markers = [".", "o", "x", "s", "*", "D", "p", ",", "<", ">", "^", "v", "1", "2", "3", "4"]
-
-
-def plot_time_space(time_data, space_data, keys):
-	# assuming time_data and space_data are in same order!
-	marker = 0
-	for id in time_data:
-		for k in keys:
-			for i in range(len(time_data[id])):
-				print(time_data[id][i][k], space_data[id][i][k])
-				plt.plot(time_data[id][i][k], space_data[id][i][k], color=colors[k], marker=markers[marker])
-		marker += 1
-	plt.show()
-
-
-# plt.cla()
-# plt.clf()
-# plt.close()
-
-def group_locationbased_tasks(data):
-	for id in data:
-		for log in data[id]:
-			loc = {"space": 0, "time": 0}
-			for k in log:
-				if k in loc_keys:
-					for i in ["space", "time"]:
-						loc[i] += log[k][i]
-			log["tasks"] = loc
-
-
-def plot_time_space_rel(combined, keys):
-	groups = defaultdict(list)
-	keys = list(keys)
-	keys.remove("other")
-	for i in loc_keys:
-		keys.remove(i)
-	keys.append("tasks")
-	ids = []
-	group_locationbased_tasks(combined)
-	for k in keys:
-		for id in sorted(combined):
-			if id not in whitelist:
-				continue
-			if not id in ids:
-				ids.append(id)
-			group = 0.0
-			count = 0
-			for item in combined[id]:
-				if k in item:
-					time = item[k]["time"] / 1000
-					distance = item[k]["space"]
-					if time > 0:
-						group += (distance / time)
-						count += 1
-					else:
-						print("div by zero", distance, time)
-			if count > 0:
-				groups[k].append(group / count)
-			else:
-				groups[k].append(0.0)
-	print(ids)
-	ind = np.arange(len(ids))
-	width = .7 / len(groups)
-	print(ind)
-	print(json.dumps(groups, indent=1))
-	bars = []
-	dpi = 200
-	plt.figure(figsize=(1280 / dpi, 720 / dpi))
-	fig, ax = plt.subplots()
-	for k in groups:
-		print(groups[k])
-		if not len(groups[k]):
-			groups[k].append(0)
-		ind = ind + (width)
-		bars.append(ax.bar((ind + width * len(groups) / 2), groups[k], width, color=colors[k]))
-	ax.set_xticks(ind + width / 2)
-	ax.set_xticklabels(list([CONFIG_NAMES[i] if i in CONFIG_NAMES else "---" for i in ids]))
-	kmh = plt.hlines((1 / 3.6), 0.3, 4.2, linestyles="dashed", label="1 km/h", linewidths=1)
-	plt.legend(bars + [kmh], keys + [kmh.get_label()])
-	print(combined.keys(), ids)
-	print([CONFIG_NAMES[i] if i in CONFIG_NAMES else "---" for i in ids])
-	# plt.show()
-	dpi = 200
-	plt.savefig("speed2_2019.png", dpi=dpi)
-
-
-
-
-
-# plot_time_space_rel(temporal_data_rel, spatial_data_rel, keys)
-
-# plot_data(combined, keys)
-# plot_data(get_data_distance(store,relative_values=False), keys)

analysis/filter_todo/pre_filter.py

@@ -1,90 +0,0 @@
-import os
-from zipfile import ZipFile
-import sqlite3
-import json
-from collections import defaultdict
-
-
-def get_json(filename):
-	log = []
-	id = None
-	with ZipFile(filename) as zipf:
-		zipf.extract('instance_log.sqlite')
-		sql = sqlite3.connect('instance_log.sqlite')
-		cursor = sql.cursor()
-		for r in cursor.execute('SELECT json FROM log_entry;'):
-			entry = json.loads(r[0])
-			log.append(entry)
-			if id is None:
-				id = entry['instance_id']
-		sql.close()
-		os.remove('instance_log.sqlite')
-	return id, log
-
-
-def is_finished(log):
-	for entry in log:
-		if "action" in entry:
-			if "LogEntryInstanceAction" in entry["@class"] and entry["action"][
-				"@class"] == "de.findevielfalt.games.game2.instance.action.EndGameEnableAction" and entry['action'][
-				'enable']:
-				return True
-	return False
-
-
-def get_simus(log):
-	simus = defaultdict(lambda: 0)
-	order = []
-	actions = 0
-	for entry in log:
-		if "LogEntryQuestion" in entry["@class"]:
-			if "SimulationBoardData" in entry["answers"]["@class"]:
-				id = entry["answers"]["@id"]
-				simus[id] += 1
-				actions += 1 if entry['selected_actions'] else 0
-				if not id in order:
-					order.append(id)
-	return dict(simus), order, actions
-
-
-def simu_dist(simus):
-	dist = defaultdict(lambda: 0)
-	for instance in simus:
-		sim = simus[instance]
-		dist[len(sim)] += 1
-	return dist
-
-
-logs = {}
-finished = []
-simus = {}
-distribution = defaultdict(lambda: 0)
-finished_and_simu = defaultdict(list)
-files = {}
-actions_dist = defaultdict(list)
-with open('/home/clemens/git/ma/test/src') as src:
-	for line in src:
-		line = line.strip()
-		instance_id, log = get_json(line)
-		logs[instance_id] = log
-		files[instance_id] = line
-for id in logs:
-	simus[id] = get_simus(logs[id])
-	simu_count = len(simus[id][1])
-	distribution[simu_count] += 1
-	actions_dist[simus[id][2]].append(id)
-	if is_finished(logs[id]):
-		finished.append(id)
-		finished_and_simu[simu_count].append(id)
-print("total: ", len(logs))
-print("finished: ", len(finished))
-print("simu_dist: ", len(distribution), json.dumps(distribution, sort_keys=True))
-for i in sorted(finished_and_simu):
-	print("fin+sim" + str(i) + ": ", len(finished_and_simu[i]))
-for i in sorted(actions_dist):
-	print("actions: ", i, len(actions_dist[i]))
-print(json.dumps(actions_dist[4], sort_keys=True, indent=2))
-
-# print(finished_and_simu)
-# for instance in finished_and_simu:
-#	print(files[instance])

analysis/loaders/neocart.py

@@ -1,70 +0,0 @@
-import logging
-from datetime import datetime
-
-from lxml import etree
-
-from .loader import Loader
-
-log = logging.getLogger(__name__)
-
-NS = {'gpx':"http://www.topografix.com/GPX/1/1"}
-
-class NeoCartLoader(Loader):
-	def load(self, file: str):
-		src = open(file, "r")
-		parser = etree.XMLParser(recover=True)
-		tree = etree.parse(src, parser=parser)
-		self.entries = []
-		for point in tree.xpath("//gpx:trkpt", namespaces=NS):
-			try: 
-				self.entries.append(self.parse_point(point))
-			except ValueError as e:
-				print(e, etree.tostring(point, pretty_print=True).decode())
-				log.exception(e)
-	
-	def parse_point(self, point):
-		raw_lat = point.xpath("@lat")[0]
-		if raw_lat.count(".") > 1:
-			log.warning(f"recreate lat/lon from: {raw_lat}")
-			log.warn(etree.tostring(point, pretty_print=True).decode())
-			start_offset = 4
-			x = raw_lat[start_offset:].index(".")
-			offset = start_offset + x
-			raw_lon = raw_lat[offset:]
-			raw_lat = raw_lat[:offset]
-		else:
-			raw_lon = point.xpath("@lon")[0]
-		lat = float(raw_lat)
-		lon = float(raw_lon)
-		times = point.xpath("gpx:time",namespaces=NS)
-		assert len(times) == 1
-		time = times[0].text
-		dt = datetime.strptime(time, "%Y-%m-%dT%H:%M:%SZ")
-		timestamp = int(dt.timestamp() * 1000) # python3.6 has no timestamp_ns (yet)
-		events = point.xpath(".//gpx:event",namespaces=NS)
-		assert 0 <= len(events) <= 1
-		event = {}
-		if events:
-			event = dict(events[0].attrib)
-			if events[0].tail and events[0].tail.strip():
-				try:
-					# base case: trailing 'geoid="0"/>'
-					key, v = events[0].tail.strip().split("=")
-					value = v.split('"')[1]
-					event[key] = value
-				except:
-					event['__tail__'] = events[0].tail.strip()
-		
-		return {
-			"location": {
-				"type": "Point",
-				"coordinates": [lon, lat]
-			},
-			"timestamp": timestamp,
-			"event": event,
-			"type": event['message'] if event else "location"
-		}
-
-	def get_entry(self) -> object:
-		for i in self.entries:
-			yield i

analysis/log_analyzer.py

@@ -1,247 +0,0 @@
-import json
-import logging
-from typing import List
-
-from analysis import analyzers
-from analysis.analyzers import get_renderer, render
-from analysis.analyzers.analyzer import ResultStore
-from analysis.analyzers.analyzer.default import write_logentry_count_csv, write_simulation_flag_csv
-from analysis.analyzers.render import wip
-from analysis.analyzers.render.default import LogEntryCountCSV, KMLRender, GeoJSON
-from analysis.analyzers.render.wip import time_distribution, plot_data
-from analysis.analyzers.settings import LogSettings, load_settings, parse_settings
-from analysis.loaders import LOADERS
-from analysis.util.processing import grep, run_analysis, src_file
-from analysis.util.meta_temp import CONFIG_NAMES
-
-logging.basicConfig(format='%(levelname)s %(name)s:%(message)s', level=logging.DEBUG)
-log: logging.Logger = logging.getLogger(__name__)
-
-logging.getLogger('requests').setLevel(logging.WARN)
-logging.getLogger("urllib3").setLevel(logging.WARN)
-logging.getLogger("shapely").setLevel(logging.WARN)
-
-
-def urach_logs(log_ids, settings):
-	# return ["data/inst_{id}.{format}".format(id=log_id, format=settings.log_format) for log_id in log_ids]
-	return ["data/{id}.{format}".format(id=log_id, format=settings.log_format) for log_id in log_ids]
-
-
-if __name__ == '__main__':
-	settings = {}
-	log_ids_gf = []
-	# settings: LogSettings = load_settings("biogames2.json")
-	# log_ids_urach: List[str] = urach_logs([
-	# 	# "34fecf49dbaca3401d745fb467",
-	# 	#	"44ea194de594cd8d63ac0314be",
-	# 	#	"57c444470dbf88605433ca935c",
-	# 	#	"78e0c545b594e82edfad55bd7f",
-	# 	#	"91abfd4b31a5562b1c66be37d9",
-	# 	# "597b704fe9ace475316c345903",
-	# 	# "e01a684aa29dff9ddd9705edf8",
-	# 	"597b704fe9ace475316c345903",
-	# 	"e01a684aa29dff9ddd9705edf8",
-	# 	"fbf9d64ae0bdad0de7efa3eec6",
-	# 	# "fbf9d64ae0bdad0de7efa3eec6",
-	# 	"fe1331481f85560681f86827ec",  # urach
-	# 	# "fe1331481f85560681f86827ec"]
-	# 	"fec57041458e6cef98652df625",
-	# ]
-	# 	, settings)
-	# log_ids_gf = grep(["9d11b749c78a57e786bf5c8d28",  # filderstadt
-	# 				   "a192ff420b8bdd899fd28573e2",  # eichstätt
-	# 				   "3a3d994c04b1b1d87168422309",  # stadtökologie
-	# 				   "fe1331481f85560681f86827ec",  # urach
-	# 				   "96f6d9cc556b42f3b2fec0a2cb7ed36e"  # oberelsbach
-	# 				   ],
-	# 				  "/home/clemens/git/ma/test/src",
-	# 				  settings)
-	# log_ids = src_file("/home/clemens/git/ma/test/filtered_5_actions")
-
-	if False:
-		store: ResultStore = run_analysis(log_ids_gf, settings, LOADERS)
-	# store: ResultStore = run_analysis(log_ids, settings, LOADERS)
-
-	if False:
-		for r in get_renderer(analyzers.LocomotionActionAnalyzer):
-			r().render(store.get_all())
-	if False:
-		render(analyzers.LocationAnalyzer, store.get_all())
-	# print(json.dumps(store.serializable(), indent=1))
-	if False:
-		for cat in store.get_categories():
-			render(analyzers.ActivityMapper, store.get_category(cat), name=cat)
-		# render(analyzers.ProgressAnalyzer, store.get_all())
-
-	if False:
-		from analysis.analyzers.postprocessing import graph
-
-		g = graph.Cache(settings)
-		g.run(store)
-	if False:
-		# render(analyzers.SimulationOrderAnalyzer, store.get_all())
-		for cat in store.get_categories():
-			data = store.get_category(cat)
-			render(analyzers.SimulationOrderAnalyzer, data, name=cat)
-	if False:
-		write_logentry_count_csv(LogEntryCountCSV, store, render, analyzers)
-	if False:
-		write_simulation_flag_csv(store)
-	if False:
-		time_distribution(store)
-
-	if False:
-		# spatial_data = get_data_distance(store,relative_values=False)
-		# temporal_data = get_data(store,relative_values=False)
-		# spatial_data_rel = get_data_distance(store,relative_values=True)
-		# temporal_data_rel = get_data(store,relative_values=True)
-		# temporal_data_rel = json.load(open("temporal_rel.json"))
-		# spatial_data_rel = json.load(open("spatial_rel.json"))
-		# import IPython
-		# IPython.embed()
-
-		# print(json.dumps(get_all_data(store)))
-		# json.dump(get_all_data(store), open("combined.json", "w"))
-		# combined = get_all_data(store, sort=True, relative=True)
-		# json.dump(combined, open("combined_rel.json", "w"))
-		# combined = json.load(open("combined_rel.json"))
-		combined = json.load(open("combined_total.json"))
-		# plot_time_space_rel(combined, keys)
-		plot_data(combined, wip.keys)
-
-	if False:
-
-		def store(x):
-			pass
-		settings: LogSettings = load_settings("../oeb_kml.json")
-		#log_ids = src_file("/app/log_data/oeb/oeb_2016_path")
-		log_ids = src_file("/app/log_data/oeb/oeb_paths")
-		#log_ids = log_ids[0:10]
-		print(log_ids)
-		store: ResultStore = run_analysis(log_ids, settings, LOADERS, ResultStore(key_index=1))
-		print("render")
-		kml = GeoJSON()
-		fields = store.get_categories()
-		artifacts = {key: kml.render(store.get_category(key)) for key in fields}
-		print(artifacts)
-		print("done")
-
-		def atrifact_to_length(filename):
-			g = json.load(open(filename))
-			from analysis.util.geo import calc_distance
-			return calc_distance(json.dumps(g), "features.0.geometry.coordinates")
-
-		def simplified_length(filename):
-			from analysis.util.geo import json_to_track,distance
-			g = json.load(open(filename))
-			track = json_to_track(json.dumps(g), "features.0.geometry.coordinates")
-			simplified = track.simplify(0.0002, preserve_topology=True)
-			from shapely.geometry import mapping
-			json.dump(mapping(simplified), open(f"{filename}.simplified.geojson","w"), indent=1)
-			return distance(simplified)
-
-		from collections import defaultdict
-
-		def get_lengths(artifacts, atrifact_to_length=atrifact_to_length):
-			stats = defaultdict(list)
-			for field in artifacts:
-				print(field, CONFIG_NAMES[field])
-				for i in artifacts[field]:
-					distance = atrifact_to_length(i)
-					warn = "\tLONG!" if distance > 10000 else "\tSHORT!" if distance < 1000 else ""
-					print(f"\t{i}\t{distance}{warn}")
-					stats[field].append(distance)
-			return stats
-
-		stats = get_lengths(artifacts)
-		import numpy as np
-
-		def quart_1(x):
-			return np.percentile(x, 25)
-		def quart_2(x):
-			return np.percentile(x, 50)
-		def quart_3(x):
-			return np.percentile(x, 75)
-		def quart_4(x):
-			return np.percentile(x, 100)
-
-		def print_stats(stats):
-			fns = [np.size, np.min, np.max, np.mean, np.median]#, quart_1, quart_2, quart_3, quart_4]
-			names = "\t".join([x.__name__ for x in fns] + ["id","name"])
-			print(names)
-			for i in stats:
-				stat = [f"{fn(stats[i]):.2f}" for fn in fns]
-				print("\t".join(stat + [i, CONFIG_NAMES[i]]))
-
-		def plot_stats(stats, filtered_stats, suffix=""):
-			import matplotlib.pyplot as plt
-			keys = sorted(stats.keys())
-			names = [CONFIG_NAMES[i] for i in keys]
-			values = [stats[i] for i in keys]
-			values_filtered = [filtered_stats[i] for i in keys]
-			fig, ax = plt.subplots()
-			ax.boxplot(values, labels=names, showfliers=False, showmeans=True, meanline=True)
-			fig.savefig(f"/app/log_data/oeb/plots/plot_raw{suffix}.png")
-			fig, ax = plt.subplots()
-			ax.boxplot(values_filtered, labels=names, showfliers=False, showmeans=True, meanline=True)
-			fig.savefig(f"/app/log_data/oeb/plots/plot_filtered{suffix}.png")
-			fig, ax = plt.subplots()
-			agg_data = values + values_filtered
-			agg_labels = names + [f"filtered(…{i[-4:]})" for i in names]
-			ax.boxplot(agg_data, labels=agg_labels, showfliers=False, showmeans=True, meanline=True)
-			fig.savefig(f"/app/log_data/oeb/plots/plot_combined{suffix}.png")
-
-		MIN = 1000
-		MAX = 100000
-
-		def filter(stats):
-			stats_filtered = defaultdict(list)
-			for i in stats:
-				stats_filtered[i] = [x for x in stats[i] if MIN < x < MAX]
-			return stats_filtered
-		stats_filtered = filter(stats)
-
-		stats_simple = get_lengths(artifacts, atrifact_to_length=simplified_length)
-		stats_filtered_simple = filter(stats_simple)
-
-		def summary(stats, stats_filtered, title):
-			print_stats(stats)
-			print(f"filter {MIN} < x < {MAX}")
-			print_stats(stats_filtered)
-			plot_stats(stats, stats_filtered, suffix=f"_{title}")
-
-		summary(stats, stats_filtered, "raw")
-		print("\nsimplified\n")
-		summary(stats_simple, stats_filtered_simple, "simplified")
-
-	if True:
-		settings: LogSettings = load_settings("time.json")
-		# log_ids = src_file("/app/log_data/oeb/oeb_2016_path")
-		log_ids = src_file("log_data/oeb/oeb_paths_host")
-		log_ids = src_file("/home/clemens/git/ma/test/src")
-		log_ids = src_file("/home/clemens/git/ma/project/log_data/neocartographer/index")
-		# log_ids = log_ids[0:10]
-		print(log_ids)
-		store: ResultStore = run_analysis(log_ids, settings, LOADERS, ResultStore(key_index=1))
-		results = {}
-		for cat in store.get_categories():
-			results[cat] = [result.get() for result in store.get_category(cat)]
-		with open("times_neo.json", "w") as out:
-			json.dump(results, out, indent=1)
-
-####################
-		#for cat in store.get_categories():
-		#	render(analyzers.ActivityMapper, store.get_category(cat), name=cat)
-
-# for analyzers in analyzers:
-#	if analyzers.name() in ["LogEntryCount", "ActionSequenceAnalyzer"]:
-#		print(json.dumps(analyzers.result(), indent=2))
-
-# for analyzers in analyzers:
-#	if analyzers.name() in ["BoardDuration"]:
-#		print(json.dumps(analyzers.result(), indent=2))
-#		print(analyzers.render())
-
-# coords = analyzers[1].render()
-# with open("test.js", "w") as out:
-#	out.write("coords = "+coords)

