ConsultancyProject_2_ETL/etl/src/mauro/createAccuracyValues.py

73 lines
2.2 KiB
Python

import pandas as pd
import os
import re
import numpy as np
def getAccuracy(df, baseLine, compLine):
try:
df = df.iloc[[baseLine,compLine]]
except IndexError:
return -1
total = 0
noChange = 0
first = True
for series_name, series in df.items():
if first:
first = False
else:
total += 1
#print(series_name)
if series[baseLine] != -1:
if series[compLine] != -1:
if series[baseLine] == series[compLine]:
noChange += 1
accuracy = noChange / total
return accuracy
def getMeanAccuracy(accList):
out = []
for row in accList:
row = [x for x in row if x != -1]
out.append(np.average(row))
return out
deltaList = [1, 2, 10, 20]
#1 = 1 Scrape Interval
#2 = ca. 1 Woche
#10 = 1 Monat (30Tage)
#20 = 2 Monate
directory = os.fsencode("dok")
columnNames = ['property_id', 'timedelay_1', 'timedelay_2','timedelay_10','timedelay_20']
accListDf = pd.DataFrame(columns = columnNames)
accMeanDf = pd.DataFrame(columns = columnNames)
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith(".csv"):
propId = re.findall("\d+", filename)[0]
print(propId)
df = pd.read_csv(f'dok/{filename}')
fullList = []
accList = []
#Loop though all deltas in the deltaList
for delta in deltaList:
accList = []
#Loop through all Dates as Baseline date
for i in range(df.shape[0]):
acc = getAccuracy(df, i, i+delta)
accList.append(acc)
fullList.append(accList)
meanList = getMeanAccuracy(fullList)
accListDf = accListDf._append({'property_id': propId, 'timedelay_1': fullList[0], 'timedelay_2': fullList[1], 'timedelay_10': fullList[2], 'timedelay_20': fullList[3]}, ignore_index=True)
accMeanDf = accMeanDf._append({'property_id': propId, 'timedelay_1': meanList[0], 'timedelay_2': meanList[1], 'timedelay_10': meanList[2], 'timedelay_20': meanList[3]}, ignore_index=True)
accListDf.to_csv('results/accListDf.csv', index=False)
accMeanDf.to_csv('results/accMeanDf.csv', index=False)