diff --git a/dags/business/business/community/consumption_stat.py b/dags/business/business/community/consumption_stat.py index c9aadee..d6ba3ed 100644 --- a/dags/business/business/community/consumption_stat.py +++ b/dags/business/business/community/consumption_stat.py @@ -21,8 +21,89 @@ if not os.path.exists(save_png_path): os.makedirs(save_png_path) nextcloud_aim_file_path = '财力评级/财力评级/财力评级统计报表' -def stat(): - pass + +def calculate_confidence(row): + """计算置信度等级""" + diff = abs(row["consumption_rating"] - row["price_rating"]) + if diff == 0: + return "高" + elif diff == 1: + return "中" + else: + return "低" + + +def stat(city): + community_summary_df = es206_client.scan_to_data_frame(query={"query": { + "bool": { + "must": [ + { + "term": { + "city": { + "value": city + } + } + } + ] + } + }}, source=[ + "city", + "region", + "consumption_rating", + "price_rating", + "consumption_score" + ], index="community_summary") + # 计算置信度 + community_summary_df["置信度"] = community_summary_df.apply(calculate_confidence, axis=1) + grouped = community_summary_df.groupby(["city", "region"]) + + results = [] + for (city, region), group in grouped: + # 计算财力评级指标 + rating_counts = group["consumption_rating"].value_counts(normalize=True) + rating_1 = rating_counts.get(1, 0) + rating_2 = rating_counts.get(2, 0) + rating_3 = rating_counts.get(3, 0) + rating_4 = rating_counts.get(4, 0) + rating_5 = rating_counts.get(5, 0) + rating_6 = rating_counts.get(6, 0) + + # 计算分数范围 + rating_1_scores = group[group["consumption_rating"] == 1]["consumption_score"] + rating_2_scores = group[group["consumption_rating"] == 2]["consumption_score"] + rating_3_scores = group[group["consumption_rating"] == 3]["consumption_score"] + rating_4_scores = group[group["consumption_rating"] == 4]["consumption_score"] + rating_5_scores = group[group["consumption_rating"] == 5]["consumption_score"] + rating_6_scores = group[group["consumption_rating"] == 6]["consumption_score"] + + # 计算置信度占比 + confidence_counts = group["置信度"].value_counts(normalize=True) + + results.append({ + "城市": city, + "区域": region, + "财力评级1级占比": round(rating_1, 4), + "财力评级1级分数范围": f"{rating_1_scores.min():.0f}-{rating_1_scores.max():.0f}" if not rating_1_scores.empty else "-", + "财力评级2级占比": round(rating_2, 4), + "财力评级2级分数范围": f"{rating_2_scores.min():.0f}-{rating_2_scores.max():.0f}" if not rating_2_scores.empty else "-", + "财力评级3级占比": round(rating_3, 4), + "财力评级3级分数范围": f"{rating_3_scores.min():.0f}-{rating_3_scores.max():.0f}" if not rating_3_scores.empty else "-", + "财力评级4级占比": round(rating_4, 4), + "财力评级4级分数范围": f"{rating_4_scores.min():.0f}-{rating_4_scores.max():.0f}" if not rating_4_scores.empty else "-", + "财力评级5级占比": round(rating_5, 4), + "财力评级5级分数范围": f"{rating_5_scores.min():.0f}-{rating_5_scores.max():.0f}" if not rating_5_scores.empty else "-", + "财力评级6级占比": round(rating_6, 4), + "财力评级6级分数范围": f"{rating_6_scores.min():.0f}-{rating_6_scores.max():.0f}" if not rating_6_scores.empty else "-", + "高置信度占比": round(confidence_counts.get("高", 0), 4), + "中置信度占比": round(confidence_counts.get("中", 0), 4), + "低置信度占比": round(confidence_counts.get("低", 0), 4) + }) + + # 生成最终报表 + report_df = pd.DataFrame(results) + aim_file = dateutils.format_date(dateutils.localize()) + '财力评级统计结果.csv' + report_df.to_csv(save_png_path + '/' + aim_file, index=False) + nextcloudutils.up_to_nextcloud(save_png_path + "/" + aim_file, nextcloud_aim_file_path + "/" + aim_file) def detail(city): @@ -83,10 +164,13 @@ def detail(city): dingutils.send_text("【统计】财力评级统计完毕,请点击 https://nextcloud.fangjia.com/s/nMbzk6ZKJDimapf 查看", "32400b949005817550937f82a82c064fe5be65c23204306442c15e8b485d7ef2") + sys_city = sys.argv[1] if len(sys.argv) > 1 else None if pd.notna(sys_city) and "," in sys_city: cities = sys_city.split(",") for city in cities: + stat(city) detail(city) else: + stat(sys_city) detail(sys_city) \ No newline at end of file