analysis/util/geo.py

@@ -1,33 +0,0 @@
-import json
-
-import pyproj
-from shapely.geometry import LineString, mapping
-from shapely.ops import transform
-from functools import partial
-
-from analysis.util import json_path
-
-
-def distance(track):
-	project = partial(
-		pyproj.transform,
-		pyproj.Proj(init='EPSG:4326'),
-		pyproj.Proj(init='EPSG:32633'))
-	return transform(project, track).length
-
-
-def json_to_track(geojson, path, load=True):
-	if load:
-		geojson = json.loads(geojson)
-	return LineString(json_path(geojson, path))
-
-
-def calc_distance(geojson: str, path="coordinates", load=True):
-	track = json_to_track(geojson, path, load)
-	return distance(track)
-
-
-def calc_distance_simplified(geojson, path="coordinates", load=True):
-	track = json_to_track(geojson, path, load)
-	simplified = track.simplify(0.0002, preserve_topology=True)
-	return distance(simplified)

analysis/util/output.py

@@ -1,28 +0,0 @@
-from datetime import datetime as dt
-
-SEP = "\",\""
-LS = "\""
-LE = "\""
-NL = LS + "\n" + LE
-
-
-
-def flat_dict_to_csv(data):
-	keys = set()
-	for i in data:
-		keys = keys.union(set(i.keys()))
-	keys = sorted(keys)
-	out = SEP.join(keys)
-	for i in data:
-		out += NL + SEP.join([escape(i.get(j, "")) for j in keys])
-	return LS + out + LE
-
-
-def escape(value):
-	val = str(value)
-	val = val.replace(".", ",")
-	return val
-
-def pretty_ts(timestamp, fmt="%Y-%m-%d %H:%M:%S"):
-	d = dt.fromtimestamp(int(timestamp)/1000.0)
-	return d.strftime(fmt)

analysis/util/processing.py

@@ -1,69 +0,0 @@
-import logging
-from typing import List
-
-from analysis.analyzers.analyzer import ResultStore, Analyzer
-from analysis.analyzers.settings import LogSettings
-
-log: logging.Logger = logging.getLogger(__name__)
-
-
-def process_log(logfile: str, settings: LogSettings, loaders) -> List[Analyzer]:
-	loader = loaders[settings.log_format]()
-	try:
-		loader.load(logfile)
-	except BaseException as e:
-		raise RuntimeError(e, logfile)
-	analyzers: List[Analyzer] = []
-	log.debug("build analyzers")
-	for analyzer in settings.analyzers:
-		analyzers.append(analyzer(settings))
-	log.debug("process entries")
-	for entry in loader.get_entry():
-		for analyzer in analyzers:
-			try:
-				if analyzer.process(entry):
-					break
-			except KeyError as e:
-				log.exception(e)
-	return analyzers
-
-
-def run_analysis(log_ids: list, settings, loaders, result_store=None):
-	if not result_store:
-		result_store = ResultStore()
-	store: ResultStore = result_store
-	for log_id in log_ids:
-		log.info("LOG_ID: "+ str(log_id))
-		for analysis in process_log(log_id, settings, loaders):
-			log.info("* Result for " + analysis.name())
-			analysis.result(store, name=log_id)
-	return store
-
-
-def load_ids(name: str):
-	log_ids = []
-	with open(name) as src:
-		for line in src:
-			line = line.strip()
-			log_ids.append(line)
-	return log_ids
-
-
-def grep(log_ids, source, settings):
-	logs = []
-	with open(source) as src:
-		lines = src.readlines()
-		for id in log_ids:
-			for line in lines:
-				if id in line:
-					logs.append(line.strip())
-	return logs
-
-
-def src_file(filename):
-	log_ids = []
-	with open(filename) as src:
-		for line in src:
-			line = line.strip()
-			log_ids.append(line)
-	return log_ids

analyzers/__init__.py

@@ -2,20 +2,18 @@ from typing import List
 
 from .analyzer import Analyzer, Result
 from .analyzer.biogames import BoardDurationAnalyzer, SimulationRoundsAnalyzer, ActivationSequenceAnalyzer, \
-	BiogamesCategorizer, ActivityMapper, BiogamesStore, InstanceConfig, SimulationOrderAnalyzer, SimulationCategorizer, \
+	BiogamesCategorizer, ActivityMapper, BiogamesStore, InstanceConfig, SimulationOrderAnalyzer, SimulationCategorizer
-	SimulationFlagsAnalyzer, GameField_InstanceCategorizer, BiogamesTasks, BiogamesDuration, GameFieldInstanceGroup
 from .analyzer.default import LogEntryCountAnalyzer, LocationAnalyzer, LogEntrySequenceAnalyzer, ActionSequenceAnalyzer, \
-	CategorizerStub, Store, ProgressAnalyzer, SimpleCategorizer, WhitelistAnalyzer
+	CategorizerStub, Store, ProgressAnalyzer
 from .analyzer.locomotion import LocomotionActionAnalyzer, CacheSequenceAnalyzer
 from .analyzer.mask import MaskSpatials
 from .render import Render
 from .render.biogames import SimulationRoundsRender, BoardDurationHistRender, BoardDurationBoxRender, \
 	ActivityMapperRender, StoreRender, SimulationOrderRender, SimulationGroupRender
 from .render.default import PrintRender, JSONRender, TrackRender, HeatMapRender, LogEntryCountAnalyzerPlot, \
-	LogEntryCountCSV, KMLRender, GeoJSON
+	LogEntryCountCSV
 from .render.locomotion import LocomotionActionRelativeRender, LocomotionActionAbsoluteRender, \
 	LocomotionActionRatioRender
-#from .render.wip import get_all_data, plot_time_space_rel
 
 __FALLBACK__ = PrintRender
 __MAPPING__ = {
@@ -42,7 +40,6 @@ __MAPPING__ = {
 	LocationAnalyzer: [
 		TrackRender,
 		HeatMapRender,
-		KMLRender,
 	],
 	ActivityMapper: [
 		ActivityMapperRender

analyzers/analyzer/__init__.py

@@ -2,17 +2,16 @@ import logging
 from collections import KeysView
 from typing import Type, Sized, Collection
 
-from analysis.analyzers.settings import LogSettings
+from analyzers.settings import LogSettings
 
 log: logging.Logger = logging.getLogger(__name__)
 
 
 class Result:
-	def __init__(self, analysis: Type, result: Sized, name: str = None):
+	def __init__(self, analysis: Type, result: Sized):
 		self.result = result
 		self.__analysis__ = analysis
 		log.debug("set" + str(len(self.result)))
-		self.name = name
 
 	def analysis(self):
 		return self.__analysis__
@@ -22,23 +21,19 @@ class Result:
 		return self.result
 
 	def __repr__(self):
-		return "<Result " + str(self.__analysis__) + ": " + str(type(self.result)) + " " + str(
+		return "<Result " + str(self.__analysis__) + ": " + str(type(self.result)) + " " + str(len(self.result)) + ">"
-			len(self.result)) + " for " + str(self.name) + ">"
 
 
 class ResultStore:
 	"""Store Results"""
 
-	def __init__(self, store_entry: Type[Collection] = list, store_action: callable = list.append, key_index=None) -> None:
+	def __init__(self, store_entry: Type[Collection] = list, store_action: callable = list.append) -> None:
 		self.store = {}
 		self.category = None
 		self.entry: Type[Collection] = store_entry
 		self.action: callable = store_action
-		self.key_index = key_index
 
 	def new_category(self, key) -> None:
-		if not self.key_index is None:
-			key = key[self.key_index]
 		self.category = key
 		if not key in self.store:
 			self.store[key] = self.entry()
@@ -71,11 +66,7 @@ class ResultStore:
 	def serializable(self):
 		values = {}
 		for key in self.store:
-			values[key] = [{
+			values[key] = [{"analysis": str(result.analysis()), "result": result.get()} for result in self.store[key]]
-				"analysis": str(result.analysis()),
-				"result": result.get(),
-				"name": result.name
-			} for result in self.store[key]]
 		return values
 
 
@@ -93,7 +84,7 @@ class Analyzer:
 		"""
 		raise NotImplementedError()
 
-	def result(self, store: ResultStore, name=None) -> None:
+	def result(self, store: ResultStore) -> None:
 		raise NotImplementedError()
 
 	def name(self) -> str:

analyzers/analyzer/biogames.py

@@ -3,8 +3,8 @@ from collections import defaultdict, namedtuple, OrderedDict
 from types import SimpleNamespace
 from typing import List, NamedTuple
 
-from analysis.util import json_path, combinate
+from util import json_path, combinate
-from analysis.util.download import download_board, get_board_data
+from util.download import download_board, get_board_data
 from . import Result, LogSettings, Analyzer, ResultStore
 from .default import CategorizerStub, Store
 
@@ -133,48 +133,6 @@ class BiogamesCategorizer(CategorizerStub):  # TODO: refactor
 		return False
 
 
-class GameField_InstanceCategorizer(CategorizerStub):  # TODO: refactor
-	__name__ = "BiogamesCategorizer"
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-
-	def process(self, entry: dict) -> bool:
-		if self.key is "default":
-			if entry[self.settings.type_field] in self.settings.custom['instance_start']:
-				try:
-					self.key = json_path(entry, self.settings.custom['instance_config_id']) + "_" + entry[self.settings.custom['instance_id']] + "_" + str(entry["timestamp"])
-				except KeyError as e:
-					print(entry)
-					raise e
-		return False
-
-
-class GameFieldInstanceGroup(Analyzer):
-	__name__ = "BiogamesGamefieldInstanceGroupAnalizer"
-
-	def __init__(self, settings: LogSettings):
-		super().__init__(settings)
-		self.metadata = None
-
-	def process(self, entry: dict) -> bool:
-		if not self.metadata:
-			if entry[self.settings.type_field] in self.settings.custom['instance_start']:
-				try:
-					self.metadata = {"instance_config_id": json_path(entry, self.settings.custom['instance_config_id']),
-									 "instance_id": entry[self.settings.custom['instance_id']],
-									 "timestamp": str(entry["timestamp"]),
-									 "player_group_name": entry['player_group_name']
-									 }
-				except KeyError as e:
-					print(entry)
-					raise e
-		return False
-
-	def result(self, store: ResultStore, **kwargs) -> None:
-		store.add(Result(type(self), self.metadata))
-
-
 class ActivityMapper(Analyzer):
 	__name__ = "ActivityMapper"
 	classes = {
@@ -182,16 +140,6 @@ class ActivityMapper(Analyzer):
 		"sequence.question.": "question",
 		"error": "error"
 	}
-	colors = {
-		"simu": "blue",
-		"question": "orange",
-		"image": "green",
-		"audio": "red",
-		"video": "purple",
-		"other": "brown",
-		"map": "violet",
-		"error": "grey"
-	}
 
 	def __init__(self, settings: LogSettings) -> None:
 		super().__init__(settings)
@@ -200,7 +148,6 @@ class ActivityMapper(Analyzer):
 		self.last_board = {}
 		self.last_board_type = "other"
 		self.last_coordinate = None
-		self.last_timestamp = None
 		self.tracks = []
 		self.track = None
 		self.instance_config_id: str = None
@@ -210,35 +157,29 @@ class ActivityMapper(Analyzer):
 
 		self.State: NamedTuple = namedtuple("State", ["sequence", "events", "track", "timestamp"])
 
-	def result(self, store: ResultStore, **kwargs) -> None:
+	def result_old(self, store: ResultStore) -> None:
-		for board in self.timeline:
+		instance_config_id = self.instance_config_id
-			if board[self.settings.type_field] in self.settings.boards:
+		for active_segment in self.store:  # active_segment → sequence or None (None → map active)
-				if board["extra_data"]["activity_type"] == "simu":
+			seq_data_url = "/game2/editor/config/{config_id}/sequence/{sequence_id}/".format(
-					board["image"] = "simu.png"
+				config_id=instance_config_id,
-					continue
+				sequence_id=active_segment.sequence,
-				try:
+			)
-					local_file = download_board(board["board_id"], self.instance_config_id, board["sequence_id"],
+			source = self.settings.source
-											self.settings.source)
+			seq_data = source._get(seq_data_url).json()
-					if local_file:
+			# TODO: use sequence names
-						board['image'] = local_file
+			logger.warning(seq_data)
-					else:
+			for event in active_segment.events:
-						raise ValueError
+				if event[self.settings.type_field] in self.settings.boards:
-				except Exception as e:
+					sequence_id = active_segment.sequence
-					board['image'] = "ERROR_FETCHING_FILE"
+					board_id = event["board_id"]
-					logger.error("error downloading board! %s %s %s", self.instance_config_id, board["sequence_id"],
+					local_file = download_board(board_id, instance_config_id, sequence_id, source)
-								 board["board_id"])
+					if local_file is not None:
-					logger.exception(e)
+						event["image"] = local_file[16:]
-			else:
+		store.add(Result(type(self), {"instance": instance_config_id, "store": [x._asdict() for x in self.store]}))
-				board["image"] = "map.png"
+
-		store.add(Result(type(self), {
+	def result(self, store: ResultStore) -> None:
-			"type": "FeatureCollection",
+
-			"features": self.tracks,
+		store.add(Result(type(self), {"instance": self.instance_config_id, "track": self.tracks, "boards": self.timeline}))
-			"properties": {
-				"instance": self.instance_config_id,
-				"boards": self.timeline,
-				"colors": self.colors,
-			},
-		}))
 
 	def process(self, entry: dict) -> bool:
 		if self.track is None:
@@ -262,15 +203,12 @@ class ActivityMapper(Analyzer):
 	def update_board_type(self, entry):
 		type = self.classify_entry(entry)
 		if not type == self.last_board_type:
-			self.add_track(activity_type=self.last_board_type, end_timestamp=entry['timestamp'])
+			self.add_track(activity_type=self.last_board_type,end_timestamp=entry['timestamp'])
 			self.last_board_type = type
 
 	def classify_entry(self, entry):
 		entry_type = entry[self.settings.type_field]
 		if self.filters.end(entry):
-			data = {"extra_data": {"activity_type": "map"}, "coordinate": self.new_coordinate()}
-			data.update(entry)
-			self.timeline.append(data)
 			return "map"
 		if not entry_type in self.settings.boards:
 			return self.last_board_type
@@ -281,9 +219,9 @@ class ActivityMapper(Analyzer):
 				return self.classes[pattern]
 		if board_data['has_video']:
 			return "video"
-		elif board_data['has_audio']:
+		elif  board_data['has_audio']:
 			return "audio"
-		elif board_data['has_image']:
+		elif  board_data['has_image']:
 			return "image"
 		return "other"
 
@@ -292,120 +230,20 @@ class ActivityMapper(Analyzer):
 
 	def add_location(self, entry):
 		coordinates = json_path(entry, self.settings.custom['coordinates'])
-		self.track["geometry"]['coordinates'].append(coordinates)
+		self.track['coordinates'].append(coordinates)
-		self.track['properties']['coordTimes'].append(entry['timestamp']) #FIXME 
 		self.last_coordinate = coordinates
-		self.last_timestamp = entry['timestamp']
 
 	def add_track(self, **props):
 		self.track['properties'].update(props)
-		if "activity_type" in self.track['properties'] and self.track['properties']['activity_type'] in self.colors:
-			if not "stroke" in self.track['properties']:
-				self.track['properties']['stroke'] = self.colors[self.track['properties']['activity_type']]
 		self.tracks.append(self.track)
 		self.track = self.new_track(props['end_timestamp'])
 		if self.last_coordinate:
-			self.track["geometry"]['coordinates'].append(self.last_coordinate)
+			self.track['coordinates'].append(self.last_coordinate)
-			self.track['properties']['coordTimes'].append(self.last_timestamp)
 
 	def new_track(self, timestamp):
-		return {"type": "Feature", "geometry": {"type": "LineString", "coordinates": []}, "properties": {'start_timestamp': timestamp, 'coordTimes': []}}
+		return {"type": "LineString", "coordinates": [], "properties": {'start_timestamp': timestamp}}
 
