From b2f2dfe2a4989da5c62c2895eae73e9000760901 Mon Sep 17 00:00:00 2001
From: Arthur Lu <learthurgo@gmail.com>
Date: Sat, 12 Jun 2021 23:57:16 +0000
Subject: [PATCH] finished refactor

---
 src/cli/dataset.py     |  74 +++++++++++++++
 src/cli/interface.py   |   4 +-
 src/cli/processing.py  | 191 ++++++++++++++++++++++++++++++++++++++
 src/cli/superscript.py | 204 +++++++++++++++++++++++++++++++++++++----
 4 files changed, 455 insertions(+), 18 deletions(-)
 create mode 100644 src/cli/dataset.py
 create mode 100644 src/cli/processing.py

diff --git a/src/cli/dataset.py b/src/cli/dataset.py
new file mode 100644
index 0000000..5a69cc9
--- /dev/null
+++ b/src/cli/dataset.py
@@ -0,0 +1,74 @@
+import data as d
+
+def get_previous_time(apikey):
+
+	previous_time = d.get_analysis_flags(apikey, "latest_update")
+
+	if previous_time == None:
+
+		d.set_analysis_flags(apikey, "latest_update", 0)
+		previous_time = 0
+
+	else:
+
+		previous_time = previous_time["latest_update"]
+
+	return previous_time
+
+def set_current_time(apikey, current_time):
+
+	d.set_analysis_flags(apikey, "latest_update", {"latest_update":current_time})
+
+def load_match(apikey, competition):
+
+	return d.get_match_data_formatted(apikey, competition)
+
+def load_metric(apikey, competition, match, group_name, metrics):
+
+	group = {}
+
+	for team in match[group_name]:
+
+		db_data = d.get_team_metrics_data(apikey, competition, team)
+
+		if d.get_team_metrics_data(apikey, competition, team) == None:
+
+			elo = {"score": metrics["elo"]["score"]}
+			gl2 = {"score": metrics["gl2"]["score"], "rd": metrics["gl2"]["rd"], "vol": metrics["gl2"]["vol"]}
+			ts = {"mu": metrics["ts"]["mu"], "sigm+a": metrics["ts"]["sigma"]}
+
+			group[team] = {"elo": elo, "gl2": gl2, "ts": ts}
+
+		else:
+
+			metrics = db_data["metrics"]
+
+			elo = metrics["elo"]
+			gl2 = metrics["gl2"]
+			ts = metrics["ts"]
+
+			group[team] = {"elo": elo, "gl2": gl2, "ts": ts}
+
+	return group
+
+def load_pit(apikey, competition):
+
+	return d.get_pit_data_formatted(apikey, competition)
+
+def push_match(apikey, competition, results):
+
+	for team in results:
+
+		d.push_team_tests_data(apikey, competition, team, results[team])
+
+def push_metric(apikey, competition, metric):
+
+	for team in metric:
+
+			d.push_team_metrics_data(apikey, competition, team, metric[team])
+
+def push_pit(apikey, competition, pit):
+
+	for variable in pit:
+
+		d.push_team_pit_data(apikey, competition, variable, pit[variable])
\ No newline at end of file
diff --git a/src/cli/interface.py b/src/cli/interface.py
index 9fd5765..9ee821a 100644
--- a/src/cli/interface.py
+++ b/src/cli/interface.py
@@ -5,7 +5,7 @@ import platform
 
 empty_delim = " "
 hard_divided_delim = "|"
-soft_divided_delim = ":"
+soft_divided_delim = "|"
 l_brack = "["
 r_brack = "]"
 
@@ -17,7 +17,7 @@ stderr = sys.stderr
 
 def log(target, level, message, code = 0):
 
