diff --git a/dags/stat/community/community_rate.py b/dags/stat/community/community_rate.py index a16e349..e9089b2 100644 --- a/dags/stat/community/community_rate.py +++ b/dags/stat/community/community_rate.py @@ -425,19 +425,19 @@ def comms_rating(data): buffer.append(group) buffer.append(data_null) data = pd.concat(buffer) - buffer = [] - data_null = data[data['block'].isna()].copy() - data_not_null = data[data['block'].notna()].copy() - buffer.append(data_null) - if "block" in data.columns and (0 < len(data_not_null)): - data_not_null['region_block'] = data_not_null['region'] + "_" + data_not_null['block'] - for item in data_not_null['region_block'].unique(): - group = data_not_null[(data_not_null['region'] == str(item).split("_")[0]) & ( - data_not_null['block'] == str(item).split("_")[1])] - group = gmm_train(COMM_RATING_LEVEL_COUNT, group, 'total_score', 'block_rating') - group['block_rating'] = group['block_rating'].map(COMM_RATING_LEVEL_NAMES) - buffer.append(group) - data = pd.concat(buffer) + if "block" in data.columns: + buffer = [] + data_null = data[data['block'].isna()].copy() + data_not_null = data[data['block'].notna()].copy() + buffer.append(data_null) + if len(data_not_null) > 0: + data_not_null['region_block'] = data_not_null['region'] + "_" + data_not_null['block'] + for item in data_not_null['region_block'].unique(): + group = data_not_null[(data_not_null['region'] == str(item).split("_")[0]) & (data_not_null['block'] == str(item).split("_")[1])] + group = gmm_train(COMM_RATING_LEVEL_COUNT, group, 'total_score', 'block_rating') + group['block_rating'] = group['block_rating'].map(COMM_RATING_LEVEL_NAMES) + buffer.append(group) + data = pd.concat(buffer) for score_factor in ['total_score', 'community_quality_score', 'community_price_score', 'location_advantage_score', 'flowability_score', 'living_facilities_score', 'education_score', 'hospital_score']: data[f'{score_factor}'] = data[f'{score_factor}'].apply(lambda x: round(x * 100, 6))