 
-class BiogamesDuration(Analyzer):
-	__name__ = "BiogamesDuration"
-
-	def __init__(self, settings: LogSettings) -> None:
-		super().__init__(settings)
-		self.first = None
-		self.last = None
-		self.sequences = defaultdict(list)
-		self.filters = SimpleNamespace()
-		self.filters.start = lambda entry: combinate(self.settings.custom["sequences2"]["start"], entry)
-		self.filters.end = lambda entry: combinate(self.settings.custom["sequences2"]["end"], entry)
-		self.sequence = None
-		self.sequence_start = None
-		self.cache = "None"
-
-	def process(self, entry: dict) -> bool:
-		if not self.first:
-			self.first = entry['timestamp']
-		self.last = entry['timestamp']
-		if not self.sequence and self.filters.start(entry):
-			self.sequence = entry['sequence_id']
-			self.sequence_start = entry['timestamp']
-		elif self.sequence and self.filters.end(entry):
-			self.sequences[f"{self.cache}+{self.sequence}"].append((self.sequence_start, entry['timestamp']))
-			self.sequences[f"only+{self.sequence}"].append((self.sequence_start, entry['timestamp']))
-			self.sequence = None
-			self.sequence_start = 0
-			self.cache = "None"
-		if entry['@class'] in self.settings.sequences['start']:
-			if entry['cache']:
-				self.cache = entry['cache']['@id']
-			else:
-				self.cache = "None"
-		return False
-
-	def result(self, store: ResultStore, name=None) -> None:
-		results = {"start": self.first, "end": self.last, "duration": self.last - self.first}
-		for sid in self.sequences:
-			seq = self.sequences[sid]
-			#print([end-start for start,end in seq])
-			results[f"sequence_{sid}_duration"] = sum([end-start for start,end in seq])
-		store.add(Result(type(self), results))
-
-
-class BiogamesTasks(Analyzer):
-	__name__ = "BiogamesTasks"
-	DATA_CLASSES = ("de.findevielfalt.games.game2.instance.log.entry.LogEntryQuestion", )
-	BOARD_CLASSES = ("de.findevielfalt.games.game2.instance.log.entry.ShowBoardLogEntry",)
-
-	def __init__(self, settings: LogSettings) -> None:
-		super().__init__(settings)
-		self.settings: LogSettings = settings
-		self.tasks = {}
-		self.first_board_view = {}
-		self.last_board = None
-		self.instance_config_id: str = None
-
-	def process(self, entry: dict) -> bool:
-		if self.instance_config_id is None:
-			if entry[self.settings.type_field] in self.settings.custom['instance_start']:
-				self.instance_config_id = json_path(entry, self.settings.custom['instance_config_id'])
-		if self.is_task(entry):
-			task_id = entry['answers']['@id']
-			if task_id not in self.first_board_view:
-				logger.error("task_id is not in self.first_board_view!", task_id, entry)
-			else:
-				entry['__duration'] = entry['timestamp'] - self.first_board_view[task_id]['timestamp']
-				self.tasks[self.ids(task_id)] = entry
-		if self.is_board(entry):
-			self.first_board_view[entry['board_id']] = entry
-		return False
-
-	def result(self, store: ResultStore, name=None) -> None:
-		results = {}
-		for ids in self.tasks:
-			task = self.tasks[ids]
-			for action in task['selected_actions']:
-				if self.is_dollar_action(action):
-					results[ids] = {"duration": task['__duration'], "result": action['increment']}
-		store.add(Result(type(self), results))
-
-	def ids(self, task_id):
-		task = self.first_board_view[task_id]
-		return f"{self.instance_config_id}_{task['sequence_id']}_{task['board_id']}"
-
-	def is_task(self, entry) -> bool:
-		return entry['@class'] in self.DATA_CLASSES
-
-	def is_board(self, entry) -> bool:
-		return entry['@class'] in self.BOARD_CLASSES
-
-	def is_dollar_action(self, action):
-		return action['@class'] in ("de.findevielfalt.games.game2.instance.action.IncrementDiversityDollarAction")
-
 class BiogamesStore(Store):
 	__name__ = "BiogamesStore"
 
@@ -443,8 +281,8 @@ class InstanceConfig(Analyzer):
 			print(entry)
 			self.store["instance_id"] = json_path(entry, self.settings.custom["instance_config_id"])
 
-	def result(self, store: ResultStore, name=None):
+	def result(self, store: ResultStore):
-		store.add(Result(type(self), dict(self.store), name=name))
+		store.add(Result(type(self), dict(self.store)))
 
 
 class SimulationOrderAnalyzer(Analyzer):
@@ -455,8 +293,8 @@ class SimulationOrderAnalyzer(Analyzer):
 		self.store = defaultdict(lambda: -1)  # TODO verify
 		self.order = []
 
-	def result(self, store: ResultStore, name=None) -> None:
+	def result(self, store: ResultStore) -> None:
-		store.add(Result(type(self), [self.store[sim] for sim in self.order], name=name))
+		store.add(Result(type(self), [self.store[sim] for sim in self.order]))
 
 	def process(self, entry: dict) -> bool:
 		entry_type = entry[self.settings.type_field]
@@ -470,7 +308,10 @@ class SimulationOrderAnalyzer(Analyzer):
 
 
 class SimulationCategorizer(CategorizerStub):  # TODO: refactor categorizer
-	__name__ = "SimulationCategorizer"  # TODO: rename -.- (InstanceConfigIDCategorizer)
+	__name__ = "SimulationCategorizer"
+
+	def __init__(self, settings: LogSettings):
+		super().__init__(settings)
 
 	def process(self, entry: dict) -> bool:
 		if self.key is "default":
@@ -481,21 +322,3 @@ class SimulationCategorizer(CategorizerStub):  # TODO: refactor categorizer
 					print(entry)
 					raise e
 		return False
-
-
-class SimulationFlagsAnalyzer(Analyzer):
-	__name__ = "SimuFlags"
-
-	def __init__(self, settings: LogSettings) -> None:
-		super().__init__(settings)
-		self.store = []
-
-	def process(self, entry: dict) -> bool:
-		entry_type = entry[self.settings.type_field]
-		if entry_type in self.settings.custom['simulation_rounds']:
-			if entry["answers"][self.settings.type_field] in self.settings.custom["simu_data"]:
-				self.store.append(entry)
-		return False
-
-	def result(self, store: ResultStore, name=None) -> None:
-		store.add(Result(type(self), self.store, name=name))

analyzers/analyzer/default.py

@@ -0,0 +1,139 @@
+import logging
+from collections import defaultdict, OrderedDict
+
+from util import json_path
+from . import Result, LogSettings, Analyzer, ResultStore
+
+
+class LocationAnalyzer(Analyzer):
+	"""
+	store spatial log entries
+	"""
+	__name__ = "Location"
+	log = logging.getLogger(__name__)
+
+	def __init__(self, settings: LogSettings):
+		super().__init__(settings)
+		self.entries = []
+
+	def result(self, store: ResultStore) -> None:
+		self.log.debug(len(self.entries))
+		store.add(Result(type(self), list(self.entries)))
+
+	def process(self, entry: dict) -> bool:
+		if entry[self.settings.type_field] in self.settings.spatials:
+			self.entries.append(entry)
+		# self.log.debug(len(self.entries))
+		return False
+
+
+class LogEntryCountAnalyzer(Analyzer):
+	#TODO: flexibler: z.b. min/max lat/long
+	"""
+	count occurrences of log entry types
+	"""
+	__name__ = "LogEntryCount"
+
+	def result(self, store: ResultStore) -> None:
+		store.add(Result(type(self), dict(self.store)))
+
+	def process(self, entry: dict) -> bool:
+		self.store[entry[self.settings.type_field]] += 1
+		return False
+
+	def __init__(self, settings: LogSettings):
+		super().__init__(settings)
+		self.store = defaultdict(lambda: 0)
+
+
+class LogEntrySequenceAnalyzer(Analyzer):
+	"""
+	store sequence of all log entry types
+	"""
+	__name__ = "LogEntrySequence"
+
+	def result(self, store: ResultStore) -> None:
+		store.add(Result(type(self), list(self.store)))
+
+	def process(self, entry: dict) -> bool:
+		entry_type = entry[self.settings.type_field]
+		self.store.append(entry_type)
+		return False
+
+	def __init__(self, settings: LogSettings):
+		super().__init__(settings)
+		self.store = []
+
+
+class ActionSequenceAnalyzer(LogEntrySequenceAnalyzer):
+	"""
+	find sequence of non-spatial log entry types
+	"""
+	__name__ = "ActionSequenceAnalyzer"
+
+	def process(self, entry: dict) -> bool:
+		entry_type = entry[self.settings.type_field]
+		if entry_type in self.settings.spatials:
+			return False
+		self.store.append(entry_type)
+		return False
+
+
+class CategorizerStub(Analyzer):
+	"""
+	generate a new Category in a ResultStore
+	"""
+
+	def process(self, entry: dict) -> bool:
+		raise NotImplementedError()
+
+	__name__ = "Categorizer"
+
+	def result(self, store: ResultStore) -> None:
+		store.new_category(self.key)
+
+	def __init__(self, settings: LogSettings):
+		super().__init__(settings)
+		self.key = "default"
+
+
+class Store(Analyzer):
+	"""
+	Store the entire log
+	"""
+	__name__ = "Store"
+
+	def result(self, store: ResultStore) -> None:
+		store.add(Result(type(self), list(self.store)))
+
+	def process(self, entry: dict) -> bool:
+		self.store.append(entry)
+		return False
+
+	def __init__(self, settings: LogSettings):
+		super().__init__(settings)
+		self.store: list = []
+
+
+class ProgressAnalyzer(Analyzer):
+	"""track spatial and ingame progress"""
+	__name__ = "ProgressAnalyzer"
+
+	def __init__(self, settings: LogSettings) -> None:
+		super().__init__(settings)
+		self.spatial = OrderedDict()
+		self.board = OrderedDict()
+
+	def result(self, store: ResultStore) -> None:
+		store.add(Result(type(self), {"spatials": self.spatial, "boards": self.board}))
+
+	def process(self, entry: dict) -> bool:
+		if entry[self.settings.type_field] in self.settings.spatials:
+			self.spatial[entry["timestamp"]] = 				{
+					'timestamp': entry['timestamp'],
+					'coordinates': json_path(entry, "location.coordinates"),
+					'accuracy': entry['accuracy']
+				}
+		if entry[self.settings.type_field] in self.settings.boards:
+			self.board[entry["timestamp"]] = entry
+		return False

analyzers/analyzer/locomotion.py

@@ -1,4 +1,4 @@
-from analysis import util
+import util
 from . import Analyzer, LogSettings, Result, ResultStore
 
 
@@ -41,7 +41,7 @@ class LocomotionActionAnalyzer(Analyzer):
 			self.current_cache = None
 			self.last = None
 
-	def result(self, store: ResultStore, **kwargs) -> None:
+	def result(self, store: ResultStore) -> None:
 		if self.last is not None:
 			if self.current_cache is None:
 				self.locomotion.append(self.last - self.cache_time)
@@ -50,14 +50,7 @@ class LocomotionActionAnalyzer(Analyzer):
 			self.last = None
 		locomotion = sum(self.locomotion)
 		action = sum(self.actions)
-		if action== 0:
-			action = 42
-			print("Division by zero") #FIXME
 		total = locomotion + action
-		if not self.last_timestamp:
-			self.last_timestamp = 0
-		if not self.instance_start:
-			self.instance_start = 0
 		store.add(Result(type(self), {
 			'locomotion_sum': locomotion,
 			'action_sum': action,

analyzers/render/__init__.py

@@ -0,0 +1,17 @@
+from typing import List
+from .. import Result
+
+
+class Render:
+	result_types = []
+
+	def render(self, results: List[Result], name=None):
+		raise NotImplementedError()
+
+	def filter(self, results: List[Result]):
+		if len(self.result_types) == 0:
+			return results
+		return filter(self.__filter__, results)
+
+	def __filter__(self, obj: Result):
+		return obj.analysis() in self.result_types

analyzers/render/biogames.py

@@ -1,5 +1,4 @@
 import json
-import tempfile
 from collections import defaultdict
 from typing import List, Tuple
 
@@ -10,13 +9,8 @@ from scipy.interpolate import interp1d
 import networkx as nx
 import itertools
 
-from analysis.analyzers import Store, BiogamesStore, SimulationOrderAnalyzer, LocationAnalyzer, BiogamesDuration, \
+from analyzers import Store, BiogamesStore, SimulationOrderAnalyzer
-	BiogamesTasks, GameFieldInstanceGroup
+from util.meta_temp import CONFIG_NAMES
-from analysis.analyzers.analyzer import ResultStore
-from analysis.analyzers.render.default import GeoJSON
-from analysis.util.geo import calc_distance, calc_distance_simplified
-from analysis.util.meta_temp import CONFIG_NAMES, TASK_NAMES, CACHE_NAMES, SEQUENCE_NAMES
-from analysis.util.output import flat_dict_to_csv, pretty_ts
 from . import Render
 from .. import Result, SimulationRoundsAnalyzer, BoardDurationAnalyzer, ActivityMapper
 
@@ -141,16 +135,16 @@ class BoardDurationHistRender(Render):
 class BoardDurationBoxRender(Render):
 	result_types = [BoardDurationAnalyzer]
 
-	def render(self, results: List[Result], name=None) -> [str]:
+	def render(self, results: List[Result], name=None):
 		data = defaultdict(list)
 		for result in self.filter(results):
-			for board in result.get():
+			get = result.get()
+			for board in get:
 				duration = board['active'] if 'active' in board else 0
 				data[board['id']].append(duration)
 		data_tuples = [(key, data[key]) for key in sorted(data)]
 		data_tuples = sorted(data_tuples, key=lambda x: sum(x[1]))
-		plot(data_tuples, name=name)
+		plot(data_tuples)
-		return [name]
 
 
 class ActivityMapperRender(Render):
@@ -158,14 +152,11 @@ class ActivityMapperRender(Render):
 
 	def render(self, results: List[Result], name=None):
 		print(os.getcwd())
-		files = []
 		for result in self.filter(results):
 			data = result.get()
-			path = os.path.join("/tmp", data["properties"]['instance'] + "_" + str(name) + ".json")
+			with open(os.path.join("static", "progress", "data", data['instance']), "w") as out:
-			with open(path, "w") as out:
+				json.dump(data["store"], out, indent=1)
-				json.dump(data, out, indent=1)
+		return "ok"
-			files.append(path)
-		return files
 
 
 class StoreRender(Render):
@@ -194,7 +185,7 @@ class SimulationOrderRender(Render):
 
 class SimulationGroupRender(Render):
 	def render(self, results: List[Result], name=None):
-		# data = [r.get() for r in self.filter(results)]
+		#data = [r.get() for r in self.filter(results)]
 		data = []
 		for r in self.filter(results):
 			raw = r.get()
@@ -202,65 +193,7 @@ class SimulationGroupRender(Render):
 				raw = [0] + raw
 			data.append(raw)
 		print(name, len(data))
-		# graph_fit(list(data), name=name)
+		graph_plot(list(data), ylabel="simulation retries", title="sequential simulation retries", rotation=None, name=name)
-		graph_plot(list(data), ylabel="simulation retries", title="sequential simulation retries", rotation=None,
+		#graph_fit(list(data), name=name)
-				   name=name)
 
 	result_types = [SimulationOrderAnalyzer]
-
-class OEBRender(Render):
-	result_types = [LocationAnalyzer, BiogamesTasks, BiogamesDuration, GameFieldInstanceGroup]
-	timestamp_fields = ("timestamp", "start", "end")
-
-	def render(self, results: List[Result], name=None) -> [str]:
-		data = {}
-		for r in self.filter(results):
-			if r.analysis() is LocationAnalyzer:
-				geojson = GeoJSON()
-				json = geojson.make_geojson(r.get())
-				data[f"{r.analysis().__name__}__distance"] = calc_distance(json, "features.0.geometry.coordinates", load=False)
-				data[f"{r.analysis().__name__}__distance_simplified"] = calc_distance_simplified(json, "features.0.geometry.coordinates", load=False)
-			else:
-				for i in r.get():
-					a = r.analysis().__name__
-					value = r.get()[i]
-					if i in self.timestamp_fields:
-						value = pretty_ts(value)
-					key = f"{a}__{i}"
-					key = self.replace(key, i)
-					if type(value) is dict:
-						for j in value:
-							data[key+"__"+j] = value[j]
-					else:
-						data[key] = value
-		return data
-
-	def render_store(self, store: ResultStore, name=None) -> str:
-		data = []
-		for category in store.get_categories():
-			data.append(self.render(store.get_category(category)))
-		#import json
-		#print(json.dumps(data, indent=1))
-		csv = flat_dict_to_csv(data)
-		#print(csv)
-		if name:
-			filename = str(name) + ".csv"
-		else:
-			filename = "/tmp/biogames" + ".csv"
-		try:
-			with open(filename, "w") as out:
-				out.write(csv)
-		except PermissionError as e:
-			raise PermissionError(e, filename)
-		return filename
-
-	def replace(self, key, i):
-		if i in TASK_NAMES:
-			key = f"{TASK_NAMES[i]} ({key})"
-		if "sequence_" in i:
-			sid = i.split("_")[1]
-			cache, seq = sid.split("+")
-			cache = CACHE_NAMES.get(cache, cache)
-			seq = SEQUENCE_NAMES.get(seq, seq)
-			key = f"{cache}->{seq} {sid} duration"
-		return key

analyzers/render/default.py

@@ -0,0 +1,86 @@
+import json
+import logging
+from typing import List
+
+import matplotlib.pyplot as plt
+
+from analyzers import LogEntryCountAnalyzer
+from . import Render, Result
+from .. import LocationAnalyzer
+
+log = logging.getLogger(__name__)
+
+
+class PrintRender(Render):
+	def render(self, results: List[Result], name=None):
+		print("\t" + "\n\t".join([str(r) for r in results]))
+
+
+class JSONRender(Render):
+	def render(self, results: List[Result], name=None):
+		print(json.dumps([r.get() for r in self.filter(results)], indent=1))
+
+
+class TrackRender(Render):
+	result_types = [LocationAnalyzer]
+
+	def render(self, results: List[Result], name=None):
+		data = []
+		log.debug(results)
+		for result in self.filter(results):
+			if len(result.get()) > 0:
+				data.append(
+					[[entry['location']['coordinates'][1], entry['location']['coordinates'][0]] for entry in
+					 # TODO: configurable
+					 result.get()])
+		dumps = json.dumps(data)
+		with open("track_data.js", "w") as out:
+			out.write("tracks=" + dumps + ";")
+		return dumps
+
+
+class HeatMapRender(TrackRender):
+	weight = 0.01
+
+	def render(self, results: List[Result], name=None):
+		raw = super(HeatMapRender, self).render(results)
+		data = []
+		for session in json.loads(raw):
+			data += [(entry[0], entry[1], self.weight) for entry in session]
+		dumps = json.dumps(data)
+		with open('heat_data.js', 'w') as out:
+			out.write("coords = " + dumps + ";")
+		return dumps
+
+
+class LogEntryCountAnalyzerPlot(Render):
+	result_types = [LogEntryCountAnalyzer]
+
+	def render(self, results: List[Result], name=None):
+		raw_data = list(self.filter(results))[0].get()
+		print(raw_data)
+		labels = []
+		data = []
+		for x in sorted(raw_data.items()):
+			labels.append(str(x[0]).split(".")[-1])
+			data.append(x[1])
+		plt.bar(range(len(data)), list(data))
+		plt.xticks(range(len(data)), labels, rotation="vertical")
+		plt.tight_layout()
+
+		name = "plots/{}.png".format(name)
+		plt.savefig(name)
+		plt.cla()
+		plt.clf()
+		plt.close()
+
+class LogEntryCountCSV(Render):
+	result_types = [LogEntryCountAnalyzer]
+	summary = None
+
+	def render(self, results: List[Result], name=None):
+		if self.summary is None:
+			return
+		for result in self.filter(results):
+			raw_data = result.get()
+			self.summary[name] = raw_data

analyzers/settings.py

@@ -1,17 +1,13 @@
 import json
-import logging
 import sys
-from clients.webclients import CLIENTS
+from sources import SOURCES
 