-	message = time.ctime() + empty_delim + str(level) + l_brack + str(code) + r_brack + empty_delim + soft_divided_delim + empty_delim + message
+	message = time.ctime() + empty_delim + str(level) + l_brack + f"{code:04}" + r_brack + empty_delim + soft_divided_delim + empty_delim + message
 	print(message, file = target)
 
 def clear():
diff --git a/src/cli/processing.py b/src/cli/processing.py
new file mode 100644
index 0000000..1f7e322
--- /dev/null
+++ b/src/cli/processing.py
@@ -0,0 +1,191 @@
+import numpy as np
+
+from tra_analysis import Analysis as an
+from dataset import push_metric
+from data import pull_new_tba_matches
+
+def simplestats(data_test):
+
+	data = np.array(data_test[0])
+	data = data[np.isfinite(data)]
+	ranges = list(range(len(data)))
+
+	test = data_test[1]
+
+	if test == "basic_stats":
+		return an.basic_stats(data)
+
+	if test == "historical_analysis":
+		return an.histo_analysis([ranges, data])
+
+	if test == "regression_linear":
+		return an.regression(ranges, data, ['lin'])
+
+	if test == "regression_logarithmic":
+		return an.regression(ranges, data, ['log'])
+
+	if test == "regression_exponential":
+		return an.regression(ranges, data, ['exp'])
+
+	if test == "regression_polynomial":
+		return an.regression(ranges, data, ['ply'])
+
+	if test == "regression_sigmoidal":
+		return an.regression(ranges, data, ['sig'])
+
+def matchloop(apikey, competition, data, tests, exec_threads):
+
+	short_mapping = {"regression_linear": "lin", "regression_logarithmic": "log", "regression_exponential": "exp", "regression_polynomial": "ply", "regression_sigmoidal": "sig"}
+
+	class AutoVivification(dict):
+		def __getitem__(self, item):
+			try:
+				return dict.__getitem__(self, item)
+			except KeyError:
+				value = self[item] = type(self)()
+				return value
+
+	return_vector = {}
+	
+	team_filtered = []
+	variable_filtered = []
+	variable_data = []
+	test_filtered = []
+	result_filtered = []
+	return_vector = AutoVivification()
+
+	for team in data:
+
+		for variable in data[team]:
+
+			if variable in tests:
+
+				for test in tests[variable]:
+
+					team_filtered.append(team)
+					variable_filtered.append(variable)
+					variable_data.append((data[team][variable], test))
+					test_filtered.append(test)
+
+	result_filtered = exec_threads.map(simplestats, variable_data)
+	i = 0
+
+	result_filtered = list(result_filtered)
+
+	for result in result_filtered:
+
+		filtered = test_filtered[i]
+
+		try:
+			short = short_mapping[filtered]
+			return_vector[team_filtered[i]][variable_filtered[i]][test_filtered[i]] = result[short]
+		except KeyError: # not in mapping
+			return_vector[team_filtered[i]][variable_filtered[i]][test_filtered[i]] = result
+		i += 1
+
+	return return_vector
+
+def metricloop(tbakey, apikey, competition, timestamp, metrics): # listener based metrics update
+
+	elo_N = metrics["elo"]["N"]
+	elo_K = metrics["elo"]["K"]
+
+	matches = pull_new_tba_matches(tbakey, competition, timestamp)
+
+	red = {}
+	blu = {}
+
+	for match in matches:
+
+		red = load_metric(apikey, competition, match, "red", metrics)
+		blu = load_metric(apikey, competition, match, "blue", metrics)
+ 
+		elo_red_total = 0
+		elo_blu_total = 0
+
+		gl2_red_score_total = 0
+		gl2_blu_score_total = 0
+
+		gl2_red_rd_total = 0
+		gl2_blu_rd_total = 0
+
+		gl2_red_vol_total = 0
+		gl2_blu_vol_total = 0
+
+		for team in red:
+
+			elo_red_total += red[team]["elo"]["score"]
+
+			gl2_red_score_total += red[team]["gl2"]["score"]
+			gl2_red_rd_total += red[team]["gl2"]["rd"]
+			gl2_red_vol_total += red[team]["gl2"]["vol"]
+
+		for team in blu:
+
+			elo_blu_total += blu[team]["elo"]["score"]
+
+			gl2_blu_score_total += blu[team]["gl2"]["score"]
