quote_lines(1, 1)
quote_lines(3, 3)
quote_lines(39, 39)

search("puheenvuorojen määrä kansanedustajat")

import json

# Load the first JSON file
with open('/mnt/data/22-PTK_53-2023_vp_parsed_discussions_1.json', 'r', encoding='utf-8') as file:
    data1 = json.load(file)

# Load the second JSON file
with open('/mnt/data/22-PTK_53-2023_vp_parsed_discussions_2.json', 'r', encoding='utf-8') as file:
    data2 = json.load(file)

# Combine the data from both files
combined_data = data1 + data2

# Count the number of speeches for each member of parliament (MP)
speech_count = {}
for entry in combined_data:
    mep_id = entry['mep_id']
    speech_count[mep_id] = speech_count.get(mep_id, 0) + 1

# Find the top three MPs with the most speeches
top_three_speeches = sorted(speech_count.items(), key=lambda x: x[1], reverse=True)[:3]
top_three_speeches

[('1311', 81), ('1496', 68), ('1455', 49)]

# Extracting the names of the MPs with the most speeches based on their IDs
def find_mep_names(mep_ids, data):
    names = {}
    for entry in data:
        if entry['mep_id'] in mep_ids:
            full_name = f"{entry['first_name']} {entry['last_name']}"
            names[entry['mep_id']] = names.get(entry['mep_id'], full_name)
    return names

# MEP IDs of the top three speakers
top_three_ids = [id for id, _ in top_three_speeches]

# Finding their names
mep_names = find_mep_names(top_three_ids, combined_data)
mep_names

{'1455': 'Kaisa Juuso', '1311': 'Joona Räsänen', '1496': 'Eemeli Peltonen'}

Rydman kommentoi rakennusalan tilaa