-log: logging.Logger = logging.getLogger(__name__)
 
 def load_source(config):
-	if config["type"] in CLIENTS:
+	if config["type"] in SOURCES:
-		source = CLIENTS[config["type"]](**config)
+		source = SOURCES[config["type"]]()
-		source.login()
+		source.connect(**config)
 		return source
-	else:
-		log.warn(f"client {config['type']} not found!")
 
 
 class LogSettings:
@@ -32,15 +28,13 @@ class LogSettings:
 		self.boards = json_dict['boards']
 		for mod in json_dict['analyzers']:
 			for name in json_dict['analyzers'][mod]:
-				print(mod, name, getattr(sys.modules[mod], name))
+				print(mod, name)
 				self.analyzers.append(getattr(sys.modules[mod], name))
 		self.sequences = json_dict['sequences']
 		if 'custom' in json_dict:
 			self.custom = json_dict['custom']
 		if "source" in json_dict:
 			self.source = load_source(json_dict['source'])
-		if "render" in json_dict:
-			self.render = json_dict['render']
 
 	def __repr__(self):
 		return str({
@@ -57,7 +51,3 @@ class LogSettings:
 
 def load_settings(file: str) -> LogSettings:
 	return LogSettings(json.load(open(file)))
-
-
-def parse_settings(config: str) -> LogSettings:
-	return LogSettings(json.loads(config))

biogames2.json

@@ -19,12 +19,10 @@
     ]
   },
   "dis":[
-      "ActivityMapper",
       "BiogamesCategorizer",
       "LogEntryCountAnalyzer",
       "SimulationOrderAnalyzer",
       "ProgressAnalyzer",
-      "SimulationCategorizer",
       "InstanceConfig"],
   "disabled_analyzers": [
       "LocomotionActionAnalyzer",
@@ -67,12 +65,7 @@
         "action":"PAUSE"
       }
     },
-    "coordinates": "location.coordinates",
+    "coordinates": "location.coordinates"
-    "metadata":{
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
   },
   "source":{
     "type": "Biogames",

clients/webclients.py

@@ -1,158 +0,0 @@
-import json
-import logging
-
-import os
-import shutil
-import tempfile
-import typing
-
-import requests
-
-log: logging.Logger = logging.getLogger(__name__)
-
-
-class Client:
-	host: str = ""
-	cookies: typing.Dict[str, str] = {}
-	headers: typing.Dict[str, str] = {}
-
-	def url(self, path):
-		if self.host:
-			return self.host + path
-		return path
-
-	def get(self, url, **kwargs) -> requests.models.Response:
-		log.info("GET " + str(url))
-		return requests.get(self.url(url), cookies=self.cookies, headers=self.headers, **kwargs)
-
-	def post(self, url, data, **kwargs) -> requests.models.Response:
-		log.info("POST " + str(url))
-		return requests.post(self.url(url), data, cookies=self.cookies, headers=self.headers, **kwargs)
-
-	def download_file(self, url, target, **kwargs) -> bool:
-		with open(target, "wb") as out:
-			try:
-				download = self.get(url, stream=True, **kwargs)
-				shutil.copyfileobj(download.raw, out)
-			except Exception as e:
-				log.exception(e)
-				os.remove(target)
-				return False
-		return True
-
-	def download_files(self, urls, **kwargs) -> tempfile.TemporaryDirectory:
-		target = tempfile.TemporaryDirectory()
-		for path in urls:
-			filename = os.path.join(target.name, path.split("/")[-1])
-			self.download_file(path, filename, **kwargs)
-		return target
-
-	def login(self):
-		pass #TODO
-
-	def list(self):
-		pass #TODO
-
-
-class BiogamesClient(Client):
-	config_fields: typing.Dict[str, typing.List[str]] = {
-		'login': ('username', 'password', 'host'),
-		'session': ('sessionid', 'csrftoken', 'host'),
-	}
-	login_url: str = "/game2/auth/json-login"
-	list_url: str = "/game2/instance/log/list/"
-	headers: typing.Dict[str, str] = {'Accept': 'application/json'}
-
-	def __init__(self, **kwargs):
-		match = {j: all([i in kwargs for i in self.config_fields[j]]) for j in self.config_fields}
-		valid = filter(lambda x: match[x], match)
-		if not valid:
-			raise ValueError("missing parameter (" + str(self.config_fields) + ")")
-		self.config = kwargs
-		self.cookies = {}
-		self.host = self.config['host']
-		if 'session' in valid:
-			self.cookies = kwargs
-
-	def login(self) -> bool:
-		csrf_request = self.get(self.list_url)
-		if not csrf_request.ok:
-			log.exception(ConnectionError("Unable to obtain CSRF token (" + str(csrf_request) + ")"))
-			return False
-		if not 'csrftoken' in self.cookies:
-			self.cookies['csrftoken'] = csrf_request.cookies['csrftoken']
-		login_payload = {
-			'username': self.config['username'],
-			'password': self.config['password'],
-			'next': '',
-			'csrfmiddlewaretoken': 'csrftoken',
-		}
-		login = self.post(self.login_url, json.dumps(login_payload))
-		if not login.ok:
-			log.exception(ConnectionError("Unable to authenticate", login, login.text))
-			return False
-		self.cookies['sessionid'] = login.cookies['sessionid']
-		print(self.cookies)
-		return True
-
-	def list(self) -> dict:
-		print(self.cookies)
-		logs = self.get(self.list_url)
-		if not logs.ok:
-			raise ConnectionError("HTTP fail", logs, logs.text)
-		return logs.json()
-
-	def load_all_logs(self) -> tempfile.TemporaryDirectory:
-		return self.download_files([i["file_url"] for i in self.list()])
-
-class GeogamesClient(Client):
-	config_fields = ("host",)
-	
-	def __init__(self, **kwargs):
-		for field in self.config_fields:
-			if not field in kwargs:
-				raise ValueError(f"missing parameter: {field}")
-		self.host = kwargs['host']
-		self.path = "neocartographer"
-		self.config = kwargs
-	
-	def login(self):
-		return True
-	
-	def list(self):
-		logs = self.get(self.path)
-		data = logs.json()
-		prepared_logs = []
-		for log in data:
-			players = self.get(f"{self.path}/{log['name']}/").json()
-			for player in players:
-				prepared_logs.append({
-					'@id': f"{log['name']}/{player['name']}",
-					'start_date': player['mtime'],
-					'player_group_name': player['name'],
-					'file_url': f"{self.path}/{log['name']}/{player['name']}",
-				})
-		return prepared_logs
-
-	def download_files(self, urls, **kwargs) -> tempfile.TemporaryDirectory:
-		target = tempfile.TemporaryDirectory()
-		for path in urls:
-			filename = os.path.join(target.name, "-".join
-(path.split("/")[-2:]))
-			self.download_file(path, filename, **kwargs)
-		return target
-
-CLIENTS: typing.Dict[str, typing.Type[Client]] = {
-	"Biogames": BiogamesClient,
-	"Geogames": GeogamesClient,
-}
-
-if __name__ == '__main__':
-	# c = BiogamesClient(host="http://biodiv", username="ba", password="853451")
-	# print(c.login())
-	# print(json.dumps(c.list(), indent=1))
-	# print(type(c.load_all_logs()))
-	# print(type(c.get("/")))
-	c = BiogamesClient(host="http://biodiv", **{'csrftoken': 'IgbwP83iEibW6RE7IADIFELYdbx0dvqQ',
-												'sessionid': 'zntsj09d92tjos1b6ruqjthlzv60xdin'})
-	print(json.dumps(c.list(), indent=1))

data/results/index.html

@@ -1,19 +0,0 @@
-<script
-        src="https://code.jquery.com/jquery-3.2.1.min.js"></script>
-<link rel="stylesheet" href="https://unpkg.com/leaflet@1.2.0/dist/leaflet.css"/>
-<script src="https://unpkg.com/leaflet@1.2.0/dist/leaflet.js"></script>
-
-<script src="https://rawgit.com/Leaflet/Leaflet.heat/gh-pages/dist/leaflet-heat.js"></script>
-
-<script src="my.js"></script>
-<link href="style.css" rel="stylesheet"/>
-<main>
-    <div class="mapDiv" id="mainMap"></div>
-    <div class="sequenceContainer">
-        <div class="sequence"></div>
-    </div>
-</main>
-
-<!--div style="font-size:0.1px;position:absolute;bottom:0;">OSM Logo: CC-BY-SA
-    http://wiki.openstreetmap.org/wiki/File:Mag_map-120x120.png
-</div-->

data/results/my.js

@@ -1,110 +0,0 @@
-function loadData() {
-    console.log($(location).attr('hash').substr(1));
-    $.getJSON($(location).attr('hash').substr(1), function (data) {
-        var images = {};
-        var tiles = {
-            "openstreetmap": L.tileLayer('https://{s}.tile.openstreetmap.org/{z}/{x}/{y}.png', {
-                maxNativeZoom: 19,
-                maxZoom: 24,
-                attribution: '&copy; <a href="http://www.openstreetmap.org/copyright">OpenStreetMap</a>'
-            }),
-            "esri sat": L.tileLayer('https://server.arcgisonline.com/ArcGIS/rest/services/World_Imagery/MapServer/tile/{z}/{y}/{x}', {
-                maxNativeZoom: 19,
-                maxZoom: 24,
-                attribution: 'Tiles &copy; Esri &mdash; Source: Esri, i-cubed, USDA, USGS, AEX, GeoEye, Getmapping, Aerogrid, IGN, IGP, UPR-EGP, and the GIS User Community'
-            }),
-            "google sat": L.tileLayer('https://{s}.google.com/vt/lyrs=s&x={x}&y={y}&z={z}', {
-                maxNativeZoom: 20,
-                maxZoom: 24,
-                subdomains: ['mt0', 'mt1', 'mt2', 'mt3']
-            })
-        };
-        var map = L.map("mainMap", {layers: [tiles.openstreetmap]});
-
-        function styleTrack(feature) {
-            var styles = {};
-            styles.color = data.properties.colors[feature.properties.activity_type];
-            return styles;
-        }
-
-        var highlighted = null;
-
-        function onClick(e) {
-            var start = e.target.feature.geometry.properties.start_timestamp;
-            var end = e.target.feature.geometry.properties.end_timestamp;
-            var changed = highlighted !== e.target.feature;
-            $.each(images, function (timestamp, board) {
-                    if ((timestamp >= start && timestamp < end) && changed) {
-                        board.image.first().addClass("highlight");
-                    } else {
-                        board.image.removeClass("highlight");
-                        highlighted = null;
-                    }
-                }
-            );
-            if (changed) {
-                highlighted = e.target.feature;
-            }
-        }
-
-        var coords = [];
-
-        function onEachFeature(feature, layer) {
-            layer.setStyle(styleTrack(feature));
-            layer.on('click', onClick);
-            if (feature.geometry.coordinates.length > 1) {
-                coords = coords.concat(feature.geometry.coordinates.map(function (p) {
-                    return [p[1], p[0], 0.1];
-                }));
-            }
-        }
-
-        var track = L.geoJSON(data['features'], {
-            //style: styleTrack,
-            onEachFeature: onEachFeature
-        }).addTo(map);
-
-        map.fitBounds(track.getBounds());
-
-        //var heat = L.heatLayer(coords);
-        //L.control.layers(tiles, {"heatmap": heat}).addTo(map);
-
-        var list = $("<ul />");
-        var current = {
-            "pos": data.properties["boards"][0].coordinate.coordinates
-        };
-        var i = 0;
-        while (current.pos == undefined) {
-        	i+=1;
-        	current.pos = data.properties["boards"][i].coordinate.coordinates;
-        }
-        console.log(current);
-        var marker = L.marker([current.pos[1], current.pos[0]]).addTo(map);
-        $.each(data.properties["boards"], function (index, entry) {
-            //console.log(index, entry);
-            var item = $("<li>", {class: entry.extra_data.activity_type});
-            var container = $("<div>", {class: "board"});
-            var image = $("<img>", {src: entry.image.replace("static/progress/", "")});
-            image.attr("data-time", entry.timestamp);
-            image.hover(function () {
-                marker.setLatLng([entry.coordinate.coordinates[1], entry.coordinate.coordinates[0]]);
-            }, function () {
-                marker.setLatLng(current.pos.coordinates[1], current.pos.coordinates[0]);
-            });
-            image.click(function (e) {
-                current.board = image;
-                current.pos = entry.coordinate;
-            });
-            images[entry.timestamp] = {image: image, coordinate: entry.coordinate};
-            image.appendTo(container);
-            container.appendTo(item);
-            item.appendTo(list);
-        });
-        current.board = images[data.properties["boards"][1].timestamp];
-        list.appendTo(".sequence");
-    });
-}
-
-$(document).ready(function () {
-    loadData();
-});

data/results/style.css

@@ -1,105 +0,0 @@
-/*.mapDiv {
-    width: 1024px;
-    height: 768px;
-}*/
-
-
-
-.highlight {
-    /*what a nice way to highlight*/
-    display: none;
-}
-
-.simu {
-    background-color: blue;
-}
-
-.question {
-    background-color: orange;
-}
-
-.image {
-    background-color: green;
-}
-
-.audio {
-    background-color: red;
-}
-
-.video {
-    background-color: purple;
-}
-
-.other {
-    background-color: brown;
-}
-
-.map {
-    background-color: violet;
-}
-
-.error {
-    background-color: grey;
-}
-
-
-.board {
-    width: 32px;
-    height: 32px;
-    display: inline-block;
-}
-
-.board img {
-    max-width: 32px;
-    max-height: 32px;
-    position: absolute;
-    /*bottom: 0px;*/
-}
-
-.board:hover img{
-    max-width: 205px;
-    max-height: 295px;
-    z-index: 99;
-    top: 5px;
-    right:0px;
-}
-ul {
-    list-style-type: none;
-    overflow: auto;
-    overflow-y: hidden;
-    display: inline-block;
-    /*max-width:100%;
-    margin: 0 0 1em;
-    white-space: nowrap;
-    height:200px;*/
-}
-
-li {
-    display: inline-block;
-    vertical-align: top;
-    padding: 2px;
-    margin-bottom: 2px;
-}
-
-body{
-    height: 100%;
-    padding:0;
-    margin:0;
-}
-
-main{
-    display: flex;
-    flex-direction: column;
-    height:100%;
-}
-
-.mapDiv {
-    flex-grow:1;
-}
-.sequenceContainer{
-    flex-grow: 0;
-    min-height:300px;
-    padding-right: 210px;
-    position: relative;
-
-}

docker-compose.yml

@@ -1,63 +0,0 @@
-version: "3"
-
-services:
- app:
-  image: docker.clkl.de/ma/celery:0.4.2
-  build: .
-  volumes:
-    - ./:/app
-  working_dir: /app/selector
-  command: python3 webserver.py
-  environment:
-    - PYTHONPATH=/app
-    - PYTHONUNBUFFERED=1
-  networks:
-   - default
-   - traefik_net
-  labels:
-   - "traefik.enable=true"
-   - "traefik.port=5000"
-   - "traefik.docker.network=traefik_net"
-   - "traefik.url.frontend.rule=Host:select.ma.potato.kinf.wiai.uni-bamberg.de"
-
- celery:
-  image: docker.clkl.de/ma/celery:0.4.2
-  environment:
-    - PYTHONPATH=/app
-    - PYTHONUNBUFFERED=1
-  volumes:
-    - ./:/app
-    - ./data/results:/data/results
-  working_dir: /app
-  command: celery -A tasks.tasks worker --loglevel=info
-
-
- redis:
-  image: redis:4-alpine
-  volumes:
-    - ./data/redis:/data
-  command: redis-server --appendonly yes
-
- nginx:
-  image: nginx:1.13-alpine
-  volumes:
-   - ./data/results:/usr/share/nginx/html:ro
-  networks:
-   - traefik_net
-  labels:
-   - "traefik.enable=true"
-   - "traefik.port=80"
-   - "traefik.docker.network=traefik_net"
-   - "traefik.url.frontend.rule=Host:results.ma.potato.kinf.wiai.uni-bamberg.de"
-
- log_data:
-  image: nginx:1.13-alpine
-  volumes:
-   - ./log_data/:/srv/:ro
-   - ./log_data.conf:/etc/nginx/conf.d/log_data.conf
-
-
-networks:
- traefik_net:
-  external:
-   name: traefik_net

