m.giller/mash-server
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Some filter stuff

Browse source
This commit is contained in:
Maximilian Giller 2023-10-08 01:56:10 +02:00
parent dffa83870d
commit 5819ed5533
1 changed files with 21 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
src/statistics/statistics.py
View file

@ -7,6 +7,7 @@ import matplotlib.pyplot as plt
# Config # Config
FILE_PATH = "log.txt" FILE_PATH = "log.txt"
AFTER_DATE = datetime(2022, 1, 1) # Only keeps log entries after the specified date. Filter applied in parse_log_entry(..)
# Read file # Read file
@ -15,14 +16,14 @@ with open(FILE_PATH, "r") as file:
content = file.readlines() content = file.readlines()
def parse_log_entry(entry: Dict) -> Dict: def parse_log_entry(entry: Dict) -> Dict | bool:
# Only keep last record of a sequence # Only keep last record of a sequence
if not is_last_in_sequence(entry): if not is_last_in_sequence(entry):
return False return False
entry["dateTime"] = datetime.strptime( entry["dateTime"] = datetime.strptime(
str(entry["dateTime"])[:19], "%Y-%m-%d %H:%M:%S") str(entry["dateTime"])[:19], "%Y-%m-%d %H:%M:%S")
if entry["dateTime"] < datetime(2022, 1, 1): if entry["dateTime"] < AFTER_DATE:
return False return False
return entry return entry
@ -59,6 +60,7 @@ fig, ax = plt.subplots() # Create a figure containing a single axes.
times: list[datetime] = [entry["dateTime"] for entry in log] times: list[datetime] = [entry["dateTime"] for entry in log]
counts: list[int] = [entry["previousPeopleCount"] for entry in log] counts: list[int] = [entry["previousPeopleCount"] for entry in log]
ax.step(times, counts, where="pre") ax.step(times, counts, where="pre")
print("-"*20)
plt.show() plt.show()
print("-"*20) print("-"*20)
@ -73,6 +75,7 @@ print("Number of walk-unders:", len(walk_unders))
print("-"*20) print("-"*20)
# Calculate faults # Calculate faults
for c, n in zip(list(range(len(log))), list(range(len(log)))[1:]): for c, n in zip(list(range(len(log))), list(range(len(log)))[1:]):
estimated_count: int = log[c]["previousPeopleCount"] + \ estimated_count: int = log[c]["previousPeopleCount"] + \
log[c]["countChange"] log[c]["countChange"]
@ -82,8 +85,9 @@ for c, n in zip(list(range(len(log))), list(range(len(log)))[1:]):
log = log[:-1] log = log[:-1]
fault_count = sum(1 for entry in log if entry["faulty"]) fault_count = sum(1 for entry in log if entry["faulty"])
fault_percentage = fault_count / len(log)
print("Number of faults:", fault_count) print("Number of faults:", fault_count)
print("Percentage of faults:", fault_count / len(log) * 100, "%") print("Percentage of faults:", fault_percentage * 100, "%")
print("-"*20) print("-"*20)
faulty_off = [entry for entry in log if entry["faulty"] faulty_off = [entry for entry in log if entry["faulty"]
@ -94,3 +98,17 @@ print("Number of false-0:", len(faulty_off))
print("Number of false-1:", len(faulty_on)) print("Number of false-1:", len(faulty_on))
print("Percentage of false-0:", len(faulty_off) / fault_count * 100, "%") print("Percentage of false-0:", len(faulty_off) / fault_count * 100, "%")
print("Percentage of false-1:", len(faulty_on) / fault_count * 100, "%") print("Percentage of false-1:", len(faulty_on) / fault_count * 100, "%")
# Number of dates
unique_dates = set()
for entry in log:
date = entry["dateTime"].strftime("%Y-%m-%d")
unique_dates.add(date)
total_days = len(unique_dates)
print("-"*20)
print("Number of days:", total_days)
print("Changes per day:", len(log) / total_days)
corrections_per_day = len(log) / total_days * fault_percentage
print("Corrections per day:", corrections_per_day)