import Data_Analysis as DA
import pandas as pd
import os
import re




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 = DA.getAccuracy(df, i, i+delta)
                accList.append(acc)
            fullList.append(accList)


        meanList = DA.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)