frontend/Readme.md

@@ -1,44 +0,0 @@
-# Traefik reverse proxy for analysis framework
-
-## Usage (default: http)
-
-1. `cd traefik`
-2. `editor docker-compose.yml`
-	* Adjust the *traefik.frontend.rule* label for the traefik dashboard
-		* Default (match any):
-			* traefik.localhost
-			* traefik.potato.kinf.wiai.uni-bamberg.de
-	* Adjust port mapping
-		* Default:
-			* 80 → 80
-		* Syntax: <host-port>:<container-port>
-3. `docker-compose up -d`
-4. `cd ../..`
-5. `editor docker-compose.yml`
-	* adjust the *traefik.url.frontend.rule* labels for services *app* and *nginx*
-	* adjust the urls in *selector/config.py* accordingly
-6. `docker-compose up -d`
-7. You have a working analysis framework setup now
-	* Stop with `docker-compose down`
-	* Start with `docker-compose up -d`
-
-## Usage (https)
-
-1. Be on a host with port 80 available from the internet
-2. Follw HTTP usage above up to step 2
-3. Reconfigure docker-compose
-	* Add acme.json volume:
-		* Uncomment the line for the acme.json volume
-		* Adjust the host path
-		* Syntax: <host-path>:<container-path>
-	* Add port mapping for HTTPS
-		* Uncomment the line for the 443:443 port mapping
-4. Create acme.json
-	* touch acme.json
-	* chmod 600 acme.json
-5. Activate traefiks ACME module
-	* `mv config.toml config_http.toml`
-	* `mv config_acme.toml config.toml`
-	* `editor config.toml`
-		* Adjust the *acme.email* value
-6. Continue with HTTP Usage steps 3 +

frontend/traefik/config.toml

@@ -1,8 +0,0 @@
-logLevel = "INFO"
-
-[web]
-address = ":8080"
-
-[docker]
-watch = true
-exposedbydefault = false

frontend/traefik/config_acme.toml

@@ -1,26 +0,0 @@
-logLevel = "INFO"
-defaultEntryPoints = ["https", "http"]
-
-[web]
-address = ":8080"
-
-[docker]
-watch = true
-exposedbydefault = false
-
-[entryPoints]
-	[entryPoints.http]
-		address = ":80"
-		[entryPoints.http.redirect]
-			entryPoint = "https"
-	[entryPoints.https]
-		address = ":443"
-		[entryPoints.https.tls]
-
-[acme]
-	email = "tls-admin@org.example"
-	storage = "acme.json"
-	entryPoint = "https"
-	OnHostRule = true
-	[acme.httpChallenge]
-		entryPoint = "http"

frontend/traefik/docker-compose.yml

@@ -1,22 +0,0 @@
-version: "3"
-services:
- traefik:
-  image: traefik:1.6
-  command: --configFile=/traefik.toml
-  volumes:
-   - ./config.toml:/traefik.toml
-#   - /srv/traefik/acme.json:/acme.json
-   - /var/run/docker.sock:/var/run/docker.sock
-  ports:
-   - 80:80
-#   - 443:443
-  networks:
-   - net
-  labels:
-   - "traefik.enable=true"
-   - "traefik.port=8080"
-   - "traefik.frontend.rule=Host:traefik.localhost,traefik.potato.kinf.wiai.uni-bamberg.de"
-  restart: on-failure:5
-networks:
- net:
-  driver: bridge

loaders/__init__.py

@@ -1,10 +1,8 @@
 from .biogames import SQLiteLoader, ZipSQLiteLoader
 from .loader import JSONLoader
-from .neocart import NeoCartLoader
 
 LOADERS = {
 	"json": JSONLoader,
 	"sqlite": SQLiteLoader,
-	"zip": ZipSQLiteLoader,
+	"zip": ZipSQLiteLoader
-	"neocartographer": NeoCartLoader,
 }

log_analyzer.py

@@ -0,0 +1,466 @@
+import json
+import logging
+from typing import List
+
+import numpy as np
+
+import analyzers
+from analyzers import get_renderer, Analyzer, render, Store
+from analyzers.analyzer import ResultStore
+from analyzers.render.default import LogEntryCountCSV
+from analyzers.settings import LogSettings, load_settings
+from loaders import LOADERS
+
+logging.basicConfig(format='%(levelname)s %(name)s:%(message)s', level=logging.DEBUG)
+log: logging.Logger = logging.getLogger(__name__)
+
+requests_log = logging.getLogger('requests')
+requests_log.setLevel(logging.WARN)
+
+
+def process_log(log_id: str, settings: LogSettings) -> List[Analyzer]:
+	logfile: str = "data/inst_{id}.{format}".format(id=log_id, format=settings.log_format)
+	logfile = log_id
+	loader = LOADERS[settings.log_format]()
+	try:
+		loader.load(logfile)
+	except BaseException as e:
+		raise RuntimeError(e)
+	analyzers: List[Analyzer] = []
+	log.debug("build analyzers")
+	for analyzer in settings.analyzers:
+		analyzers.append(analyzer(settings))
+	log.debug("process entries")
+	for entry in loader.get_entry():
+		for analyzer in analyzers:
+			try:
+				if analyzer.process(entry):
+					break
+			except KeyError as e:
+				log.exception(e)
+	return analyzers
+
+
+if __name__ == '__main__':
+	settings: LogSettings = load_settings("biogames2.json")
+	log_ids: List[str] = [
+		"20d4244719404ffab0ca386c76e4b112",
+		"56d9b64144ab44e7b90bf766f3be32e3",
+		"dc2cdc28ca074715b905e4aa5badff10",
+		"e32b16998440475b994ab46d481d3e0c",
+	]
+	log_ids: List[str] = [
+		# "34fecf49dbaca3401d745fb467",
+		#	"44ea194de594cd8d63ac0314be",
+		#	"57c444470dbf88605433ca935c",
+		#	"78e0c545b594e82edfad55bd7f",
+		#	"91abfd4b31a5562b1c66be37d9",
+		"597b704fe9ace475316c345903",
+		"e01a684aa29dff9ddd9705edf8",
+		"fbf9d64ae0bdad0de7efa3eec6",
+		#	"fe1331481f85560681f86827ec",
+		"fe1331481f85560681f86827ec"]
+	# "fec57041458e6cef98652df625", ]
+	log_ids = []
+	# with open("/home/clemens/git/ma/test/filtered") as src:
+	if False:
+		with open("/home/clemens/git/ma/test/filtered_5_actions") as src:
+			for line in src:
+				line = line.strip()
+				log_ids.append(line)
+		store: ResultStore = ResultStore()
+		for log_id in log_ids:
+			for analysis in process_log(log_id, settings):
+				log.info("* Result for " + analysis.name())
+				# print(analysis.result())
+				# print(analysis.render())
+				analysis.result(store)
+	if False:
+		for r in get_renderer(analyzers.LocomotionActionAnalyzer):
+			r().render(store.get_all())
+	if False:
+		render(analyzers.LocationAnalyzer, store.get_all())
+	# print(json.dumps(store.serializable(), indent=1))
+	if False:
+		render(analyzers.ActivityMapper, store.get_all())
+		render(analyzers.ProgressAnalyzer, store.get_all())
+
+	if False:
+		from analyzers.postprocessing import graph
+
+		g = graph.Cache(settings)
+		g.run(store)
+	if False:
+		# render(analyzers.SimulationOrderAnalyzer, store.get_all())
+		for cat in store.get_categories():
+			data = store.get_category(cat)
+			render(analyzers.SimulationOrderAnalyzer, data, name=cat)
+	if False:
+		LogEntryCountCSV.summary = None
+		for cat in store.get_categories():
+			data = store.get_category(cat)
+			render(analyzers.LogEntryCountAnalyzer, data, name=cat)
+		if LogEntryCountCSV.summary:
+			headers = []
+			lines = []
+			for name in LogEntryCountCSV.summary:
+				data = LogEntryCountCSV.summary[name]
+				for head in data:
+					if not head in headers:
+						headers.append(head)
+				line = [name]
+				for head in headers:
+					line.append(data[head]) if head in data else line.append(0)
+				lines.append(line)
+			import csv
+
+			with open('logentrycount.csv', 'w', newline='') as csvfile:
+				writer = csv.writer(csvfile, quoting=csv.QUOTE_NONE)
+				writer.writerow(["name"] + [h.split(".")[-1] for h in headers])
+				for line in lines:
+					writer.writerow(line)
+
+	if True:
+		# json.dump(store.serializable(), open("new.json", "w"), indent=1)
+		from collections import defaultdict
+		import matplotlib.pyplot as plt
+		from util.meta_temp import CONFIG_NAMES
+
+		keys = [
+			"simu",
+			"question",
+			"image",
+			"audio",
+			"video",
+			"other",
+			"map",
+			# "error"
+		]
+
+		loc_keys=[
+			"question",
+			"image",
+			"audio",
+			"video"
+		]
+
+
+		def get_data(store, relative_values=True, sort=True, show_errors=False):
+			places = defaultdict(list)
+
+			for log in store.get_all():
+				if not log.analysis() == analyzers.ActivityMapper:
+					continue
+				result = defaultdict(lambda: 0)
+				for i in log.get()['track']:
+					duration = i['properties']['end_timestamp'] - i['properties']['start_timestamp']
+					result[i['properties']['activity_type']] += duration
+				print(json.dumps(result, indent=4))
+				total = sum(result.values())
+				print(total)
+				percentage = defaultdict(lambda: 0)
+				minutes = defaultdict(lambda: 0)
+				for i in result:
+					percentage[i] = result[i] / total
+					minutes[i] = result[i] / 60_000
+				print(json.dumps(percentage, indent=4))
+				if not 'error' in result or show_errors:
+					if relative_values:
+						places[log.get()['instance']].append(percentage)
+					else:
+						places[log.get()['instance']].append(minutes)
+			if sort:
+				for place in places:
+					places[place] = sorted(places[place], key=lambda item: item['map'])
+			return places
+
+
+		from shapely.geometry import LineString
+		from shapely.ops import transform
+		from functools import partial
+		import pyproj
+
+
+		def calc_distance(coordinates):
+			track = LineString(coordinates)
+			project = partial(
+				pyproj.transform,
+				pyproj.Proj(init='EPSG:4326'),
+				pyproj.Proj(init='EPSG:32633'))
+			return transform(project, track).length
+
+
+		whitelist = ['16fc3117-61db-4f50-b84f-81de6310206f', '5e64ce07-1c16-4d50-ac4e-b3117847ea43',
+					 '90278021-4c57-464e-90b1-d603799d07eb', 'ff8f1e8f-6cf5-4a7b-835b-5e2226c1e771']
+
+
+		def get_data_distance(store, relative_values=True, sort=True, show_errors=False):
+			places = defaultdict(list)
+
+			for log in store.get_all():
+				if not log.analysis() == analyzers.ActivityMapper:
+					continue
+				result = defaultdict(lambda: 0)
+				for i in log.get()['track']:
+					coords = i['coordinates']
+					if len(coords) > 1:
+						distance = calc_distance(coords)
+						result[i['properties']['activity_type']] += distance
+				total = sum(result.values())
+				percentage = defaultdict(lambda: 0)
+				for i in result:
+					if not total == 0:
+						percentage[i] = result[i] / total
+				if not 'error' in result or show_errors:
+					if relative_values:
+						places[log.get()['instance']].append(percentage)
+					else:
+						places[log.get()['instance']].append(result)
+			if sort:
+				for place in places:
+					places[place] = sorted(places[place], key=lambda item: item['map'])
+			return places
+
+
+		def get_all_data(store, sort=False, relative=True):
+			places = defaultdict(list)
+			simu_distribution = defaultdict(lambda: 0)
+			# divisiors = {"time":60_000, "space":1000000}
+			for log in store.get_all():
+				if not log.analysis() == analyzers.ActivityMapper:
+					continue
+				result = defaultdict(lambda: defaultdict(lambda: 0))
+				for i in log.get()['track']:
+					coords = i['coordinates']
+					if len(coords) > 1:
+						distance = calc_distance(coords)
+					else:
+						distance = 0.0
+					result["space"][i['properties']['activity_type']] += distance
+					duration = i['properties']['end_timestamp'] - i['properties']['start_timestamp']
+					result["time"][i['properties']['activity_type']] += duration
+				total_space = sum(result["space"].values())
+				total_time = sum(result["time"].values())
+				percentage = defaultdict(lambda: defaultdict(lambda: 0))
+				total = defaultdict(lambda: defaultdict(lambda: 0))
+				for i in result["space"]:
+					if not total_space == 0:
+						percentage[i]["space"] = result["space"][i] / total_space
+					else:
+						percentage[i]["space"] = 0
+					if not total_time == 0:
+						percentage[i]["time"] = result["time"][i] / total_time
+					else:
+						percentage[i]["time"] = 0
+					for t in ("space", "time"):
+						# total[i][t] += (result[t][i] / divisiors[t])
+						total[i][t] += result[t][i]
+				print(percentage)
+				if not 'error' in result:
+					if relative:
+						value = percentage
+					else:
+						value = total
+					places[log.get()['instance']].append(value)
+					simus = defaultdict(lambda: 0)
+					for item in log.get()['boards']:
+						if item["extra_data"]["activity_type"] == "simu":
+							simus[item["board_id"]] += 1
+					simu_distribution[len(simus)] += 1
+
+			if sort:
+				for place in places:
+					places[place] = sorted(places[place], key=lambda item: item['map']['time'])
+			print(simu_distribution)
+			return places
+
+
+		def stack_data(keys, places, type="space"):
+			divisiors = {"time": 60_000, "space": 1000}
+			#divisiors = {"time": 1, "space": 1}
+			dummy = [0] * len(keys)
+			results = []
+			sites = []
+			for i in sorted(places):
+				if not i in whitelist:
+					continue
+				place = sorted(places[i], key=lambda item: item['map'][type])
+				for j in place:
+					ordered = []
+					for k in keys:
+						if k in j:
+							ordered.append(j[k][type] / divisiors[type])
+						else:
+							ordered.append(0)
+					print(sum(ordered))
+					#if sum(ordered) > 0.9 and sum(ordered) < 4000 and sum(ordered)>10:
+					if sum(ordered) > 0.9 and sum(ordered)<100:
+						# print(sum(ordered), 1-sum(ordered))
+						# if sum(ordered)<1:
+						#	ordered[-2] = 1-sum(ordered[:-2], ordered[-1])
+						results.append(ordered)
+				results.append(dummy)
+				sites.append(CONFIG_NAMES[i] if i in CONFIG_NAMES else "---")
+			return results, sites
+
+
+		def plot_data(places, keys):
+			results, sites = stack_data(keys, places)
+			dpi = 86.1
+			plt.figure(figsize=(1280 / dpi, 720 / dpi))
+			size = len(results)
+			print("{} elements total".format(size))
+			ind = np.arange(size)
+			width = 1
+			# print(results)
+			data = list(zip(*results))
+			# print(data)
+			lines = []
+			bottom = [0] * size
+			plt.ticklabel_format(useMathText=False)
+			for i in range(0, len(data)):
+				lines.append(plt.bar(ind, data[i], bottom=bottom, width=width)[0])
+				for k, x in enumerate(data[i]):
+					bottom[k] += x
+			plt.legend(lines, keys)
+			plt.title(", ".join(sites))
+			# plt.show()
+			dpi = 86
+			plt.savefig("space_abs_{}.png".format(size), dpi=dpi, bbox_inches="tight")
+
+
+		colors = {
+			"simu": "blue",
+			"question": "orange",
+			"image": "green",
+			"audio": "red",
+			"video": "purple",
+			"other": "brown",
+			"map": "violet",
+			# "error":"grey",
+			"tasks": "olive",
+		}
+		markers = [".", "o", "x", "s", "*", "D", "p", ",", "<", ">", "^", "v", "1", "2", "3", "4"]
+
+
+		def plot_time_space(time_data, space_data, keys):
+			# assuming time_data and space_data are in same order!
+			marker = 0
+			for id in time_data:
+				for k in keys:
+					for i in range(len(time_data[id])):
+						print(time_data[id][i][k], space_data[id][i][k])
+						plt.plot(time_data[id][i][k], space_data[id][i][k], color=colors[k], marker=markers[marker])
+				marker += 1
+			plt.show()
+
+
+		# plt.cla()
+		# plt.clf()
+		# plt.close()
+
+		def group_locationbased_tasks(data):
+			for id in data:
+				for log in data[id]:
+					loc = {"space":0,"time":0}
+					for k in log:
+						if k in loc_keys:
+							for i in ["space","time"]:
+								loc[i] += log[k][i]
+					log["tasks"] = loc
+
+
+
+		def plot_time_space_rel(combined, keys):
+			groups = defaultdict(list)
+			keys = list(keys)
+			keys.remove("other")
+			for i in loc_keys:
+				keys.remove(i)
+			keys.append("tasks")
+			ids = []
+			group_locationbased_tasks(combined)
+			for k in keys:
+				for id in sorted(combined):
+					if id not in whitelist:
+						continue
+					if not id in ids:
+						ids.append(id)
+					group = 0.0
+					count = 0
+					for item in combined[id]:
+						if k in item:
+							time = item[k]["time"] / 1000
+							distance = item[k]["space"]
+							if time > 0:
+								group += (distance / time)
+								count += 1
+							else:
+								print("div by zero", distance, time)
+					if count > 0:
+						groups[k].append(group / count)
+					else:
+						groups[k].append(0.0)
+			print(ids)
+			ind = np.arange(len(ids))
+			width = .7 / len(groups)
+			print(ind)
+			print(json.dumps(groups, indent=1))
+			bars = []
+			dpi = 200
+			plt.figure(figsize=(1280 / dpi, 720 / dpi))
+			fig, ax = plt.subplots()
+			for k in groups:
+				print(groups[k])
+				if not len(groups[k]):
+					groups[k].append(0)
+				ind = ind + (width)
+				bars.append(ax.bar((ind + width * len(groups) / 2), groups[k], width, color=colors[k]))
+			ax.set_xticks(ind + width / 2)
+			ax.set_xticklabels(list([CONFIG_NAMES[i] if i in CONFIG_NAMES else "---" for i in ids]))
+			kmh = plt.hlines((1 / 3.6), 0.3, 4.2, linestyles="dashed", label="1 km/h", linewidths=1)
+			plt.legend(bars+[kmh], keys+[kmh.get_label()])
+			print(combined.keys(), ids)
+			print([CONFIG_NAMES[i] if i in CONFIG_NAMES else "---" for i in ids])
+			# plt.show()
+			dpi = 200
+			plt.savefig("speed2.png", dpi=dpi)
+
+
+		# spatial_data = get_data_distance(store,relative_values=False)
+		# temporal_data = get_data(store,relative_values=False)
+		# spatial_data_rel = get_data_distance(store,relative_values=True)
+		# temporal_data_rel = get_data(store,relative_values=True)
+		# temporal_data_rel = json.load(open("temporal_rel.json"))
+		# spatial_data_rel = json.load(open("spatial_rel.json"))
+		# import IPython
+		# IPython.embed()
+
+		# print(json.dumps(get_all_data(store)))
+		# json.dump(get_all_data(store), open("combined.json", "w"))
+		# combined = get_all_data(store, sort=True, relative=True)
+		# json.dump(combined, open("combined_rel.json", "w"))
+		# combined = json.load(open("combined_rel.json"))
+		combined = json.load(open("combined_total.json"))
+		#plot_time_space_rel(combined, keys)
+		plot_data(combined, keys)
+
+
+	# plot_time_space_rel(temporal_data_rel, spatial_data_rel, keys)
+
+	# plot_data(combined, keys)
+	# plot_data(get_data_distance(store,relative_values=False), keys)
+
+
+# for analyzers in analyzers:
+#	if analyzers.name() in ["LogEntryCount", "ActionSequenceAnalyzer"]:
+#		print(json.dumps(analyzers.result(), indent=2))
+
+# for analyzers in analyzers:
+#	if analyzers.name() in ["BoardDuration"]:
+#		print(json.dumps(analyzers.result(), indent=2))
+#		print(analyzers.render())
+
+# coords = analyzers[1].render()
+# with open("test.js", "w") as out:
+#	out.write("coords = "+coords)

