diff --git a/dags/stat/community/community_rate.py b/dags/stat/community/community_rate.py index 352a235..266ad48 100644 --- a/dags/stat/community/community_rate.py +++ b/dags/stat/community/community_rate.py @@ -211,16 +211,18 @@ def load_comms(city): seaweed = seaweed.rename(columns={"create_year": "build_year", "estate_type2": "estate_type", "business_quarter": "block", "_id": "comm_id"}) year = datetime.now().year seaweed['build_year'] = seaweed['build_year'].apply(lambda x: extract_years(x)) + seaweed['org_build_year'] = seaweed['build_year'] seaweed['age'] = seaweed['build_year'].apply(lambda x: (year - x) if pd.notna(x) else None) seaweed = seaweed.reset_index() for field in ['age', "cubage_percent", "virescence_percent", "estate_charge"]: seaweed[field] = seaweed[field].apply(lambda x: str2number(x)) + seaweed[f"org_{field}"] = seaweed[field] seaweed = fill_missing_by_around(seaweed, field) seaweed[field] = seaweed[field].fillna(seaweed[field].mean()) - seaweed['age'] = seaweed['age'].apply(lambda x: int(x)) - seaweed['cubage_percent'] = seaweed['cubage_percent'].apply(lambda x: round(x, 2)) - seaweed['virescence_percent'] = seaweed['virescence_percent'].apply(lambda x: round(x, 2)) - seaweed['estate_charge'] = seaweed['estate_charge'].apply(lambda x: round(x, 2)) + if field == 'age': + seaweed['age'] = seaweed['age'].apply(lambda x: int(x)) + else: + seaweed[field] = seaweed[field].apply(lambda x: round(x, 2)) return seaweed @@ -232,6 +234,7 @@ def load_comm_stat(city): {"city": 1, "region": 1, "district_name": 1, "avg_price_2b": 1, "_id": 0}))) stat = stat.rename(columns={"district_name": "name", "avg_price_2b": "avg_price"}) + stat['org_avg_price'] = stat["avg_price"] one_year_before_stat = pd.DataFrame(list( stat_client.find({"weekend": dateutils.add_months(dateutils.get_last_weekend(), days=-52 * 7), "city": city}, {"city": 1, "region": 1, "district_name": 1, "avg_price_2b": 1, "_id": 0}))) @@ -239,6 +242,7 @@ def load_comm_stat(city): columns={"district_name": "name", "avg_price_2b": "one_year_before_avg_price"}) stat = stat.merge(one_year_before_stat, on=['city', 'region', 'name'], how="left") stat['yoy'] = (stat['avg_price'] - stat['one_year_before_avg_price']) * 100 / stat['one_year_before_avg_price'] + stat['org_yoy'] = stat["yoy"] stat['yoy'] = stat['yoy'].fillna(stat['yoy'].mean()) stat['resistance_coef'] = normalize_to_01(stat['yoy']) * 95 stat['resistance_coef'] = stat['resistance_coef'] + 2 @@ -264,6 +268,8 @@ def load_comm_stat(city): sqmetre_rent = sqmetre_rent.rename(columns={"district_name": "name", "avg_price": "sqmetre_rent"}) stat = stat.merge(sqmetre_rent, on=['city', 'region', 'name'], how='left') stat['rent_to_price_ratio'] = stat['sqmetre_rent'] * 12 / stat['avg_price'] * 100 + stat["org_sqmetre_rent"] = stat['sqmetre_rent'] + stat["org_rent_to_price_ratio"] = stat['rent_to_price_ratio'] stat['rent_to_price_ratio'] = stat['rent_to_price_ratio'].fillna(stat['rent_to_price_ratio'].mean()) return stat @@ -278,6 +284,7 @@ def load_comms_summary(city): for key in source.keys(): if key.endswith("num") or key.endswith("_distance"): community_summary[key] = source[key] + community_summary[f"org_{key}"] = source[key] all_community_summary.append(community_summary) all_community_summary = pd.DataFrame(all_community_summary) return all_community_summary @@ -489,7 +496,11 @@ def process_city(city): "key_primary_school_num", "ordinary_primary_school_num", "key_middle_school_num", "ordinary_middle_school_num", "top_three_hospital_num", "non_3a_hospital_num", "build_year", "age", "cubage_percent", "virescence_percent", "estate_charge", 'estate_type', 'resistance_coef', "region_rating"] - + # 恢复经过转换,填充的数据 + for field in data.columns: + if field.startswith("org_"): + data[f"{field.replace('org_', '')}"] = data[field] + del data[field] df_simple = data[db_fields].copy() if "block" not in df_simple.columns: df_simple['block'] = None