import pandas as pd

# Sample DataFrame
data = {
    'predicted_categories': [
        ['80814001 - Freze Uçları', '13003106 - Freze', '80805004 - Sanayi Makineleri'],
        ['13003144 - Torna Makinesi', '13003195 - Kumpas']
    ],
    'pred_category_id': [80814001, 13003195],
    'text_predicted_probs': [
        [0.943, 0.018, 0.008],
        [0.6, 0.4]
    ]
}
df = pd.DataFrame(data)

# 1. Explode both list columns simultaneously to maintain alignment between category and probability
df_exploded = df.explode(['predicted_categories', 'text_predicted_probs'])

# 2. Extract the numeric ID from the category string using vectorized regex
df_exploded['extracted_id'] = df_exploded['predicted_categories'].str.extract(r'^(\d+)').astype(float)

# 3. Filter for rows where the extracted ID matches the target 'pred_category_id'
matched = df_exploded[df_exploded['extracted_id'] == df_exploded['pred_category_id']]

# 4. Dedup the index (safety net in case an ID appears twice within the same list)
matched = matched[~matched.index.duplicated(keep='first')]

# 5. Map the extracted probability column back to the original DataFrame using the index
df['pred_category_prob'] = matched['text_predicted_probs']

df