log_data.conf

@@ -1,9 +0,0 @@
-server {
-	listen 80;
-	server_name log_data;
-	location / {
-		root /srv/;
-		autoindex on;
-		autoindex_format json;
-	}
-}

neocart.json

@@ -1,34 +0,0 @@
-{
-  "logFormat": "neocartographer",
-  "entryType": "type",
-  "spatials": [
-    "location"
-  ],
-  "actions": [],
-  "boards": [],
-  "analyzers": {
-    "analysis.analyzers": [
-      "SimpleCategorizer",
-      "LocationAnalyzer"
-    ]
-  },
-  "sequences": {},
-  "custom": {
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Geogames",
-    "host": "http://log_data/",
-    "path": "neocartographer"
-  },
-  "render": [
-    "KMLRender"
-  ]
-}
-
-

oeb_kml.json

@@ -1,66 +0,0 @@
-{
-  "logFormat": "zip",
-  "entryType": "@class",
-  "spatials": [
-    "de.findevielfalt.games.game2.instance.log.entry.LogEntryLocation"
-  ],
-  "actions": [
-    "...QuestionAnswerEvent",
-    "...SimuAnswerEvent"
-  ],
-  "boards": [
-    "de.findevielfalt.games.game2.instance.log.entry.ShowBoardLogEntry"
-  ],
-  "analyzers": {
-    "analysis.analyzers": [
-      "SimulationCategorizer",
-      "LocationAnalyzer"
-    ]
-  },
-  "sequences": {
-    "start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryCache",
-    "end": {
-      "@class": "de.findevielfalt.games.game2.instance.log.entry.LogEntryInstanceAction",
-      "action.@class": "de.findevielfalt.games.game2.instance.action.CacheEnableAction"
-    }
-  },
-  "custom": {
-    "simulation_rounds": [
-      "de.findevielfalt.games.game2.instance.log.entry.LogEntryQuestion"
-    ],
-    "simu_data": [
-      "de.findevielfalt.games.game2.instance.data.sequence.simulation.SimulationBoardData"
-    ],
-    "instance_start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryStartInstance",
-    "instance_id": "instance_id",
-    "instance_config_id": "config.@id",
-    "sequences2": {
-      "id_field": "sequence_id",
-      "start": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "START"
-      },
-      "end": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "PAUSE"
-      }
-    },
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Biogames",
-   "username": "ba",
-    "password": "853451",
-    "host": "http://biogames.potato.kinf.wiai.uni-bamberg.de"
-  },
-  "render": [
-    "KMLRender"
-  ]
-}
-
-

requirements.txt

@@ -1,18 +1,8 @@
 requests==2.18.4
-numpy==1.14.2
+numpy==1.13.1
 matplotlib==2.1.0
-#osmnx==0.6
+osmnx==0.6
 networkx==2.0
-#pydot==1.2.3
+pydot==1.2.3
-scipy==1.0.1
+scipy==1.0.0
-#ipython==6.2.1
+ipython==6.2.1
-
-flask==0.12.2
-
-celery==4.1.1
-redis==2.10.6
-
-lxml==4.2.1
-
-shapely==1.6.4
-pyproj==1.9.5.1

selector/config.py

@@ -1,252 +0,0 @@
-KML = """{
-  "logFormat": "zip",
-  "entryType": "@class",
-  "spatials": [
-    "de.findevielfalt.games.game2.instance.log.entry.LogEntryLocation"
-  ],
-  "actions": [],
-  "boards": [
-    "de.findevielfalt.games.game2.instance.log.entry.ShowBoardLogEntry"
-  ],
-  "analyzers": {
-    "analysis.analyzers": [
-      "BiogamesCategorizer",
-      "LocationAnalyzer"
-    ]
-  },
-  "sequences": {
-    "start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryCache",
-    "end": {
-      "@class": "de.findevielfalt.games.game2.instance.log.entry.LogEntryInstanceAction",
-      "action.@class": "de.findevielfalt.games.game2.instance.action.CacheEnableAction"
-    }
-  },
-  "custom": {
-    "simulation_rounds": [
-      "de.findevielfalt.games.game2.instance.log.entry.LogEntryQuestion"
-    ],
-    "simu_data": [
-      "de.findevielfalt.games.game2.instance.data.sequence.simulation.SimulationBoardData"
-    ],
-    "instance_start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryStartInstance",
-    "instance_id": "instance_id",
-    "instance_config_id": "config.@id",
-    "sequences2": {
-      "id_field": "sequence_id",
-      "start": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "START"
-      },
-      "end": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "PAUSE"
-      }
-    },
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Biogames",
-   "username": "ba",
-    "password": "853451",
-    "host": "http://biodiv2govm.kinf.wiai.uni-bamberg.de"
-  },
-  "render": [
-    "KMLRender"
-  ]
-}"""
-
-ACTIVITY = """{
-  "logFormat": "zip",
-  "entryType": "@class",
-  "spatials": [
-    "de.findevielfalt.games.game2.instance.log.entry.LogEntryLocation"
-  ],
-  "actions": [],
-  "boards": [
-    "de.findevielfalt.games.game2.instance.log.entry.ShowBoardLogEntry"
-  ],
-  "analyzers": {
-    "analysis.analyzers": [
-      "BiogamesCategorizer",
-      "ActivityMapper"
-    ]
-  },
-  "sequences": {
-    "start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryCache",
-    "end": {
-      "@class": "de.findevielfalt.games.game2.instance.log.entry.LogEntryInstanceAction",
-      "action.@class": "de.findevielfalt.games.game2.instance.action.CacheEnableAction"
-    }
-  },
-  "custom": {
-    "simulation_rounds": [
-      "de.findevielfalt.games.game2.instance.log.entry.LogEntryQuestion"
-    ],
-    "simu_data": [
-      "de.findevielfalt.games.game2.instance.data.sequence.simulation.SimulationBoardData"
-    ],
-    "instance_start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryStartInstance",
-    "instance_id": "instance_id",
-    "instance_config_id": "config.@id",
-    "sequences2": {
-      "id_field": "sequence_id",
-      "start": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "START"
-      },
-      "end": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "PAUSE"
-      }
-    },
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Biogames",
-   "username": "ba",
-    "password": "853451",
-    "host": "http://biodiv2govm.kinf.wiai.uni-bamberg.de"
-  },
-  "render": [
-    "ActivityMapper"
-  ]
-}"""
-
-KML_geo = """{
-  "logFormat": "neocartographer",
-  "entryType": "type",
-  "spatials": [
-    "location"
-  ],
-  "actions": [],
-  "boards": [],
-  "analyzers": {
-    "analysis.analyzers": [
-      "SimpleCategorizer",
-      "LocationAnalyzer"
-    ]
-  },
-  "sequences": {},
-  "custom": {
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Geogames",
-    "host": "http://log_data/",
-    "path": "neocartographer"
-  },
-  "render": [
-    "KMLRender"
-  ]
-}"""
-
-OEB = """{
-  "logFormat": "zip",
-  "entryType": "@class",
-  "spatials": [
-    "de.findevielfalt.games.game2.instance.log.entry.LogEntryLocation"
-  ],
-  "actions": [
-    "...QuestionAnswerEvent",
-    "...SimuAnswerEvent"
-  ],
-  "boards": [
-    "de.findevielfalt.games.game2.instance.log.entry.ShowBoardLogEntry"
-  ],
-  "analyzers": {
-    "analysis.analyzers": [
-      "BiogamesCategorizer",
-      "LocationAnalyzer",
-      "BiogamesDuration",
-      "BiogamesTasks",
-      "GameFieldInstanceGroup"
-    ]
-  },
-  "sequences": {
-    "start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryCache",
-    "end": {
-      "@class": "de.findevielfalt.games.game2.instance.log.entry.LogEntryInstanceAction",
-      "action.@class": "de.findevielfalt.games.game2.instance.action.CacheEnableAction"
-    }
-  },
-  "custom": {
-    "simulation_rounds": [
-      "de.findevielfalt.games.game2.instance.log.entry.LogEntryQuestion"
-    ],
-    "simu_data": [
-      "de.findevielfalt.games.game2.instance.data.sequence.simulation.SimulationBoardData"
-    ],
-    "instance_start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryStartInstance",
-    "instance_id": "instance_id",
-    "instance_config_id": "config.@id",
-    "sequences2": {
-      "id_field": "sequence_id",
-      "start": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "START"
-      },
-      "end": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "PAUSE"
-      }
-    },
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Biogames",
-   "username": "ba",
-    "password": "853451",
-    "host": "https://biogames.kinf.wiai.uni-bamberg.de"
-  },
-  "render": [
-    "OEBRender"
-  ]
-}
-
-
-"""
-CONFIGS = {
-	"Biogames": {
-		"ActivityMapper": ACTIVITY,
-		"KML": KML,
-		"DauerEntfernungPunkteZeit": OEB,
-	},
-	"Geogames": {
-		"KML": KML_geo,
-	},
-}
-
-URLS = {
-	"KML": "/",
-	"DauerEntfernungPunkteZeit": "/",
-	"ActivityMapper": "#",
-}
-
-HOSTS = {
-	#"Biogames": "http://biogames.potato.kinf.wiai.uni-bamberg.de",
-	#"Biogames": "http://www.biodiv2go.de",
-	"Biogames": "http://biogames.kinf.wiai.uni-bamberg.de/",
-	"Geogames": "http://log_data/",
-}
-
-RESULT_HOST = "http://results.ma.potato.kinf.wiai.uni-bamberg.de/"

selector/static/script.js

@@ -1,4 +0,0 @@
-function validateSettings() {
-    alert(document.getElementById('safety').checked);
-    return false;
-}

selector/static/style.css

@@ -1,9 +0,0 @@
-body {
-   /* background-color: limegreen;*/
-}
-#data{
-    display: none;
-}
-li{
-    list-style-type: none;
-}

selector/templates/base.html

@@ -1,5 +0,0 @@
-<!doctype html>
-<title>…</title>
-<link rel="stylesheet" type="text/css" href="{{ url_for('static', filename='style.css') }}">
-<script type="application/javascript" src="{{url_for('static', filename='script.js') }}"></script>
-{% block body %} {% endblock %}

selector/templates/games.html

@@ -1,25 +0,0 @@
-{% extends "base.html" %}
-{% block body %}
-<form action="/start" method="post">
-    <div id="data"> {{logs}}</div>
-    <ul>
-        {% for log in logs %}
-        <li>
-            <input type="checkbox" name="logs" value="{{log['@id']}}">
-            {{log.start_date}}: {{log.player_group_name}}
-        </li>
-        <!--{{log}}-->
-        {% endfor %}
-    </ul>
-    <!--input type="checkbox" id="safety"><label for="safety">Confirm selection</label-->
-    <input type="text" id="name" maxlength="128" placeholder="name" name="name"/><br>
-    <select name="config">
-        {% for config in configs %}
-        <option>{{config}}</option>
-        {% endfor %}
-    </select>
-    <input type="submit">
-
-</form>
-<a href="/results">show analysis progress/results</a>
-{% endblock %}

selector/templates/index.html

@@ -1,14 +0,0 @@
-{% extends "base.html" %}
-{% block body %}
-<form action="/login" method="post">
-    <select name="game">
-        {% for game in clients %}
-        <option>{{ game }}</option>
-        {% endfor %}
-    </select>
-    <input type="text" name="username" placeholder="username"/>
-    <input type="password" name="password" placeholder="passwort"/>
-    <input type="submit">
-</form>
-
-{% endblock %}

selector/templates/results.html

@@ -1,22 +0,0 @@
-{% extends "base.html" %}
-{% block body %}
-
-<a href="/games">create new analysis</a>
-
-<div id="results">
-    <ul>
-        {% for job in jobs %}
-        <li> {{jobs[job].status}}: "{{job}}":
-            <ul>
-                {% for r in jobs[job].results %}
-                <li><a href="{{jobs[job] | get_prefix}}{{r | get_name}}">{{r|get_name}} {{jobs[job].start}}</a></li>
-                {% endfor %}
-            </ul>
-
-
-        </li>
-        {% endfor %}
-    </ul>
-</div>
-
-{% endblock %}

selector/webserver.py

@@ -1,120 +0,0 @@
-import json
-import logging
-import typing
-import uuid
-
-import time
-
-from clients.webclients import Client, CLIENTS
-
-from flask import Flask, render_template, request, redirect, session
-
-from tasks import tasks
-from selector.config import CONFIGS, URLS, HOSTS, RESULT_HOST
-
-app = Flask(__name__)
-clients: typing.Dict[str, Client] = {}
-log: logging.Logger = logging.getLogger(__name__)
-
-
-@app.route("/")
-def index():
-	return render_template("index.html", clients=CLIENTS)
-
-
-@app.route("/login", methods=["POST"])
-def login():
-	game = request.form["game"]
-	if not game in CLIENTS or game not in HOSTS:
-		return redirect("/?invalid_game")
-	client = CLIENTS[game](host=HOSTS[game], username=request.form['username'], password=request.form['password'])
-	if client.login():
-		session['logged_in'] = True
-		session['uid'] = str(uuid.uuid4())
-		session['username'] = request.form['username']
-		session['cookies'] = client.cookies
-		session['game'] = game
-		session['host'] = HOSTS[game]
-		clients[session['uid']] = client
-		return redirect("/results")
-	return redirect("/?fail")
-
-
-@app.route("/results")
-def results():
-	if not ('logged_in' in session and session['logged_in']):
-		return redirect("/")
-	if session['logged_in'] and not session['uid'] in clients:
-		clients[session['uid']] = CLIENTS[session['game']](host=session['host'], **session['cookies'])
-	status = tasks.redis.get(session['username'])
-	if status:
-		job_status = json.loads(status)
-	else:
-		job_status = {}
-	#for job in job_status:
-	#	results = []
-	#	for path in job_status[job]['results']:
-	#		results.append(path.replace(tasks.DATA_PATH, RESULT_HOST))
-	#	print(results) #TODO???
-	return render_template("results.html",  jobs=job_status)
-
-
-@app.route("/games")
-def games():
-	if not ('logged_in' in session and session['logged_in']):
-		return redirect("/")
-	if session['logged_in'] and not session['uid'] in clients:
-		clients[session['uid']] = CLIENTS[session['game']](host=session['host'], **session['cookies'])
-	return render_template("games.html", logs=clients[session['uid']].list(), configs=CONFIGS[session['game']])
-
-
-@app.route("/start", methods=['POST'])
-def start():
-	print(str(request.form['logs']))
-	status = {
-		"status": "PENDING",
-		"submit": time.strftime("%c"),
-		"log_ids": request.form.getlist('logs'),
-		"config": request.form['config'],
-	}
-	params = {
-		"log_ids": request.form.getlist('logs'),
-		"config": CONFIGS[session['game']][request.form['config']],
-		"username": session['username'],
-		"cookies": session['cookies'],
-		"host": session['host'],
-		"clientName": session['game'],
-		"name": request.form['name'],
-	}
-	tasks.status_update(session['username'], request.form['name'], status)
-	tasks.analyze.delay(**params)
-	return redirect("/results")
-
-
-@app.route("/status")
-def status():
-	return json.dumps(json.loads(tasks.redis.get(session['username'])), indent=2)
-
-
-@app.template_filter('get_url')
-def get_url(path: str):
-	return path.replace(tasks.DATA_PATH, RESULT_HOST)
-
-@app.template_filter('get_name')
-def get_url(path: str):
-	return path.replace(tasks.DATA_PATH, "")
-
-
-@app.template_filter('get_prefix')
-def get_prefix(job):
-	print(job)
-	try:
-		return RESULT_HOST + URLS[job['config']]
-	except:
-		return RESULT_HOST + "#"
-
-
-
-if __name__ == '__main__':
-	app.config.update({"SECRET_KEY": "59765798-2784-11e8-8d05-db4d6f6606c9"})
-	app.run(host="0.0.0.0", debug=True)