+			gl2_blu_rd_total += blu[team]["gl2"]["rd"]
+			gl2_blu_vol_total += blu[team]["gl2"]["vol"]
+
+		red_elo = {"score": elo_red_total / len(red)}
+		blu_elo = {"score": elo_blu_total / len(blu)}
+
+		red_gl2 = {"score": gl2_red_score_total / len(red), "rd": gl2_red_rd_total / len(red), "vol": gl2_red_vol_total / len(red)}
+		blu_gl2 = {"score": gl2_blu_score_total / len(blu), "rd": gl2_blu_rd_total / len(blu), "vol": gl2_blu_vol_total / len(blu)}
+
+
+		if match["winner"] == "red":
+
+			observations = {"red": 1, "blu": 0}
+
+		elif match["winner"] == "blue":
+
+			observations = {"red": 0, "blu": 1}
+
+		else:
+
+			observations = {"red": 0.5, "blu": 0.5}
+
+		red_elo_delta = an.Metric().elo(red_elo["score"], blu_elo["score"], observations["red"], elo_N, elo_K) - red_elo["score"]
+		blu_elo_delta = an.Metric().elo(blu_elo["score"], red_elo["score"], observations["blu"], elo_N, elo_K) - blu_elo["score"]
+
+		new_red_gl2_score, new_red_gl2_rd, new_red_gl2_vol = an.Metric().glicko2(red_gl2["score"], red_gl2["rd"], red_gl2["vol"], [blu_gl2["score"]], [blu_gl2["rd"]], [observations["red"], observations["blu"]])
+		new_blu_gl2_score, new_blu_gl2_rd, new_blu_gl2_vol = an.Metric().glicko2(blu_gl2["score"], blu_gl2["rd"], blu_gl2["vol"], [red_gl2["score"]], [red_gl2["rd"]], [observations["blu"], observations["red"]])
+
+		red_gl2_delta = {"score": new_red_gl2_score - red_gl2["score"], "rd": new_red_gl2_rd - red_gl2["rd"], "vol": new_red_gl2_vol - red_gl2["vol"]}
+		blu_gl2_delta = {"score": new_blu_gl2_score - blu_gl2["score"], "rd": new_blu_gl2_rd - blu_gl2["rd"], "vol": new_blu_gl2_vol - blu_gl2["vol"]}
+
+		for team in red:
+
+			red[team]["elo"]["score"] = red[team]["elo"]["score"] + red_elo_delta
+
+			red[team]["gl2"]["score"] = red[team]["gl2"]["score"] + red_gl2_delta["score"]
+			red[team]["gl2"]["rd"] = red[team]["gl2"]["rd"] + red_gl2_delta["rd"]
+			red[team]["gl2"]["vol"] = red[team]["gl2"]["vol"] + red_gl2_delta["vol"]
+
+		for team in blu:
+
+			blu[team]["elo"]["score"] = blu[team]["elo"]["score"] + blu_elo_delta
+
+			blu[team]["gl2"]["score"] = blu[team]["gl2"]["score"] + blu_gl2_delta["score"]
+			blu[team]["gl2"]["rd"] = blu[team]["gl2"]["rd"] + blu_gl2_delta["rd"]
+			blu[team]["gl2"]["vol"] = blu[team]["gl2"]["vol"] + blu_gl2_delta["vol"]
+
+		temp_vector = {}
+		temp_vector.update(red)
+		temp_vector.update(blu)
+
+		push_metric(apikey, competition, temp_vector)
+
+def pitloop(apikey, competition, pit, tests):
+
+	return_vector = {}
+	for team in pit:
+		for variable in pit[team]:
+			if variable in tests:
+				if not variable in return_vector:
+					return_vector[variable] = []
+				return_vector[variable].append(pit[team][variable])
+
+	return return_vector
\ No newline at end of file
diff --git a/src/cli/superscript.py b/src/cli/superscript.py
index 09ef513..0cbe4a0 100644
--- a/src/cli/superscript.py
+++ b/src/cli/superscript.py
@@ -11,6 +11,8 @@ __changelog__ = """changelog:
 		- moved printing and logging related functions to interface.py (changelog will stay in this file)
 		- changed function return files for load_config and save_config to standard C values (0 for success, 1 for error)
 		- added local variables for config location
+		- moved dataset getting and setting functions to dataset.py (changelog will stay in this file)
+		- moved matchloop, metricloop, pitloop and helper functions (simplestats) to processing.py
 	0.8.6:
 		- added proper main function
 	0.8.5:
@@ -121,23 +123,22 @@ __author__ = (
 __all__ = [
 	"load_config",
 	"save_config",
-	"get_previous_time",
-	"load_match",
-	"matchloop",
-	"load_metric",
-	"metricloop",
-	"load_pit",
-	"pitloop",
-	"push_match",
-	"push_metric",
-	"push_pit",
 ]
 
