From 9d2c12653d56e1c8288cc63308faf6320d25436d Mon Sep 17 00:00:00 2001 From: liuhongyang Date: Thu, 10 Apr 2025 11:34:02 +0800 Subject: [PATCH] =?UTF-8?q?=E8=B4=A2=E5=8A=9B=E8=AF=84=E7=BA=A7=E7=BB=9F?= =?UTF-8?q?=E8=AE=A1=E4=BC=98=E5=8C=96?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../business/community/consumption_stat.py | 30 ++++++++++++++----- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/dags/business/business/community/consumption_stat.py b/dags/business/business/community/consumption_stat.py index fe6c52b..c298e69 100644 --- a/dags/business/business/community/consumption_stat.py +++ b/dags/business/business/community/consumption_stat.py @@ -22,11 +22,25 @@ if not os.path.exists(save_png_path): nextcloud_aim_file_path = '财力评级/财力评级/财力评级统计报表' +def format_score_range(min_score, max_score): + """格式化分数范围,防止Excel自动转换""" + if pd.isna(min_score) or pd.isna(max_score): + return "-" + # 使用Excel公式语法强制识别为文本 + return f'="{int(min_score)}-{int(max_score)}"' + + def stat(community_summary_df): - grouped = community_summary_df.groupby(["city"]) + df = community_summary_df + grouped = df.groupby(["city"]) results = [] for city, group in grouped: + # 总数 + total_num = len(group) + # 财力评级不为空数量 + group = group.dropna(subset=['consumption_rating']) + rating_num = len(group) # 计算财力评级指标 rating_counts = group["consumption_rating"].value_counts(normalize=True) rating_1 = rating_counts.get(1, 0) @@ -49,18 +63,20 @@ def stat(community_summary_df): results.append({ "城市": city, + "楼盘总量": total_num, + "有财力评级数量": rating_num, "财力评级1级占比": round(rating_1 * 100, 1), - "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1级分数范围": format_score_range(rating_1_scores.min(), rating_1_scores.max()) if not rating_1_scores.empty else "-", "财力评级2级占比": round(rating_2 * 100, 1), - "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2级分数范围": format_score_range(rating_2_scores.min(), rating_2_scores.max()) if not rating_2_scores.empty else "-", "财力评级3级占比": round(rating_3 * 100, 1), - "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3级分数范围": format_score_range(rating_3_scores.min(), rating_3_scores.max()) if not rating_3_scores.empty else "-", "财力评级4级占比": round(rating_4 * 100, 1), - "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4级分数范围": format_score_range(rating_4_scores.min(), rating_4_scores.max()) if not rating_4_scores.empty else "-", "财力评级5级占比": round(rating_5 * 100, 1), - "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5级分数范围": format_score_range(rating_5_scores.min(), rating_5_scores.max()) if not rating_5_scores.empty else "-", "财力评级6级占比": round(rating_6 * 100, 1), - "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 "-", + "财力评级6级分数范围": format_score_range(rating_6_scores.min(), rating_6_scores.max()) if not rating_6_scores.empty else "-", "高置信度占比": round(confidence_counts.get("高", 0) * 100, 1), "中置信度占比": round(confidence_counts.get("中", 0) * 100, 1), "低置信度占比": round(confidence_counts.get("低", 0) * 100, 1)