sources/__init__.py

@@ -0,0 +1,5 @@
+from .biogames import Biogames
+
+SOURCES = {
+	"Biogames": Biogames,
+}

sources/biogames.py

@@ -0,0 +1,85 @@
+import json
+import logging
+import typing
+from tempfile import TemporaryDirectory
+
+import os
+
+from sources.source import Source
+
+import shutil
+import requests
+
+log: logging.Logger = logging.getLogger(__name__)
+
+
+class Biogames(Source):
+	def __init__(self):
+		self.headers: typing.Dict[str, str] = {'Accept': 'application/json'}
+		self.cookies: typing.Dict[str, str] = {}
+		self.id2link: typing.Dict[str, str] = {}
+		self.host: str = None
+
+	def connect(self, **kwargs):
+		for i in ['username', 'password', 'url', 'login_url', 'host']:
+			if not i in kwargs:
+				raise ValueError("missing value " + i)
+		csrf_request = requests.get(kwargs['url'])
+		if csrf_request.status_code != 200:
+			raise ConnectionError("unable to obtain CSRF token (" + str(csrf_request) + ")")
+		self.cookies['csrftoken'] = csrf_request.cookies['csrftoken']
+		log.info("obtained CSRF token (" + self.cookies['csrftoken'] + ")")
+		login_payload = {
+			'username': kwargs['username'],
+			'password': kwargs['password'],
+			'next': '',
+			'csrfmiddlewaretoken': 'csrftoken'
+		}
+		login = requests.post(kwargs['login_url'], data=json.dumps(login_payload), cookies=self.cookies)
+		if login.status_code != 200:
+			raise ConnectionError("Unable to authenticate!", login, login.text)
+		self.cookies['sessionid'] = login.cookies['sessionid']
+		log.info("obtained sessionid (" + self.cookies['sessionid'] + ")")
+		self.url = kwargs['url']
+		self.host = kwargs['host']
+		log.info("stored url (" + self.url + ")")
+
+	def list(self):
+		logs = self.get_json(self.url)
+		log.info(len(logs))
+		for i in logs:
+			self.id2link[i["id"]] = i["link"]  # TODO
+		return logs
+
+	def get(self, ids: typing.Collection):
+		dir = TemporaryDirectory()
+		files = []
+		for i in ids:
+			url = self.id2link[i]
+			filename = os.path.join(dir.name, url.split("/")[-1])
+			file = self.download_file(url, filename)
+			if file:
+				files.append(file)
+		return dir
+
+	def download_file(self, url, filename):
+		with open(filename, "wb") as out:
+			try:
+				download = self._get(url)
+				shutil.copyfileobj(download.raw, out)
+				return filename
+			except Exception as e:
+				log.exception(e)
+				os.remove(filename)
+
+	def get_json(self, url):
+		http = self._get(url, stream=False)
+		if not http.ok:
+			raise ConnectionError("HTTP status is not OK", http.url)
+		return http.json()
+
+	def close(self):
+		pass
+
+	def _get(self, url, stream=True):
+		return requests.get(self.host + url, cookies=self.cookies, headers=self.headers, stream=stream)

sources/source.py

@@ -0,0 +1,18 @@
+import typing
+
+
+class Source:
+	def connect(self, **kwargs):
+		raise NotImplementedError
+
+	def list(self):
+		raise NotImplementedError
+
+	def get(self, ids: typing.Collection):
+		raise NotImplementedError
+
+	def get_json(self, url:str) -> dict:
+		raise NotImplementedError
+
+	def close(self):
+		raise NotImplementedError

static/heatmap.html

@@ -0,0 +1,45 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Leaflet.heat demo</title>
+    <link rel="stylesheet" href="http://cdn.leafletjs.com/leaflet/v0.7.7/leaflet.css" />
+    <script src="http://cdn.leafletjs.com/leaflet/v0.7.7/leaflet.js"></script>
+    <style>
+        #map { width: 1024px; height: 768px; }
+        body { font: 16px/1.4 "Helvetica Neue", Arial, sans-serif; }
+        .ghbtns { position: relative; top: 4px; margin-left: 5px; }
+        a { color: #0077ff; }
+    </style>
+</head>
+<body>
+
+<div id="map"></div>
+
+<!-- <script src="../node_modules/simpleheat/simpleheat.js"></script>
+<script src="../src/HeatLayer.js"></script> -->
+
+<script src="https://rawgit.com/Leaflet/Leaflet.heat/gh-pages/dist/leaflet-heat.js"></script>
+
+<script src="./heat_data.js"></script>
+<script>
+var options = {maxZoom:22};
+var map = L.map('map', options).setView(coords[0], 17);
+L.control.scale().addTo(map);
+var tiles = L.tileLayer('http://{s}.tile.osm.org/{z}/{x}/{y}.png', {
+    attribution: '&copy; <a href="http://osm.org/copyright">OpenStreetMap</a> contributors',
+}).addTo(map);
+
+function addHeat(coords){
+    var heat = L.heatLayer(coords).addTo(map);
+}
+//coords = coords.map(function (p) { return [p[1], p[0], 0.05]; });
+
+//var heat = L.heatLayer(coords).addTo(map);
+    addHeat(coords);
+</script>
+<!--script src="./coord.js"></script>
+<script>
+    //addHeat(coords);
+</script-->
+</body>
+</html>

static/progress/index.html

@@ -0,0 +1,15 @@
+<script
+  src="https://code.jquery.com/jquery-3.2.1.min.js"
+  integrity="sha256-hwg4gsxgFZhOsEEamdOYGBf13FyQuiTwlAQgxVSNgt4="
+  crossorigin="anonymous"></script>
+    <link rel="stylesheet" href="https://unpkg.com/leaflet@1.2.0/dist/leaflet.css"
+   integrity="sha512-M2wvCLH6DSRazYeZRIm1JnYyh22purTM+FDB5CsyxtQJYeKq83arPe5wgbNmcFXGqiSH2XR8dT/fJISVA1r/zQ=="
+   crossorigin=""/>
+    <script src="https://unpkg.com/leaflet@1.2.0/dist/leaflet.js"
+   integrity="sha512-lInM/apFSqyy1o6s89K4iQUKg6ppXEgsVxT35HbzUupEVRh2Eu9Wdl4tHj7dZO0s1uvplcYGmt3498TtHq+log=="
+   crossorigin=""></script>
+  
+<script src="my.js"></script>
+    <style>
+       .map { width: 512px; height: 256px; }
+    </style>

static/progress/log.html

@@ -0,0 +1,15 @@
+<script
+  src="https://code.jquery.com/jquery-3.2.1.min.js"
+  integrity="sha256-hwg4gsxgFZhOsEEamdOYGBf13FyQuiTwlAQgxVSNgt4="
+  crossorigin="anonymous"></script>
+    <link rel="stylesheet" href="https://unpkg.com/leaflet@1.2.0/dist/leaflet.css"
+   integrity="sha512-M2wvCLH6DSRazYeZRIm1JnYyh22purTM+FDB5CsyxtQJYeKq83arPe5wgbNmcFXGqiSH2XR8dT/fJISVA1r/zQ=="
+   crossorigin=""/>
+    <script src="https://unpkg.com/leaflet@1.2.0/dist/leaflet.js"
+   integrity="sha512-lInM/apFSqyy1o6s89K4iQUKg6ppXEgsVxT35HbzUupEVRh2Eu9Wdl4tHj7dZO0s1uvplcYGmt3498TtHq+log=="
+   crossorigin=""></script>
+  
+<script src="log.js"></script>
+    <style>
+       .map { width: 512px; height: 512px; }
+    </style>

static/progress/log.js

@@ -0,0 +1,72 @@
+$.getJSON("data/fooo", function (data) {
+    var list = $("<ul />");
+    var mapC = $("<div />", {class: "map", id: "map"});
+    mapC.appendTo("body");
+    var track = [];
+    var times = [];
+    $.each(data.spatials, function (i, elem) {
+        track.push([elem.coordinates[1], elem.coordinates[0]]);
+        times.push(i);
+    });
+    var tiles = L.tileLayer('http://{s}.tile.osm.org/{z}/{x}/{y}.png', {
+            attribution: '&copy; <a href="http://osm.org/copyright">OpenStreetMap</a> contributors',
+        });
+    var map = L.map("map", {layers: [tiles]});
+    L.control.scale().addTo(map);
+    var layer = L.polyline(track).addTo(map);
+    map.fitBounds(layer.getBounds());
+    $.each(data, function (key, value) {
+        //console.log(key, value);
+        //key: instance_id, value: AnlysisResult
+        //value.result.instance: InstanceConfig_id
+        // console.log(key, value[0].result.store[0].timestamp);
+        /*$.each(value[0].result.store, function (index, entry) {
+            //console.log(entry);
+            var time = new Date(entry.timestamp);
+            var item = $("<li>", {html: entry.sequence + " @ " + time.toLocaleDateString() + " "+ time.toLocaleTimeString()});
+            var container = $("<p />");
+            if (entry.track.length > 0) {
+                var mapName = "map" + index;
+                //console.log(mapName, entry.track.length);
+                var mapContainer = $("<div />", {id: mapName, class: "map"});
+                var track = [];
+                $.each(entry.track, function (i, elem) {
+                    track.push([elem.coordinates[1], elem.coordinates[0]]);
+                });
+                maps[mapName] = track;
+
+                mapContainer.appendTo(container);
+            }
+            $.each(entry.events, function (i, event) {
+                if ("image" in event) {
+                    $("<img />", {src: event.image, height: 200}).appendTo(container);
+                }
+            });
+            container.appendTo(item);
+            item.appendTo(list);
+        });*/
+    });
+    list.appendTo("body");
+    var slider = $("<input />", {type: "range", start:0,end:100});
+    slider.appendTo("body");
+    /*});
+
+    $(window).on("load", function () {*/
+    // setTimeout(function () {
+
+    //console.log(maps);
+    /*$.each(maps, function (mapName, track) {
+        //console.log("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAa");
+        var tiles = L.tileLayer('http://{s}.tile.osm.org/{z}/{x}/{y}.png', {
+            attribution: '&copy; <a href="http://osm.org/copyright">OpenStreetMap</a> contributors',
+        });
+        var map = L.map(mapName, {layers: [tiles]});
+        L.control.scale().addTo(map);
+        // console.log(mapName, track);
+        var layer = L.polyline(track, {color: "green"}).addTo(map);
+        map.fitBounds(layer.getBounds());
+        //console.log(layer)
+        //L.control.layers({"osm":tiles}, {layer]).addTo(map);
+    });*/
+    // }, 2000);
+});

static/progress/my.js

@@ -0,0 +1,71 @@
+$.getJSON("tmp3.json", function (data) {
+    var list = $("<ul />");
+    var maps = {};
+    $.each(data, function (index, entry) {
+        //key: instance_id, value: AnlysisResult
+        //value.result.instance: InstanceConfig_id
+        // console.log(key, value[0].result.store[0].timestamp);
+        //$.each(value[0].result.store, function (index, entry) {
+            //console.log(entry);
+            var time = new Date(entry.timestamp);
+            var item = $("<li>", {html: entry.sequence + " @ " + time.toLocaleDateString() + " "+ time.toLocaleTimeString()});
+            var container = $("<p />");
+            if (entry.track.length > 0) {
+                var mapName = "map" + index;
+                //console.log(mapName, entry.track.length);
+                var mapContainer = $("<div />", {id: mapName, class: "map"});
+                var track = [];
+                $.each(entry.track, function (i, elem) {
+                    track.push([elem.coordinates[1], elem.coordinates[0]]);
+                });
+                maps[mapName] = track;
+
+                /* mapContainer.ready(function () {
+                     var map = L.map(mapName, {maxZoom: 22});
+                     L.control.scale().addTo(map);
+                     var tiles = L.tileLayer('http://{s}.tile.osm.org/{z}/{x}/{y}.png', {
+                         attribution: '&copy; <a href="http://osm.org/copyright">OpenStreetMap</a> contributors',
+                     }).addTo(map);
+                     var track = [];
+                     $.each(entry.track, function (i, elem) {
+                         track.push([elem.coordinates[1], elem.coordinates[0]]);
+                     });
+                     var layer = L.polyline(track, {color: "green"});
+                     console.log(track);
+                     L.control.layers(null, [layer]).addTo(map);
+                 });*/
+
+                mapContainer.appendTo(container);
+            }
+            $.each(entry.events, function (i, event) {
+                if ("image" in event) {
+                    $("<img />", {src: event.image, height: 200}).appendTo(container);
+                }
+            });
+            container.appendTo(item);
+            item.appendTo(list);
+        //});
+    });
+    list.appendTo("body");
+    var slider = $("<input />", {type: "range" })
+    /*});
+
+    $(window).on("load", function () {*/
+    // setTimeout(function () {
+
+    //console.log(maps);
+    $.each(maps, function (mapName, track) {
+        //console.log("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAa");
+        var tiles = L.tileLayer('http://{s}.tile.osm.org/{z}/{x}/{y}.png', {
+            attribution: '&copy; <a href="http://osm.org/copyright">OpenStreetMap</a> contributors',
+        });
+        var map = L.map(mapName, {layers: [tiles]});
+        L.control.scale().addTo(map);
+        // console.log(mapName, track);
+        var layer = L.polyline(track, {color: "green"}).addTo(map);
+        map.fitBounds(layer.getBounds());
+        //console.log(layer)
+        //L.control.layers({"osm":tiles}, {layer]).addTo(map);
+    });
+    // }, 2000);
+});

static/trackmap.html

@@ -0,0 +1,68 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Leaflet.heat demo</title>
+    <link rel="stylesheet" href="https://unpkg.com/leaflet@1.2.0/dist/leaflet.css"
+   integrity="sha512-M2wvCLH6DSRazYeZRIm1JnYyh22purTM+FDB5CsyxtQJYeKq83arPe5wgbNmcFXGqiSH2XR8dT/fJISVA1r/zQ=="
+   crossorigin=""/>
+    <script src="https://unpkg.com/leaflet@1.2.0/dist/leaflet.js"
+   integrity="sha512-lInM/apFSqyy1o6s89K4iQUKg6ppXEgsVxT35HbzUupEVRh2Eu9Wdl4tHj7dZO0s1uvplcYGmt3498TtHq+log=="
+   crossorigin=""></script>
+    <style>
+        #map { width: 1024px; height: 768px; }
+        body { font: 16px/1.4 "Helvetica Neue", Arial, sans-serif; }
+        .ghbtns { position: relative; top: 4px; margin-left: 5px; }
+        a { color: #0077ff; }
+    </style>
+</head>
+<body>
+
+<div id="map"></div>
+
+<!-- <script src="../node_modules/simpleheat/simpleheat.js"></script>
+<script src="../src/HeatLayer.js"></script> -->
+
+<script src="http://rawgit.com/Leaflet/Leaflet.heat/gh-pages/dist/leaflet-heat.js"></script>
+
+<script src="./track_data.js"></script>
+<script>
+var options = {maxZoom:22};
+//var map = L.map('map', options).setView([49.90299388, 10.87004638], 17);
+var map = L.map('map', options);
+L.control.scale().addTo(map);
+var tiles = L.tileLayer('http://{s}.tile.osm.org/{z}/{x}/{y}.png', {
+    attribution: '&copy; <a href="http://osm.org/copyright">OpenStreetMap</a> contributors',
+}).addTo(map);
+
+function addHeat(coords){
+    //var transformed = coords.map(function (p) { return [p[1], p[0], 0.25]; });
+    var heat = L.heatLayer(coords).addTo(map);
+}
+var layers=[];
+function addTrack(tracks, i){
+    var elem = L.polyline(tracks[i], {color:"green"});
+    // layers[i] =L.LayerGroup([elem]);
+    layers[i] = elem;
+    map.fitBounds(elem.getBounds());
+    layers[i].on('mouseover', function (e) {
+        e.target.setStyle({'color':'red'});
+    });
+    layers[i].on('mouseout', function (e) {
+         e.target.setStyle({'color':'green'});
+    });
+}
+//coords = coords.map(function (p) { return [p[1], p[0], 0.05]; });
+
+//var heat = L.heatLayer(coords).addTo(map);
+    //addHeat(coords);
+for (var i in tracks) {
+    addTrack(tracks, i);
+}
+L.control.layers(null, layers).addTo(map);
+</script>
+<!--script src="./heat_data.js"></script>
+<script>
+    addHeat(coords);
+</script-->
+</body>
+</html>

tasks/__init__.py

@@ -1,65 +0,0 @@
-from .tasks import analyze
-
-__log__ = ["/app/data/008cad400ab848f729913d034a.zip"]
-
-__config__ = """{
-  "logFormat": "zip",
-  "entryType": "@class",
-  "spatials": [
-    "de.findevielfalt.games.game2.instance.log.entry.LogEntryLocation"
-  ],
-  "actions": [
-    "...QuestionAnswerEvent",
-    "...SimuAnswerEvent"
-  ],
-  "boards": [
-    "de.findevielfalt.games.game2.instance.log.entry.ShowBoardLogEntry"
-  ],
-  "analyzers": {
-    "analysis.analyzers": [
-      "BiogamesCategorizer",
-      "LocationAnalyzer"
-    ]
-  },
-  "sequences": {
-    "start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryCache",
-    "end": {
-      "@class": "de.findevielfalt.games.game2.instance.log.entry.LogEntryInstanceAction",
-      "action.@class": "de.findevielfalt.games.game2.instance.action.CacheEnableAction"
-    }
-  },
-  "custom": {
-    "simulation_rounds": [
-      "de.findevielfalt.games.game2.instance.log.entry.LogEntryQuestion"
-    ],
-    "simu_data": [
-      "de.findevielfalt.games.game2.instance.data.sequence.simulation.SimulationBoardData"
-    ],
-    "instance_start": "de.findevielfalt.games.game2.instance.log.entry.LogEntryStartInstance",
-    "instance_id": "instance_id",
-    "instance_config_id": "config.@id",
-    "sequences2": {
-      "id_field": "sequence_id",
-      "start": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "START"
-      },
-      "end": {
-        "@class": "de.findevielfalt.games.game2.instance.log.entry.ShowSequenceLogEntry",
-        "action": "PAUSE"
-      }
-    },
-    "coordinates": "location.coordinates",
-    "metadata": {
-      "timestamp": "timestamp",
-      "gamefield": "instance_id",
-      "user": "player_group_name"
-    }
-  },
-  "source": {
-    "type": "Biogames",
-   "username": "ba",
-    "password": "853451",
-    "host": "http://biogames.potato.kinf.wiai.uni-bamberg.de"
-  }
-}"""