 # imports:
 
 import json
+import multiprocessing
+import os
+import math
+from multiprocessing import Pool
+import time
+import warnings
+import sys
 
-from cli_interface import splash, log, ERR, INF, stdout, stderr
+from interface import splash, log, ERR, INF, stdout, stderr
+from dataset import get_previous_time, set_current_time, load_match, push_match, load_metric, push_metric, load_pit, push_pit
+from processing import matchloop, metricloop, pitloop
 
 config_path = "config.json"
 sample_json = """{
@@ -189,21 +190,190 @@ sample_json = """{
 
 def main():
 
+	warnings.filterwarnings("ignore")
+	sys.stderr = open("errorlog.txt", "w")
+
 	splash(__version__)
 
+	loop_exit_code = 0
+	loop_stored_exception = None
+
+	while True:
+
+		try:
+
+			loop_start = time.time()
+
+			current_time = time.time()
+			log(stdout, INF, "current time: " + str(current_time))
+
+			config = {}
+			if load_config(config_path, config) == 1:
+				exit(1)
+
+			error_flag = False
+
+			try:
+				competition = config["competition"]
+			except:
+				log(stderr, ERR, "could not find competition field in config", code = 101)
+				error_flag = True
+			try:
+				match_tests = config["statistics"]["match"]
+			except:
+				log(stderr, ERR, "could not find match_tests field in config", code = 102)
+				error_flag = True
+			try:
+				metrics_tests = config["statistics"]["metric"]
+			except:
+				log(stderr, ERR, "could not find metrics_tests field in config", code = 103)
+				error_flag = True
+			try:
+				pit_tests = config["statistics"]["pit"]
+			except:
+				log(stderr, ERR, "could not find pit_tests field in config", code = 104)
+				error_flag = True
+			
+			if error_flag:
+				exit(1)
+			error_flag = False
+
+			if competition == None or competition == "":
+				log(stderr, ERR, "competition field in config must not be empty", code = 105)
+				error_flag = True
+			if match_tests == None:
+				log(stderr, ERR, "match_tests field in config must not be empty", code = 106)
+				error_flag = True
+			if metrics_tests == None:
+				log(stderr, ERR, "metrics_tests field in config must not be empty", code = 107)
+				error_flag = True
+			if pit_tests == None:
+				log(stderr, ERR, "pit_tests field in config must not be empty", code = 108)
+				error_flag = True
+			
+			if error_flag:
+				exit(1)
+
+			log(stdout, INF, "found and loaded competition, match_tests, metrics_tests, pit_tests from config")
+
+			sys_max_threads = os.cpu_count()
+			try:
+				cfg_max_threads = config["max-threads"]
+			except:
+				log(stderr, ERR, "max-threads field in config must not be empty, refer to documentation for configuration options", code = 109)
+				exit(1)
+
+			if cfg_max_threads > -sys_max_threads and cfg_max_threads < 0 :
+				alloc_processes = sys_max_threads + cfg_max_threads
+			elif cfg_max_threads > 0 and cfg_max_threads < 1:
+				alloc_processes = math.floor(cfg_max_threads * sys_max_threads)
+			elif cfg_max_threads > 1 and cfg_max_threads <= sys_max_threads:
+				alloc_processes = cfg_max_threads
+			elif cfg_max_threads == 0:
+				alloc_processes = sys_max_threads
+			else:
+				log(stderr, ERR, "max-threads must be between -" + str(sys_max_threads) + " and " + str(sys_max_threads) + ", but got " + cfg_max_threads, code = 110)
+				exit(1)
+
+			log(stdout, INF, "found and loaded max-threads from config")
+			log(stdout, INF, "attempting to start " + str(alloc_processes) + " threads")
+			try:
+				exec_threads = Pool(processes = alloc_processes)
+			except Exception as e:
+				log(stderr, ERR, "unable to start threads", code = 200)
+				log(stderr, INF, e)
+				exit(1)
+			log(stdout, INF, "successfully initialized " + str(alloc_processes) + " threads")
+
+			exit_flag = False
