13hannes11/UU_NCML_Project
1
0
Fork 0
mirror of https://github.com/13hannes11/UU_NCML_Project.git synced 2024-09-03 20:50:59 +02:00
Code Issues Projects Releases Wiki Activity

Data split based on election period and model is trained on each set, closes #15

Browse Source
This commit is contained in:
Deepthi Pathare
2021-05-11 23:59:08 +02:00
parent 69759ccd3b
commit 82cef720fc
3 changed files with 42 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
voting_lib/load_data.py
View File

@@ -12,8 +12,10 @@ def load_german_data():
"""
title_file = "filename_to_titles.csv"
vote_counter = -1
data = pd.DataFrame()
#data = pd.DataFrame()
data = {}
period_column_g = 'Wahlperiode'
name_column_g = 'Bezeichnung'
party_column_g = 'Fraktion/Gruppe'
name_column = 'Member'
@@ -25,6 +27,9 @@ def load_german_data():
for dirname, _, filenames in os.walk('./de/csv'):
for filename in filenames:
if filename != title_file:
print(filename)
vote_counter += 1
df = pd.read_csv(os.path.join(dirname, filename))
@@ -41,13 +46,15 @@ def load_german_data():
df=df.rename(columns={name_column_g:name_column,party_column_g:party_column})
if data.empty:
# if first file that is loaded set data equal to data from first file
data = df[[name_column, party_column, vote_column_name]]
else:
period = df.iloc[0][period_column_g]
if period in data:
# merge data with already loaded data
data = data.merge(df[[name_column, vote_column_name]], on=name_column)
data[period] = data[period].merge(df[[name_column, vote_column_name]], on=name_column)
else:
# if first file that is loaded set data equal to data from first file
data[period] = df[[name_column, party_column, vote_column_name]]
print(data)
return data