stoffelmauro
/
ConsultancyProject_2_ETL
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: stoffelmauro:2a9ef9d991bea42782475d2dd70f35cad5e57a1e
Branches Tags
stoffelmauro:main
stoffelmauro:refactor-to-mono
..
compare: stoffelmauro:8655255782a92a0e94df1398833064a89c098f0b
Branches Tags
stoffelmauro:main
stoffelmauro:refactor-to-mono

No commits in common. "2a9ef9d991bea42782475d2dd70f35cad5e57a1e" and "8655255782a92a0e94df1398833064a89c098f0b" have entirely different histories.
2a9ef9d991 ... 8655255782

1 changed files with 7 additions and 13 deletions
Show Stats Expand all files Collapse all files

20
etl/src/data/etl_region_capacities.py
View File

@ -23,8 +23,10 @@ def region_capacities(id: int):
# Merge Dataframe to generate indices # Merge Dataframe to generate indices
df = df.join(datesDF, on='ScrapeDate') df = df.join(datesDF, on='ScrapeDate')
df = df.join(propIdDF, on='property_id') df = df.join(propIdDF, on='property_id')
# Drop now useless columns ScrapeDate and property_id # Drop now useless columns ScrapeDate and property_id
df = df[['ScrapeDate', 'calendarBody', 'date_index', 'prop_index']] df = df[['calendarBody', 'date_index', 'prop_index']]
# Calculate grid values # Calculate grid values
gridData = [] gridData = []
for row in df.rows(named=True): for row in df.rows(named=True):
@ -34,18 +36,13 @@ def region_capacities(id: int):
sum_hor = calDF.sum_horizontal()[0] sum_hor = calDF.sum_horizontal()[0]
else: else:
sum_hor = 0 sum_hor = 0
# With Index gridData.append([row['prop_index'], row['date_index'], sum_hor])
# gridData.append([row['prop_index'], row['date_index'], sum_hor])
# With ScrapeDate
gridData.append([row['ScrapeDate'], row['date_index'], sum_hor])
gridData = np.array(gridData) gridData = np.array(gridData)
# get all values to calculate Max # get all values to calculate Max
allValues = gridData[:, 2].astype(int) allValues = gridData[:, 2]
print(allValues)
maxValue = np.max(allValues) maxValue = np.max(allValues)
print(maxValue) gridData[:, 2] = (gridData[:, 2]*100)/maxValue
gridData[:, 2] = (allValues*100)/maxValue
# Return back to list # Return back to list
gridData = gridData.tolist() gridData = gridData.tolist()
@ -58,6 +55,3 @@ def region_capacities(id: int):
outDict = {'scrapeDates': listOfDates, 'property_ids': listOfPropertyIDs, 'values': gridData} outDict = {'scrapeDates': listOfDates, 'property_ids': listOfPropertyIDs, 'values': gridData}
return outDict return outDict
out = region_capacities(1)
print(out)