+
+			try:
+				apikey = config["key"]["database"]
+			except:
+				log(stderr, ERR, "database key field in config must not be empty, please populate the database key", code = 111)
+				exit_flag = True
+			try:
+				tbakey = config["key"]["tba"]
+			except:
+				log(stderr, ERR, "tba key field in config must not be empty, please populate the tba key", code = 112)
+				exit_flag = True
+
+			if exit_flag:
+				exit(1)
+			
+			log(stdout, INF, "found and loaded database and tba keys")
+
+			previous_time = get_previous_time(apikey)
+			log(stdout, INF, "analysis backtimed to: " + str(previous_time))
+
+			start = time.time()
+			log(stdout, INF, "loading match data")
+			match_data = load_match(apikey, competition)
+			log(stdout, INF, "finished loading match data in " + str(time.time() - start) + " seconds")
+
+			start = time.time()
+			log(stdout, INF, "performing analysis on match data")
+			results = matchloop(apikey, competition, match_data, match_tests, exec_threads)
+			log(stdout, INF, "finished match analysis in " + str(time.time() - start) + " seconds")
+
+			start = time.time()
+			log(stdout, INF, "uploading match results to database")
+			push_match(apikey, competition, results)
+			log(stdout, INF, "finished uploading match results in " + str(time.time() - start) + " seconds")
+
+			start = time.time()
+			log(stdout, INF, "performing analysis on team metrics")
+			results = metricloop(tbakey, apikey, competition, current_time, metrics_tests)
+			log(stdout, INF, "finished metric analysis and pushed to database in " + str(time.time() - start) + " seconds")
+
+			start = time.time()
+			log(stdout, INF, "loading pit data")
+			pit_data = load_pit(apikey, competition)
+			log(stdout, INF, "finished loading pit data in " + str(time.time() - start) + " seconds")
+
+			start = time.time()
+			log(stdout, INF, "performing analysis on pit data")
+			results = pitloop(apikey, competition, pit_data, pit_tests)
+			log(stdout, INF, "finished pit analysis in " + str(time.time() - start) + " seconds")
+
+			start = time.time()
+			log(stdout, INF, "uploading pit results to database")
+			push_pit(apikey, competition, results)
+			log(stdout, INF, "finished uploading pit results in " + str(time.time() - start) + " seconds")
+
+			set_current_time(apikey, current_time)
+			log(stdout, INF, "finished all tests in " + str(time.time() - loop_start) + " seconds, looping")
+
+		except KeyboardInterrupt:
+			log(stdout, INF, "detected KeyboardInterrupt, killing threads")
+			if "exec_threads" in locals():
+				exec_threads.terminate()
+				exec_threads.close()
+			log(stdout, INF, "terminated threads, exiting")
+			loop_stored_exception = sys.exc_info()
+			loop_exit_code = 0
+			break
+		except Exception as e:
+			log(stderr, ERR, "encountered an exception while running")
+			print(e, file = stderr)
+			loop_exit_code = 1
+			break
+
+	sys.exit(loop_exit_code)
+
 def load_config(path, config_vector):
 	try:
 		f = open(path, "r")
+		config_vector.update(json.load(f))
+		f.close()
+		log(stdout, INF, "found and opened config at <" + path + ">")
+		return 0
 	except:
-		log(stderr, ERR, "could not find config at <" + path + ">, generating blank config and exiting")
+		log(stderr, ERR, "could not find config at <" + path + ">, generating blank config and exiting", code = 100)
 		f = open(path, "w")
 		f.write(sample_json)
 		f.close()
 		return 1
-	
-	config_vector = json.load(f)
-	f.close()
-	return 0
 
 def save_config(path, config_vector):
 	try:
@@ -215,4 +385,6 @@ def save_config(path, config_vector):
 		return 1
 
 if __name__ == "__main__":
+	if sys.platform.startswith("win"):
+		multiprocessing.freeze_support()
 	main()
\ No newline at end of file