TheCloud/PronounsPage
1
0
Fork 0
mirror of https://gitlab.com/PronounsPage/PronounsPage.git synced 2025-09-24 05:05:20 -04:00
Code Issues Packages Projects Releases Wiki Activity

(pl)(census) raport 2024 – WIP

Browse Source
This commit is contained in:
Andrea Vos 2024-03-10 15:29:05 +01:00
parent 0f17885c06
commit 2faf01072f
1 changed files with 34 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
census/analyse.py
View File

@ -317,44 +317,46 @@ if __name__ == '__main__':
'transitionSurgical': 'Tranzycja medyczna – zmiany chirurgiczne', 'transitionSurgical': 'Tranzycja medyczna – zmiany chirurgiczne',
} }
for group, group_stats in stats.items(): # for group, group_stats in stats.items():
for graph, graph_label in graphs.items(): # for graph, graph_label in graphs.items():
generateBar(group_stats[graph], group, graph, graph_label) # generateBar(group_stats[graph], group, graph, graph_label)
#
for comparison_key, comparison_groups in comparisons.items(): # for comparison_key, comparison_groups in comparisons.items():
ensureEmptyDir(outputDir / comparison_key) # ensureEmptyDir(outputDir / comparison_key)
for graph, graph_label in graphs.items(): # for graph, graph_label in graphs.items():
data = pd.DataFrame({ # data = pd.DataFrame({
groupLabel: stats[group][graph] # groupLabel: stats[group][graph]
for group, groupLabel # for group, groupLabel
in comparison_groups.items() # in comparison_groups.items()
}) # })
generateBar(data, comparison_key, graph, graph_label) # generateBar(data, comparison_key, graph, graph_label)
#
by_year = {} # by_year = {}
for prev_year in [*diffs, year]: # for prev_year in [*diffs, year]:
file_path = outputDir.parent / f'spis-{prev_year}' / 'general' / 'stats.json' # file_path = outputDir.parent / f'spis-{prev_year}' / 'general' / 'stats.json'
if not file_path.exists(): # if not file_path.exists():
continue # continue
with open(file_path, 'r') as f: # with open(file_path, 'r') as f:
by_year[prev_year] = json.load(f) # by_year[prev_year] = json.load(f)
#
ensureEmptyDir(outputDir / 'by_year') # ensureEmptyDir(outputDir / 'by_year')
for graph, graph_label in graphs.items(): # for graph, graph_label in graphs.items():
data = pd.DataFrame({ # data = pd.DataFrame({
column_year: year_data[graph] # column_year: year_data[graph]
for column_year, year_data # for column_year, year_data
in by_year.items() # in by_year.items()
if graph in year_data # if graph in year_data
}) # })
generateBar(data, 'by_year', graph, graph_label) # generateBar(data, 'by_year', graph, graph_label)
write_ins_dir = outputDir / 'write_ins' write_ins_dir = outputDir / 'write_ins'
write_ins_dir.mkdir(parents=True, exist_ok=True) write_ins_dir.mkdir(parents=True, exist_ok=True)
for column in df.columns: for column in df.columns:
if not column.endswith('__writein'): if not column.endswith('__writein') and column != '29_':
continue continue
print(f'Extracting write-ins for question {column}')
writeins = df[column].dropna().value_counts().reset_index() writeins = df[column].dropna().value_counts().reset_index()
writeins.columns = ['write-in', 'count'] writeins.columns = ['write-in', 'count']
writeins = writeins[['count', 'write-in']] writeins = writeins[['count', 'write-in']]