tasks/tasks.py

@@ -1,95 +0,0 @@
-import json
-import logging
-import shutil
-import uuid
-import os.path
-import os
-
-import redis as redis_lib
-import time
-from celery import Celery
-from analysis import log_analyzer as la
-from analysis.analyzers import KMLRender, ActivityMapperRender
-from analysis.analyzers.render.biogames import OEBRender
-from clients.webclients import CLIENTS
-
-FLASK_DB = 1
-REDIS_HOST = "redis"
-DATA_PATH = "/data/results/"
-
-RENDERERS = {  # TODO
-	"KMLRender": KMLRender,
-	"ActivityMapper": ActivityMapperRender,
-	"OEBRender": OEBRender
-}
-
-app = Celery('tasks', backend='redis://redis', broker='redis://redis')
-redis = redis_lib.StrictRedis(host=REDIS_HOST, db=FLASK_DB)
-log: logging.Logger = logging.getLogger(__name__)
-
-
-def update_status(username, name, state, **kwargs):
-	status = json.loads(redis.get(username))
-	status[name][state[0]] = time.strftime("%c")
-	status[name]['status'] = state[1]
-	for i in kwargs:
-		status[name][i] = kwargs[i]
-	redis.set(username, json.dumps(status))
-
-
-@app.task
-def analyze(config, log_ids, **kwargs):
-	update_status(kwargs['username'], kwargs['name'], ('load', 'LOADING'))
-
-	try:
-		log.info("start analysis")
-		client = CLIENTS[kwargs['clientName']](host=kwargs['host'], **kwargs['cookies'])
-		logs = client.list()
-		id_urls = {str(x['@id']): x['file_url'] for x in logs}
-		urls = [id_urls[i] for i in log_ids]
-		tmpdir = client.download_files(urls)
-		log.info(tmpdir.name, list(os.scandir(tmpdir.name)))
-
-		uid = str(uuid.uuid4())
-		update_status(kwargs['username'], kwargs['name'], ('start', 'RUNNING'), uid=uid)
-
-		results = []
-		settings = la.parse_settings(config)
-		store = la.run_analysis([p.path for p in os.scandir(tmpdir.name)], settings, la.LOADERS)
-		os.mkdir(os.path.join(DATA_PATH, uid))
-		render = RENDERERS[settings.render[0]]()  # TODO
-		files = []
-		if settings.render[0] == "OEBRender":
-			files.append(render.render_store(store))
-		else:
-			for category in store.get_categories():
-				data = store.get_category(category)
-				print(category, type(category))
-				files = render.render(data, name=category[1])
-		log.error(files)
-		for file in files:
-			try:
-				head, tail = os.path.split(file)
-				target = os.path.join(DATA_PATH, uid, tail)
-				log.error(target)
-				log.error(shutil.move(file, target))
-				results.append(target)
-			except FileNotFoundError as e:
-				log.exception(e)
-		tmpdir.cleanup()
-
-		update_status(kwargs['username'], kwargs['name'], ('done', 'FINISHED'), results=results)
-	except Exception as e:
-		log.exception(e)
-		update_status(kwargs['username'], kwargs['name'], ('abort', 'ERROR'), exception=str(e))
-
-
-def status_update(key, status_key, status):
-	record = redis.get(key)
-	if not record:
-		redis.set(key, json.dumps({status_key: status}))
-	else:
-		data = json.loads(record)
-		data[status_key] = status
-		redis.set(key, json.dumps(data))
-	redis.save()

test_neo.py

@@ -1,41 +0,0 @@
-
-from analysis import log_analyzer as la
-settings = la.load_settings("neocart.json")
-client = settings.source
-logs = client.list()
-id_urls = {str(x['@id']): x['file_url'] for x in logs}
-
-log_ids=['20351/playerid1430317168972.gpx','20351/playerid1430317188358.gpx']
-
-urls = [id_urls[i] for i in log_ids]
-tmpdir = client.download_files(urls)
-import os
-store = la.run_analysis([p.path for p in os.scandir(tmpdir.name)], settings, la.LOADERS)
-
-import json
-print(json.dumps(store.serializable(), indent=1))
-
-
-from analysis.analyzers import KMLRender, ActivityMapperRender
-RENDERERS = {  # TODO
-	"KMLRender": KMLRender,
-	"ActivityMapper": ActivityMapperRender,
-}
-render = RENDERERS[settings.render[0]]()
-files = render.render(store.get_all())
-DATA_PATH = "/app/data/results/"
-import uuid
-uid = str(uuid.uuid4())
-results = []
-os.mkdir(os.path.join(DATA_PATH, uid))
-import shutil
-
-for file in files:
-	try:
-		head, tail = os.path.split(file)
-		target = os.path.join(DATA_PATH, uid, tail)
-		shutil.move(file, target)
-		results.append(target)
-	except FileNotFoundError as e:
-		log.exception(e)
-tmpdir.cleanup()

util/download.py

@@ -1,30 +1,31 @@
 import logging
 import os
 
-from analysis.util import json_path
+from util import json_path
 
 logger = logging.getLogger(__name__)
 
 
-#def download_board(board_id, instance_config_id, sequence_id, source, path="/data/results/"): #FIXME: I was changed
+def download_board(board_id, instance_config_id, sequence_id, source):
-def download_board(board_id, instance_config_id, sequence_id, source, path="activity/data/results/"):
+	local_file = "static/progress/images/{config_id}/{sequence_id}/{board_id}".format(
-	local_file = os.path.join("static", instance_config_id, sequence_id, board_id)
+		config_id=instance_config_id,
-	abs_path = os.path.join(path, local_file)
+		sequence_id=sequence_id,
-	if os.path.exists(abs_path):
+		board_id=board_id)
+	if os.path.exists(local_file):
 		return local_file
 	url = "/game2/editor/config/{config_id}/sequence/{sequence_id}/board/{board_id}/".format(
 		config_id=instance_config_id,
 		sequence_id=sequence_id,
 		board_id=board_id
 	)
-	board = source.get(url)
+	board = source._get(url)
 	if not board.ok:
-		raise ConnectionError(url, board, board.status_code)
+		raise ConnectionError()
 	data = board.json()
 	preview_url = json_path(data, "preview_url.medium")
 	logger.debug(preview_url)
-	os.makedirs(abs_path[:-len(board_id)], exist_ok=True)
+	os.makedirs(local_file[:-len(board_id)], exist_ok=True)
-	source.download_file(preview_url, abs_path)
+	source.download_file(preview_url, local_file)
 	return local_file
 
 
@@ -53,6 +54,7 @@ def get_board_data(source, instance_id, sequence_id, board_id):
 		return {"class": "error"}
 	result = {
 		"class": instance_data["@class"],
+		"id": instance_data["@id"]
 	}
 	for i in ["image", "audio", "video"]:
 		key = i + "_file"
@@ -67,11 +69,10 @@ def get_json(source, url):
 	if url in cache:
 		return cache[url]
 	try:
-		data = source.get(url).json()
+		data = source.get_json(url)
 
 	except Exception as e:
-		print("exception", e, e.args)
+		print("exception", e, e.args)  # TODO: logging
-		logger.exception(e)
 		data = None
 	cache[url] = data
 	return data

util/iter.py

@@ -1,21 +1,14 @@
-def json_path(obj: dict, key: str):# TODO: test me!
+def json_path(obj: dict, key: str):
 	"""Query a nested dict with a dot-separated path"""
-	#if type(obj) is list and not "." in key:
+	if not type(obj) is dict:
-	#	return obj[int(key)]
+		return None
-	if type(obj) not in (dict, list):
-		raise ValueError("obj is no object (no list, too)")
 	if "." not in key:
 		if key not in obj:
-			return KeyError("key not in object", key)
+			return None
 		return obj[key]
 	child_key = key.split(".")
 	if child_key[0] not in obj:
-		try:
+		return None
-			index = int(child_key[0])
-			return json_path(obj[index], ".".join(child_key[1:]))
-		except:
-			raise KeyError("key not in object", key)
-		raise KeyError("key not in object", key)
 	return json_path(obj[child_key[0]], ".".join(child_key[1:]))
 
 

util/meta_temp.py

@@ -97,108 +97,3 @@ CONFIG_NAMES = {
 	'fe43a0f0-3dea-11e6-a065-00199963ac6e': u'Vorlagen',
 	'ff8f1e8f-6cf5-4a7b-835b-5e2226c1e771': u'Bad Urach'
 }
-
-
-KML_PATTERN = """<?xml version="1.0" encoding="UTF-8"?>
-<kml xmlns="http://www.opengis.net/kml/2.2" xmlns:gx="http://www.google.com/kml/ext/2.2">
-  <Document>
-    <Placemark>
-    	<gx:MultiTrack>
-    		<gx:Track>
-    			{when}
-    			{coordinates}
-    		</gx:Track>
-    	</gx:MultiTrack>
-      {coordinates}
-    </Placemark>
-  </Document>
-</kml>
-"""
-
-GEOJSON_PATTERN = """{
-	"type": "FeatureCollection",
-	"features": [
-		{
-			"type": "Feature",
-			"properties": {properties},
-			"geometry": {
-				"type": "LineString",
-				"coordinates": {coordinates}
-			}			
-		}
-	]
-}
-"""# TODO: fix me
-
-GEOJSON_COORDINATES = "[{lon},{lat}]"
-
-TASK_NAMES = {
-	"16fc3117-61db-4f50-b84f-81de6310206f_13127209-103c-4aed-9cce-b8a2cd9f7663_32e93082-1aa7-11e5-9827-74d43509b03a": "Lebensraum",
-	"16fc3117-61db-4f50-b84f-81de6310206f_13127209-103c-4aed-9cce-b8a2cd9f7663_3a27040f-1a9c-11e5-9827-74d43509b03a": "Simulation",
-	"16fc3117-61db-4f50-b84f-81de6310206f_2119b80e-74d3-4f3b-b0e0-e6a1f2c1d075_096093b0-d1ca-49f3-8d51-f32fa8874db5": "Biosphärenreservat",
-	"16fc3117-61db-4f50-b84f-81de6310206f_2119b80e-74d3-4f3b-b0e0-e6a1f2c1d075_b10951a5-1a8a-11e5-b1a2-74d43509b03a": "Simulation",
-	"16fc3117-61db-4f50-b84f-81de6310206f_41abfe17-aef3-41ee-b1e5-eedc8208680f_255d9c6d-1aa0-11e5-9827-74d43509b03a": "Simulation",
-	"16fc3117-61db-4f50-b84f-81de6310206f_41abfe17-aef3-41ee-b1e5-eedc8208680f_e0d2dee8-1a9f-11e5-9827-74d43509b03a": "Fellbestimmung",
-	"16fc3117-61db-4f50-b84f-81de6310206f_b9571a6b-c537-4a92-8618-2d73415dec87_10c3329f-7a88-4aa4-9567-14c811d2a6bc": "Lockstock-Code",
-	"16fc3117-61db-4f50-b84f-81de6310206f_b9571a6b-c537-4a92-8618-2d73415dec87_5732fe6c-1a9e-11e5-9827-74d43509b03a": "Lockstock-Nachweis",
-	"16fc3117-61db-4f50-b84f-81de6310206f_b9571a6b-c537-4a92-8618-2d73415dec87_e4bbaf4c-1a9d-11e5-9827-74d43509b03a": "Simulation",
-	"16fc3117-61db-4f50-b84f-81de6310206f_e08ffe7c-b24d-4fcd-9355-8a459a2c07b7_597c651a-1a8c-11e5-b1a2-74d43509b03a": "Simulation",
-	"16fc3117-61db-4f50-b84f-81de6310206f_e08ffe7c-b24d-4fcd-9355-8a459a2c07b7_da49b7be-bc13-11e4-a0de-6364e0bfe983": "Holzbedarf",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_027dcc39-d642-4900-91c4-abbd9c317cb8_610e91d9-0a1c-4a38-9399-deb0ff8dcb05": "Fellbestimmung",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_027dcc39-d642-4900-91c4-abbd9c317cb8_6a03c92d-9e23-4c67-9e76-6a5e28224371": "Simulation",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_25a3a482-a119-4db4-8c4e-235ea9d8dab7_90a01be2-dc8a-4733-b302-de5554969453": "Simulation",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_25a3a482-a119-4db4-8c4e-235ea9d8dab7_914778bc-f7e9-4327-a78b-71b6fa8762b1": "Biosphärenreservat",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_7a8ff4c4-7976-45e0-8ef5-cb386d536cb3_3ae4452e-ed67-4687-849d-e9341fca2900": "Simulation",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_7a8ff4c4-7976-45e0-8ef5-cb386d536cb3_f6f5c087-487c-43d8-9409-648a59684a09": "Lebensraum",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_97b86d4e-4724-4431-9c94-d2f57696fe2e_26e6558e-8069-45a1-961d-ab1ec9c5aa83": "Holzbedarf",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_97b86d4e-4724-4431-9c94-d2f57696fe2e_970ff4e0-16bd-4380-8e69-91a324a59523": "Simulation",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_a4f5c5d8-43b0-45f3-b3cf-3749fcb81f05_3366d6a3-684f-423a-bd7f-5c0107d4b972": "Simulation",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_a4f5c5d8-43b0-45f3-b3cf-3749fcb81f05_a7188b81-e25b-456d-9742-5f11adb7d461": "Lockstock-Nachweis",
-	"17d401a9-de21-49a2-95bc-7dafa53dda64_a4f5c5d8-43b0-45f3-b3cf-3749fcb81f05_d29537b9-de0b-42c2-b3da-27a3dbc57988": "Lockstock-Code",
-}
-
-CACHE_NAMES = {
-	"043ab9fe-64e8-4e76-8bf6-8cc9db35eba1": "1a_Infozentrum",
-	"37f326ed-9732-44b5-9ba7-e666d31cc4e7": "2a_Holzlager",
-	"bf96eee0-4c92-43d8-aced-a95e4eedae9f": "2b_Holzstapel",
-	"a5723715-7ba7-4431-9d0b-c91c351a3ccc": "3a_Lebensraum_Hecke",
-	"dd68ba57-a081-46be-9a76-e49cd5209383": "3b_Lebensraum_Hecke",
-	"bb21628e-d039-4c16-9fe1-68de7f448fa4": "4a_Lockstock_finden",
-	"8291c397-b3a9-4564-9365-bd660ab1abcc": "4b_Lockstock_finden",
-	"e92d8175-a65f-40de-ae76-3cbde55dfd4d": "5a_Straße",
-	"30451de3-2d5d-44c7-84b2-2abddbc8adcc": "5b_Straße",
-	"22fcc44c-64d4-4f84-ad05-8107542a04d2": "6a_Jaegerstand",
-	"1740e151-cd75-45c0-a06e-d724b9d69729": "6a_Jaegerstand",
-	"6d97d48a-7ac1-4e3a-b797-c2b4aa681a10": "5a_Straße",
-	"98e60f51-c4d5-4833-bc3b-2820e1bdd09d": "4b_Lockstock_finden",
-	"61d6dc12-11b5-4a9c-b0d8-7a38a29d772a": "5b_Straße",
-	"f4762feb-addb-4e82-b923-78f8c7b6aff9": "2b_Holzstapel",
-	"25b2cc3b-f8fd-4a21-9350-d175d837f6b6": "3a_Lebensraum_Hecke",
-	"5ba5046f-c956-4c21-aea5-a0a6055ed7e4": "1a_Infozentrum",
-	"fb60b94b-3f82-4ba9-98ac-f52105bd26f1": "2a_Holzlager",
-	"12b9584a-14b4-40c6-aa13-9fb11062e917": "4a_Lockstock_finden",
-	"19908306-8c70-4861-bec8-49e849e94722": "3b_Lebensraum_Hecke",
-	"None": "initial",
-	"only": "",
-}
-
-SEQUENCE_NAMES = {
-	"89b769f8-2c98-4f55-b741-1dfa022c3286": "1_Videoerklaerung",
-	"286cab41-6a81-4dfe-9bef-e86923ca8c97": "A_Einleitung",
-	"2119b80e-74d3-4f3b-b0e0-e6a1f2c1d075": "B",
-	"25a3a482-a119-4db4-8c4e-235ea9d8dab7": "B",
-	"97b86d4e-4724-4431-9c94-d2f57696fe2e": "C_mit_Dilemma",
-	"e08ffe7c-b24d-4fcd-9355-8a459a2c07b7": "C_mit_Dilemma",
-	"5f644fb4-5cc7-43a2-afb4-191dce80c875": "D_Dilemmasequenz",
-	"847ab5ff-7c98-4cdc-bc9e-bb619a0a98bb": "D_Dilemmasequenz",
-	"13127209-103c-4aed-9cce-b8a2cd9f7663": "E",
-	"7a8ff4c4-7976-45e0-8ef5-cb386d536cb3": "E",
-	"a4f5c5d8-43b0-45f3-b3cf-3749fcb81f05": "F",
-	"b9571a6b-c537-4a92-8618-2d73415dec87": "F",
-	"027dcc39-d642-4900-91c4-abbd9c317cb8": "G",
-	"41abfe17-aef3-41ee-b1e5-eedc8208680f": "G",
-	"be59a20a-69ce-471b-8f70-76ce200e32c9": "H_Abschlusserzaehlung",
-	"d4073563-da42-4ad2-9a9b-20ef29da6309": "H_Abschlusserzaehlung",
-	"54e03082-1a6b-11e5-aa26-00199963ac6e": "seq_score",
-	"95d82cd3-5bda-465a-8757-7179cdafe590": "seq_score",
-}